@article{PereiraPereiraSilvaetal., author = {Pereira, Clayton R. and Pereira, Danilo R. and Silva, Francisco A. and Masieiro, Joao P. and Weber, Silke A. T. and Hook, Christian and Papa, Jo{\~a}o Paulo}, title = {A new computer vision-based approach to aid the diagnosis of Parkinson's disease}, series = {Computer Methods and Programs in Biomedicine}, volume = {136}, journal = {Computer Methods and Programs in Biomedicine}, publisher = {Elsevier}, doi = {10.1016/j.cmpb.2016.08.005}, pages = {79 -- 88}, abstract = {Background and Objective: Even today, pointing out an exam that can diagnose a patient with Parkinson's disease (PD) accurately enough is not an easy task. Although a number of techniques have been used in search for a more precise method, detecting such illness and measuring its level of severity early enough to postpone its side effects are not straightforward. In this work, after reviewing a considerable number of works, we conclude that only a few techniques address the problem of PD recognition by means of micrography using computer vision techniques. Therefore, we consider the problem of aiding automatic PD diagnosis by means of spirals and meanders filled out in forms, which are then compared with the template for feature extraction. Methods: In our work, both the template and the drawings are identified and separated automatically using image processing techniques, thus needing no user intervention. Since we have no registered images, the idea is to obtain a suitable representation of both template and drawings using the very same approach for all images in a fast and accurate approach. Results: The results have shown that we can obtain very reasonable recognition rates (around approximate to 67\%), with the most accurate class being the one represented by the patients, which outnumbered the control individuals in the proposed dataset. Conclusions: The proposed approach seemed to be suitable for aiding in automatic PD diagnosis by means of computer vision and machine learning techniques. Also, meander images play an important role, leading to higher accuracies than spiral images. We also observed that the main problem in detecting PD is the patients in the early stages, who can draw near-perfect objects, which are very similar to the ones made by control patients. (C) 2016 Elsevier Ireland Ltd. All rights reserved.}, language = {en} } @unpublished{RueckertRauberMaerkletal., author = {R{\"u}ckert, Tobias and Rauber, David and Maerkl, Raphaela and Klausmann, Leonard and Yildiran, Suemeyye R. and Gutbrod, Max and Nunes, Danilo Weber and Moreno, Alvaro Fernandez and Luengo, Imanol and Stoyanov, Danail and Toussaint, Nicolas and Cho, Enki and Kim, Hyeon Bae and Choo, Oh Sung and Kim, Ka Young and Kim, Seong Tae and Arantes, Gon{\c{c}}alo and Song, Kehan and Zhu, Jianjun and Xiong, Junchen and Lin, Tingyi and Kikuchi, Shunsuke and Matsuzaki, Hiroki and Kouno, Atsushi and Manesco, Jo{\~a}o Renato Ribeiro and Papa, Jo{\~a}o Paulo and Choi, Tae-Min and Jeong, Tae Kyeong and Park, Juyoun and Alabi, Oluwatosin and Wei, Meng and Vercauteren, Tom and Wu, Runzhi and Xu, Mengya and an Wang, and Bai, Long and Ren, Hongliang and Yamlahi, Amine and Hennighausen, Jakob and Maier-Hein, Lena and Kondo, Satoshi and Kasai, Satoshi and Hirasawa, Kousuke and Yang, Shu and Wang, Yihui and Chen, Hao and Rodr{\´i}guez, Santiago and Aparicio, Nicol{\´a}s and Manrique, Leonardo and Lyons, Juan Camilo and Hosie, Olivia and Ayobi, Nicol{\´a}s and Arbel{\´a}ez, Pablo and Li, Yiping and Khalil, Yasmina Al and Nasirihaghighi, Sahar and Speidel, Stefanie and R{\"u}ckert, Daniel and Feussner, Hubertus and Wilhelm, Dirk and Palm, Christoph}, title = {Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge}, pages = {36}, abstract = {Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.}, language = {en} } @article{RueckertRauberMaerkletal., author = {Rueckert, Tobias and Rauber, David and Maerkl, Raphaela and Klausmann, Leonard and Yildiran, Suemeyye R. and Gutbrod, Max and Nunes, Danilo Weber and Moreno, Alvaro Fernandez and Luengo, Imanol and Stoyanov, Danail and Toussaint, Nicolas and Cho, Enki and Kim, Hyeon Bae and Choo, Oh Sung and Kim, Ka Young and Kim, Seong Tae and Arantes, Gon{\c{c}}alo and Song, Kehan and Zhu, Jianjun and Xiong, Junchen and Lin, Tingyi and Kikuchi, Shunsuke and Matsuzaki, Hiroki and Kouno, Atsushi and Manesco, Jo{\~a}o Renato Ribeiro and Papa, Jo{\~a}o Paulo and Choi, Tae-Min and Jeong, Tae Kyeong and Park, Juyoun and Alabi, Oluwatosin and Wei, Meng and Vercauteren, Tom and Wu, Runzhi and Xu, Mengya and Wang, An and Bai, Long and Ren, Hongliang and Yamlahi, Amine and Hennighausen, Jakob and Maier-Hein, Lena and Kondo, Satoshi and Kasai, Satoshi and Hirasawa, Kousuke and Yang, Shu and Wang, Yihui and Chen, Hao and Rodr{\´i}guez, Santiago and Aparicio, Nicol{\´a}s and Manrique, Leonardo and Palm, Christoph and Wilhelm, Dirk and Feussner, Hubertus and Rueckert, Daniel and Speidel, Stefanie and Nasirihaghighi, Sahar and Al Khalil, Yasmina and Li, Yiping and Arbel{\´a}ez, Pablo and Ayobi, Nicol{\´a}s and Hosie, Olivia and Lyons, Juan Camilo}, title = {Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge}, series = {Medical Image Analysis}, volume = {109}, journal = {Medical Image Analysis}, publisher = {Elsevier}, issn = {1361-8415}, doi = {10.1016/j.media.2026.103945}, pages = {31}, abstract = {Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.}, language = {en} } @incollection{PereiraPassosLopesetal., author = {Pereira, Clayton R. and Passos, Leandro A. and Lopes, Ricardo R. and Weber, Silke A. T. and Hook, Christian and Papa, Joao Paulo}, title = {Parkinson's Disease Identification Using Restricted Boltzmann Machines}, series = {Computer Analysis of Images and Patterns, 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part II}, volume = {10425}, booktitle = {Computer Analysis of Images and Patterns, 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part II}, publisher = {Springer}, isbn = {978-3-319-64697-8}, doi = {10.1007/978-3-319-64698-5_7}, pages = {70 -- 80}, abstract = {Currently, Parkinson's Disease (PD) has no cure or accurate diagnosis, reaching approximately 60, 000 new cases yearly and worldwide, being more often in the elderly population. Its main symptoms can not be easily uncorrelated with other illness, being way more difficult to be identified at the early stages. As such, computer-aided tools have been recently used to assist in this task, but the challenge in the automatic identification of Parkinson's Disease still persists. In order to cope with this problem, we propose to employ Restricted Boltzmann Machines (RBMs) to learn features in an unsupervised fashion by analyzing images from handwriting exams, which aim at assessing the writing skills of potential individuals. These are one of the main symptoms of PD-prone people, since such kind of ability ends up being severely affected. We show that RBMs can learn proper features that help supervised classifiers in the task of automatic identification of PD patients, as well as one can obtain a more compact representation of the exam for the sake of storage and computational load purposes.}, language = {en} } @article{PereiraPereiraRosaetal., author = {Pereira, Clayton R. and Pereira, Danilo R. and Rosa, Gustavo H. and Albuquerque, Victor Hugo C. and Weber, Silke A. T. and Hook, Christian and Papa, Jo{\~a}o Paulo}, title = {Handwritten dynamics assessment through convolutional neural networks}, series = {Artificial Intelligence in Medicine}, volume = {37}, journal = {Artificial Intelligence in Medicine}, number = {May}, publisher = {Elsevier}, doi = {10.1016/j.artmed.2018.04.001}, pages = {67 -- 77}, abstract = {Background and objective Parkinson's disease (PD) is considered a degenerative disorder that affects the motor system, which may cause tremors, micrography, and the freezing of gait. Although PD is related to the lack of dopamine, the triggering process of its development is not fully understood yet. Methods In this work, we introduce convolutional neural networks to learn features from images produced by handwritten dynamics, which capture different information during the individual's assessment. Additionally, we make available a dataset composed of images and signal-based data to foster the research related to computer-aided PD diagnosis. Results The proposed approach was compared against raw data and texture-based descriptors, showing suitable results, mainly in the context of early stage detection, with results nearly to 95\%. Conclusions The analysis of handwritten dynamics using deep learning techniques showed to be useful for automatic Parkinson's disease identification, as well as it can outperform handcrafted features.}, language = {en} } @article{AfonsoRosaPereiraetal., author = {Afonso, Luis Claudio Sugi and Rosa, Gustavo H. and Pereira, Clayton R. and Weber, Silke A. T. and Hook, Christian and Albuquerque, Victor Hugo C. and Papa, Joao Paulo}, title = {A recurrence plot-based approach for Parkinson's disease identification}, series = {Future generation computer systems - The international journal of escience}, volume = {94}, journal = {Future generation computer systems - The international journal of escience}, number = {May}, publisher = {Elsevier}, doi = {10.1016/j.future.2018.11.054}, pages = {282 -- 292}, abstract = {Parkinson's disease (PD) is a neurodegenerative disease that affects millions of people worldwide, causing mental and mainly motor dysfunctions. The negative impact on the patient's daily routine has moved the science in search of new techniques that can reduce its negative effects and also identify the disease in individuals. One of the main motor characteristics of PD is the hand tremor faced by patients, which turns out to be a crucial information to be used towards a computer-aided diagnosis. In this context, we make use of handwriting dynamics data acquired from individuals when submitted to some tasks that measure abilities related to writing skills. This work proposes the application of recurrence plots to map the signals onto the image domain, which are further used to feed a Convolutional Neural Network for learning proper information that can help the automatic identification of PD. The proposed approach was assessed in a public dataset under several scenarios that comprise different combinations of deep-based architectures, image resolutions, and training set sizes. Experimental results showed significant accuracy improvement compared to our previous work with an average accuracy of over 87\%. Moreover, it was observed an improvement in accuracy concerning the classification of patients (i.e., mean recognition rates above to 90\%). The promising results showed the potential of the proposed approach towards the automatic identification of Parkinson's disease.}, language = {en} } @article{AfonsoPereiraWeberetal., author = {Afonso, Luis Claudio Sugi and Pereira, Clayton R. and Weber, Silke A. T. and Hook, Christian and Falc{\~a}o, Alexandre X. and Papa, Joao Paulo}, title = {Hierarchical learning using deep optimum-path forest}, series = {Journal of Visual Communication and Image Representation}, volume = {71}, journal = {Journal of Visual Communication and Image Representation}, number = {August}, publisher = {Elsevier}, doi = {10.1016/j.jvcir.2020.102823}, abstract = {Bag-of-Visual Words (BoVW) and deep learning techniques have been widely used in several domains, which include computer-assisted medical diagnoses. In this work, we are interested in developing tools for the automatic identification of Parkinson's disease using machine learning and the concept of BoVW. The proposed approach concerns a hierarchical-based learning technique to design visual dictionaries through the Deep Optimum-Path Forest classifier. The proposed method was evaluated in six datasets derived from data collected from individuals when performing handwriting exams. Experimental results showed the potential of the technique, with robust achievements.}, language = {en} } @inproceedings{PereiraPereiradaSilvaetal., author = {Pereira, Clayton R. and Pereira, Danilo R. and da Silva, Francisco A. and Hook, Christian and Weber, Silke A. T. and Pereira, Luis A. M. and Papa, Jo{\~a}o Paulo}, title = {A Step Towards the Automated Diagnosis of Parkinson's Disease: Analyzing Handwriting Movements}, series = {2015 IEEE 28th International Symposium on Computer-Based Medical Systems, 22.-25.06.2015, Sao Carlos, Brazil}, booktitle = {2015 IEEE 28th International Symposium on Computer-Based Medical Systems, 22.-25.06.2015, Sao Carlos, Brazil}, publisher = {IEEE}, isbn = {978-1-4673-6775-2}, issn = {2372-9198}, doi = {10.1109/cbms.2015.34}, pages = {171 -- 176}, abstract = {Parkinson's disease (PD) has affected millions of people world-wide, being its major problem the loss of movements and, consequently, the ability of working and locomotion. Although we can find several works that attempt at dealing with this problem out there, most of them make use of datasets composed by a few subjects only. In this work, we present some results toward the automated diagnosis of PD by means of computer vision-based techniques in a dataset composed by dozens of patients, which is one of the main contributions of this work. The dataset is part of a joint research project that aims at extracting both visual and signal-based information from healthy and PD patients in order to go forward the early diagnosis of PD patients. The dataset is composed by handwriting clinical exams that are analyzed by means of image processing and machine learning techniques, being the preliminary results encouraging and promising. Additionally, a new quantitative feature to measure the amount of tremor of an individual's handwritten trace called Mean Relative Tremor is also presented.}, language = {en} } @article{EbigboMendelScheppachetal., author = {Ebigbo, Alanna and Mendel, Robert and Scheppach, Markus W. and Probst, Andreas and Shahidi, Neal and Prinz, Friederike and Fleischmann, Carola and R{\"o}mmele, Christoph and G{\"o}lder, Stefan Karl and Braun, Georg and Rauber, David and R{\"u}ckert, Tobias and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Byrne, Michael F. and Palm, Christoph and Messmann, Helmut}, title = {Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm}, series = {Gut}, volume = {71}, journal = {Gut}, number = {12}, publisher = {BMJ}, address = {London}, doi = {10.1136/gutjnl-2021-326470}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-54293}, pages = {2388 -- 2390}, abstract = {In this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63\% and 76\%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85\% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.}, language = {en} } @article{SouzaJrPalmMendeletal., author = {Souza Jr., Luis Antonio de and Palm, Christoph and Mendel, Robert and Hook, Christian and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Weber, Silke A. T. and Papa, Jo{\~a}o Paulo}, title = {A survey on Barrett's esophagus analysis using machine learning}, series = {Computers in Biology and Medicine}, volume = {96}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2018.03.014}, pages = {203 -- 213}, abstract = {This work presents a systematic review concerning recent studies and technologies of machine learning for Barrett's esophagus (BE) diagnosis and treatment. The use of artificial intelligence is a brand new and promising way to evaluate such disease. We compile some works published at some well-established databases, such as Science Direct, IEEEXplore, PubMed, Plos One, Multidisciplinary Digital Publishing Institute (MDPI), Association for Computing Machinery (ACM), Springer, and Hindawi Publishing Corporation. Each selected work has been analyzed to present its objective, methodology, and results. The BE progression to dysplasia or adenocarcinoma shows a complex pattern to be detected during endoscopic surveillance. Therefore, it is valuable to assist its diagnosis and automatic identification using computer analysis. The evaluation of the BE dysplasia can be performed through manual or automated segmentation through machine learning techniques. Finally, in this survey, we reviewed recent studies focused on the automatic detection of the neoplastic region for classification purposes using machine learning methods.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{EbigboPalmProbstetal., author = {Ebigbo, Alanna and Palm, Christoph and Probst, Andreas and Mendel, Robert and Manzeneder, Johannes and Prinz, Friederike and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Siersema, Peter and Messmann, Helmut}, title = {A technical review of artificial intelligence as applied to gastrointestinal endoscopy: clarifying the terminology}, series = {Endoscopy International Open}, volume = {07}, journal = {Endoscopy International Open}, number = {12}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/a-1010-5705}, pages = {1616 -- 1623}, abstract = {The growing number of publications on the application of artificial intelligence (AI) in medicine underlines the enormous importance and potential of this emerging field of research. In gastrointestinal endoscopy, AI has been applied to all segments of the gastrointestinal tract most importantly in the detection and characterization of colorectal polyps. However, AI research has been published also in the stomach and esophagus for both neoplastic and non-neoplastic disorders. The various technical as well as medical aspects of AI, however, remain confusing especially for non-expert physicians. This physician-engineer co-authored review explains the basic technical aspects of AI and provides a comprehensive overview of recent publications on AI in gastrointestinal endoscopy. Finally, a basic insight is offered into understanding publications on AI in gastrointestinal endoscopy.}, subject = {Diagnose}, language = {en} } @article{SouzaJrMendelStrasseretal., author = {Souza Jr., Luis Antonio de and Mendel, Robert and Strasser, Sophia and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Convolutional Neural Networks for the evaluation of cancer in Barrett's esophagus: Explainable AI to lighten up the black-box}, series = {Computers in Biology and Medicine}, volume = {135}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, issn = {0010-4825}, doi = {10.1016/j.compbiomed.2021.104578}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-20126}, pages = {1 -- 14}, abstract = {Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their level of accountability and transparency must be provided in such evaluations. The reliability related to machine learning predictions must be explained and interpreted, especially if diagnosis support is addressed. For this task, the black-box nature of deep learning techniques must be lightened up to transfer its promising results into clinical practice. Hence, we aim to investigate the use of explainable artificial intelligence techniques to quantitatively highlight discriminative regions during the classification of earlycancerous tissues in Barrett's esophagus-diagnosed patients. Four Convolutional Neural Network models (AlexNet, SqueezeNet, ResNet50, and VGG16) were analyzed using five different interpretation techniques (saliency, guided backpropagation, integrated gradients, input × gradients, and DeepLIFT) to compare their agreement with experts' previous annotations of cancerous tissue. We could show that saliency attributes match best with the manual experts' delineations. Moreover, there is moderate to high correlation between the sensitivity of a model and the human-and-computer agreement. The results also lightened that the higher the model's sensitivity, the stronger the correlation of human and computational segmentation agreement. We observed a relevant relation between computational learning and experts' insights, demonstrating how human knowledge may influence the correct computational learning.}, subject = {Deep Learning}, language = {en} } @misc{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Manzeneder, Johannes and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph and Messmann, Helmut}, title = {Artificial Intelligence in Early Barrett's Cancer: The Segmentation Task}, series = {Endoscopy}, volume = {51}, journal = {Endoscopy}, number = {04}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/s-0039-1681187}, pages = {6}, abstract = {Aims: The delineation of outer margins of early Barrett's cancer can be challenging even for experienced endoscopists. Artificial intelligence (AI) could assist endoscopists faced with this task. As of date, there is very limited experience in this domain. In this study, we demonstrate the measure of overlap (Dice coefficient = D) between highly experienced Barrett endoscopists and an AI system in the delineation of cancer margins (segmentation task). Methods: An AI system with a deep convolutional neural network (CNN) was trained and tested on high-definition endoscopic images of early Barrett's cancer (n = 33) and normal Barrett's mucosa (n = 41). The reference standard for the segmentation task were the manual delineations of tumor margins by three highly experienced Barrett endoscopists. Training of the AI system included patch generation, patch augmentation and adjustment of the CNN weights. Then, the segmentation results from patch classification and thresholding of the class probabilities. Segmentation results were evaluated using the Dice coefficient (D). Results: The Dice coefficient (D) which can range between 0 (no overlap) and 1 (complete overlap) was computed only for images correctly classified by the AI-system as cancerous. At a threshold of t = 0.5, a mean value of D = 0.72 was computed. Conclusions: AI with CNN performed reasonably well in the segmentation of the tumor region in Barrett's cancer, at least when compared with expert Barrett's endoscopists. AI holds a lot of promise as a tool for better visualization of tumor margins but may need further improvement and enhancement especially in real-time settings.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{SouzaJrEbigboProbstetal., author = {Souza Jr., Luis Antonio de and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, Jo{\~a}o Paulo and Mendel, Robert and Palm, Christoph}, title = {Barrett's Esophagus Identification Using Color Co-occurrence Matrices}, series = {31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana, 2018}, booktitle = {31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana, 2018}, doi = {10.1109/SIBGRAPI.2018.00028}, pages = {166 -- 173}, abstract = {In this work, we propose the use of single channel Color Co-occurrence Matrices for texture description of Barrett'sEsophagus (BE)and adenocarcinoma images. Further classification using supervised learning techniques, such as Optimum-Path Forest (OPF), Support Vector Machines with Radial Basisunction (SVM-RBF) and Bayesian classifier supports the contextof automatic BE and adenocarcinoma diagnosis. We validated three approaches of classification based on patches, patients and images in two datasets (MICCAI 2015 and Augsburg) using the color-and-texture descriptors and the machine learning techniques. Concerning MICCAI 2015 dataset, the best results were obtained using the blue channel for the descriptors and the supervised OPF for classification purposes in the patch-based approach, with sensitivity nearly to 73\% for positive adenocarcinoma identification and specificity close to 77\% for BE (non-cancerous) patch classification. Regarding the Augsburg dataset, the most accurate results were also obtained using both OPF classifier and blue channel descriptor for the feature extraction, with sensitivity close to 67\% and specificity around to76\%. Our work highlights new advances in the related research area and provides a promising technique that combines color and texture information, allied to three different approaches of dataset pre-processing aiming to configure robust scenarios for the classification step.}, language = {en} } @article{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Manzeneder, Johannes and Prinz, Friederike and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph and Messmann, Helmut}, title = {Real-time use of artificial intelligence in the evaluation of cancer in Barrett's oesophagus}, series = {Gut}, volume = {69}, journal = {Gut}, number = {4}, publisher = {BMJ}, address = {London}, doi = {10.1136/gutjnl-2019-319460}, pages = {615 -- 616}, abstract = {Based on previous work by our group with manual annotation of visible Barrett oesophagus (BE) cancer images, a real-time deep learning artificial intelligence (AI) system was developed. While an expert endoscopist conducts the endoscopic assessment of BE, our AI system captures random images from the real-time camera livestream and provides a global prediction (classification), as well as a dense prediction (segmentation) differentiating accurately between normal BE and early oesophageal adenocarcinoma (EAC). The AI system showed an accuracy of 89.9\% on 14 cases with neoplastic BE.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{EbigboMendelRueckertetal., author = {Ebigbo, Alanna and Mendel, Robert and R{\"u}ckert, Tobias and Schuster, Laurin and Probst, Andreas and Manzeneder, Johannes and Prinz, Friederike and Mende, Matthias and Steinbr{\"u}ck, Ingo and Faiss, Siegbert and Rauber, David and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Deprez, Pierre and Oyama, Tsuneo and Takahashi, Akiko and Seewald, Stefan and Sharma, Prateek and Byrne, Michael F. and Palm, Christoph and Messmann, Helmut}, title = {Endoscopic prediction of submucosal invasion in Barrett's cancer with the use of Artificial Intelligence: A pilot Study}, series = {Endoscopy}, volume = {53}, journal = {Endoscopy}, number = {09}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/a-1311-8570}, pages = {878 -- 883}, abstract = {Background and aims: The accurate differentiation between T1a and T1b Barrett's cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an Artificial Intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett's cancer white-light images. Methods: Endoscopic images from three tertiary care centres in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross-validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) was evaluated with the AI-system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett's cancer. Results: The sensitivity, specificity, F1 and accuracy of the AI-system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.73 and 0.71, respectively. There was no statistically significant difference between the performance of the AI-system and that of human experts with sensitivity, specificity, F1 and accuracy of 0.63, 0.78, 0.67 and 0.70 respectively. Conclusion: This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett's cancer. AI scored equal to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and in a real-life setting. Nevertheless, the correct prediction of submucosal invasion in Barret´s cancer remains challenging for both experts and AI.}, subject = {Maschinelles Lernen}, language = {en} } @article{SouzaJrPassosMendeletal., author = {Souza Jr., Luis Antonio de and Passos, Leandro A. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Assisting Barrett's esophagus identification using endoscopic data augmentation based on Generative Adversarial Networks}, series = {Computers in Biology and Medicine}, volume = {126}, journal = {Computers in Biology and Medicine}, number = {November}, publisher = {Elsevier}, doi = {10.1016/j.compbiomed.2020.104029}, pages = {12}, abstract = {Barrett's esophagus figured a swift rise in the number of cases in the past years. Although traditional diagnosis methods offered a vital role in early-stage treatment, they are generally time- and resource-consuming. In this context, computer-aided approaches for automatic diagnosis emerged in the literature since early detection is intrinsically related to remission probabilities. However, they still suffer from drawbacks because of the lack of available data for machine learning purposes, thus implying reduced recognition rates. This work introduces Generative Adversarial Networks to generate high-quality endoscopic images, thereby identifying Barrett's esophagus and adenocarcinoma more precisely. Further, Convolution Neural Networks are used for feature extraction and classification purposes. The proposed approach is validated over two datasets of endoscopic images, with the experiments conducted over the full and patch-split images. The application of Deep Convolutional Generative Adversarial Networks for the data augmentation step and LeNet-5 and AlexNet for the classification step allowed us to validate the proposed methodology over an extensive set of datasets (based on original and augmented sets), reaching results of 90\% of accuracy for the patch-based approach and 85\% for the image-based approach. Both results are based on augmented datasets and are statistically different from the ones obtained in the original datasets of the same kind. Moreover, the impact of data augmentation was evaluated in the context of image description and classification, and the results obtained using synthetic images outperformed the ones over the original datasets, as well as other recent approaches from the literature. Such results suggest promising insights related to the importance of proper data for the accurate classification concerning computer-assisted Barrett's esophagus and adenocarcinoma detection.}, subject = {Maschinelles Lernen}, language = {en} } @article{MendelRauberSouzaJretal., author = {Mendel, Robert and Rauber, David and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Error-Correcting Mean-Teacher: Corrections instead of consistency-targets applied to semi-supervised medical image segmentation}, series = {Computers in Biology and Medicine}, volume = {154}, journal = {Computers in Biology and Medicine}, number = {March}, publisher = {Elsevier}, issn = {0010-4825}, doi = {10.1016/j.compbiomed.2023.106585}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-57790}, pages = {13}, abstract = {Semantic segmentation is an essential task in medical imaging research. Many powerful deep-learning-based approaches can be employed for this problem, but they are dependent on the availability of an expansive labeled dataset. In this work, we augment such supervised segmentation models to be suitable for learning from unlabeled data. Our semi-supervised approach, termed Error-Correcting Mean-Teacher, uses an exponential moving average model like the original Mean Teacher but introduces our new paradigm of error correction. The original segmentation network is augmented to handle this secondary correction task. Both tasks build upon the core feature extraction layers of the model. For the correction task, features detected in the input image are fused with features detected in the predicted segmentation and further processed with task-specific decoder layers. The combination of image and segmentation features allows the model to correct present mistakes in the given input pair. The correction task is trained jointly on the labeled data. On unlabeled data, the exponential moving average of the original network corrects the student's prediction. The combined outputs of the students' prediction with the teachers' correction form the basis for the semi-supervised update. We evaluate our method with the 2017 and 2018 Robotic Scene Segmentation data, the ISIC 2017 and the BraTS 2020 Challenges, a proprietary Endoscopic Submucosal Dissection dataset, Cityscapes, and Pascal VOC 2012. Additionally, we analyze the impact of the individual components and examine the behavior when the amount of labeled data varies, with experiments performed on two distinct segmentation architectures. Our method shows improvements in terms of the mean Intersection over Union over the supervised baseline and competing methods. Code is available at https://github.com/CloneRob/ECMT.}, language = {en} } @inproceedings{MendelSouzaJrRauberetal., author = {Mendel, Robert and Souza Jr., Luis Antonio de and Rauber, David and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Semi-supervised Segmentation Based on Error-Correcting Supervision}, series = {Computer vision - ECCV 2020: 16th European conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIX}, booktitle = {Computer vision - ECCV 2020: 16th European conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIX}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-58525-9}, doi = {10.1007/978-3-030-58526-6_9}, pages = {141 -- 157}, abstract = {Pixel-level classification is an essential part of computer vision. For learning from labeled data, many powerful deep learning models have been developed recently. In this work, we augment such supervised segmentation models by allowing them to learn from unlabeled data. Our semi-supervised approach, termed Error-Correcting Supervision, leverages a collaborative strategy. Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network. The secondary correction network learns on the labeled data to optimally spot correct predictions, as well as to amend incorrect ones. As auxiliary regularization term, the corrector directly influences the supervised training of the segmentation network. On unlabeled data, the output of the correction network is essential to create a proxy for the unknown truth. The corrector's output is combined with the segmentation network's prediction to form the new target. We propose a loss function that incorporates both the pseudo-labels as well as the predictive certainty of the correction network. Our approach can easily be added to supervised segmentation models. We show consistent improvements over a supervised baseline on experiments on both the Pascal VOC 2012 and the Cityscapes datasets with varying amounts of labeled data.}, subject = {Semi-Supervised Learning}, language = {en} } @inproceedings{SouzaPachecodeAngeloetal., author = {Souza, Luis A. and Pacheco, Andr{\´e} G.C. and de Angelo, Gabriel G. and Oliveira-Santos, Thiago and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {LiwTERM: A Lightweight Transformer-Based Model for Dermatological Multimodal Lesion Detection}, series = {2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Manaus, Brazil, 9/30/2024 - 10/3/2024}, booktitle = {2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Manaus, Brazil, 9/30/2024 - 10/3/2024}, publisher = {IEEE}, isbn = {979-8-3503-7603-6}, doi = {10.1109/SIBGRAPI62404.2024.10716324}, pages = {1 -- 6}, abstract = {Skin cancer is the most common type of cancer in the world, accounting for approximately 30\% of all diagnosed tumors. Early diagnosis reduces mortality rates and prevents disfiguring effects in different body regions. In recent years, machine learning techniques, particularly deep learning, have shown promising results in this task, presenting studies that have demonstrated that combining a patient's clinical information with images of the lesion is crucial for improving the classification of skin lesions. Despite that, meaningful use of clinical information with multiple images is mandatory, requiring further investigation. Thus, this project aims to contribute to developing multimodal machine learning-based models to cope with the skin lesion classification task employing a lightweight transformer model. As a main hypothesis, models can take multiple images from different sources as input, along with clinical information from the patient's history, leading to a more reliable diagnosis. Our model deals with the not-trivial task of combining images and clinical information (from anamneses) concerning the skin lesions in a lightweight transformer architecture that does not demand high computation resources but still presents competitive classification results.}, language = {en} } @inproceedings{SouzaJrPassosMendeletal., author = {Souza Jr., Luis Antonio de and Passos, Leandro A. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Fine-tuning Generative Adversarial Networks using Metaheuristics}, series = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, doi = {10.1007/978-3-658-33198-6_50}, pages = {205 -- 210}, abstract = {Barrett's esophagus denotes a disorder in the digestive system that affects the esophagus' mucosal cells, causing reflux, and showing potential convergence to esophageal adenocarcinoma if not treated in initial stages. Thus, fast and reliable computer-aided diagnosis becomes considerably welcome. Nevertheless, such approaches usually suffer from imbalanced datasets, which can be addressed through Generative Adversarial Networks (GANs). Such techniques generate realistic images based on observed samples, even though at the cost of a proper selection of its hyperparameters. Many works employed a class of nature-inspired algorithms called metaheuristics to tackle the problem considering distinct deep learning approaches. Therefore, this paper's main contribution is to introduce metaheuristic techniques to fine-tune GANs in the context of Barrett's esophagus identification, as well as to investigate the feasibility of generating high-quality synthetic images for early-cancer assisted identification.}, subject = {Endoskopie}, language = {en} } @misc{MendelSouzaJrRauberetal., author = {Mendel, Robert and Souza Jr., Luis Antonio de and Rauber, David and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Abstract: Semi-supervised Segmentation Based on Error-correcting Supervision}, series = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, journal = {Bildverarbeitung f{\"u}r die Medizin 2021. Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, doi = {10.1007/978-3-658-33198-6_43}, pages = {178}, abstract = {Pixel-level classification is an essential part of computer vision. For learning from labeled data, many powerful deep learning models have been developed recently. In this work, we augment such supervised segmentation models by allowing them to learn from unlabeled data. Our semi-supervised approach, termed Error-Correcting Supervision, leverages a collaborative strategy. Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network.}, subject = {Deep Learning}, language = {en} } @article{PassosSouzaJrMendeletal., author = {Passos, Leandro A. and Souza Jr., Luis Antonio de and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Barrett's esophagus analysis using infinity Restricted Boltzmann Machines}, series = {Journal of Visual Communication and Image Representation}, volume = {59}, journal = {Journal of Visual Communication and Image Representation}, publisher = {Elsevier}, doi = {10.1016/j.jvcir.2019.01.043}, pages = {475 -- 485}, abstract = {The number of patients with Barret's esophagus (BE) has increased in the last decades. Considering the dangerousness of the disease and its evolution to adenocarcinoma, an early diagnosis of BE may provide a high probability of cancer remission. However, limitations regarding traditional methods of detection and management of BE demand alternative solutions. As such, computer-aided tools have been recently used to assist in this problem, but the challenge still persists. To manage the problem, we introduce the infinity Restricted Boltzmann Machines (iRBMs) to the task of automatic identification of Barrett's esophagus from endoscopic images of the lower esophagus. Moreover, since iRBM requires a proper selection of its meta-parameters, we also present a discriminative iRBM fine-tuning using six meta-heuristic optimization techniques. We showed that iRBMs are suitable for the context since it provides competitive results, as well as the meta-heuristic techniques showed to be appropriate for such task.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @inproceedings{SouzaJrAfonsoPalmetal., author = {Souza Jr., Luis Antonio de and Afonso, Luis Claudio Sugi and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {Barrett's Esophagus Identification Using Optimum-Path Forest}, series = {Proceedings of the 30th Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T 2017), Niter{\´o}i, Rio de Janeiro, Brazil, 2017, 17-20 October}, booktitle = {Proceedings of the 30th Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T 2017), Niter{\´o}i, Rio de Janeiro, Brazil, 2017, 17-20 October}, doi = {10.1109/SIBGRAPI.2017.47}, pages = {308 -- 314}, abstract = {Computer-assisted analysis of endoscopic images can be helpful to the automatic diagnosis and classification of neoplastic lesions. Barrett's esophagus (BE) is a common type of reflux that is not straight forward to be detected by endoscopic surveillance, thus being way susceptible to erroneous diagnosis, which can cause cancer when not treated properly. In this work, we introduce the Optimum-Path Forest (OPF) classifier to the task of automatic identification of Barrett'sesophagus, with promising results and outperforming the well known Support Vector Machines (SVM) in the aforementioned context. We consider describing endoscopic images by means of feature extractors based on key point information, such as the Speeded up Robust Features (SURF) and Scale-Invariant Feature Transform (SIFT), for further designing a bag-of-visual-wordsthat is used to feed both OPF and SVM classifiers. The best results were obtained by means of the OPF classifier for both feature extractors, with values lying on 0.732 (SURF) - 0.735(SIFT) for sensitivity, 0.782 (SURF) - 0.806 (SIFT) for specificity, and 0.738 (SURF) - 0.732 (SIFT) for the accuracy.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{EbigboMendelProbstetal., author = {Ebigbo, Alanna and Mendel, Robert and Probst, Andreas and Manzeneder, Johannes and Souza Jr., Luis Antonio de and Papa, Jo{\~a}o Paulo and Palm, Christoph and Messmann, Helmut}, title = {Computer-aided diagnosis using deep learning in the evaluation of early oesophageal adenocarcinoma}, series = {GuT}, volume = {68}, journal = {GuT}, number = {7}, publisher = {British Society of Gastroenterology}, doi = {10.1136/gutjnl-2018-317573}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-68}, pages = {1143 -- 1145}, abstract = {Computer-aided diagnosis using deep learning (CAD-DL) may be an instrument to improve endoscopic assessment of Barrett's oesophagus (BE) and early oesophageal adenocarcinoma (EAC). Based on still images from two databases, the diagnosis of EAC by CAD-DL reached sensitivities/specificities of 97\%/88\% (Augsburg data) and 92\%/100\% (Medical Image Computing and Computer-Assisted Intervention [MICCAI] data) for white light (WL) images and 94\%/80\% for narrow band images (NBI) (Augsburg data), respectively. Tumour margins delineated by experts into images were detected satisfactorily with a Dice coefficient (D) of 0.72. This could be a first step towards CAD-DL for BE assessment. If developed further, it could become a useful adjunctive tool for patient management.}, subject = {Speiser{\"o}hrenkrebs}, language = {en} } @inproceedings{SouzaJrHookPapaetal., author = {Souza Jr., Luis Antonio de and Hook, Christian and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Barrett's Esophagus Analysis Using SURF Features}, series = {Bildverarbeitung f{\"u}r die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. M{\"a}rz 2017 in Heidelberg}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2017; Algorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. M{\"a}rz 2017 in Heidelberg}, publisher = {Springer}, address = {Berlin}, doi = {10.1007/978-3-662-54345-0_34}, pages = {141 -- 146}, abstract = {The development of adenocarcinoma in Barrett's esophagus is difficult to detect by endoscopic surveillance of patients with signs of dysplasia. Computer assisted diagnosis of endoscopic images (CAD) could therefore be most helpful in the demarcation and classification of neoplastic lesions. In this study we tested the feasibility of a CAD method based on Speeded up Robust Feature Detection (SURF). A given database containing 100 images from 39 patients served as benchmark for feature based classification models. Half of the images had previously been diagnosed by five clinical experts as being "cancerous", the other half as "non-cancerous". Cancerous image regions had been visibly delineated (masked) by the clinicians. SURF features acquired from full images as well as from masked areas were utilized for the supervised training and testing of an SVM classifier. The predictive accuracy of the developed CAD system is illustrated by sensitivity and specificity values. The results based on full image matching where 0.78 (sensitivity) and 0.82 (specificity) were achieved, while the masked region approach generated results of 0.90 and 0.95, respectively.}, subject = {Speiser{\"o}hrenkrankheit}, language = {en} } @article{SouzaJrPassosSantanaetal., author = {Souza Jr., Luis Antonio de and Passos, Leandro A. and Santana, Marcos Cleison S. and Mendel, Robert and Rauber, David and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Papa, Jo{\~a}o Paulo and Palm, Christoph}, title = {Layer-selective deep representation to improve esophageal cancer classification}, series = {Medical \& Biological Engineering \& Computing}, volume = {62}, journal = {Medical \& Biological Engineering \& Computing}, publisher = {Springer Nature}, address = {Heidelberg}, doi = {10.1007/s11517-024-03142-8}, pages = {3355 -- 3372}, abstract = {Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis.For this task, the deep learning techniques' black-box nature must somehow be lightened up to clarify its promising results. Hence, we aim to investigate the impact of the ResNet-50 deep convolutional design for Barrett's esophagus and adenocarcinoma classification. For such a task, and aiming at proposing a two-step learning technique, the output of each convolutional layer that composes the ResNet-50 architecture was trained and classified for further definition of layers that would provide more impact in the architecture. We showed that local information and high-dimensional features are essential to improve the classification for our task. Besides, we observed a significant improvement when the most discriminative layers expressed more impact in the training and classification of ResNet-50 for Barrett's esophagus and adenocarcinoma classification, demonstrating that both human knowledge and computational processing may influence the correct learning of such a problem.}, language = {en} } @article{SouzaJrPachecoPassosetal., author = {Souza Jr., Luis Antonio de and Pacheco, Andr{\´e} G.C. and Passos, Leandro A. and Santana, Marcos Cleison S. and Mendel, Robert and Ebigbo, Alanna and Probst, Andreas and Messmann, Helmut and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {DeepCraftFuse: visual and deeply-learnable features work better together for esophageal cancer detection in patients with Barrett's esophagus}, series = {Neural Computing and Applications}, volume = {36}, journal = {Neural Computing and Applications}, publisher = {Springer}, address = {London}, doi = {10.1007/s00521-024-09615-z}, pages = {10445 -- 10459}, abstract = {Limitations in computer-assisted diagnosis include lack of labeled data and inability to model the relation between what experts see and what computers learn. Even though artificial intelligence and machine learning have demonstrated remarkable performances in medical image computing, their accountability and transparency level must be improved to transfer this success into clinical practice. The reliability of machine learning decisions must be explained and interpreted, especially for supporting the medical diagnosis. While deep learning techniques are broad so that unseen information might help learn patterns of interest, human insights to describe objects of interest help in decision-making. This paper proposes a novel approach, DeepCraftFuse, to address the challenge of combining information provided by deep networks with visual-based features to significantly enhance the correct identification of cancerous tissues in patients affected with Barrett's esophagus (BE). We demonstrate that DeepCraftFuse outperforms state-of-the-art techniques on private and public datasets, reaching results of around 95\% when distinguishing patients affected by BE that is either positive or negative to esophageal cancer.}, subject = {Deep Learning}, language = {en} } @article{SouzaPachecodeSouzaetal., author = {Souza, Luis A. and Pacheco, Andr{\´e} G.C. and de Souza, Alberto F. and Oliveira-Santos, Thiago and Badue, Claudine and Palm, Christoph and Papa, Jo{\~a}o Paulo}, title = {TransConv: a lightweight architecture based on transformers and convolutional neural networks for adenocarcinoma and Barrett's esophagus identification}, series = {Neural Computing and Applications}, journal = {Neural Computing and Applications}, number = {37}, publisher = {Springer}, doi = {10.1007/s00521-025-11299-y}, pages = {15535 -- 15546}, abstract = {Barrett's esophagus, also known as BE, is commonly associated with repeated exposure to stomach acid. If not treated properly, it may evolve into esophageal adenocarcinoma, aka esophageal cancer. This paper proposes TransConv, a hybrid architecture that benefits from features learned by pre-trained vision transformers (ViTs) and convolutional neural networks (CNNs), followed by a shallow neural network composed of three normalizations, ReLU activations, and fully connected layers, and a SoftMax head to distinguish between BE and esophageal cancer. TransConv is designed to be training-lightweight, and for the ViT and CNN backbone models, weights are kept frozen during training, i.e., the primary goal of TransConv is to learn the weights of the fully connected layer from both backbones only, avoiding the burden of updating their weights but still learning their final descriptions for the lightweight convolutional model. We report promising results with low computational training costs in two datasets, one public and another private. From our achievements, TransConv was able to deliver balanced accuracy results around 85\% and 86\% for each evaluated dataset, respectively, in a design that required only 50 epochs of model training, a very reduced number compared to state-of-the-art conducted studies in the same domain.}, language = {en} }