Refine
Year of publication
Document Type
- Article (60) (remove)
Is part of the Bibliography
- no (60)
Keywords
- Bildgebendes Verfahren (10)
- Maschinelles Lernen (8)
- Artificial Intelligence (7)
- Diagnose (7)
- Dreidimensionale Bildverarbeitung (6)
- Adenocarcinoma (5)
- Barrett's esophagus (5)
- Deep Learning (5)
- Deep learning (4)
- Gehirn (4)
Institute
- Fakultät Informatik und Mathematik (60) (remove)
Begutachtungsstatus
- peer-reviewed (41)
Backround
Scaphoidectomy and midcarpal fusion can be performed using traditional fixation methods like K-wires, staples, screws or different dorsal (non)locking arthrodesis systems. The aim of this study is to test the Aptus four corner locking plate and to compare the clinical findings to the data revealed by CT scans and semi-automated segmentation.
Methods:
This is a retrospective review of eleven patients suffering from scapholunate advanced collapse (SLAC) or scaphoid non-union advanced collapse (SNAC) wrist, who received a four corner fusion between August 2011 and July 2014. The clinical evaluation consisted of measuring the range of motion (ROM), strength and pain on a visual analogue scale (VAS). Additionally, the Disabilities of the Arm, Shoulder and Hand (QuickDASH) and the Mayo Wrist Score were assessed. A computerized tomography (CT) of the wrist was obtained six weeks postoperatively. After semi-automated segmentation of the CT scans, the models were post processed and surveyed.
Results
During the six-month follow-up mean range of motion (ROM) of the operated wrist was 60°, consisting of 30° extension and 30° flexion. While pain levels decreased significantly, 54% of grip strength and 89% of pinch strength were preserved compared to the contralateral healthy wrist. Union could be detected in all CT scans of the wrist. While X-ray pictures obtained postoperatively revealed no pathology, two user related technical complications were found through the 3D analysis, which correlated to the clinical outcome.
Conclusion
Due to semi-automated segmentation and 3D analysis it has been proved that the plate design can keep up to the manufacturers’ promises. Over all, this case series confirmed that the plate can compete with the coexisting techniques concerning clinical outcome, union and complication rate.
We present the Regensburg Breast Shape Model (RBSM)—a 3D statistical shape model of the female breast built from 110 breast scans acquired in a standing position, and the first publicly available. Together with the model, a fully automated, pairwise surface registration pipeline used to establish dense correspondence among 3D breast scans is introduced. Our method is computationally efficient and requires only four landmarks to guide the registration process. A major challenge when modeling female breasts from surface-only 3D breast scans is the non-separability of breast and thorax. In order to weaken the strong coupling between breast and surrounding areas, we propose to minimize the variance outside the breast region as much as possible. To achieve this goal, a novel concept called breast probability masks (BPMs) is introduced. A BPM assigns probabilities to each point of a 3D breast scan, telling how likely it is that a particular point belongs to the breast area. During registration, we use BPMs to align the template to the target as accurately as possible inside the breast region and only roughly outside. This simple yet effective strategy significantly reduces the unwanted variance outside the breast region, leading to better statistical shape models in which breast shapes are quite well decoupled from the thorax. The RBSM is thus able to produce a variety of different breast shapes as independently as possible from the shape of the thorax. Our systematic experimental evaluation reveals a generalization ability of 0.17 mm and a specificity of 2.8 mm. To underline the expressiveness of the proposed model, we finally demonstrate in two showcase applications how the RBSM can be used for surgical outcome simulation and the prediction of a missing breast from the remaining one. Our model is available at https://www.rbsm.re-mic.de/.
Whole-body PET/CT imaging
(2008)
Aim
Combined whole-body (WB) PET/CT imaging provides better overall co-registration compared to separate CT and PET. However, in clinical routine local PET-CT mis-registration cannot be avoided. Thus, the reconstructed PET tracer distribution may be biased when using the misaligned CT transmission data for CT-based attenuation correction (CT-AC). We investigate the feasibility of retrospective co-registration techniques to align CT and PET images prior to CT-AC, thus improving potentially the quality of combined PET/CT imaging in clinical routine.
Methods
First, using a commercial software registration package CT images were aligned to the uncorrected PET data by rigid and non-rigid registration methods. Co-registration accuracy of both alignment approaches was assessed by reviewing the PET tracer uptake patterns (visual, linked cursor display) following attenuation correction based on the original and co-registered CT. Second, we investigated non-rigid registration based on a prototype ITK implementation of the B-spline algorithm on a similar targeted MR-CT registration task, there showing promising results.
Results
Manual rigid, landmark-based co-registration introduced unacceptable misalignment, in particular in peripheral areas of the whole-body images. Manual, non-rigid landmark-based co-registration prior to CT-AC was successful with minor loco-regional distortions. Nevertheless, neither rigid nor non-rigid automatic co-registration based on the Mutual Information image to image metric succeeded in co-registering the CT and noAC-PET images. In contrast to widely available commercial software registration our implementation of an alternative automated, non-rigid B-spline co-registration technique yielded promising results in this setting with MR-CT data.
Conclusion
In clinical PET/CT imaging, retrospective registration of CT and uncorrected PET images may improve the quality of the AC-PET images. As of today no validated and clinically viable commercial registration software is in routine use. This has triggered our efforts in pursuing new approaches to a validated, non-rigid co-registration algorithm applicable to whole-body PET/CT imaging of which first results are presented here. This approach appears suitable for applications in retrospective WB-PET/CT alignment.
Ziel
Kombinierte PET/CT-Bildgebung ermöglicht verbesserte Koregistrierung von PET- und CT-Daten gegenüber separat akquirierten Bildern. Trotzdem entstehen in der klinischen Anwendung lokale Fehlregistrierungen, die zu Fehlern in der rekonstruierten PET- Tracerverteilung führen können, falls die unregistrierten CT-Daten zur Schwächungskorrektur (AC) der Emissionsdaten verwendet werden. Wir untersuchen daher die Anwendung von Bildregistrierungsalgorithmen vor der CT-basierten AC zur Verbesserung der PET-Aufnahmen.
Methoden
Mittels einer kommerziellen Registrierungssoftware wurden die CT-Daten eines PET/CT- Tomographen durch landmarken- und intensitätsbasierte rigide (starre) und nicht-rigide Registrierungsverfahren räumlich an die unkorrigierten PET-Emissionsdaten angepasst und zur AC verwendet. Zur Bewertung wurden die Tracerverteilungen in den PET-Bildern (vor AC, CT-AC, CT-AC nach Koregistrierung) visuell und mit Hilfe korrelierter Fadenkreuze verglichen. Zusätzlich untersuchten wir die ITK-Implementierung der bekannten B-spline basierten, nicht-rigiden Registrierungsansätze im Hinblick auf ihre Verwendbarkeit für die multimodale PET/CT-Ganzkörperregistrierung.
Ergebnisse
Mittels landmarkenbasierter, nicht-rigider Registrierung konnte die Tracerverteilung in den PET-Daten lokal verbessert werden. Landmarkenbasierte rigide Registrierung führte zu starker Fehlregistrierung in entfernten Körperregionen. Automatische rigide und nicht-rigide Registrierung unter Verwendung der Mutual-Information-Ähnlichkeitsmetrik versagte auf allen verwendeten Datensätzen. Die automatische Registrierung mit B-spline-Funktionen zeigte vielversprechende Resultate in der Anwendung auf einem ähnlich gelagerten CT–MR-Registrierungsproblem.
Fazit
Retrospektive, nicht-rigide Registrierung unkorrigierter PET- und CT-Aufnahmen aus kombinierten Aufnahmensystemen vor der AC kann die Qualität von PET-Aufnahmen im klinischen Einsatz verbessern. Trotzdem steht bis heute im klinischen Alltag keine validierte, automatische Registrierungssoftware zur Verfügung. Wir verfolgen dazu Ansätze für validierte, nicht-rigide Bildregistrierung für den klinischen Einsatz und präsentieren erste Ergebnisse.
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.
Background and aims
Celiac disease with its endoscopic manifestation of villous atrophy is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of villous atrophy at routine esophagogastroduodenoscopy may improve diagnostic performance.
Methods
A dataset of 858 endoscopic images of 182 patients with villous atrophy and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet 18 deep learning model to detect villous atrophy. An external data set was used to test the algorithm, in addition to six fellows and four board certified gastroenterologists. Fellows could consult the AI algorithm’s result during the test. From their consultation distribution, a stratification of test images into “easy” and “difficult” was performed and used for classified performance measurement.
Results
External validation of the AI algorithm yielded values of 90 %, 76 %, and 84 % for sensitivity, specificity, and accuracy, respectively. Fellows scored values of 63 %, 72 % and 67 %, while the corresponding values in experts were 72 %, 69 % and 71 %, respectively. AI consultation significantly improved all trainee performance statistics. While fellows and experts showed significantly lower performance for “difficult” images, the performance of the AI algorithm was stable.
Conclusion
In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of villous atrophy on endoscopic still images. AI decision support significantly improved the performance of non-expert endoscopists. The stable performance on “difficult” images suggests a further positive add-on effect in challenging cases.
ARTIFICIAL INTELLIGENCE (AI) – ASSISTED VESSEL AND TISSUE RECOGNITION IN THIRD-SPACE ENDOSCOPY
(2022)
Aims
Third-space endoscopy procedures such as endoscopic submucosal dissection (ESD) and peroral endoscopic myotomy (POEM) are complex interventions with elevated risk of operator-dependent adverse events, such as intra-procedural bleeding and perforation. We aimed to design an artificial intelligence clinical decision support solution (AI-CDSS, “Smart ESD”) for the detection and delineation of vessels, tissue structures, and instruments during third-space endoscopy procedures.
Methods
Twelve full-length third-space endoscopy videos were extracted from the Augsburg University Hospital database. 1686 frames were annotated for the following categories: Submucosal layer, blood vessels, electrosurgical knife and endoscopic instrument. A DeepLabv3+neural network with a 101-layer ResNet backbone was trained and validated internally. Finally, the ability of the AI system to detect visible vessels during ESD and POEM was determined on 24 separate video clips of 7 to 46 seconds duration and showing 33 predefined vessels. These video clips were also assessed by an expert in third-space endoscopy.
Results
Smart ESD showed a vessel detection rate (VDR) of 93.94%, while an average of 1.87 false positive signals were recorded per minute. VDR of the expert endoscopist was 90.1% with no false positive findings. On the internal validation data set using still images, the AI system demonstrated an Intersection over Union (IoU), mean Dice score and pixel accuracy of 63.47%, 76.18% and 86.61%, respectively.
Conclusions
This is the first AI-CDSS aiming to mitigate operator-dependent limitations during third-space endoscopy. Further clinical trials are underway to better understand the role of AI in such procedures.
In the field of computer- and robot-assisted minimally invasive surgery, enormous progress has been made in recent years based on the recognition of surgical instruments in endoscopic images and videos. In particular, the determination of the position and type of instruments is of great interest. Current work involves both spatial and temporal information, with the idea that predicting the movement of surgical tools over time may improve the quality of the final segmentations. The provision of publicly available datasets has recently encouraged the development of new methods, mainly based on deep learning. In this review, we identify and characterize datasets used for method development and evaluation and quantify their frequency of use in the literature. We further present an overview of the current state of research regarding the segmentation and tracking of minimally invasive surgical instruments in endoscopic images and videos. The paper focuses on methods that work purely visually, without markers of any kind attached to the instruments, considering both single-frame semantic and instance segmentation approaches, as well as those that incorporate temporal information. The publications analyzed were identified through the platforms Google Scholar, Web of Science, and PubMed. The search terms used were “instrument segmentation”, “instrument tracking”, “surgical tool segmentation”, and “surgical tool tracking”, resulting in a total of 741 articles published between 01/2015 and 07/2023, of which 123 were included using systematic selection criteria. A discussion of the reviewed literature is provided, highlighting existing shortcomings and emphasizing the available potential for future developments.
The endoscopic features associated with eosinophilic esophagitis (EoE) may be missed during routine endoscopy. We aimed to develop and evaluate an Artificial Intelligence (AI) algorithm for detecting and quantifying the endoscopic features of EoE in white light images, supplemented by the EoE Endoscopic Reference Score (EREFS). An AI algorithm (AI-EoE) was constructed and trained to differentiate between EoE and normal esophagus using endoscopic white light images extracted from the database of the University Hospital Augsburg. In addition to binary classification, a second algorithm was trained with specific auxiliary branches for each EREFS feature (AI-EoE-EREFS). The AI algorithms were evaluated on an external data set from the University of North Carolina, Chapel Hill (UNC), and compared with the performance of human endoscopists with varying levels of experience. The overall sensitivity, specificity, and accuracy of AI-EoE were 0.93 for all measures, while the AUC was 0.986. With additional auxiliary branches for the EREFS categories, the AI algorithm (AI-EoEEREFS) performance improved to 0.96, 0.94, 0.95, and 0.992 for sensitivity, specificity, accuracy, and AUC, respectively. AI-EoE and AI-EoE-EREFS performed significantly better than endoscopy beginners and senior fellows on the same set of images. An AI algorithm can be trained to detect and quantify endoscopic features of EoE with excellent performance scores. The addition of the EREFS criteria improved the performance of the AI algorithm, which performed significantly better than endoscopists with a lower or medium experience level.
Digital nerve lesions result in a loss of tactile sensation reflected by an anesthetic area (AA) at the radial or ulnar aspect of the respective digit. Yet, available tools to monitor the recovery of tactile sense have been criticized for their lack of validity. However, the precise quantification of AA dynamics by three-dimensional (3-D) imaging could serve as an accurate surrogate to monitor recovery following digital nerve repair.
For validation, AAs were marked on digits of healthy volunteers to simulate the AA of an impaired cutaneous innervation. Three dimensional models were composed from raw images that had been acquired with a 3-D camera (Vectra H2) to precisely quantify relative AA for each digit (3-D models, n= 80). Operator properties varied regarding individual experience in 3-D imaging and image processing. Additionally, the concept was applied in a clinical case study.
Images taken by experienced photographers were rated better quality (p< 0.001) and needed less processing time (p= 0.020). Quantification of the relative AA was neither altered significantly by experience levels of the photographer (p= 0.425) nor the image assembler (p= 0.749).
The proposed concept allows precise and reliable surface quantification of digits and can be performed consistently without relevant distortion by lack of examiner experience. Routine 3-D imaging of the AA has the great potential to provide visual evidence of various returning states of sensation and to convert sensory nerve recovery into a metric variable with high responsiveness to temporal progress.