TY - GEN A1 - Tack, Alexander A1 - Shestakov, Alexey A1 - Lüdke, David A1 - Zachow, Stefan T1 - A deep multi-task learning method for detection of meniscal tears in MRI data from the Osteoarthritis Initiative database N2 - We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on a complete 3D MRI scan. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, meniscal body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data or how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences. T3 - ZIB-Report - 21-33 Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-84415 SN - 1438-0064 ER - TY - JOUR A1 - Tack, Alexander A1 - Shestakov, Alexey A1 - Lüdke, David A1 - Zachow, Stefan T1 - A deep multi-task learning method for detection of meniscal tears in MRI data from the Osteoarthritis Initiative database JF - Frontiers in Bioengineering and Biotechnology, section Biomechanics N2 - We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on a complete 3D MRI scan. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, meniscal body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data or how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences. Y1 - 2021 U6 - https://doi.org/10.3389/fbioe.2021.747217 SP - 28 EP - 41 ER - TY - JOUR A1 - Tack, Alexander A1 - Preim, Bernhard A1 - Zachow, Stefan T1 - Fully automated Assessment of Knee Alignment from Full-Leg X-Rays employing a "YOLOv4 And Resnet Landmark regression Algorithm" (YARLA): Data from the Osteoarthritis Initiative JF - Computer Methods and Programs in Biomedicine N2 - We present a method for the quantification of knee alignment from full-leg X-Rays. A state-of-the-art object detector, YOLOv4, was trained to locate regions of interests (ROIs) in full-leg X-Ray images for the hip joint, the knee, and the ankle. Residual neural networks (ResNets) were trained to regress landmark coordinates for each ROI.Based on the detected landmarks the knee alignment, i.e., the hip-knee-ankle (HKA) angle, was computed. The accuracy of landmark detection was evaluated by a comparison to manually placed landmarks for 360 legs in 180 X-Rays. The accuracy of HKA angle computations was assessed on the basis of 2,943 X-Rays. Results of YARLA were compared to the results of two independent image reading studies(Cooke; Duryea) both publicly accessible via the Osteoarthritis Initiative. The agreement was evaluated using Spearman's Rho, and weighted kappa as well as regarding the correspondence of the class assignment (varus/neutral/valgus). The average difference between YARLA and manually placed landmarks was less than 2.0+- 1.5 mm for all structures (hip, knee, ankle). The average mismatch between HKA angle determinations of Cooke and Duryea was 0.09 +- 0.63°; YARLA resulted in a mismatch of 0.10 +- 0.74° compared to Cooke and of 0.18 +- 0.64° compared to Duryea. Cooke and Duryea agreed almost perfectly with respect to a weighted kappa value of 0.86, and showed an excellent reliability as measured by a Spearman's Rho value of 0.99. Similar values were achieved by YARLA, i.e., a weighted kappa value of0.83 and 0.87 and a Spearman's Rho value of 0.98 and 0.99 to Cooke and Duryea,respectively. Cooke and Duryea agreed in 92% of all class assignments and YARLA did so in 90% against Cooke and 92% against Duryea. In conclusion, YARLA achieved results comparable to those of human experts and thus provides a basis for an automated assessment of knee alignment in full-leg X-Rays. Y1 - 2021 U6 - https://doi.org/https://doi.org/10.1016/j.cmpb.2021.106080 VL - 205 IS - 106080 ER - TY - GEN A1 - Tack, Alexander A1 - Ambellan, Felix A1 - Zachow, Stefan T1 - Towards novel osteoarthritis biomarkers: Multi-criteria evaluation of 46,996 segmented knee MRI data from the Osteoarthritis Initiative (Supplementary Material) T2 - PLOS One N2 - Convolutional neural networks (CNNs) are the state-of-the-art for automated assessment of knee osteoarthritis (KOA) from medical image data. However, these methods lack interpretability, mainly focus on image texture, and cannot completely grasp the analyzed anatomies’ shapes. In this study we assess the informative value of quantitative features derived from segmentations in order to assess their potential as an alternative or extension to CNN-based approaches regarding multiple aspects of KOA A fully automated method is employed to segment six anatomical structures around the knee (femoral and tibial bones, femoral and tibial cartilages, and both menisci) in 46,996 MRI scans. Based on these segmentations, quantitative features are computed, i.e., measurements such as cartilage volume, meniscal extrusion and tibial coverage, as well as geometric features based on a statistical shape encoding of the anatomies. The feature quality is assessed by investigating their association to the Kellgren-Lawrence grade (KLG), joint space narrowing (JSN), incident KOA, and total knee replacement (TKR). Using gold standard labels from the Osteoarthritis Initiative database the balanced accuracy (BA), the area under the Receiver Operating Characteristic curve (AUC), and weighted kappa statistics are evaluated. Features based on shape encodings of femur, tibia, and menisci plus the performed measurements showed most potential as KOA biomarkers. Differentiation between healthy and severely arthritic knees yielded BAs of up to 99%, 84% were achieved for diagnosis of early KOA. Substantial agreement with weighted kappa values of 0.73, 0.73, and 0.79 were achieved for classification of the grade of medial JSN, lateral JSN, and KLG, respectively. The AUC was 0.60 and 0.75 for prediction of incident KOA and TKR within 5 years, respectively. Quantitative features from automated segmentations yield excellent results for KLG and JSN classification and show potential for incident KOA and TKR prediction. The validity of these features as KOA biomarkers should be further evaluated, especially as extensions of CNN-based approaches. To foster such developments we make all segmentations publicly available together with this publication. Y1 - 2021 U6 - https://doi.org/10.12752/8328 N1 - 46,996 automated segmentations for data from the OAI database. VL - 16 IS - 10 ER - TY - JOUR A1 - Tack, Alexander A1 - Ambellan, Felix A1 - Zachow, Stefan T1 - Towards novel osteoarthritis biomarkers: Multi-criteria evaluation of 46,996 segmented knee MRI data from the Osteoarthritis Initiative JF - PLOS One N2 - Convolutional neural networks (CNNs) are the state-of-the-art for automated assessment of knee osteoarthritis (KOA) from medical image data. However, these methods lack interpretability, mainly focus on image texture, and cannot completely grasp the analyzed anatomies’ shapes. In this study we assess the informative value of quantitative features derived from segmentations in order to assess their potential as an alternative or extension to CNN-based approaches regarding multiple aspects of KOA. Six anatomical structures around the knee (femoral and tibial bones, femoral and tibial cartilages, and both menisci) are segmented in 46,996 MRI scans. Based on these segmentations, quantitative features are computed, i.e., measurements such as cartilage volume, meniscal extrusion and tibial coverage, as well as geometric features based on a statistical shape encoding of the anatomies. The feature quality is assessed by investigating their association to the Kellgren-Lawrence grade (KLG), joint space narrowing (JSN), incident KOA, and total knee replacement (TKR). Using gold standard labels from the Osteoarthritis Initiative database the balanced accuracy (BA), the area under the Receiver Operating Characteristic curve (AUC), and weighted kappa statistics are evaluated. Features based on shape encodings of femur, tibia, and menisci plus the performed measurements showed most potential as KOA biomarkers. Differentiation between non-arthritic and severely arthritic knees yielded BAs of up to 99%, 84% were achieved for diagnosis of early KOA. Weighted kappa values of 0.73, 0.72, and 0.78 were achieved for classification of the grade of medial JSN, lateral JSN, and KLG, respectively. The AUC was 0.61 and 0.76 for prediction of incident KOA and TKR within one year, respectively. Quantitative features from automated segmentations provide novel biomarkers for KLG and JSN classification and show potential for incident KOA and TKR prediction. The validity of these features should be further evaluated, especially as extensions of CNN- based approaches. To foster such developments we make all segmentations publicly available together with this publication. Y1 - 2021 U6 - https://doi.org/10.1371/journal.pone.0258855 VL - 16 IS - 10 ER - TY - JOUR A1 - Sekuboyina, Anjany A1 - Husseini, Malek E. A1 - Bayat, Amirhossein A1 - Löffler, Maximilian A1 - Liebl, Hans A1 - Li, Hongwei A1 - Tetteh, Giles A1 - Kukačka, Jan A1 - Payer, Christian A1 - Štern, Darko A1 - Urschler, Martin A1 - Chen, Maodong A1 - Cheng, Dalong A1 - Lessmann, Nikolas A1 - Hu, Yujin A1 - Wang, Tianfu A1 - Yang, Dong A1 - Xu, Daguang A1 - Ambellan, Felix A1 - Amiranashvili, Tamaz A1 - Ehlke, Moritz A1 - Lamecker, Hans A1 - Lehnert, Sebastian A1 - Lirio, Marilia A1 - de Olaguer, Nicolás Pérez A1 - Ramm, Heiko A1 - Sahu, Manish A1 - Tack, Alexander A1 - Zachow, Stefan A1 - Jiang, Tao A1 - Ma, Xinjun A1 - Angerman, Christoph A1 - Wang, Xin A1 - Brown, Kevin A1 - Kirszenberg, Alexandre A1 - Puybareau, Élodie A1 - Chen, Di A1 - Bai, Yiwei A1 - Rapazzo, Brandon H. A1 - Yeah, Timyoas A1 - Zhang, Amber A1 - Xu, Shangliang A1 - Hou, Feng A1 - He, Zhiqiang A1 - Zeng, Chan A1 - Xiangshang, Zheng A1 - Liming, Xu A1 - Netherton, Tucker J. A1 - Mumme, Raymond P. A1 - Court, Laurence E. A1 - Huang, Zixun A1 - He, Chenhang A1 - Wang, Li-Wen A1 - Ling, Sai Ho A1 - Huynh, Lê Duy A1 - Boutry, Nicolas A1 - Jakubicek, Roman A1 - Chmelik, Jiri A1 - Mulay, Supriti A1 - Sivaprakasam, Mohanasankar A1 - Paetzold, Johannes C. A1 - Shit, Suprosanna A1 - Ezhov, Ivan A1 - Wiestler, Benedikt A1 - Glocker, Ben A1 - Valentinitsch, Alexander A1 - Rempfler, Markus A1 - Menze, Björn H. A1 - Kirschke, Jan S. T1 - VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images JF - Medical Image Analysis N2 - Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse. Y1 - 2021 U6 - https://doi.org/10.1016/j.media.2021.102166 VL - 73 ER - TY - JOUR A1 - Sahu, Manish A1 - Mukhopadhyay, Anirban A1 - Zachow, Stefan T1 - Simulation-to-Real domain adaptation with teacher-student learning for endoscopic instrument segmentation JF - International Journal of Computer Assisted Radiology and Surgery N2 - Purpose Segmentation of surgical instruments in endoscopic video streams is essential for automated surgical scene understanding and process modeling. However, relying on fully supervised deep learning for this task is challenging because manual annotation occupies valuable time of the clinical experts. Methods We introduce a teacher–student learning approach that learns jointly from annotated simulation data and unlabeled real data to tackle the challenges in simulation-to-real unsupervised domain adaptation for endoscopic image segmentation. Results Empirical results on three datasets highlight the effectiveness of the proposed framework over current approaches for the endoscopic instrument segmentation task. Additionally, we provide analysis of major factors affecting the performance on all datasets to highlight the strengths and failure modes of our approach. Conclusions We show that our proposed approach can successfully exploit the unlabeled real endoscopic video frames and improve generalization performance over pure simulation-based training and the previous state-of-the-art. This takes us one step closer to effective segmentation of surgical instrument in the annotation scarce setting. Y1 - 2021 U6 - https://doi.org/10.1007/s11548-021-02383-4 N1 - Honorary Mention: Machine Learning for Computer-Assisted Intervention (CAI) Award @IPCAI2021 N1 - Honorary Mention: Audience Award for Best Innovation @IPCAI2021 VL - 16 SP - 849 EP - 859 PB - Springer Nature ER - TY - JOUR A1 - Picht, Thomas A1 - Le Calve, Maxime A1 - Tomasello, Rosario A1 - Fekonja, Lucius A1 - Gholami, Mohammad Fardin A1 - Bruhn, Matthias A1 - Zwick, Carola A1 - Rabe, Jürgen P. A1 - Müller-Birn, Claudia A1 - Vajkoczy, Peter A1 - Sauer, Igor M. A1 - Zachow, Stefan A1 - Nyakatura, John A. A1 - Ribault, Patricia A1 - Pulvermüller, Friedemann T1 - A note on neurosurgical resection and why we need to rethink cutting JF - Neurosurgery Y1 - 2021 U6 - https://doi.org/10.1093/neuros/nyab326 VL - 89 IS - 5 SP - 289 EP - 291 ER - TY - JOUR A1 - Li, Jianning A1 - Pimentel, Pedro A1 - Szengel, Angelika A1 - Ehlke, Moritz A1 - Lamecker, Hans A1 - Zachow, Stefan A1 - Estacio, Laura A1 - Doenitz, Christian A1 - Ramm, Heiko A1 - Shi, Haochen A1 - Chen, Xiaojun A1 - Matzkin, Franco A1 - Newcombe, Virginia A1 - Ferrante, Enzo A1 - Jin, Yuan A1 - Ellis, David G. A1 - Aizenberg, Michele R. A1 - Kodym, Oldrich A1 - Spanel, Michal A1 - Herout, Adam A1 - Mainprize, James G. A1 - Fishman, Zachary A1 - Hardisty, Michael R. A1 - Bayat, Amirhossein A1 - Shit, Suprosanna A1 - Wang, Bomin A1 - Liu, Zhi A1 - Eder, Matthias A1 - Pepe, Antonio A1 - Gsaxner, Christina A1 - Alves, Victor A1 - Zefferer, Ulrike A1 - von Campe, Cord A1 - Pistracher, Karin A1 - Schäfer, Ute A1 - Schmalstieg, Dieter A1 - Menze, Bjoern H. A1 - Glocker, Ben A1 - Egger, Jan T1 - AutoImplant 2020 - First MICCAI Challenge on Automatic Cranial Implant Design JF - IEEE Transactions on Medical Imaging N2 - The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use. Y1 - 2021 U6 - https://doi.org/10.1109/TMI.2021.3077047 SN - 0278-0062 VL - 40 IS - 9 SP - 2329 EP - 2342 ER - TY - JOUR A1 - Hembus, Jessica A1 - Ambellan, Felix A1 - Zachow, Stefan A1 - Bader, Rainer T1 - Establishment of a rolling-sliding test bench to analyze abrasive wear propagation of different bearing materials for knee implants JF - Applied Sciences N2 - Currently, new materials for knee implants need to be extensively and expensive tested in a knee wear simulator in a realized design. However, using a rolling-sliding test bench, these materials can be examined under the same test conditions but with simplified geometries. In the present study, the test bench was optimized, and forces were adapted to the physiological contact pressure in the knee joint using the available geometric parameters. Various polymers made of polyethylene and polyurethane articulating against test wheels made of cobalt-chromium and aluminum titanate were tested in the test bench using adapted forces based on ISO 14243-1. Polyurethane materials showed distinctly higher wear rates than polyethylene materials and showed inadequate wear resistance for use as knee implant material. Thus, the rolling-sliding test bench is an adaptable test setup for evaluating newly developed bearing materials for knee implants. It combines the advantages of screening and simulator tests and allows testing of various bearing materials under physiological load and tribological conditions of the human knee joint. The wear behavior of different material compositions and the influence of surface geometry and quality can be initially investigated without the need to produce complex implant prototypes of total knee endoprosthesis or interpositional spacers. Y1 - 2021 U6 - https://doi.org/10.3390/app11041886 VL - 11 IS - 4 ER -