CHAOS Challenge- combined (CT-MR) healthy abdominal organ segmentation

Kavur, A. Emre
Gezer, N. Sinem
Baris, Mustafa
Conze, Pierre-Henri
Groza, Vladimir
Duc Duy Pham, Duc Duy Pham
Chatterjee, Soumick
Ernst, Philipp
Ozkan, Savas
Baydar, Bora
Lachinov, Dmitry
Han, Shuo
Pauli, Josef
Isensee, Fabian
Perkonigg, Matthias
Sathish, Rachana
Rajan, Ronnie
Sheet, Debdoot
Dovletov, Gurbandurdy
Speck, Oliver
Nurnberger, Andreas
Maier-Hein, Klaus H.
Akar, Gözde
Ünal, Gözde
Segmentation of abdominal organs has been a comprehensive, yet unresolved, research field for many years. In the last decade, intensive developments in deep learning (DL) introduced new state-of-the-art segmentation systems. Despite outperforming the overall accuracy of existing systems, the effects of DL model properties and parameters on the performance are hard to interpret. This makes comparative anal-ysis a necessary tool towards interpretable studies and systems. Moreover, the performance of DL for emerging learning approaches such as cross-modality and multi-modal semantic segmentation tasks has been rarely discussed. In order to expand the knowledge on these topics, the CHAOS & ndash; Combined (CT-MR) Healthy Abdominal Organ Segmentation challenge was organized in conjunction with the IEEE Interna-tional Symposium on Biomedical Imaging (ISBI), 2019, in Venice, Italy. Abdominal organ segmentation from routine acquisitions plays an important role in several clinical applications, such as pre-surgical planning or morphological and volumetric follow-ups for various diseases. These applications require a certain level of performance on a diverse set of metrics such as maximum symmetric surface distance (MSSD) to determine surgical error-margin or overlap errors for tracking size and shape differences. Pre-vious abdomen related challenges are mainly focused on tumor/lesion detection and/or classification with a single modality. Conversely, CHAOS provides both abdominal CT and MR data from healthy subjects for single and multiple abdominal organ segmentation. Five different but complementary tasks were de-signed to analyze the capabilities of participating approaches from multiple perspectives. The results were investigated thoroughly, compared with manual annotations and interactive methods. The analysis shows that the performance of DL models for single modality (CT / MR) can show reliable volumetric analysis performance (DICE: 0.98 +/- 0.00 / 0.95 +/- 0.01), but the best MSSD performance remains limited (21.89 +/- 13.94 / 20.85 +/- 10.63 mm). The performances of participating models decrease dramatically for cross-modality tasks both for the liver (DICE: 0.88 +/- 0.15 MSSD: 36.33 +/- 21.97 mm). Despite contrary examples on different applications, multi-tasking DL models designed to segment all organs are observed to perform worse compared to organ-specific ones (performance drop around 5%). Nevertheless, some of the successful models show better performance with their multi-organ versions. We conclude that the exploration of those pros and cons in both single vs multi-organ and cross-modality segmentations is poised to have an impact on further research for developing effective algorithms that would support real-world clinical applications. Finally, having more than 1500 participants and receiving more than 550 submissions, another important contribution of this study is the analysis on shortcomings of challenge organizations such as the effects of multiple submissions and peeking phenomenon. (c) 2020 Elsevier B.V. All rights reserved.


Prediction of multiphase flow properties from nuclear magnetic resonance imaging
Karaman, Türker; Akın, Serhat; Department of Petroleum and Natural Gas Engineering (2009)
In this study a hybrid Pore Network (PN) model that simulates two-phase (water-oil) drainage and imbibition mechanisms is developed. The developed model produces Nuclear Magnetic Resonance (NMR) T2 relaxation times using correlations available in the literature. The developed PN was calibrated using experimental relative permeability data obtained for Berea Sandstone, Kuzey Marmara Limestone, Yeniköy Dolostone and Dolomitic Limestone core plugs. Pore network body and throat parameters were obtained from ser...
Segmentation registration and visualization of medical images for treatment planning
Tuncer, Özgür; Severcan, Mete; Department of Electrical and Electronics Engineering (2003)
Medical imaging has become the key to access inside human body for the purpose of diagnosis and treatment planning. In order to understand the effectiveness of planned treatment following the diagnosis, treated body part may have to be monitored several times during a period of time. Information gained from successive imaging of body part provides guidance to next step of treatment. Comparison of images or datasets taken at different times requires registration of these images or datasets since the same con...
Narcı, Kübra; Aydın Son, Yeşim; Atalay, Rengül; Department of Medical Informatics (2021-9-06)
The underlying mechanism for the development of Hepatocellular Carcinoma (HCC) is highly complex due to tissue heterogeneity. Although the traditional approaches mainly focus on a single gene or locus, understanding the variations in the signaling pathways of cancerogenic cells during hepatocarcinogenesis may help to develop novel strategies for treatment and drug development to prevent cancer progression in the patients. This thesis study primarily focuses on unveiling the transcriptome sequencing of dif...
Phase-field approach to model fracture in human aorta
Gültekin, Osman; Holzapfel, Gerhard A.; Dal, Hüsnü (null; 2019-08-23)
Over the last decades the supra-physiological and pathological aspects of arterial tissues have become a prominent research topic in computational biomechanics in terms of constitutive modeling considering damage and fracture [1]. The current study presents a variational approach to the fracture of human arterial walls, featuring a thermodynamically consistent, gradient-type, diffusive crack phase-field approach. A power balance renders the Euler-Lagrange equations of the multi-field problem, i.e. the defor...
Systems-level analysis reveals multiple modulators of epithelial-mesenchymal transition and identifies DNAJB4 and CD81 as novel metastasis inducers in breast cancer
Kagiali, Zeynep Cansu Üretmen; Sanal, Erdem; Karayel, Özge; Polat, Ayşe Nur; Saatçi, Özge; Ersan, Pelin Gülizar; Trappe, Kathrin; Renard, Bernhard Y.; Önder, Tamer T.; Tunçbağ, Nurcan; Şahin, Özgür; Özlü, Nurhan (American Society for Biochemistry & Molecular Biology (ASBMB), 2019-09)
Epithelial-mesenchymal transition (EMT) is driven by complex signaling events that induce dramatic biochemical and morphological changes whereby epithelial cells are converted into cancer cells. However, the underlying molecular mechanisms remain elusive. Here, we used mass spectrometry based quantitative proteomics approach to systematically analyze the post-translational biochemical changes that drive differentiation of human mammary epithelial (HMLE) cells into mesenchymal. We identified 314 proteins out...
Citation Formats
A. E. Kavur et al., “CHAOS Challenge- combined (CT-MR) healthy abdominal organ segmentation,” MEDICAL IMAGE ANALYSIS, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: