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

Kavur, Ali Emre; Gezer, Naciye Sinem; Barış, Mustafa; Aslan, Sinem; Conze, Pierre-Henri; Groza, Vladimir; Pham, Duc Duy; Chatterjee, Soumick; Ernst, Philipp; Özkan, Sevgi; Baydar, Bora; Lachinov, Dmitrii; Han, S.; Pauli, Josef; Isensee, Fabian; Perkonigg, Matthias; Sathish, Rachana; Rajan, Ronnie; Sheet, Debdoot; Dovletov, Gurbandurdy; Speck, Oliver; Nürnberger, Andreas; Maier‐Hein, Klaus H.; Akar, Gözde Bozdağı; Ünal, Gözde; Dıcle, Oğuz; Selver, M. Alper

doi:10.1016/j.media.2020.101950

Cited by 438 publications

(217 citation statements)

References 28 publications

Supporting

Mentioning

176

Contrasting

Order By: Relevance

“…It can be found that the performances of all organs are lower than the performances in existing benchmarks (Table 2). Although fully supervised abdominal organ segmentation seems to be a solved problem (e.g., liver, kidney, and spleen segmentation) because SOTA methods have achieved interexpert accuracy [63], [71]. However, our studies on a large and diverse dataset demonstrate that abdominal organ seg-mentation is still not a solved problem, especially for the challenging cases and situations.…”

Section: Baseline Resultsmentioning

confidence: 77%

“…CHAOS (Combined Healthy Abdominal Organ Segmentation) dataset [63] consists of 20 training cases with liver annotations and 20 testing cases with hidden annotations, which are provided by Dokuz Eylul University (DEU) hospital (İzmir, Turkey). Different from the other datasets, all the 40 liver CT cases are from healthy population.…”

Section: Existing Abdominal Ct Organ Segmentation Benchmark Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?

Zhang

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

176

View full text Add to dashboard Cite

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs (i.e., liver, kidney, and spleen) seems to be a solved problem as the state-of-the-art (SOTA) methods have achieved comparable results with inter-observer variability on existing benchmark datasets. However, most of the existing abdominal organ segmentation benchmark datasets only contain single-center, single-phase, single-vendor, or single-disease cases, thus, it is unclear whether the excellent performance can generalize on more diverse datasets. In this paper, we present a large and diverse abdominal CT organ segmentation dataset, termed as AbdomenCT-1K, with more than 1000 (1K) CT scans from 11 countries, including multi-center, multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation, as well as reveal the unsolved segmentation problems of the SOTA method, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we build four organ segmentation benchmarks for fully supervised, semi-supervised, weakly supervised, and continual learning, which are currently challenging and active research topics. Accordingly, we develop a simple and effective method for each benchmark, which can be used as out-of-the-box methods and strong baselines. We believe the introduction of the AbdomenCT-1K dataset will promote the future in-depth research towards clinical applicable abdominal organ segmentation methods. Moreover, the datasets, codes and trained models of baseline methods will be publicly available.

show abstract

Section: Baseline Resultsmentioning

confidence: 77%

Section: Existing Abdominal Ct Organ Segmentation Benchmark Datasetsmentioning

confidence: 99%

AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?

Zhang

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

176

View full text Add to dashboard Cite

show abstract

“…The three datasets used in this experiment are illustrated briefly in Figure 2 . The magnetic resonance imaging (MRI) data used in our experiments are a set of scans available in [ 37 ]. The dataset in [ 37 ] includes 120 DICOM scans (40 T1-DUAL in phase, 40 T1-DUAL out phase and 40 T2-SPIR), obtained from healthy patients (routine scans, no tumors, lesions or any other diseases).…”

Section: Methodsmentioning

confidence: 99%

Testing Segmentation Popular Loss and Variations in Three Multiclass Medical Imaging Problems

Furtado

2021

J. Imaging

View full text Add to dashboard Cite

Image structures are segmented automatically using deep learning (DL) for analysis and processing. The three most popular base loss functions are cross entropy (crossE), intersect-over-the-union (IoU), and dice. Which should be used, is it useful to consider simple variations, such as modifying formula coefficients? How do characteristics of different image structures influence scores? Taking three different medical image segmentation problems (segmentation of organs in magnetic resonance images (MRI), liver in computer tomography images (CT) and diabetic retinopathy lesions in eye fundus images (EFI)), we quantify loss functions and variations, as well as segmentation scores of different targets. We first describe the limitations of metrics, since loss is a metric, then we describe and test alternatives. Experimentally, we observed that DeeplabV3 outperforms UNet and fully convolutional network (FCN) in all datasets. Dice scored 1 to 6 percentage points (pp) higher than cross entropy over all datasets, IoU improved 0 to 3 pp. Varying formula coefficients improved scores, but the best choices depend on the dataset: compared to crossE, different false positive vs. false negative weights improved MRI by 12 pp, and assigning zero weight to background improved EFI by 6 pp. Multiclass segmentation scored higher than n-uniclass segmentation in MRI by 8 pp. EFI lesions score low compared to more constant structures (e.g., optic disk or even organs), but loss modifications improve those scores significantly 6 to 9 pp. Our conclusions are that dice is best, it is worth assigning 0 weight to class background and to test different weights on false positives and false negatives.

show abstract

“…The application of CNN's and deep learning into medical imaging analysis has been a major advancement in the field, leading to significant gains in segmentation performance across multiple medical imaging applications (for a comprehensive review see Hesamian et al (2019)) 45 . New architectures are continuing to be developed, leading to further improvements in segmentation performance over the V-Net and U-Net architectures 46 . Examples include recurrent neural networks, such as long Table 4.…”

Section: Muscle Mfi (%)mentioning

confidence: 99%

Multi-muscle deep learning segmentation to automate the quantification of muscle fat infiltration in cervical spine conditions

Weber

Abbott

Bojilov

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Muscle fat infiltration (MFI) has been widely reported across cervical spine disorders. The quantification of MFI requires time-consuming and rater-dependent manual segmentation techniques. A convolutional neural network (CNN) model was trained to segment seven cervical spine muscle groups (left and right muscles segmented separately, 14 muscles total) from Dixon MRI scans (n = 17, 17 scans < 2 weeks post motor vehicle collision (MVC), and 17 scans 12 months post MVC). The CNN MFI measures demonstrated high test reliability and accuracy in an independent testing dataset (n = 18, 9 scans < 2 weeks post MVC, and 9 scans 12 months post MVC). Using the CNN in 84 participants with scans < 2 weeks post MVC (61 females, 23 males, age = 34.2 ± 10.7 years) differences in MFI between the muscle groups and relationships between MFI and sex, age, and body mass index (BMI) were explored. Averaging across all muscles, females had significantly higher MFI than males (p = 0.026). The deep cervical muscles demonstrated significantly greater MFI than the more superficial muscles (p < 0.001), and only MFI within the deep cervical muscles was moderately correlated to age (r > 0.300, p ≤ 0.001). CNN’s allow for the accurate and rapid, quantitative assessment of the composition of the architecturally complex muscles traversing the cervical spine. Acknowledging the wider reports of MFI in cervical spine disorders and the time required to manually segment the individual muscles, this CNN may have diagnostic, prognostic, and predictive value in disorders of the cervical spine.

show abstract

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

Cited by 438 publications

References 28 publications

AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?

AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?

Testing Segmentation Popular Loss and Variations in Three Multiclass Medical Imaging Problems

Multi-muscle deep learning segmentation to automate the quantification of muscle fat infiltration in cervical spine conditions

Contact Info

Product

Resources

About