CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation

Abstract

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) have introduced new state-of-the-art segmentation systems. In order to expand the knowledge on these topics, the CHAOS - Combined (CT-MR) Healthy Abdominal Organ Segmentation challenge has been organized in conjunction with IEEE International Symposium on Biomedical Imaging (ISBI), 2019, in Venice, Italy. CHAOS provides both abdominal CT and MR data from healthy subjects for single and multiple abdominal organ segmentation. Five different but complementary tasks have been designed to analyze the capabilities of current approaches from multiple perspectives. The results are 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 $\pm$ 0.00 / 0.95 $\pm$ 0.01) but the best MSSD performance remain limited (21.89 $\pm$ 13.94 / 20.85 $\pm$ 10.63 mm). The performances of participating models decrease significantly for cross-modality tasks for the liver (DICE: 0.88 $\pm$ 0.15 MSSD: 36.33 $\pm$ 21.97 mm) and all organs (DICE: 0.85 $\pm$ 0.21 MSSD: 33.17 $\pm$ 38.93 mm). Despite contrary examples on different applications, multi-tasking DL models designed to segment all organs seem to perform worse compared to organ-specific ones (performance drop around 5\%). Besides, such directions of further research for cross-modality segmentation would significantly support real-world clinical applications. Moreover, having more than 1500 participants, another important contribution of the paper is the analysis on shortcomings of challenge organizations such as the effects of multiple submissions and peeking phenomena.

arXiv comment23 pages, 11 tables, 9 figures

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• The Liver Tumor Segmentation Benchmark (LiTS)
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• NiftyNet: a deep-learning platform for medical imaging
• Why rankings of biomedical image analysis competitions should be interpreted with care
• Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning
• nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
• Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy
• Pyramid Attention Network for Semantic Segmentation
• Cascaded V-Net using ROI masks for brain tumor segmentation
• FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images

Cited by in corpus (60)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• The Liver Tumor Segmentation Benchmark (LiTS)
• Medical Image Segmentation Using Deep Learning: A Survey
• Segment Anything Model for Medical Images?
• Annotation-efficient deep learning for automatic medical image segmentation
• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• Recent Progress in Transformer-based Medical Image Analysis
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• Learning Disentangled Representations in the Imaging Domain
• CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
• TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI
• LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation
• FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
• MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
• Cross-dimensional transfer learning in medical image segmentation with deep learning
• PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
• Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
• Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation
• Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding
• MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation
• Multi-structure bone segmentation in pediatric MR images with combined regularization from shape priors and adversarial network
• Is SAM 2 Better than SAM in Medical Image Segmentation?
• Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
• AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
• Harvesting, Detecting, and Characterizing Liver Lesions from Large-scale Multi-phase CT Data via Deep Dynamic Texture Learning
• A Systematic Collection of Medical Image Datasets for Deep Learning
• A-Eval: A Benchmark for Cross-Dataset Evaluation of Abdominal Multi-Organ Segmentation
• DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets
• Automated segmentation of microtomography imaging of Egyptian mummies
• Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation
• Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation
• FAS-UNet: A Novel FAS-driven Unet to Learn Variational Image Segmentation
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• Semi-overcomplete convolutional auto-encoder embedding as shape priors for deep vessel segmentation
• Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation
• MRAnnotator: multi-Anatomy and many-Sequence MRI segmentation of 44 structures
• Self-supervised Tumor Segmentation through Layer Decomposition
• Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation
• TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation
• A low-rank representation for unsupervised registration of medical images
• Fréchet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasets
• Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth
• Architecture Analysis and Benchmarking of 3D U-shaped Deep Learning Models for Thoracic Anatomical Segmentation
• Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning
• Liver Segmentation in Time-resolved C-arm CT Volumes Reconstructed from Dynamic Perfusion Scans using Time Separation Technique
• Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration
• BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
• Liver Segmentation using Turbolift Learning for CT and Cone-beam C-arm Perfusion Imaging
• Universal Undersampled MRI Reconstruction
• Regularized directional representations for medical image registration
• PoissonSeg: Semi-Supervised Few-Shot Medical Image Segmentation via Poisson Learning
• DPL: Spatial-Conditioned Diffusion Prototype Enhancement for One-Shot Medical Segmentation
• Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration
• TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation
• Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning
• DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark
• A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework