AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (2020-10-28T00:00:00.000000Z)

TL;DR

A large and diverse abdominal CT organ segmentation dataset with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases is presented and a simple and effective method is developed for each benchmark, which can be used as out-of-the-box methods and strong baselines.

Abstract

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets. However, most of the existing abdominal datasets only contain single-center, single-phase, single-vendor, or single-disease cases, and it is unclear whether the excellent performance can generalize on diverse datasets. This paper presents a large and diverse abdominal CT organ segmentation dataset, termed AbdomenCT-1K, with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation and reveal the unsolved segmentation problems of the SOTA methods, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we further 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 AbdomenCT-1K dataset will promote future in-depth research towards clinical applicable abdominal organ segmentation methods.

Authors

References117 items

DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation

Loss odyssey in medical image segmentation

Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

DeepTarget: Gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy

CT-ORG, a new dataset for multiple organ segmentation in computed tomography

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

Learning Geodesic Active Contours for Embedding Object Global Information in Segmentation CNNs

Precision Liver Resection: Three-Dimensional Reconstruction Combined with Fluorescence Laparoscopic Imaging

Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist

A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises

Fully Automatic Volume Measurement of the Spleen at CT Using Deep Learning.

An international challenge to use artificial intelligence to define the state of the art in kidney and kidney tumor segmentation in CT imaging

Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation

Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation

Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

Organ at Risk Segmentation for Head and Neck Cancer Using Stratified Learning and Neural Architecture Search

Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers.

Block Level Skip Connections Across Cascaded V-Net for Multi-Organ Segmentation

An international challenge to use artificial intelligence to define the state-of-the-art in kidney and kidney tumor segmentation in CT imaging.

Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans

Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning

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

Cascaded MultiTask 3-D Fully Convolutional Networks for Pancreas Segmentation

The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge

A survey on semi-supervised learning

Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision

Self-Training With Noisy Student Improves ImageNet Classification

Weakly Supervised Learning of Recurrent Residual ConvNets for Pancreas Segmentation in CT Scans

Modified U-Net (mU-Net) With Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images

Scribble-Based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation

Integrating 3D Geometry of Organ for Improving Medical Image Segmentation

Continual learning: A comparative study on how to defy forgetting in classification tasks

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

A sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation

V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation

The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation

A comprehensive, application-oriented study of catastrophic forgetting in DNNs

OBELISK‐Net: Fewer layers to solve 3D multi‐organ segmentation with sparse deformable convolutions

Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation

Automated Design of Deep Learning Methods for Biomedical Image Segmentation

Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation

Label Propagation for Deep Semi-Supervised Learning

A large annotated medical image dataset for the development and evaluation of segmentation algorithms

The Liver Tumor Segmentation Benchmark (LiTS)

Weakly Supervised Scene Parsing with Point-based Distance Metric Learning

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

3D MRI brain tumor segmentation using autoencoder regularization

Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy

Inter-observer variability of manual contour delineation of structures in CT

A multi-scale pyramid of 3D fully convolutional networks for abdominal multi-organ segmentation

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion

Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis

Semi-Supervised 3D Abdominal Multi-Organ Segmentation Via Deep Multi-Planar Co-Training

An application of cascaded 3D fully convolutional networks for medical image segmentation

Continual Lifelong Learning with Neural Networks: A Review

Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks

Combined endeavor of Neutrosophic Set and Chan-Vese model to extract accurate liver image from CT scan

Fully convolutional neural network with post-processing methods for automatic liver segmentation from CT

Joint Supervoxel Classification Forest for Weakly-Supervised Organ Segmentation

Pathological Pulmonary Lobe Segmentation from CT Images Using Progressive Holistically Nested Neural Networks and Random Walker

Robust Abdominal Organ Segmentation Using Regional Convolutional Neural Networks

Progressive and Multi-path Holistically Nested Neural Networks for Pathological Lung Segmentation from CT Images

CORe50: a New Dataset and Benchmark for Continuous Object Recognition

The 2017 DAVIS Challenge on Video Object Segmentation

A deep learning model integrating FCNNs and CRFs for brain tumor segmentation

Spatial aggregation of holistically‐nested convolutional neural networks for automated pancreas localization and segmentation☆

A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans

Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets

Three-Dimensional CT Image Segmentation by Combining 2D Fully Convolutional Network with 3D Majority Voting

Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields

Learning without Forgetting

Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks

A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation

Incremental robot learning of new objects with fixed update time

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Segmentation label propagation using deep convolutional neural networks and dense conditional random field

An Automated System for Atlas Based Multiple OrganSegmentation of Abdominal CT Images

Abdominal multi-organ segmentation from CT images using conditional shape-location and unsupervised intensity priors

3D liver segmentation using multiple region appearances and graph cuts.

Automatic Liver Segmentation Based on Shape Constraints and Deformable Graph Cut in CT Images

Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning

Discriminative dictionary learning for abdominal multi-organ segmentation

DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

What's the Point: Semantic Segmentation with Point Supervision

U-Net: Convolutional Networks for Biomedical Image Segmentation

Multi-atlas segmentation of biomedical images: A survey

Reflections on the current status of commercial automated segmentation systems in clinical practice

An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks

The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Computer-aided diagnosis: how to move from the laboratory to the clinic.

Automatic Liver Segmentation Using a Statistical Shape Model With Optimal Surface Detection

Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets

100

Construction of a probabilistic atlas for automated liver segmentation in non-contrast torso CT images

101

Computerized planning of liver surgery - an overview

102

Active Shape Models-Their Training and Application

103

Cheng Ge received the BS degree in mechanical engineering from Nanhang Jincheng College

104

Data from pancreas-CT

105

Three-Dimensional CT Image Segmentation by Combining 2 D Fully Convolutional Network with 3 D Majority Voting

106

He was the runner-up in the Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac Image Segmentation Challenge in MICCAI 2020 and the third place in the Brain Lesion Segmentation Challenge

107

gra-dientbased neural networks

108

Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

109

Snakes: Active contour models

110

Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem

111

Cheng Zhu received the PhD degree from the Institute of High Energy Physics Chinese Academy of Sciences in 2012. He is currently an engineer with Shenzhen Haichuang Medical Company Ltd

112

Song Gu received the BS degree in control technology and instruments in 2018 from the Nanjing University of Information Science and Technology

113

We conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation based on the AbdomenCT-1K dataset and the SOTA method nnU-Net [24]. The

114

DAVIS: Densely Annotated VIdeo Segmentation

115

Lack of benchmarks for recently emerging annotation-efﬁcient segmentation tasks

116

Medical Image Analysis

117

Multi - atlas labeling beyond the cranial vault - workshop and challenge , ” 2015 . [ 60 ] “ NIH Pancreas