The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes

Abstract

The morphometry of a kidney tumor revealed by contrast-enhanced Computed Tomography (CT) imaging is an important factor in clinical decision making surrounding the lesion's diagnosis and treatment. Quantitative study of the relationship between kidney tumor morphology and clinical outcomes is difficult due to data scarcity and the laborious nature of manually quantifying imaging predictors. Automatic semantic segmentation of kidneys and kidney tumors is a promising tool towards automatically quantifying a wide array of morphometric features, but no sizeable annotated dataset is currently available to train models for this task. We present the KiTS19 challenge dataset: A collection of multi-phase CT imaging, segmentation masks, and comprehensive clinical outcomes for 300 patients who underwent nephrectomy for kidney tumors at our center between 2010 and 2018. 210 (70%) of these patients were selected at random as the training set for the 2019 MICCAI KiTS Kidney Tumor Segmentation Challenge and have been released publicly. With the presence of clinical context and surgical outcomes, this data can serve not only for benchmarking semantic segmentation models, but also for developing and studying biomarkers which make use of the imaging and semantic segmentation masks.

13 pages, 2 figures

Cited by in corpus (61)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Medical Image Segmentation Using Deep Learning: A Survey
• Segment Anything Model for Medical Images?
• CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection
• UNETR: Transformers for 3D Medical Image Segmentation
• Efficient Medical Image Segmentation Based on Knowledge Distillation
• CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects
• MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
• Multi-Scale Supervised 3D U-Net for Kidneys and Kidney Tumor Segmentation
• nnDetection: A Self-configuring Method for Medical Object Detection
• Recent Progress in Transformer-based Medical Image Analysis
• The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods
• CLIP in Medical Imaging: A Survey
• Free-form tumor synthesis in computed tomography images via richer generative adversarial network
• SegTransVAE: Hybrid CNN -- Transformer with Regularization for medical image segmentation
• Federated Multi-organ Segmentation with Inconsistent Labels
• Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge
• TuNet: End-to-end Hierarchical Brain Tumor Segmentation using Cascaded Networks
• RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation
• Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets
• Domain specific cues improve robustness of deep learning based segmentation of ct volumes
• Evaluating the Robustness of Self-Supervised Learning in Medical Imaging
• 3D Kidneys and Kidney Tumor Semantic Segmentation using Boundary-Aware Networks
• I${}^3$Net: Inter-Intra-slice Interpolation Network for Medical Slice Synthesis
• Lesion-Aware Cross-Phase Attention Network for Renal Tumor Subtype Classification on Multi-Phase CT Scans
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Sauron U-Net: Simple automated redundancy elimination in medical image segmentation via filter pruning
• Deep learning based registration using spatial gradients and noisy segmentation labels
• Taming Detection Transformers for Medical Object Detection
• A Systematic Collection of Medical Image Datasets for Deep Learning
• Multi-organ Segmentation over Partially Labeled Datasets with Multi-scale Feature Abstraction
• 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
• w-Net: Dual Supervised Medical Image Segmentation Model with Multi-Dimensional Attention and Cascade Multi-Scale Convolution
• Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models
• Self-Supervised Learning for Segmentation
• MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets
• Benefits of Linear Conditioning with Metadata for Image Segmentation
• Critical Assessment of Transfer Learning for Medical Image Segmentation with Fully Convolutional Neural Networks
• Marginal loss and exclusion loss for partially supervised multi-organ segmentation
• FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
• Interpretable and synergistic deep learning for visual explanation and statistical estimations of segmentation of disease features from medical images
• Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations
• Neural ODEs for Image Segmentation with Level Sets
• End-to-End Cascaded U-Nets with a Localization Network for Kidney Tumor Segmentation
• Kidney and Kidney Tumor Segmentation using a Logical Ensemble of U-nets with Volumetric Validation
• Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Multi-organ Segmentation via Co-training Weight-averaged Models from Few-organ Datasets
• ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
• Task-Oriented Low-Dose CT Image Denoising
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
• Architecture Analysis and Benchmarking of 3D U-shaped Deep Learning Models for Thoracic Anatomical Segmentation
• Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives
• TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
• Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
• Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models
• Coarse-to-fine Kidney Segmentation Framework Incorporating with Abnormal Detection and Correction
• Technical report: Kidney tumor segmentation using a 2D U-Net followed by a statistical post-processing filter
• Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection
• Body Part Regression for CT Images
• Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation