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

By N. Heller, Fabian Isensee, Klaus Hermann Maier-Hein, X. Hou, Chunmei Xie, Fengyi Li, Yang Nan, Guangrui Mu, Zhiyong Lin, M. Han and 31 more. Medical Image Anal., 2019

625 citations recorded by the source corpus.

There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sørensen-Dice coefficient between the kidney and tumor across all 90 cases. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an “open leaderboard” phase where it serves as a challenging benchmark in 3D semantic segmentation.

Subfields: Computer Vision and Pattern Recognition, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/4d55dfb3db28064d0313332fce937e036a2f72a3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem? (2020, methodology): “To address the above limitations, in this work, we first create a large-scale abdominal multi-organ CT dataset by extending the existing benchmark datasets withmore organ annotations, including LiTS [16], MSD [20], KiTS [17],NIH-Pancreas [21], [22], [23].”
Diffusion models in medical imaging: A comprehensive survey (2022, background): “The results of the Kidney CT (C4KC-KiTS) dataset [105] regarding SSIM and PSNR metrics demonstrate that DOLCE is effective in producing sharp CT images.”
Segment Anything in Medical Images (2023, background): “, T1, T2, ADC, FLAIR) [24][10][6][41][5][8][29][42], abdomen tumor, COVID-19 infection, gallbladder, head and neck tumor, liver, pancreas, pleural effusion, and stomach segmentation in CT images [34][19][7][33][32][42][4][28][27][12], breast tumor, liver, and vessel segmentation in ultrasound images”
Medical Image Segmentation Review: The Success of U-Net (2022, background): “To further support this we find the top 9/10 participants of the Kidney Tumor Segmentation (KiTS) 2021 challenge hosted by the Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021 society [93], [94] challenge utilized a 3D UNet and 1/10 utilized a 2D one 1.”
Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, background): “Accurate segmentation can provide reliable volumetric and shape information so as to assist in further clinical applications like disease diagnosis and quantitative analysis [3], [4], [5].”
Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation (2021, background): “We therefore exclude the 90 scans without segmentation masks, and further exclude another 6 scans (case 15, 23, 37, 68, 125 and 133) due to concern over ground truth quality (Heller et al., 2021), leaving 204 scans for use.”
U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation (2024, background): “…to deep learning-based paradigm, which significantly improved the segmentation accuracy and efficiency for a broad range of biomedical tasks, such as tumor segmentation [3,19] and organ segmentation [35] in 3D Computed Tomograph (CT) scans, as well as cell segmentation in microscopy images [43,34].”
MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation (2023, positive): “…demonstrate the benefits of the MedNeXt architecture – 1) Beyond-the-Cranial-Vault (BTCV) Abdominal CT Organ Segmentation [16], 2) AMOS22 Abdominal CT Organ Segmentation [14] 3) Kidney Tumor Segmentation Challenge 2019 Dataset (KiTS19) [11], 4) Brain Tumor Segmentation Challenge 2021 (BraTS21) [1].”
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation (2020, methodology): “…of the current practice in deep learning-based biomedical image segmentation, we analyze as examples the participating algorithms in the recent Kidney and Kidney Tumor Segmentation (KiTS) 2019 challenge hosted by the Medical Image Computing and Computer Assisted Intervention (MICCAI) society 25 .”
Automated Design of Deep Learning Methods for Biomedical Image Segmentation (2019, methodology): “Other metrics used by some of the challenges include the Normalized Surface Dice (higher is better) [7] and the Hausdorff Distance (lower is better), both quantifying the distance between the borders of two segmentations.”
An OpenMind for 3D Medical Vision Self-supervised Learning (2024, unknown): “KiTS19 (KIT) [39]: CT images of kidneys and kidney tumors.”