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

Abstract

626 Background: The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was an international competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) and sought to stimulate progress on this automatic segmentation frontier. Growing rates of kidney tumor incidence led to research into the use of artificial inteligence (AI) to radiographically differentiate and objectively characterize these tumors. Automated segmentation using AI objectively quantifies complexity and aggression of renal tumors to better differentiate and describe the tumors for improved treatment decision making. Methods: A training set of over 31,000 CT images from 210 patients with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated deep learning systems to predict the true segmentation masks on a test set of an additional 13,500 CT images in 90 patients for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sørensen-Dice coefficient between kidney and tumor across the 90 test cases. Results: The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the human 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. Conclusions: Results of the KiTS19 challenge show deep learning methods are fully capable of reliable segmentation of kidneys and kidney tumors. The KiTS19 challenge attracted a high number of submissions and serves as an important and challenging benchmark in 3D segmentation. The publicly available data will further propel the use of automated 3D segmentation analysis. Fully segmented kidneys and tumors allow for automated calculation of all types of nephrometry, tumor textural variation and discovery of new predictive features important for personalized medicine and accurate prediction of patient relevant outcomes.

The cancer multidisciplinary team meeting: in need of change? History, challenges and future perspectives

“…Similarly, AI has been used to help in the planning of surgery by constructing threedimensional models of renal anatomy from CT scans. [53] Pattern recognition algorithms have been developed both to diagnose bladder cancer on cystoscopy, and also stage urothelial cancer from imaging studies. [54,55].…”

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

“…Different from the other datasets, all the 40 liver CT cases are from healthy population. KiTS (Kidney Tumor Segmentation) dataset [64] includes 210 training cases with kidney and kidney tumor annotations and 90 testing cases with hidden annotations, which are provided by University of Minnesota Medical Center (Minnesota, USA). The patients in this dataset underwent partial or radical nephrectomy for one or more kidney tumors.…”

“…There are several different weak annotation strategies for segmentation tasks, such as random scribbles, bounding boxes, extreme points and sparse labels. Sparse labels are most commonly used weak annotations for organ segmentation when radiologists manually delineate the organs [64]. In this benchmark, we provide slice-level sparse labels in the training set, where only part (≤ 50%) of the slices are well annotated.…”

“…The training set contains 41 cases with sparse multi-organ labels, where only a fraction of the slices are annotated at roughly uniform intervals. We generate sparse labels with roughly uniform intervals because, in practice, human-raters usually annotate such sparse labels and then interpolate the unlabelled slices [64]. Specifically, we set three different annotation rate 5%, 30% and 50%, which is similar to existing work [81] on brain tissue segmentation.…”

Combining Hybrid Architecture and Pseudo-label for Semi-supervised Abdominal Organ Segmentation

“…The FLARE2022 dataset is curated from more than 20 medical groups under the license permission, including MSD [13], KiTS [4,5], AbdomenCT-1K [11], and TCIA [2]. The training set includes 50 labelled CT scans with pancreas disease and 2000 unlabelled CT scans with liver, kidney, spleen, or pancreas diseases.…”