The 2019 Kidney Tumor Segmentation Challenge (KiTS19) was one of several "grand challenges" associated with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI19) held in in Shenzhen, China. The challenge task was the develop an algorithm to automatically segment contrast-enhanced abdominal CT images into "kidney", "tumor", and "background" classes. To aid machine-learning-based approaches to this problem, 210 such CT scans were publicly released along with segmentation masks created manually by medical students under the supervision of an experienced urologic oncology surgeon. Teams were then asked to run their algorithm on a further 90 CT scans for which the manual segmentation masks were not available. Each team's output, or "predictions", for these 90 cases were uploaded to a web platform where they were automatically scored against the private manual segmentations. The challenge attracted submissions from 100 research teams around the world, and was won by Fabian Isensee and Klaus Maier-Hein at the German Cancer Research Center, who achieved a kidney Sørensen–Dice coefficient of 0.974 and a tumor Sørensen–Dice coefficient of 0.851. The prize for this challenge was $5,000 USD graciously provided by Intuitive Surgical. The lead organizer for this challenge was Nicholas Heller at the University of Minnesota, and he was aided by Niranjan Sathianathen, Arveen Kalapara, Christopher Weight, and Nikolaos Papanikolopoulos. The organization of this challenge was funded by the non-profit "Climb 4 Kidney Cancer" as well as the National Cancer Institute of the National Institutes of Health under award number R01CA225435.
The U-Net is arguably the most successful segmentation architecture in the medical domain. Here we apply a 3D U-Net to the 2019 Kidney and Kidney Tumor Segmentation Challenge and attempt ... Read More
doi: 10.24926/548719.001
Automated detection and segmentation of kidney tumors from 3D CT images is very useful for doctors to make diagnosis and treatment plan. In this paper, we described a multi-stage semantic ... Read More
doi: 10.24926/548719.002
Accurate segmentation of kidney tumors can assist doctors to diagnose diseases, and to improve treatment planning, which is highly demanded in the clinical practice. In this work, we propose multi-resolution ... Read More
doi: 10.24926/548719.003
Automated segmentation of kidney and tumor from 3D CT scans is necessary for the diagnosis, monitoring, and treatment planning of the disease. In this paper, we describe a two-stage framework ... Read More
doi: 10.24926/548719.004
Kidney and kidney tumor segmentation are essential steps in kidney cancer surgery. In this paper, we focus on addressing hard cases and exploring the kidney tumor shape prior rather than ... Read More
doi: 10.24926/548719.005
Accurate segmentation of kidney tumor is a key step in image-guided radiation therapy. However, shapes, scales and appearance vary greatly from patient to patient, which pose a serious challenge to ... Read More
doi: 10.24926/548719.006
U-Net has achieved huge success in various medical image segmentation challenges. Kinds of new architectures with bells and whistles might succeed in certain dataset when employed with optimal hyperparameter, but ... Read More
doi: 10.24926/548719.007
Fully automatic segmentation of kidney and its lesions is an important step to obtain accurate clinical diagnosis and computer aided decision support system. In this paper, a method of automatic ... Read More
doi: 10.24926/548719.008
Automated segmentation of kidneys and kidney tumors is an important step in quantifying the tumor’s morphometrical details to monitor the progression of the disease and accurately compare decisions regarding the ... Read More
doi: 10.24926/548719.009
Accurate segmentation of kidney and kidney tumor is an important step for treatment. Due to the wide variety in kidney and kidney tumor morphology, it’s really a challenging task. In ... Read More
doi: 10.24926/548719.010