REVIEW 23 cited by
The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 23 Pith papers
-
Learning Segmentation from Radiology Reports
R-Super converts tumor count, size, and location information from radiology reports into voxel-wise losses that improve CT tumor segmentation beyond training with masks alone.
-
Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge
The AortaSeg24 challenge provides a public dataset of 100 CTA scans labeled for 23 aortic branches and zones, and evaluates 16 algorithms, with the best averaging 0.782 Dice.
-
RadGPT: Constructing 3D Image-Text Tumor Datasets
AbdomenAtlas 3.0 is a new public dataset of 9,262 abdominal CT scans with paired tumor masks and radiology reports, alongside RadGPT, a segmentation-based report generator that outperforms end-to-end models in tumor d...
-
Inference-Time Orthogonal Seeding Enables Geometry-Aligned 3D Organ Segmentation for Slice-Propagation Methods
Orthogonal seeding with three perpendicular annotated slices improves slice-propagation CT organ segmentation by 21.9% Dice over a single axial seed, with the gain due to seed geometry rather than annotation count or ...
-
Beyond scalar losses: calibrating segmentation models via gradient vector field surgery
Scaling region-based segmentation loss gradients by per-voxel prediction error improves calibration metrics on 2D/3D medical segmentation datasets with little or no loss in Dice score.
-
PanTS: The Pancreatic Tumor Segmentation Dataset
PanTS is a new large CT dataset with expert-drawn pancreatic tumor and anatomy labels, and models trained on it beat prior public benchmarks.
-
Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline
IMed-361M, built by combining 110 public and private datasets and adding 273 million machine-generated masks, is released with an interactive segmentation baseline that outperforms existing models on several external ...
-
SED Fitting of Globular Clusters in NGC 4874: Masses and Metallicities
SED fitting of 29 bright globular clusters in NGC 4874 with ten HST filters yields masses, metallicities, and mass-to-light ratios of about 2-4.
-
MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds
An unbuilt OS design, MaLV-OS, aims to improve ML performance in virtualized clouds by moving model preprocessing into the kernel and integrating GPU virtualization into the hypervisor.
-
Adaptively Distilled ControlNet: Accelerated Training and Superior Sampling for Medical Image Synthesis
A teacher-student diffusion framework, Adaptively Distilled ControlNet, uses mask-only student generation with teacher-guided noise alignment and adaptive lesion weighting, improving downstream segmentation on KiTS19 ...
-
Reasoning in machine vision by learning fast and slow thinking
A dual-process vision system improves segmentation accuracy by spending more inference-time compute, using a fast predictor and a slow self-play refiner, reporting gains on cancer localisation with only 8-16 labels.
-
SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation
SGTC uses CLIP semantic guidance and three-view co-training to segment medical volumes from just three annotated slices per volume, with gains over baselines mainly driven by the extra label.
-
An attempt at beating the 3D U-Net
A plain 3D U-Net and its residual variants performed almost identically on KiTS2019, and the residual version won the challenge by a small margin.
-
Test-time Adaptation of Pelvic Bone Segmentation Models via Dynamic Reliability-Guided
ReGA adapts a source-trained pelvic bone segmentation model to unseen CT domains by gating pseudo-labels, feature refinement, and teacher updates on a dropout-based reliability score.
-
Comparing the Effects of Persistence Barcodes Aggregation and Feature Concatenation on Medical Imaging
Concatenating per-barcode feature vectors outperforms aggregating persistence barcodes before vectorization for TDA-based medical image classification in most tested settings.
-
Efficient Parameter Adaptation for Multi-Modal Medical Image Segmentation and Prognosis
PEMMA adapts a CT-only transformer segmentation model to CT+PET with LoRA/DoRA, reaching early-fusion-level Dice while training only 0.5-8% of parameters, and extends the same adapters to prognosis.
-
Lightweight Method for Interactive 3D Medical Image Segmentation with Multi-Round Result Fusion
A compact CNN-based interactive segmentation system with multi-round fusion claims to match or beat SAM-based models on unseen medical datasets while using fewer user clicks.
-
Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge
A multi-stage 2.5D ensemble of residual convolutional networks segments kidneys and kidney tumors in CT, reporting mean Dice of 0.96 for kidneys and 0.74 for tumors on the KiTS19 test set.
-
Coarse-to-fine Kidney Segmentation Framework Incorporating with Abnormal Detection and Correction
A coarse-to-fine U-Net pipeline with abnormal detection and correction reaches 94.53 percent average Dice on the KiTS19 kidney segmentation test set.
-
Multi Scale Supervised 3D U-Net for Kidney and Tumor Segmentation
A multi-scale supervised 3D U-Net with exponential logarithmic loss and connected-component postprocessing achieved composite Dice 0.8961, ranking 7th in the KiTS19 kidney tumor segmentation challenge.
-
Automatic segmentation of kidney and liver tumors in CT images
A LinkNet-34 model with transfer learning, augmentation, and a BCE-plus-Dice loss reaches DICE 78.8% for liver tumors on 3DIRCADb and 67.4% tumor DICE on KiTS-2019.
-
U-Net in Medical Image Segmentation: A Review of Its Applications Across Modalities
A review summarizing U-Net, U-Net++, and U-Net 3+ applications across four medical imaging modalities with tables of recent studies.
-
Towards One-shot Federated Learning: Advances, Challenges, and Future Directions
A literature survey of one-shot federated learning that organizes methods, datasets, and code, but reports no new experimental or theoretical results.
Discussion (0). Continue with ORCID to comment.