mlsanityData to 14 Oct 2026

PanTS: The Pancreatic Tumor Segmentation Dataset

arXiv 2507.01291 ↗First posted 2 Jul 2025eess.IV cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validated, voxel-wise annotations of over 993,000 anatomical structures, covering pancreatic tumors, pancreas head, body, and tail, and 24 surrounding anatomical structures such as vascular/skeletal structures and abdominal/thoracic organs. Each scan includes metadata such as patient age, sex, diagnosis, contrast phase, in-plane spacing, slice thickness, etc. AI models trained on PanTS achieve significantly better performance in pancreatic tumor detection, localization, and segmentation compared to those trained on existing public datasets. Our analysis indicates that these gains are directly attributable to the 16x larger-scale tumor annotations and indirectly supported by the 24 additional surrounding anatomical structures. As the largest and most comprehensive resource of its kind, PanTS offers a new benchmark for developing and evaluating AI models in pancreatic CT analysis.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 31 of its 73 references that are in the map. First posted on arXiv 2 Jul 2025.

Builds on

31 of 73 references.

References · 31

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2021Scaling Vision Transformerscited by 999
  3. 2021The Medical Segmentation Decathloncited by 628
  4. 2022TotalSegmentator: robust segmentation of 104 anatomical structures in CT imagescited by 613
  5. 2019The Liver Tumor Segmentation Benchmark (LiTS)cited by 509
  6. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  7. 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 422
  8. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  9. 2020CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentationcited by 309
  10. 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentationcited by 240
  11. 2020AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?cited by 224
  12. 2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
19 more
  1. 2019The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomescited by 172
  2. 2015DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentationcited by 159
  3. 2024AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarkingcited by 65
  4. 2019C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentationcited by 50
  5. 2021DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentationcited by 48
  6. 2023Continual Learning for Abdominal Multi-Organ and Tumor Segmentationcited by 43
  7. 2022MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Imagescited by 39
  8. 2025RadGPT: Constructing 3D Image-Text Tumor Datasetscited by 36
  9. 2024Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomographycited by 31
  10. 2024Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?cited by 31
  11. 2024Automatic Organ and Pan-cancer Segmentation in Abdomen CT: the FLARE 2023 Challengecited by 23
  12. 2019Scalable Neural Architecture Search for 3D Medical Image Segmentationcited by 21
  13. 2021Label-Assemble: Leveraging Multiple Datasets with Partial Labelscited by 20
  14. 2023Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesiscited by 17
  15. 2024Text-Driven Tumor Synthesiscited by 13
  16. 2024The RSNA Abdominal Traumatic Injury CT (RATIC) Datasetcited by 12
  17. 2024Leveraging AI Predicted and Expert Revised Annotations in Interactive Segmentation: Continual Tuning or Full Training?cited by 9
  18. 2024Embracing Massive Medical Datacited by 9
  19. 2024Label Critic: Design Data Before Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 10.

16 papers.

Sort:

By area:

  1. 2025Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Datacited by 13
  2. 2025Learning Segmentation from Radiology Reportscited by 11
  3. 2025Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Maskscited by 9
  4. 2025Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generationcited by 8
  5. 2026RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiologycited by 4
  6. 2025See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancementcited by 3
  7. 2025Auditing Significance, Metric Choice, and Demographic Fairness in Medical AI Challengescited by 2
  8. 2026PanGuide3D: Cohort-Robust Pancreas Tumor Segmentation via Probabilistic Pancreas Conditioning and a Transformer Bottleneckcited by 0
  9. 2026Beyond Masks: The Case for Medical Image Parsingcited by 0
  10. 2026Native Multi-Dimensional Subquadratic Operators via Input Dependent Long Convolutionscited by 0
  11. 2026Report Supervisioncited by 0
  12. 2026Weakly-supervised Kidney Tumor Classification from CT Scans with Multi-Instance Learning and Anatomical Filteringcited by 0
4 more
  1. 2026Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Conceptscited by 0
  2. 2026RT-Super: Learning Tumor Segmentation from Longitudinal Images and Reportscited by 0
  3. 2026Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Datasetcited by 0
  4. 2026FLASHSWIN: Unlocking Large Windows and Dense Tokens in Swin Vision Transformers with Memory Efficient Attentioncited by 0