Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Dataset

Pedro R. A. S. Bassi, Wenxuan Li, Szymon Plotka, Ruby Honjol, Jakub Przado +8 more
9/29/2026
cs.CV

Official code: MrGiovanni/MerlinPlus (29 stars, last commit 2026-09-24).

Abstract

Multi-cancer segmentation in computed tomography (CT) is fundamentally limited by the scarcity of tumor masks across different organs. We present Merlin Plus, the first large-scale CT dataset with radiologist-created tumor masks across 9 organs. Merlin Plus extends the Merlin dataset by adding 1,153 per-voxel tumor masks and longitudinal metadata. To create these tumor masks, we developed a report-based active-learning framework in which radiology reports identify tumor cases for annotation and support training of a tumor segmentation model. The model generates initial masks, which radiologists review and correct to produce the final masks, reducing annotation burden while maintaining high-quality annotations. Besides tumor masks, the longitudinal metadata in Merlin Plus enables temporal modeling of cancer progression. By directly addressing the major bottleneck of limited multi-cancer segmentation masks, Merlin Plus supports scalable multi-organ cancer detection, segmentation, and longitudinal analysis in CT. Dataset is available at: https://github.com/MrGiovanni/MerlinPlus

View on arXivView PDF

Code Implementations(1)

MrGiovanni/MerlinPlusOfficial100%

[MICCAI 2026] Merlin Plus is the first large-scale public CT dataset with radiologist-created tumor masks across 9 organs (spleen, bladder, gallbladder, stomach, duodenum, prostate, adrenal glands, esophagus, and uterus), adding 1,153 per-voxel tumor masks to the Stanford Merlin dataset.

290PythonJun 26, 20263 weeks agoNOASSERTION
annotationscancerdatasetlongitudinal-data

Similar Papers

RT-Super: Learning Tumor Segmentation from Longitudinal Images and Reports

90% match1 repo162026

Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks

87% match1 repo1262025

Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data

86% match2025

MRGen: Segmentation Data Engine for Underrepresented MRI Modalities

86% match1 repo412024

RadGPT: Constructing 3D Image-Text Tumor Datasets

86% match1 repo2152025

Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation

85% match1 repo372024

Cite this paper

@article{bassi2026merlin,
  title  = {Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Dataset},
  author = {Pedro R. A. S. Bassi and Wenxuan Li and Szymon Plotka and Ruby Honjol and Jakub Przado and Xinze Zhou and Kang Wang and Yang Yang and Malte Jensen and Akshay S. Chaudhari and Curtis P. Langlotz and Alan L. Yuille and Zongwei Zhou},
  year   = {2026},
  eprint = {2609.36436},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.36436v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.36436.svg)](https://codeofpaper.com/paper/2609.36436)

Discussion