Merlin Plus offers large multi-cancer CT images with tumor masks
Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Dataset
Computer Vision and Pattern Recognition
Summary
Finding tumors in CT scans for many different organs is hard because there aren't enough detailed labeled images. The authors created Merlin Plus, a large collection of CT scans with tumors marked by doctors for nine organs, which is much bigger than before. They used a smart method where a computer guesses the tumor shapes, and doctors then correct these guesses, saving a lot of work. The dataset also includes information about how cancers change over time, helping track disease progress.
What this means in practice
- •For medical imaging teams: Train CT scan tumor detection models using a large dataset with expert tumor masks across multiple organs.
- •For clinical software developers: Build cancer progression tracking tools that use longitudinal CT data and tumor masks for better patient monitoring.
Authors
Pedro R. A. S. Bassi, Wenxuan Li, Szymon Plotka, Ruby Honjol, Jakub Przado, Xinze Zhou, Kang Wang, Yang Yang, Malte Jensen, Akshay S. Chaudhari, Curtis P. Langlotz, Alan L. Yuille, Zongwei Zhou
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