Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST

2018/07/02 by Jinzheng Cai, Cai, Jinzheng, Youbao Tang +14 · 1 citation
Computer Science · Medicine · Physics and Astronomy · #Advanced Radiotherapy Techniques #Artificial intelligence #Clinical trial #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Convolutional neural network #FOS: Computer and information sciences #Image segmentation #Lesion #Medical Imaging Techniques and Applications #Medicine #Pathology #Pattern recognition (psychology) #Radiomics and Machine Learning in Medical Imaging #Response Evaluation Criteria in Solid Tumors #Segmentation #Sørensen–Dice coefficient #cs.CV

paper · pdf · doi:10.48550/arxiv.1807.01172

9 pages, 3 figures, accepted to MICCAI 2018. arXiv admin note: substantial text overlap with arXiv:1801.08614

arxiv created 2018/07/02 · openalex publication_date 2018/07/02 · arxiv updated 2018/07/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Volumetric lesion segmentation from computed tomography (CT) images is a powerful means to precisely assess multiple time-point lesion/tumor changes. However, because manual 3D segmentation is prohibitively time consuming, current practices rely on an imprecise surrogate called response evaluation criteria in solid tumors (RECIST). Despite their coarseness, RECIST markers are commonly found in current hospital picture and archiving systems (PACS), meaning they can provide a potentially powerful, yet extraordinarily challenging, source of weak supervision for full 3D segmentation. Toward this end, we introduce a convolutional neural network (CNN) based weakly supervised slice-propagated segmentation (WSSS) method to 1) generate the initial lesion segmentation on the axial RECIST-slice; 2) learn the data distribution on RECIST-slices; 3) extrapolate to segment the whole lesion slice by slice to finally obtain a volumetric segmentation. To validate the proposed method, we first test its performance on a fully annotated lymph node dataset, where WSSS performs comparably to its fully supervised counterparts. We then test on a comprehensive lesion dataset with 32,735 RECIST marks, where we report a mean Dice score of 92% on RECIST-marked slices and 76% on the entire 3D volumes.

Citations

• Improving Deep Pancreas Segmentation in CT and MRI Images via Recurrent Neural Contextual Learning and Direct Loss Function
• Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECIST
• Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Database

Cited by

• A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation

Related

• Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECIST
• Weakly Supervised Lesion Co-segmentation on CT Scans
• Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentation
• RECIST Weakly Supervised Lesion Segmentation via Label-Space Co-Training
• Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss