MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation

Ke Yan, Youbao Tang, Yifan Peng, Veit Sandfort, Mohammadhadi Bagheri +2 more
8/12/2019
cs.CV

Official code: rsummers11/CADLab (462 stars, last commit 2024-08-15).

Abstract

When reading medical images such as a computed tomography (CT) scan, radiologists generally search across the image to find lesions, characterize and measure them, and then describe them in the radiological report. To automate this process, we propose a multitask universal lesion analysis network (MULAN) for joint detection, tagging, and segmentation of lesions in a variety of body parts, which greatly extends existing work of single-task lesion analysis on specific body parts. MULAN is based on an improved Mask R-CNN framework with three head branches and a 3D feature fusion strategy. It achieves the state-of-the-art accuracy in the detection and tagging tasks on the DeepLesion dataset, which contains 32K lesions in the whole body. We also analyze the relationship between the three tasks and show that tag predictions can improve detection accuracy via a score refinement layer.

View on arXivView PDF

Code Implementations(1)

rsummers11/CADLabOfficial100%

Imaging Biomarkers and Computer-Aided Diagnosis Laboratory

462182C, MSep 10, 20142 years ago

Similar Papers

3D Universal Lesion Detection and Tagging in CT with Self-Training

86% match2025

3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection

84% match1 repo4622018

IAFI-FCOS: Intra- and across-layer feature interaction FCOS model for lesion detection of CT images

84% match2024

TP-Seg: Task-Prototype Framework for Unified Medical Lesion Segmentation

83% match1 repo122026

Multi-Scale Transformer Architecture for Accurate Medical Image Classification

83% match2025

From FDG to PSMA: A Hitchhiker's Guide to Multitracer, Multicenter Lesion Segmentation in PET/CT Imaging

83% match1 repo262024

Cite this paper

@article{yan2019mulan,
  title  = {MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation},
  author = {Ke Yan and Youbao Tang and Yifan Peng and Veit Sandfort and Mohammadhadi Bagheri and Zhiyong Lu and Ronald M. Summers},
  year   = {2019},
  eprint = {1908.04373},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1908.04373}
}

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/1908.04373.svg)](https://codeofpaper.com/paper/1908.04373)

Discussion