mlsanityData to 7 Oct 2026

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

arXiv 1908.04373 ↗First posted 12 Aug 2019cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 9; 2024: 5; 2025: 7; 2026: 4.

39 papers.

Sort:

By area:

  1. 2023CLIP-Driven Universal Model for Organ Segmentation and Tumor Detectioncited by 224
  2. 2023PACO: Parts and Attributes of Common Objectscited by 146
  3. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  4. 2024Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomographycited by 31
  5. 2024The ULS23 Challenge: a Baseline Model and Benchmark Dataset for 3D Universal Lesion Segmentation in Computed Tomographycited by 26
  6. 2022SATr: Slice Attention with Transformer for Universal Lesion Detectioncited by 17
  7. 2021Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Losscited by 16
  8. 2023CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scanscited by 15
  9. 2021Asymmetric 3D Context Fusion for Universal Lesion Detectioncited by 14
  10. 2021Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connectioncited by 8
  11. 2021Universal Lesion Detection in CT Scans using Neural Network Ensemblescited by 8
  12. 2022Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximizationcited by 7
27 more
  1. 2021Conditional Training with Bounding Map for Universal Lesion Detectioncited by 5
  2. 2021RECIST-Net: Lesion detection via grouping keypoints on RECIST-based annotationcited by 4
  3. 2022View-Disentangled Transformer for Brain Lesion Detectioncited by 4
  4. 2023Anatomy-Aware Lymph Node Detection in Chest CT using Implicit Station Stratificationcited by 4
  5. 2024YOLO-MED : Multi-Task Interaction Network for Biomedical Imagescited by 3
  6. 2024Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformercited by 3
  7. 2023RECIST Weakly Supervised Lesion Segmentation via Label-Space Co-Trainingcited by 2
  8. 2021Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Datacited by 1
  9. 2022DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detectioncited by 1
  10. 2022Ultrasound Detection of Subquadricipital Recess Distensioncited by 1
  11. 2023An End-to-End Framework For Universal Lesion Detection With Missing Annotationscited by 1
  12. 2023Tackling the Incomplete Annotation Issue in Universal Lesion Detection Task By Exploratory Trainingcited by 1
  13. 2024Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustmentcited by 1
  14. 2025Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CTcited by 1
  15. 2022An Efficient Anchor-free Universal Lesion Detection in CT-scanscited by 0
  16. 2023Integrating features from lymph node stations for metastatic lymph node detectioncited by 0
  17. 2023Mixed-order self-paced curriculum learning for universal lesion detectioncited by 0
  18. 2025From Slices to Sequences: Autoregressive Tracking Transformer for Cohesive and Consistent 3D Lymph Node Detection in CT Scanscited by 0
  19. 2025Correcting Class Imbalances with Self-Training for Improved Universal Lesion Detection and Taggingcited by 0
  20. 2025Context Aware Grounded Teacher for Source Free Object Detectioncited by 0
  21. 2025MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality imagescited by 0
  22. 2025PDSE: A Multiple Lesion Detector for CT Images using PANet and Deformable Squeeze-and-Excitation Blockcited by 0
  23. 2025MTMed3D: A Multi-Task Transformer-Based Model for 3D Medical Imagingcited by 0
  24. 20263DLAND: 3D Lesion Abdominal Anomaly Localization Datasetcited by 0
  25. 2026Multi-Granularity 3D Kidney Lesion Characterization from CT Volumescited by 0
  26. 2026A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generationcited by 0
  27. 2026Lesion Detection in CT with Frozen Self-Distilled Features: SALT, a Spatially Adaptive Label-Guided Temperaturecited by 0