mlsanityData to 14 Oct 2026

Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss

arXiv 2105.01218 ↗First posted 3 May 2021eess.IV cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as universal lesion segmentation (ULS). Manual annotation is the current clinical practice, being highly time-consuming and inconsistent on tumor's longitudinal assessment. Effectively training an automatic segmentation model is desirable but relies heavily on a large number of pixel-wise labelled data. Existing weakly-supervised segmentation approaches often struggle with regions nearby the lesion boundaries. In this paper, we present a novel weakly-supervised universal lesion segmentation method by building an attention enhanced model based on the High-Resolution Network (HRNet), named AHRNet, and propose a regional level set (RLS) loss for optimizing lesion boundary delineation. AHRNet provides advanced high-resolution deep image features by involving a decoder, dual-attention and scale attention mechanisms, which are crucial to performing accurate lesion segmentation. RLS can optimize the model reliably and effectively in a weakly-supervised fashion, forcing the segmentation close to lesion boundary. Extensive experimental results demonstrate that our method achieves the best performance on the publicly large-scale DeepLesion dataset and a hold-out test set.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 3 May 2021.

Builds on

29 of 47 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2017Mask R-CNNcited by 7,277
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  8. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  9. 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
  10. 2020SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Imagescited by 67
  11. 2020Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CTcited by 42
  12. 2019MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentationcited by 39
17 more
  1. 2018CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentationcited by 34
  2. 2017Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networkscited by 28
  3. 2020Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studiescited by 25
  4. 2018Multi-Scale Coarse-to-Fine Segmentation for Screening Pancreatic Ductal Adenocarcinomacited by 24
  5. 2019ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Miningcited by 21
  6. 2018Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECISTcited by 17
  7. 2020Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentationcited by 15
  8. 2020Lymph Node Gross Tumor Volume Detection and Segmentation via Distance-based Gating using 3D CT/PET Imaging in Radiotherapycited by 15
  9. 2020E2Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scanscited by 12
  10. 2020One Click Lesion RECIST Measurement and Segmentation on CT Scanscited by 10
  11. 2020Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scanscited by 8
  12. 2019CNN-based Semantic Segmentation using Level Set Losscited by 7
  13. 2020Weakly Supervised Lesion Co-segmentation on CT Scanscited by 7
  14. 2018Semi-Automatic RECIST Labeling on CT Scans with Cascaded Convolutional Neural Networkscited by 5
  15. 2018CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvementcited by 5
  16. 2020Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentationcited by 5
  17. 2018A Progressively-trained Scale-invariant and Boundary-aware Deep Neural Network for the Automatic 3D Segmentation of Lung Lesionscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 4; 2024: 5; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentationcited by 116
  2. 2024The ULS23 Challenge: a Baseline Model and Benchmark Dataset for 3D Universal Lesion Segmentation in Computed Tomographycited by 26
  3. 2022SATr: Slice Attention with Transformer for Universal Lesion Detectioncited by 17
  4. 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
  5. 2024Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotationcited by 9
  6. 2021Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connectioncited by 8
  7. 2022Accurate and Robust Lesion RECIST Diameter Prediction and Segmentation with Transformerscited by 4
  8. 2024Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Modelscited by 4
  9. 2023RECIST Weakly Supervised Lesion Segmentation via Label-Space Co-Trainingcited by 2
  10. 2024Optimizing Universal Lesion Segmentation: State Space Model-Guided Hierarchical Networks with Feature Importance Adjustmentcited by 1
  11. 2024Label Filling via Mixed Supervision for Medical Image Segmentation from Noisy Annotationscited by 1
  12. 2022Coarse Retinal Lesion Annotations Refinement via Prototypical Learningcited by 0
4 more
  1. 2023Mixed-order self-paced curriculum learning for universal lesion detectioncited by 0
  2. 2025Weakly Supervised Segmentation Framework for Thyroid Nodule Based on High-confidence Labels and High-rationality Lossescited by 0
  3. 2025MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality imagescited by 0
  4. 2026A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generationcited by 0