mlsanityData to 14 Oct 2026

Boosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts

arXiv 2310.02906 ↗First posted 4 Oct 2023cs.CV cs.AIcited by 17

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Image synthesis approaches, e.g., generative adversarial networks, have been popular as a form of data augmentation in medical image analysis tasks. It is primarily beneficial to overcome the shortage of publicly accessible data and associated quality annotations. However, the current techniques often lack control over the detailed contents in generated images, e.g., the type of disease patterns, the location of lesions, and attributes of the diagnosis. In this work, we adapt the latest advance in the generative model, i.e., the diffusion model, with the added control flow using lesion-specific visual and textual prompts for generating dermatoscopic images. We further demonstrate the advantage of our diffusion model-based framework over the classical generation models in both the image quality and boosting the segmentation performance on skin lesions. It can achieve a 9% increase in the SSIM image quality measure and an over 5% increase in Dice coefficients over the prior arts.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 13 of its 19 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

13 of 19 references.

References · 13

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  7. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  8. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  9. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  10. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 147
  11. 2023Label-Free Liver Tumor Segmentationcited by 56
  12. 2023Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesiscited by 17
1 more
  1. 2022Synthetic Tumors Make AI Segment Tumors Bettercited by 14

Built on by

Cited by year

Citing papers per year: 2024: 12; 2025: 5.

17 papers.

Sort:

By area:

  1. 2024Towards Generalizable Tumor Synthesiscited by 65
  2. 2024A Survey on Data Augmentation in Large Model Eracited by 31
  3. 2024Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?cited by 31
  4. 2024From Pixel to Cancer: Cellular Automata in Computed Tomographycited by 20
  5. 2024FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesiscited by 15
  6. 2024CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentationcited by 14
  7. 2024Exploiting Structural Consistency of Chest Anatomy for Unsupervised Anomaly Detection in Radiography Imagescited by 13
  8. 2024Text-Driven Tumor Synthesiscited by 13
  9. 2024Analyzing Tumors by Synthesiscited by 11
  10. 2024CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentationcited by 5
  11. 2024Physics-Inspired Generative Models in Medical Imaging: A Reviewcited by 5
  12. 2025Expectation-Maximization as the Engine of Scalable Medical Intelligencecited by 5
5 more
  1. 2025See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancementcited by 3
  2. 2024Towards Synchronous Memorizability and Generalizability with Site-Modulated Diffusion Replay for Cross-Site Continual Segmentationcited by 1
  3. 2025ShapeKitcited by 0
  4. 2025Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Modelcited by 0
  5. 2025AURAD: Anatomy-Pathology Unified Radiology Synthesis with Progressive Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SkinDualGen: Prompt-Driven Diffusion for Simultaneous Image-Mask Generation in Skin Lesions
  2. 2024Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
  3. 2025Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images
  4. 2023Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images
  5. 2025LesionGen: A Concept-Guided Diffusion Model for Dermatology Image Synthesis
  6. 2025SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis
  7. 2025Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis
  8. 2022Improving dermatology classifiers across populations using images generated by large diffusion models