mlsanityData to 14 Oct 2026

Evaluation of Machine-generated Biomedical Images via A Tally-based Similarity Measure

arXiv 2503.22658 ↗First posted 28 Mar 2025eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Super-resolution, in-painting, whole-image generation, unpaired style-transfer, and network-constrained image reconstruction each include an aspect of machine-learned image synthesis where the actual ground truth is not known at time of use. It is generally difficult to quantitatively and authoritatively evaluate the quality of synthetic images; however, in mission-critical biomedical scenarios robust evaluation is paramount. In this work, all practical image-to-image comparisons really are relative qualifications, not absolute difference quantifications; and, therefore, meaningful evaluation of generated image quality can be accomplished using the Tversky Index, which is a well-established measure for assessing perceptual similarity. This evaluation procedure is developed and then demonstrated using multiple image data sets, both real and simulated. The main result is that when the subjectivity and intrinsic deficiencies of any feature-encoding choice are put upfront, Tversky's method leads to intuitive results, whereas traditional methods based on summarizing distances in deep feature spaces do not.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 52 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

17 of 52 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  4. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
  5. 2015A note on the evaluation of generative modelscited by 292
  6. 2018Generative Adversarial Network in Medical Imaging: A Reviewcited by 257
  7. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  8. 2018A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentationcited by 172
  9. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  10. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  11. 2022Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesiscited by 42
  12. 2022Deep Learning-enabled Virtual Histological Staining of Biological Samplescited by 42
5 more
  1. 2018PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learningcited by 41
  2. 2020Deep Learning for Biomedical Image Reconstruction: A Surveycited by 17
  3. 2023Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparisoncited by 11
  4. 2024Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statisticscited by 4
  5. 2020Learning Tversky Similaritycited by 1

Built on by

Not cited yet.