mlsanityData to 14 Oct 2026

Quantitative Imaging Principles Improves Medical Image Learning

arXiv 2206.06663 ↗First posted 14 Jun 2022q-bio.QM cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Fundamental differences between natural and medical images have recently favored the use of self-supervised learning (SSL) over ImageNet transfer learning for medical image applications. Differences between image types are primarily due to the imaging modality and medical images utilize a wide range of physics based techniques while natural images are captured using only visible light. While many have demonstrated that SSL on medical images has resulted in better downstream task performance, our work suggests that more performance can be gained. The scientific principles which are used to acquire medical images are not often considered when constructing learning problems. For this reason, we propose incorporating quantitative imaging principles during generative SSL to improve image quality and quantitative biological accuracy. We show that this training schema results in better starting states for downstream supervised training on limited data. Our model also generates images that validate on clinical quantitative analysis software.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 61 references that are in the map. First posted on arXiv 14 Jun 2022.

Builds on

25 of 61 references.

References · 25

  1. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  5. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  6. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  7. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 461
  8. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 368
  9. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  10. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  11. 2019Large Scale Adversarial Representation Learningcited by 239
  12. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 179
13 more
  1. 2018MedGAN: Medical Image Translation using GANscited by 152
  2. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 147
  3. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  4. 2021Breaking the Dilemma of Medical Image-to-image Translationcited by 82
  5. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  6. 2018Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?cited by 54
  7. 2020A scoping review of transfer learning research on medical image analysis using ImageNetcited by 54
  8. 2022Self-supervised Learning from 100 Million Medical Imagescited by 31
  9. 2019Surrogate Supervision for Medical Image Analysis: Effective Deep Learning From Limited Quantities of Labeled Datacited by 23
  10. 2020Sherpa: Robust Hyperparameter Optimization for Machine Learningcited by 14
  11. 2018Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networkscited by 10
  12. 2020Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomycited by 7
  13. 2020CycleQSM: Unsupervised QSM Deep Learning using Physics-Informed CycleGANcited by 2

Built on by

Not cited yet.