mlsanityData to 7 Oct 2026

Photoacoustic image synthesis with generative adversarial networks

arXiv 2103.15510 ↗First posted 29 Mar 2021eess.IV cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties with high spatial resolution. However, previous attempts to solve the optical inverse problem with supervised machine learning were hampered by the absence of labeled reference data. While this bottleneck has been tackled by simulating training data, the domain gap between real and simulated images remains an unsolved challenge. We propose a novel approach to PAT image synthesis that involves subdividing the challenge of generating plausible simulations into two disjoint problems: (1) Probabilistic generation of realistic tissue morphology, and (2) pixel-wise assignment of corresponding optical and acoustic properties. The former is achieved with Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data. According to a validation study on a downstream task our approach yields more realistic synthetic images than the traditional model-based approach and could therefore become a fundamental step for deep learning-based quantitative PAT (qPAT).

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 47 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

18 of 47 references.

References · 18

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  5. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  6. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  7. 2020Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learningcited by 292
  8. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  9. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 146
  10. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  11. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  12. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
6 more
  1. 2019Methods and open-source toolkit for analyzing and visualizing challenge resultscited by 60
  2. 2018Learning To Simulatecited by 43
  3. 2020Deep Learning in Photoacoustic Tomography: Current approaches and future directionscited by 25
  4. 2020Deep learning for biomedical photoacoustic imaging: A reviewcited by 21
  5. 2020Fed-Sim: Federated Simulation for Medical Imagingcited by 14
  6. 2019Estimation of blood oxygenation with learned spectral decoloring for quantitative photoacoustic imaging (LSD-qPAI)cited by 7

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023Moving beyond simulation: data-driven quantitative photoacoustic imaging using tissue-mimicking phantomscited by 10
  2. 2023Unsupervised Domain Transfer with Conditional Invertible Neural Networkscited by 4
  3. 2023Application-driven Validation of Posteriors in Inverse Problemscited by 0