orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nataraj, Niran, Sogabe, Maina, Kawashima, Kenji
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915348330053632
author Nataraj, Niran
Sogabe, Maina
Kawashima, Kenji
author_facet Nataraj, Niran
Sogabe, Maina
Kawashima, Kenji
contents Deep learning in medical imaging faces obstacles: limited data diversity, ethical issues, high acquisition costs, and the need for precise annotations. Bleeding detection and localization during surgery is especially challenging due to the scarcity of high-quality datasets that reflect real surgical scenarios. We propose orGAN, a GAN-based system for generating high-fidelity, annotated surgical images of bleeding. By leveraging small "mimicking organ" datasets, synthetic models that replicate tissue properties and bleeding, our approach reduces ethical concerns and data-collection costs. orGAN builds on StyleGAN with Relational Positional Learning to simulate bleeding events realistically and mark bleeding coordinates. A LaMa-based inpainting module then restores clean, pre-bleed visuals, enabling precise pixel-level annotations. In evaluations, a balanced dataset of orGAN and mimicking-organ images achieved 90% detection accuracy in surgical settings and up to 99% frame-level accuracy. While our development data lack diverse organ morphologies and contain intraoperative artifacts, orGAN markedly advances ethical, efficient, and cost-effective creation of realistic annotated bleeding datasets, supporting broader integration of AI in surgical practice.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14303
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
Nataraj, Niran
Sogabe, Maina
Kawashima, Kenji
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Deep learning in medical imaging faces obstacles: limited data diversity, ethical issues, high acquisition costs, and the need for precise annotations. Bleeding detection and localization during surgery is especially challenging due to the scarcity of high-quality datasets that reflect real surgical scenarios. We propose orGAN, a GAN-based system for generating high-fidelity, annotated surgical images of bleeding. By leveraging small "mimicking organ" datasets, synthetic models that replicate tissue properties and bleeding, our approach reduces ethical concerns and data-collection costs. orGAN builds on StyleGAN with Relational Positional Learning to simulate bleeding events realistically and mark bleeding coordinates. A LaMa-based inpainting module then restores clean, pre-bleed visuals, enabling precise pixel-level annotations. In evaluations, a balanced dataset of orGAN and mimicking-organ images achieved 90% detection accuracy in surgical settings and up to 99% frame-level accuracy. While our development data lack diverse organ morphologies and contain intraoperative artifacts, orGAN markedly advances ethical, efficient, and cost-effective creation of realistic annotated bleeding datasets, supporting broader integration of AI in surgical practice.
title orGAN: A Synthetic Data Augmentation Pipeline for Simultaneous Generation of Surgical Images and Ground Truth Labels
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14303