DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology

Aversa, M. et al. (2024) DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology. In: 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, Louisiana, USA, 10-16 December 2023,

Abstract

We present DiffInfinite, a hierarchical diffusion model that generates arbitrarily large histological images while preserving long-range correlation structural information. Our approach first generates synthetic segmentation masks, subsequently used as conditions for the high-fidelity generative diffusion process. The proposed sampling method can be scaled up to any desired image size while only requiring small patches for fast training. Moreover, it can be parallelized more efficiently than previous large-content generation methods while avoiding tiling artefacts. The training leverages classifier-free guidance to augment a small, sparsely annotated dataset with unlabelled data. Our method alleviates unique challenges in histopathological imaging practice: large-scale information, costly manual annotation, and protective data handling. The biological plausibility of DiffInfinite data is validated in a survey by ten experienced pathologists as well as a downstream segmentation task. Furthermore, the model scores strongly on anti-copying metrics which is beneficial for the protection of patient data.

• Item Type: Conference Proceedings
• Additional Information: This work was supported by the Federal Ministry of Education and Research (BMBF) as grants [SyReal (01IS21069B)]. RM-S is grateful for EPSRC support through grants EP/T00097X/1, EP/R018634/1 and EP/T021020/1, and DI for EP/R513222/1. MA is funded by Dotphoton, QuantIC and a UofG Ph.D. scholarship.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Ivanova, Ms Daniela and Murray-Smith, Professor Roderick and Aversa, Marco
• Authors: Aversa, M., Nobis, G., Hägele, M., Standvoss, K., Chirica, M., Murray-Smith, R., Alaa, A., Ruff, L., Ivanova, D., Samek, W., Klauschen, F., Sanguinetti, B., and Oala, L.
• College/School: College of Science and Engineering > School of Computing Science
• Copyright Holders: Copyright © 2023 The Author(s)
• First Published: First published in Advances in Neural Information Processing Systems 36 (NeurIPS 2023)
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Related URLs

• Organisation
• Publisher

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
305567		QuantIC - The UK Quantum Technoogy Hub in Quantum Enhanced Imaging	Miles Padgett	Engineering and Physical Sciences Research Council (EPSRC)	EP/T00097X/1	P&S - Physics & Astronomy
300982		Exploiting Closed-Loop Aspects in Computationally and Data Intensive Analytics	Roderick Murray-Smith	Engineering and Physical Sciences Research Council (EPSRC)	EP/R018634/1	Computing Science
307829		Quantum-Inspired Imaging for Remote Monitoring of Health & Disease in Community Healthcare	Jonathan Cooper	Engineering and Physical Sciences Research Council (EPSRC)	EP/T021020/1	ENG - Biomedical Engineering
305200		DTP 2018-19 University of Glasgow	Mary Beth Kneafsey	Engineering and Physical Sciences Research Council (EPSRC)	EP/R513222/1	MVLS - Education Hub