Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
Overview
Authors
Affiliations
Histopathological analysis is the present gold standard for precancerous lesion diagnosis. The goal of automated histopathological classification from digital images requires supervised training, which requires a large number of expert annotations that can be expensive and time-consuming to collect. Meanwhile, accurate classification of image patches cropped from whole-slide images is essential for standard sliding window based histopathology slide classification methods. To mitigate these issues, we propose a carefully designed conditional GAN model, namely HistoGAN, for synthesizing realistic histopathology image patches conditioned on class labels. We also investigate a novel synthetic augmentation framework that selectively adds new synthetic image patches generated by our proposed HistoGAN, rather than expanding directly the training set with synthetic images. By selecting synthetic images based on the confidence of their assigned labels and their feature similarity to real labeled images, our framework provides quality assurance to synthetic augmentation. Our models are evaluated on two datasets: a cervical histopathology image dataset with limited annotations, and another dataset of lymph node histopathology images with metastatic cancer. Here, we show that leveraging HistoGAN generated images with selective augmentation results in significant and consistent improvements of classification performance (6.7% and 2.8% higher accuracy, respectively) for cervical histopathology and metastatic cancer datasets.
Deep learning-based image analysis in muscle histopathology using photo-realistic synthetic data.
Mill L, Aust O, Ackermann J, Burger P, Pascual M, Palumbo-Zerr K Commun Med (Lond). 2025; 5(1):64.
PMID: 40050400 PMC: 11885816. DOI: 10.1038/s43856-025-00777-y.
Liu Q, Zhou T, Cheng C, Ma J, Tania M BMC Bioinformatics. 2025; 26(1):29.
PMID: 39871140 PMC: 11773846. DOI: 10.1186/s12859-025-06057-9.
SIAN: STYLE-GUIDED INSTANCE-ADAPTIVE NORMALIZATION FOR MULTI-ORGAN HISTOPATHOLOGY IMAGE SYNTHESIS.
Wang H, Xian M, Vakanski A, Shareef B Proc IEEE Int Symp Biomed Imaging. 2024; 2023.
PMID: 38572450 PMC: 10989245. DOI: 10.1109/isbi53787.2023.10230507.
Budginaite E, Magee D, Kloft M, Woodruff H, Grabsch H J Pathol Inform. 2024; 15:100367.
PMID: 38455864 PMC: 10918266. DOI: 10.1016/j.jpi.2024.100367.
Jiang L, Huang S, Luo C, Zhang J, Chen W, Liu Z Front Oncol. 2023; 13:1240645.
PMID: 38023227 PMC: 10679330. DOI: 10.3389/fonc.2023.1240645.