Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification

Abstract

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.

arXiv commentElsevier Medical Image Analysis Best Paper Award runner up. arXiv admin note: substantial text overlap with arXiv:1912.03837

References in corpus (23)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Self-Attention Generative Adversarial Networks
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Conditional Image Synthesis With Auxiliary Classifier GANs
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Data Augmentation Generative Adversarial Networks
• SegAN: Adversarial Network with Multi-scale $L_1$ Loss for Medical Image Segmentation
• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
• Modulating early visual processing by language
• BAGAN: Data Augmentation with Balancing GAN
• Attention-Based Deep Neural Networks for Detection of Cancerous and Precancerous Esophagus Tissue on Histopathological Slides
• Learning to Compose Domain-Specific Transformations for Data Augmentation
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
• High-Fidelity Image Generation With Fewer Labels
• Generative Image Translation for Data Augmentation of Bone Lesion Pathology
• Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification

Cited by in corpus (6)

• Semi-supervised Body Parsing and Pose Estimation for Enhancing Infant General Movement Assessment
• A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis
• PlantPlotGAN: A Physics-Informed Generative Adversarial Network for Plant Disease Prediction
• Adaptive Input-image Normalization for Solving the Mode Collapse Problem in GAN-based X-ray Images
• Label Geometry Aware Discriminator for Conditional Generative Networks
• Accuracy Improvement for Fully Convolutional Networks via Selective Augmentation with Applications to Electrocardiogram Data