Improving High Resolution Histology Image Classification with Deep Spatial Fusion Network

TL;DR

This paper introduces a deep spatial fusion network that enhances high-resolution histology image classification by capturing spatial relationships and hierarchical features, achieving near pathologist-level accuracy.

Contribution

The study proposes a novel deep fusion architecture combining residual networks and spatial relationship modeling for improved high-resolution histology image classification.

Findings

Achieved 95% accuracy on 4-class breast histology classification.

Reported 98.5% accuracy and 99.6% AUC on 2-class carcinoma detection.

Outperformed previous methods, approaching expert pathologist performance.

Abstract

Histology imaging is an essential diagnosis method to finalize the grade and stage of cancer of different tissues, especially for breast cancer diagnosis. Specialists often disagree on the final diagnosis on biopsy tissue due to the complex morphological variety. Although convolutional neural networks (CNN) have advantages in extracting discriminative features in image classification, directly training a CNN on high resolution histology images is computationally infeasible currently. Besides, inconsistent discriminative features often distribute over the whole histology image, which incurs challenges in patch-based CNN classification method. In this paper, we propose a novel architecture for automatic classification of high resolution histology images. First, an adapted residual network is employed to explore hierarchical features without attenuation. Second, we develop a robust deep fusion network to utilize the spatial relationship between patches and learn to correct the prediction bias generated from inconsistent discriminative feature distribution. The proposed method is evaluated using 10-fold cross-validation on 400 high resolution breast histology images with balanced labels and reports 95% accuracy on 4-class classification and 98.5% accuracy, 99.6% AUC on 2-class classification (carcinoma and non-carcinoma), which substantially outperforms previous methods and close to pathologist performance.