Unsupervised Segmentation of Micro-CT Images of Lung Cancer Specimen Using Deep Generative Models

Abstract

This paper presents a novel unsupervised segmentation method for the three-dimensional microstructure of lung cancer specimens in micro-computed tomography (micro-CT) images. Micro-CT scanning can nondestructively capture detailed histopathological components of resected lung cancer specimens. However, it is difficult to manually annotate cancer components on micro-CT images. Moreover, since most of the recent segmentation methods using deep neural networks have relied on supervised learning, it is also difficult to cope with unlabeled micro-CT images. In this paper, we propose an unsupervised segmentation method using a deep generative model. Our method consists of two phases. In the first phase, we train our model by iterating two steps: (1) inferring pairs of continuous and categorical latent variables of image patches randomly extracted from an unlabeled image and (2) reconstructing image patches from the inferred pairs of latent variables. In the second phase, our trained model estimates te probabilities of belonging to each category and assigns labels to patches from an entire image in order to obtain the segmented image. We apply our method to seven micro-CT images of resected lung cancer specimens. The original sizes of the micro-CT images were $1024 \times 1024 \times (544{-}2185)$ voxels, and their resolutions were 25–30 $\upmu$m/voxel. Our aim was to automatically divide each image into three regions: invasive carcinoma, noninvasive carcinoma, and normal tissue. From quantitative evaluation, mean normalized mutual information scores of our results are 0.437. From qualitative evaluation, our segmentation results prove helpful for observing the anatomical extent of cancer components. Moreover, we visualize the degree of certainty of segmentation results by using values of categorical latent variables.