AUTHOR=Lin Qiang , Gao Runxia , Luo Mingyang , Wang Haijun , Cao Yongchun , Man Zhengxing , Wang Rong 

TITLE=Semi-supervised segmentation of metastasis lesions in bone scan images

JOURNAL=Frontiers in Molecular Biosciences

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2022.956720

DOI=10.3389/fmolb.2022.956720

ISSN=2296-889X

ABSTRACT=To develop a deep image segmentation model to automatically identify and delineate lesions of skeletal metastasis in bone scan images, facilitating clinical diagnosis of lung cancer-caused bone metastasis by nuclear medicine physicians. A semi-supervised segmentation model is proposed, comprising feature extraction subtask and pixel classification subtask. During the feature extraction stage, cascaded layers including the dilated residual convolution, Inception connection, and feature aggregation learn the hierarchal representations of low-resolution bone scan images. During the pixel classification stage, each pixel is first classified into categories in a semi-supervised manner and the boundary of pixels belonging to an individual lesion is then delineated using a closed curve. Experimental evaluation conducted on 2280 augmented samples (112 original images) demonstrates that the proposed model performs well for automated segmentation of metastasis lesions, with obtaining a score of 0.692 for DSC if the model was trained using 37% of the labelled samples. The self-defined semi-supervised segmentation model can be utilized as an automated clinical tool to detect and delineate metastasis lesions in bone scan images with only a few manually-labeled image samples being used. Nuclear medicine physicians need only to attend to those segmented lesions while ignoring background when they diagnose bone metastasis using low-resolution images. More images from the multiple-center patients are typically needed to further improve the scalability and performance of the model via mitigating the impacts of variability in size, shape and intensity of bone metastasis lesions.