文献类型：期刊文献

英文题名：Automated detection of skeletal metastasis of lung cancer with bone scans using convolutional nuclear network

作者：Li, Tongtong[1,2];Lin, Qiang[1,2,3];Guo, Yanru[1,2];Zhao, Shaofang[1,2];Zeng, Xianwu[4];Man, Zhengxing[1,2,3];Cao, Yongchun[1,2,3];Hu, Yonghua[5]

第一作者：Li, Tongtong

通信作者：Lin, Q[1];Lin, Q[2];Lin, Q[3]

机构：[1]Northwest Minzu Univ, Sch Math & Comp Sci, Lanzhou, Peoples R China;[2]Northwest Minzu Univ, Key Lab Streaming Data Comp Technol & Applicat, Lanzhou, Peoples R China;[3]Minist Educ, Key Lab Chinas Ethn Languages & Informat Technol, Lanzhou, Peoples R China;[4]Gansu Prov Tumour Hosp, Dept Nucl Med, Lanzhou, Peoples R China;[5]Gansu Univ Chinese Med, Sch Clin Med 1, Lanzhou, Peoples R China

第一机构：Northwest Minzu Univ, Sch Math & Comp Sci, Lanzhou, Peoples R China

通信机构：[1]corresponding author), Northwest Minzu Univ, Sch Math & Comp Sci, Lanzhou, Peoples R China;[2]corresponding author), Northwest Minzu Univ, Key Lab Streaming Data Comp Technol & Applicat, Lanzhou, Peoples R China;[3]corresponding author), Minist Educ, Key Lab Chinas Ethn Languages & Informat Technol, Lanzhou, Peoples R China.

年份：2022

卷号：67

期号：1

外文期刊名：PHYSICS IN MEDICINE AND BIOLOGY

收录：;EI(收录号：20220511580715);Scopus(收录号：2-s2.0-85123864860);WOS:【SCI-EXPANDED(收录号:WOS:000743302000001)】；

基金：This work was supported by the Youth PhD Foundation of Education Department of Gansu Province (2021QB-063), the Fundamental Research Funds for the Central Universities (31920210013, Yxm2021003, 31920190029), KeyR&DPlan of Gansu Province (21YF5GA063), the Natural Science Foundation of Gansu Province (20JR5RA511), the National Natural Science Foundation of China (61562075), the Gansu Provincial First-class Discipline Program of Northwest Minzu University (11080305), and the Program for Innovative Research Team of SEAC ([2018] 98).

语种：英文

外文关键词：bone scan; skeletal metastasis; image classification; deep learning; convolutional neural network

摘要：A bone scan is widely used for surveying bone metastases caused by various solid tumors. Scintigraphic images are characterized by inferior spatial resolution, bringing a significant challenge to manual analysis of images by nuclear medicine physicians. We present in this work a new framework for automatically classifying scintigraphic images collected from patients clinically diagnosed with lung cancer. The framework consists of data preparation and image classification. In the data preparation stage, data augmentation is used to enlarge the dataset, followed by image fusion and thoracic region extraction. In the image classification stage, we use a self-defined convolutional neural network consisting of feature extraction, feature aggregation, and feature classification sub-networks. The developed multi-class classification network can not only predict whether a bone scan image contains bone metastasis but also tell which subcategory of lung cancer that a bone metastasis metastasized from is present in the image. Experimental evaluations on a set of clinical bone scan images have shown that the proposed multi-class classification network is workable for automated classification of metastatic images, with achieving average scores of 0.7392, 0.7592, 0.7242, and 0.7292 for accuracy, precision, recall, and F-1 score, respectively.