Abstract
The objective of this study is to develop and evaluate a new deep learning architecture, namely regenerative semi-supervised bidirectional W-network (RSS-BW), to predict the tumor state of the knee bone from radiographic images. First, we constructed an autoencoder model, called Bidirectional W-network (BW), for segmenting three-region (i.e., femur, tibia, and fibula) of knee bone. Using these regions as input data, RSS-BW architecture consisting of the autoencoding model for regenerating the bone structures, the backbone model for extracting features with pretrained ImageNet, and the predicting model for knee bone tumor classification are established. The developed scheme rapidly obtained segmentation results of the three-region of knee bone with a mean dice score of 98.06 ± 0.08%. Moreover, two types of classification are conducted: single-step and double-step. The single-step classifies the bone images into normal, benign, and malignant states. The mean values of accuracy, precision, recall and F-beta score obtained from the segmented images were 85.23±3.91%, 82.23±3.22%, 82.15±3.31%, and 82.21±3.25%, respectively. For the double-step of bone tumor classification, the images are classified first as normal versus abnormal. The second classification is conducted for abnormal images as benign versus malignant. The double-step classification shows an improvement of the mean accuracy by 1.7% compared to the single-step classification. In conclusion, the RSS-BW model presents higher accuracy than conventional models, indicating its potential clinical decision support for bone tumor classification.
Highlights
The radiological diagnosis of bone tumors, often identified as incidental findings in asymptomatic patients, requires caution and evaluation by a specialist
The objective of the present study is to develop and evaluate a new deep learning architecture to predict the tumor state of the knee bone from radiographs based on bone segmentation results
Utilizing the advantages of U-Net [7], we propose a new deep learning model, namely bidirectional W-network (BW), to segment three regions of a knee bone: femur, tibia, and fibula
Summary
The radiological diagnosis of bone tumors, often identified as incidental findings in asymptomatic patients, requires caution and evaluation by a specialist. Conventional radiography is a complementary method of diagnosis that is essential to the investigation. The incidence of bone tumors among all tumors is 2%−−3%, and rising in recent years [1]. The early detection of bone tumors is difficult. The associate editor coordinating the review of this manuscript and approving it for publication was Chongsheng Zhang. It is not easy to cure completely in the later stages, often being treated with surgical resection, with or without adjuvant therapy. Doctors often use multiple methods such as imaging, and observing the clinical manifestations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
