GHA-DenseNet prediction and diagnosis of malignancy in femoral bone tumors using magnetic resonance imaging

Y Yuguang; Yusi Chen; Daxin Zhu; Yifeng Huang; Ying Huang; Xiadong Li; Jianbing Xiahou

doi:10.1016/j.jbo.2023.100520

GHA-DenseNet prediction and diagnosis of malignancy in femoral bone tumors using magnetic resonance imaging

J Bone Oncol. 2023 Dec 29:44:100520. doi: 10.1016/j.jbo.2023.100520. eCollection 2024 Feb.

Authors

Y Yuguang^{1

2

3}, Yusi Chen^{1

2

3}, Daxin Zhu^{1

2

3}, Yifeng Huang⁴, Ying Huang⁴, Xiadong Li⁵, Jianbing Xiahou^{1

2

3}

Affiliations

¹ Faculty of Mathematics and Computer Science, Quanzhou Normal University, Quanzhou 362000, China.
² Fujian Provincial Key Laboratory of Data Intensive Computing, Quanzhou 362000, China.
³ Key Laboratory of Intelligent Computing and Information Processing, Fujian Province University, Quanzhou 362000, China.
⁴ Department of Diagnostic Radiology, Huaqiao University Affiliated Strait Hospital, Quanzhou, Fujian 362000, China.
⁵ Department of Radiation Oncology, Children's Hospital of Zhejiang University School of Medicine, Zhejiang University, Hangzhou 310052, China.

Abstract

Background and objective: Due to their aggressive nature and poor prognosis, malignant femoral bone tumors present considerable hurdles. Early treatment commencement is essential for enhancing vital and practical outcomes. In this investigation, deep learning algorithms will be used to analyze magnetic resonance imaging (MRI) data to identify bone tumors that are malignant.

Methodology: The study cohort included 44 patients, with ages ranging from 17 to 78 (22 women and 22 males). To categorize T1 and T2 weighted MRI data, this paper presents an improved DenseNet network model for the classification of bone tumor MRI, which is named GHA-DenseNet. Based on the original DenseNet model, the attention module is added to solve the problem that the deep convolutional model can reduce the loss of key features when capturing the location and content information of femoral bone tumor tissue due to the limitation of local receptive field. In addition, the sparse connection mode is used to prune the connection mode of the original model, so as to remove unnecessary and retain more useful fast connection mode, and alleviate the overfitting problem caused by small dataset size and image characteristics. In a clinical model designed to anticipate tumor malignancy, the utilization of T1 and T2 classifier output values, in combination with patient-specific clinical information, was a crucial component.

Results: The T1 classifier's accuracy during the training phase was 92.88% whereas the T2 classifier's accuracy was 87.03%. Both classifiers demonstrated accuracy of 95.24% throughout the validation phase. During training and validation, the clinical model's accuracy was 82.17% and 81.51%, respectively. The clinical model's receiver operating characteristic (ROC) curve demonstrated its capacity to separate classes.

Conclusions: The proposed method does not require manual segmentation of MRI scans because it makes use of pretrained deep learning classifiers. These algorithms have the ability to predict tumor malignancy and shorten the diagnostic and therapeutic turnaround times. Although the procedure only needs a little amount of radiologists' involvement, more testing on a larger patient cohort is required to confirm its efficacy.

Keywords: Attention module; Bone tumour; Deep convolutional network model; GHA-DenseNet; Magnetic resonance imaging.