Imaging assessment of osteosarcoma chemotherapy efficacy based on multi-scale lesion attention network
10.16098/j.issn.0529-1356.2025.01.004
- VernacularTitle:基于多尺度病变注意力网络的骨肉瘤化疗效果影像评估
- Author:
Jie ZANG
1
;
Ze-Qun SONG
;
Zhen-Yu TANG
;
Fang-Zhou HE
;
Chao-Wei DING
;
Ling-Feng WANG
;
Xiao-Dong TANG
Author Information
1. 北京大学人民医院骨肿瘤科,北京 100044
- Keywords:
Osteosarcoma;
Chemotherapy assessment;
Clinical application;
Multiscale lesion attention
- From:
Acta Anatomica Sinica
2025;56(1):30-36
- CountryChina
- Language:Chinese
-
Abstract:
Objective To propose a high-precision deep learning-based image assessment method of osteosarcoma chemotherapy efficacy for clinical treatment,as existing methos have low accuracy of osteosarcoma assessment.Methods The low incidence of osteosarcoma led to the small scale of its imaging data and the problem of imbalance in data categories.This study combined deep learning with clinical medical information,combined the bone sarcoma generation module of BoneGAN and the scale lesion information capture module,and proposed OMLA-Net,a deep learning assessment network for chemotherapy effect of bone sarcoma based on multi-scale lesion attention network,which achieved computer-aided bone tumor assessment with integrated data augmentation and focused lesion information through pre-training and generalized loss training.Results In this study,40 cases of osteosarcoma MRI data were used as the basis for the comparison test on the generated dataset,and the OMLA-Net assessment outperformed the SOTA method Conv-LSTM-GAN in terms of the assessment effects such as accuracy and F1 scores,and the difference was statistically significant(Bootstrap statistical method P＜0.05);the subsequent K-fold cross-validation ablation experiments further demonstrated the effectiveness of each module proposed by OMLA-Net.Conclusion OMLA-Net can effectively perform the impact assessment of chemotherapy effect on osteosarcoma,which provides a new idea for subsequent clinical application.
