基于深度学习的乳腺肿瘤良恶性自动诊断
Automatic Diagnosis of Benign and Malignant Breast Tumours Based on Deep Learning
张宁1
作者信息
- 1. 中国石油大学(华东)计算机科学与技术学院 青岛 266580
- 折叠
摘要
超声是目前诊断乳腺肿瘤的常用手段之一.针对超声中良恶性肿瘤纹理相似,区分度小等问题,论文提出了一个基于深度学习的乳腺超声良恶性自动诊断模型以辅助医生诊断.论文采用Densenet加强细节特征提取,注意力机制模拟临床诊断,迁移学习缓解数据依赖.实验结果表明,该模型可为年轻医生提供良好的辅助诊断,具有较好的可靠性和临床实用性.
Abstract
Ultrasound is now one of the common means of diagnosing breast tumours.To address the problems of similar tex-ture and low differentiation between benign and malignant tumours in ultrasound,this paper proposes a deep learning-based auto-matic diagnosis model for benign and malignant breast ultrasound to assist doctors in diagnosis.This paper uses Densenet to enhance detailed feature extraction,attention mechanisms to simulate clinical diagnosis,and transfer learning to alleviate data dependency.The experimental results show that the model can provide a good aid to diagnosis for young doctors,with good reliability and clinical utility.
关键词
乳腺肿瘤/超声图像/注意力机制/迁移学习Key words
breast tumours/ultrasound images/attentional mechanisms/transfer learning引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据