The self‐distillation trained multitask dense‐attention network for diagnosing lung cancers based on CT scans

计算机科学 人工智能 计算机断层摄影术 蒸馏 医学物理学 放射科 医学 化学 有机化学
作者
Liuyin Chen,Zijun Zhang
出处
期刊:Medical Physics [Wiley]
卷期号:51 (3): 1738-1753 被引量:3
标识
DOI:10.1002/mp.16736
摘要

Abstract Background The latest international multidisciplinary histopathological classification of lung cancer indicates that a deeper study of the lung adenocarcinoma requires a comprehensive multidisciplinary platform. However, in the traditional pathological examination or previous computer‐vision‐based research, the entire lung is not considered in a comprehensive manner. Purpose The study aims to develop a deep learning model proposed for diagnosing the lung adenocarcinoma histopathologically based on CT scans. Instead of just classifying the lung adenocarcinoma, the pathological report should be inferred based on both the invasiveness and growth pattern of the tumors. Methods A self‐distillation trained multitask dense‐attention network (SD‐MdaNet) is proposed and validated based on 2412 labeled CT scans from 476 patients and 845 unlabeled scans. Inferring the pathological report is divided into two tasks, predicting the invasiveness of the lung tumor and inferring growth patterns of tumor cells in a comprehensive histopathological subtyping manner with excellent accuracy. In the proposed method, the dense‐attention module is introduced to better extract features from a small dataset in the main branch of the MdaNet. Next, task‐specific attention modules are utilized in different branches and finally integrated as a multitask model. The second task is a blend of classification and regression tasks. Thus, a specialized loss function is developed. In the proposed knowledge distillation (KD) process, the MdaNet as well as its main branch trained for solving two single tasks, respectively, are treated as multiple teachers to produce a student model. A novel KD loss function is developed to take the advantage of all the models as well as data with labels and without labels. Results SD‐MdaNet achieves an AUC of on invasiveness prediction, and on predominant growth pattern prediction on our dataset. Moreover, the average mean squared error in inferring growth pattern proportion reaches , and the AUC for predominant growth pattern proportion reaches . The proposed SD‐MdaNet is significantly better than all other benchmarking methods (). Conclusions Experimental results demonstrate that the proposed SD‐MdaNet can significantly improve the performance of the lung adenocarcinoma pathological diagnosis using only CT scans. Analyses and discussions are conducted to interpret the advantages of the SD‐MdaNet.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
乐观的海雪完成签到,获得积分20
刚刚
1秒前
1秒前
miao发布了新的文献求助10
1秒前
moneymoney完成签到,获得积分10
1秒前
清新的Q完成签到,获得积分10
2秒前
2秒前
高高高完成签到,获得积分10
3秒前
3秒前
3秒前
3秒前
4秒前
xiaochuan完成签到,获得积分10
4秒前
尊敬的扬发布了新的文献求助10
4秒前
文静的翠安完成签到,获得积分10
4秒前
猫猫发布了新的文献求助10
4秒前
UU完成签到,获得积分10
4秒前
善良身影发布了新的文献求助10
4秒前
5秒前
DEREK发布了新的文献求助10
5秒前
xmz完成签到,获得积分10
5秒前
李太白云游四海完成签到,获得积分10
5秒前
Zgrey完成签到,获得积分10
5秒前
烂漫的汲完成签到,获得积分10
6秒前
jingyi完成签到,获得积分10
6秒前
石石刘发布了新的文献求助10
6秒前
yang完成签到,获得积分10
6秒前
zhaofw完成签到,获得积分10
7秒前
甜酒发布了新的文献求助10
7秒前
7秒前
wyl发布了新的文献求助10
7秒前
传奇3应助ty采纳,获得10
7秒前
7秒前
willow完成签到,获得积分10
7秒前
8秒前
9秒前
9秒前
10秒前
行走的鱼完成签到,获得积分10
10秒前
Sugar完成签到,获得积分10
10秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968934
求助须知:如何正确求助?哪些是违规求助? 3513835
关于积分的说明 11170238
捐赠科研通 3249167
什么是DOI,文献DOI怎么找? 1794650
邀请新用户注册赠送积分活动 875278
科研通“疑难数据库(出版商)”最低求助积分说明 804755