IMAL‐Net: Interpretable multi‐task attention learning network for invasive lung adenocarcinoma screening in CT images

可解释性 计算机科学 卷积神经网络 人工智能 分割 模式识别(心理学) 深度学习 可视化 判别式 机器学习 特征(语言学) 特征选择 语言学 哲学
作者
Jun Wang,Yuan Cheng,Can Han,Yaofeng Wen,Hongbing Lu,Chen Liu,Yunlang She,Jiajun Deng,Biao Li,Dahong Qian,Chang Chen
出处
期刊:Medical Physics [Wiley]
卷期号:48 (12): 7913-7929 被引量:7
标识
DOI:10.1002/mp.15293
摘要

Feature maps created from deep convolutional neural networks (DCNNs) have been widely used for visual explanation of DCNN-based classification tasks. However, many clinical applications such as benign-malignant classification of lung nodules normally require quantitative and objective interpretability, rather than just visualization. In this paper, we propose a novel interpretable multi-task attention learning network named IMAL-Net for early invasive adenocarcinoma screening in chest computed tomography images, which takes advantage of segmentation prior to assist interpretable classification.Two sub-ResNets are firstly integrated together via a prior-attention mechanism for simultaneous nodule segmentation and invasiveness classification. Then, numerous radiomic features from the segmentation results are concatenated with high-level semantic features from the classification subnetwork by FC layers to achieve superior performance. Meanwhile, an end-to-end feature selection mechanism (named FSM) is designed to quantify crucial radiomic features greatly affecting the prediction of each sample, and thus it can provide clinically applicable interpretability to the prediction result.Nodule samples from a total of 1626 patients were collected from two grade-A hospitals for large-scale verification. Five-fold cross validation demonstrated that the proposed IMAL-Net can achieve an AUC score of 93.8% ± 1.1% and a recall score of 93.8% ± 2.8% for identification of invasive lung adenocarcinoma.It can be concluded that fusing semantic features and radiomic features can achieve obvious improvements in the invasiveness classification task. Moreover, by learning more fine-grained semantic features and highlighting the most important radiomics features, the proposed attention and FSM mechanisms not only can further improve the performance but also can be used for both visual explanations and objective analysis of the classification results.
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
星辰大海应助33采纳,获得10
1秒前
彭彭发布了新的文献求助10
3秒前
5秒前
老大蒂亚戈应助潇湘雪月采纳,获得10
6秒前
6秒前
8秒前
8秒前
kk完成签到,获得积分10
8秒前
9秒前
HOPE发布了新的文献求助10
9秒前
AAA完成签到,获得积分10
11秒前
Singularity应助讨厌科研采纳,获得10
11秒前
古月发布了新的文献求助10
12秒前
13秒前
33发布了新的文献求助10
13秒前
汉堡包应助于平川春野采纳,获得10
13秒前
星星发布了新的文献求助10
15秒前
16秒前
赘婿应助十九岁的时差采纳,获得10
16秒前
怠惰vs勤劳完成签到,获得积分10
17秒前
夏天应助青山采纳,获得100
18秒前
19秒前
乖猫要努力应助潇湘雪月采纳,获得10
20秒前
wdy111举报风之星求助涉嫌违规
20秒前
古月完成签到,获得积分10
21秒前
21秒前
22秒前
吴所谓发布了新的文献求助50
25秒前
英吉利25发布了新的文献求助10
26秒前
27秒前
酷波er应助南冥采纳,获得10
27秒前
李沐唅完成签到 ,获得积分10
31秒前
lv完成签到,获得积分10
31秒前
周婷完成签到 ,获得积分10
32秒前
shy完成签到,获得积分10
32秒前
34秒前
犹豫的忆枫完成签到,获得积分10
34秒前
35秒前
夕沫发布了新的文献求助50
35秒前
勤奋大地发布了新的文献求助10
36秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989390
求助须知:如何正确求助?哪些是违规求助? 3531487
关于积分的说明 11254109
捐赠科研通 3270153
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809174