Interpretable Wavelet-CNN for Accurate Serum Raman Lung Cancer Diagnosis under Leakage-Safe, Patient-Level Splits

可解释性 模式识别(心理学) 人工智能 特征(语言学) 化学 拉曼光谱 卷积神经网络 小波 肺癌 主成分分析 噪音(视频) 平滑的 鉴定(生物学) 癌症 光学(聚焦) 拉曼散射 人工神经网络 交叉验证 生物系统 队列
作者
Jinglei Zhang,Bo Dai,Hong Wang,Dong Han,Chenmei Li,Yong Zhou,Weishu Gao,Yusong Peng,Lingyun Gu,Shuming Nie,Yiqing Wang,Christopher J. Butch
出处
期刊:Analytical Chemistry [American Chemical Society]
卷期号:98 (17): 12292-12304 被引量:2
标识
DOI:10.1021/acs.analchem.5c06703
摘要

Clinical cancer diagnostics require ML that maintains accuracy under biological variability with interpretable feature attribution─a particular challenge for serum-based approaches where healthy and diseased samples share >95% chemical composition. Continuous wavelet transformation (CWT) combined with convolutional neural networks (CNN) has demonstrated robust classification of Raman spectra for materials under synthetic noise conditions, but whether this approach can handle biological variability in clinical samples, and which spectral features drive its predictions, has not been explored. Here, we demonstrate application of CWT-CNN deep learning to clinical disease diagnosis, analyzing spontaneous Raman spectra from a retrospective cohort of 213 patient serum samples (106 lung cancer, 107 controls) collected over 3 years. We extend the established CWT-CNN framework with interpretability analysis using Gradient-weighted Class Activation Mapping (Grad-CAM) and inverse-CWT reconstruction. Using only 5 μL of serum and 10 min of acquisition time per patient, our approach achieved 90.5% accuracy in an independent validation cohort (19/21 correct diagnoses, 91.7% sensitivity, 88.9% specificity) using strict patient-wise data splitting. Interpretability analysis revealed that classification decisions focus on Raman shifts at 1004 cm –1 (phenylalanine), 1129 cm –1 (lipid trans-conformation), 1458 cm –1 (nucleotides), and 1560 cm –1 (tryptophan). These spectral features correspond to molecules with established roles in cancer metabolism. This demonstration that CWT-CNN maintains high accuracy under biological variability and leakage-safe, patient-level validation, combined with biochemically meaningful feature attribution, establishes a data-first approach where comprehensive spectral analysis enables both diagnostic accuracy and identification of disease-relevant molecular features.
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
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
刚刚
OK的应助被科研通管家采纳,获得100
刚刚
英俊的铭的应助被科研通管家采纳,获得10
刚刚
完美世界的应助被科研通管家采纳,获得10
刚刚
null的应助被科研通管家采纳,获得10
1秒前
情怀的应助被科研通管家采纳,获得10
1秒前
华仔的应助被科研通管家采纳,获得10
1秒前
SciGPT的应助被科研通管家采纳,获得10
1秒前
所所的应助被科研通管家采纳,获得10
1秒前
1秒前
共享精神的应助被科研通管家采纳,获得10
1秒前
华仔的应助被科研通管家采纳,获得10
1秒前
小豆糕发布了新的文献求助10
1秒前
赘婿的应助被科研通管家采纳,获得10
1秒前
今后的应助被科研通管家采纳,获得10
2秒前
李健的应助被科研通管家采纳,获得10
2秒前
灵兰完成签到,获得积分10
2秒前
桐桐的应助被科研通管家采纳,获得10
2秒前
2秒前
2秒前
null的应助被科研通管家采纳,获得10
2秒前
2秒前
3秒前
思源的应助被科研通管家采纳,获得10
3秒前
研友_VZG7GZ的应助被科研通管家采纳,获得10
3秒前
3秒前
852的应助被科研通管家采纳,获得10
3秒前
清秀送终发布了新的文献求助30
3秒前
彭于晏的应助被科研通管家采纳,获得10
3秒前
123完成签到,获得积分10
3秒前
3秒前
3秒前
星辰大海的应助被科研通管家采纳,获得10
3秒前
秋风的应助被科研通管家采纳,获得10
3秒前
4秒前
没素质的香菜完成签到 ,获得积分10
4秒前
脑洞疼的应助被科研通管家采纳,获得10
4秒前
Orange的应助被科研通管家采纳,获得10
4秒前
Litty完成签到,获得积分10
4秒前
大个的应助被科研通管家采纳,获得10
4秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183792
求助须知:如何正确求助?哪些是违规求助? 9573020
关于积分的说明 21828776
捐赠科研通 7780959
什么是DOI,文献DOI怎么找? 3434116
关于科研通互助平台的介绍 2558301
邀请新用户注册赠送积分活动 2480611