Hyperspectral Imaging for Benign and Malignant Diagnosis of Breast Tumors.

Journal of biophotonics Pub Date : 2025-06-24 DOI:10.1002/jbio.202500188

Yihui He, Yihan Zhao, Jia Xu, Dongsheng Zhou, Weichen Shi, Yulong Wang, Yunchao Wang, Xulei Wang, Mengqiu Zhang, Ning Kang, Jianning Wang

引用次数: 0

Abstract

Objective: To assess the feasibility of combining microscopic hyperspectral imaging (370-1100 nm) with a lightweight 1D-CNN for rapid, label-free discrimination of benign and malignant breast tumors.

Methods: Breast specimens (43 malignant, 39 benign) were imaged; 2 050 000 pixel spectra were preprocessed (dark-current subtraction, white-reference calibration, Savitzky-Golay smoothing, z-score normalization) and input to a custom 1D-CNN. Performance was benchmarked against SVM, AlexNet, and LSTM using accuracy, sensitivity, specificity.

Results: The 1D-CNN achieved 90.43% accuracy, 89.10% sensitivity, 91.34% specificity, exceeding baseline models.

Conclusions: Combining HSI with 1D CNN enables rapid and highly accurate classification of breast tumors, providing a new approach to rapid pathological diagnosis.

查看原文本刊更多论文

高光谱成像在乳腺肿瘤良恶性诊断中的应用。

目的：探讨显微高光谱成像（370 ~ 1100nm）与轻型1D-CNN相结合快速、无标记区分乳腺良恶性肿瘤的可行性。方法：对乳腺标本（恶性43例，良性39例）进行影像学检查；对205万像素光谱进行预处理（暗电流减去、白基准校准、Savitzky-Golay平滑、z-score归一化），并输入到自定义1D-CNN中。使用准确性，灵敏度，特异性对SVM， AlexNet和LSTM进行性能基准测试。结果：1D-CNN准确率为90.43%，灵敏度为89.10%，特异性为91.34%，优于基线模型。结论：HSI联合1D CNN对乳腺肿瘤进行快速、高精度的分类，为快速病理诊断提供了新途径。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of biophotonics

自引率

0.00%

发文量