Department of Laser and Biotechnical Systems, Samara University, 34 Moskovskoe Shosse, Samara, 443086, Russian Federation.
Department of Laser and Biotechnical Systems, Samara University, 34 Moskovskoe Shosse, Samara, 443086, Russian Federation.
Comput Methods Programs Biomed. 2022 Jun;219:106755. doi: 10.1016/j.cmpb.2022.106755. Epub 2022 Mar 21.
Skin cancer is the most common malignancy in whites accounting for about one third of all cancers diagnosed per year. Portable Raman spectroscopy setups for skin cancer "optical biopsy" are utilized to detect tumors based on their spectral features caused by the comparative presence of different chemical components. However, low signal-to-noise ratio in such systems may prevent accurate tumors classification. Thus, there is a challenge to develop methods for efficient skin tumors classification.
We compare the performance of convolutional neural networks and the projection on latent structures with discriminant analysis for discriminating skin cancer using the analysis of Raman spectra with a high autofluorescence background stimulated by a 785 nm laser. We have registered the spectra of 617 cases of skin neoplasms (615 patients, 70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) in vivo with a portable Raman setup and created classification models both for convolutional neural networks and projection on latent structures approaches. To check the classification models stability, a 10-fold cross-validation was performed for all created models. To avoid models overfitting, the data was divided into a training set (80% of spectral dataset) and a test set (20% of spectral dataset).
The results for different classification tasks demonstrate that the convolutional neural networks significantly (p<0.01) outperforms the projection on latent structures. For the convolutional neural networks implementation we obtained ROC AUCs of 0.96 (0.94 - 0.97; 95% CI), 0.90 (0.85-0.94; 95% CI), and 0.92 (0.87 - 0.97; 95% CI) for classifying a) malignant vs benign tumors, b) melanomas vs pigmented tumors and c) melanomas vs seborrheic keratosis respectively.
The performance of the convolutional neural networks classification of skin tumors based on Raman spectra analysis is higher or comparable to the accuracy provided by trained dermatologists. The increased accuracy with the convolutional neural networks implementation is due to a more precise accounting of low intensity Raman bands in the intense autofluorescence background. The achieved high performance of skin tumors classifications with convolutional neural networks analysis opens a possibility for wide implementation of Raman setups in clinical setting.
皮肤癌是白人中最常见的恶性肿瘤，占每年诊断出的所有癌症的三分之一左右。便携式拉曼光谱仪用于皮肤癌的“光学活检”，根据肿瘤光谱特征进行检测，这些特征是由不同化学成分的相对存在引起的。然而，此类系统中的信噪比低可能会妨碍准确的肿瘤分类。因此，开发有效的皮肤肿瘤分类方法具有挑战性。
我们比较了卷积神经网络和潜在结构投影与判别分析在使用 785nm 激光刺激的高自发荧光背景下分析拉曼光谱时区分皮肤癌的性能。我们使用便携式拉曼装置注册了 617 例皮肤肿瘤（615 例患者，70 例黑素瘤，122 例基底细胞癌，12 例鳞状细胞癌和 413 例良性肿瘤）的光谱，并为卷积神经网络和潜在结构投影方法创建了分类模型。为了检查分类模型的稳定性，对所有创建的模型都进行了 10 折交叉验证。为了避免模型过拟合，将数据分为训练集（光谱数据集的 80%）和测试集（光谱数据集的 20%）。
不同分类任务的结果表明，卷积神经网络的性能明显优于潜在结构投影（p<0.01）。对于卷积神经网络的实现，我们获得了恶性与良性肿瘤分类的 ROC AUC 为 0.96（0.94-0.97；95%CI）、黑素瘤与色素性肿瘤分类的 ROC AUC 为 0.90（0.85-0.94；95%CI）和黑素瘤与脂溢性角化病分类的 ROC AUC 为 0.92（0.87-0.97；95%CI）。
基于拉曼光谱分析的卷积神经网络对皮肤肿瘤的分类性能高于或可与训练有素的皮肤科医生的准确性相媲美。卷积神经网络实现的准确性提高是由于在强烈的自发荧光背景下更精确地考虑了低强度拉曼带。卷积神经网络分析实现的皮肤肿瘤分类的高性能为在临床环境中广泛实施拉曼装置提供了可能性。
