Vasanthakumari Priyanka, Romano Renan A, Rosa Ramon G T, Salvio Ana G, Yakovlev Vladislav, Kurachi Cristina, Hirshburg Jason M, Jo Javier A
Texas A&M University, Department of Biomedical Engineering, College Station, TX, USA.
University of São Paulo, São Carlos Institute of Physics, São Paulo, Brazil.
Biomed Opt Express. 2024 Jul 9;15(8):4557-4583. doi: 10.1364/BOE.523831. eCollection 2024 Aug 1.
There is no clinical tool available to primary care physicians or dermatologists that could provide objective identification of suspicious skin cancer lesions. Multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy enables label-free biochemical and metabolic imaging of skin lesions. This study investigated the use of pixel-level maFLIM dermoscopy features for objective discrimination of malignant from visually similar benign pigmented skin lesions. Clinical maFLIM dermoscopy images were acquired from 60 pigmented skin lesions before undergoing a biopsy examination. Random forest and deep neural networks classification models were explored, as they do not require explicit feature selection. Feature pools with either spectral intensity or bi-exponential maFLIM features, and a combined feature pool, were independently evaluated with each classification model. A rigorous cross-validation strategy tailored for small-size datasets was adopted to estimate classification performance. Time-resolved bi-exponential autofluorescence features were found to be critical for accurate detection of malignant pigmented skin lesions. The deep neural network model produced the best lesion-level classification, with sensitivity and specificity of 76.84%±12.49% and 78.29%±5.50%, respectively, while the random forest classifier produced sensitivity and specificity of 74.73%±14.66% and 76.83%±9.58%, respectively. Results from this study indicate that machine-learning driven maFLIM dermoscopy has the potential to assist doctors with identifying patients in real need of biopsy examination, thus facilitating early detection while reducing the rate of unnecessary biopsies.
对于初级保健医生或皮肤科医生而言，目前尚无临床工具可用于客观识别可疑的皮肤癌病变。多光谱自体荧光寿命成像（maFLIM）皮肤镜检查能够对皮肤病变进行无标记的生化和代谢成像。本研究调查了像素级maFLIM皮肤镜检查特征在客观区分视觉上相似的良性色素沉着性皮肤病变与恶性病变方面的应用。在进行活检检查之前，从60个色素沉着性皮肤病变获取了临床maFLIM皮肤镜检查图像。研究探索了随机森林和深度神经网络分类模型，因为它们不需要进行明确的特征选择。分别使用每个分类模型独立评估具有光谱强度或双指数maFLIM特征的特征库以及一个组合特征库。采用了针对小尺寸数据集量身定制的严格交叉验证策略来估计分类性能。发现时间分辨双指数自体荧光特征对于准确检测恶性色素沉着性皮肤病变至关重要。深度神经网络模型产生了最佳的病变级分类，敏感性和特异性分别为76.84%±12.49%和78.29%±5.50%，而随机森林分类器的敏感性和特异性分别为74.73%±14.66%和76.83%±9.58%。本研究结果表明，机器学习驱动的maFLIM皮肤镜检查有潜力协助医生识别真正需要活检检查的患者，从而促进早期检测，同时降低不必要活检的比率。
