Department of Biomedical Engineering, University of Basel, Allschwil, Switzerland.
Department of Dermatology, University Hospital of Basel, Basel, Switzerland.
J Eur Acad Dermatol Venereol. 2024 Dec;38(12):2280-2285. doi: 10.1111/jdv.20306. Epub 2024 Aug 28.
Vulvar lichen sclerosus (VLS) is a chronic inflammatory skin condition associated with significant impairment of quality of life and potential risk of malignant transformation. However, diagnosis of VLS is often delayed due to its variable clinical presentation and shame-related late consultation. Machine learning (ML)-trained image recognition software could potentially facilitate early diagnosis of VLS.
To develop a ML-trained image-based model for the detection of VLS.
Images of both VLS and non-VLS anogenital skin were collected, anonymized, and selected. In the VLS images, 10 typical skin signs (whitening, hyperkeratosis, purpura/ecchymosis, erosion/ulcers/excoriation, erythema, labial fusion, narrowing of the introitus, labia minora resorption, posterior commissure (fourchette) band formation and atrophic shiny skin) were manually labelled. A deep convolutional neural network was built using the training set as input data and then evaluated using the test set, where the developed algorithm was run three times and the results were then averaged.
A total of 684 VLS images and 403 non-VLS images (70% healthy vulva and 30% with other vulvar diseases) were included after the selection process. A deep learning algorithm was developed by training on 775 images (469 VLS and 306 non-VLS) and testing on 312 images (215 VLS and 97 non-VLS). This algorithm performed accurately in discriminating between VLS and non-VLS cases (including healthy individuals and non-VLS dermatoses), with mean values of 0.94, 0.99 and 0.95 for recall, precision and accuracy, respectively.
This pilot project demonstrated that our image-based deep learning model can effectively discriminate between VLS and non-VLS skin, representing a promising tool for future use by clinicians and possibly patients. However, prospective studies are needed to validate the applicability and accuracy of our model in a real-world setting.
外阴硬化性苔藓（VLS）是一种慢性炎症性皮肤病，与生活质量显著受损和潜在恶性转化风险相关。然而，由于其临床表现多变和因羞耻感而导致的延迟就诊，VLS 的诊断常常被延误。基于机器学习（ML）的图像识别软件有可能促进 VLS 的早期诊断。
开发一种基于 ML 训练的图像模型，用于检测 VLS。
收集并匿名选择 VLS 和非 VLS 肛门生殖器皮肤的图像。在 VLS 图像中，手动标记了 10 种典型的皮肤征象（变白、角化过度、瘀斑/瘀点、糜烂/溃疡/抓挠、红斑、阴唇融合、入口变窄、小阴唇吸收、后联合（叉）带形成和萎缩性光亮皮肤）。使用训练集作为输入数据构建深度卷积神经网络，然后使用测试集进行评估，其中开发的算法运行三次，然后取平均值。
经过选择过程，共纳入 684 张 VLS 图像和 403 张非 VLS 图像（70%为健康外阴，30%为其他外阴疾病）。通过对 775 张图像（469 张 VLS 和 306 张非 VLS）进行训练和对 312 张图像（215 张 VLS 和 97 张非 VLS）进行测试，开发了一种深度学习算法。该算法在区分 VLS 和非 VLS 病例（包括健康个体和非 VLS 皮肤病）方面表现出较高的准确性，召回率、精度和准确性的平均值分别为 0.94、0.99 和 0.95。
本初步研究表明，我们的基于图像的深度学习模型可以有效地将 VLS 与非 VLS 皮肤区分开来，代表了一种有前途的工具，可供临床医生和患者未来使用。然而，需要进一步的前瞻性研究来验证我们模型在实际环境中的适用性和准确性。
