Deep learning based histological classification of adnex tumors.

Cutaneous adnexal tumors are a diverse group of tumors arising from structures of the hair appendages. Although often benign, malignant entities occur which can metastasize and lead to patients´ death. Correct diagnosis is critical to ensure optimal treatment and best possible patient outcome. Artificial intelligence (AI) in the form of deep neural networks has recently shown enormous potential in the field of medicine including pathology, where we and others have found common cutaneous tumors can be detected with high sensitivity and specificity. To become a widely applied tool, AI approaches will also need to reliably detect and distinguish less common tumor entities including the diverse group of cutaneous adnexal tumors. To assess the potential of AI to recognize cutaneous adnexal tumors, we selected a diverse set of these entities from five German centers. The algorithm was trained with samples from four centers and then tested on slides from the fifth center. The neural network was able to differentiate 14 different cutaneous adnexal tumors and distinguish them from more common cutaneous tumors (i.e. basal cell carcinoma and seborrheic keratosis). The total accuracy on the test set for classifying 248 samples into these 16 diagnoses was 89.92 %. Our findings support AI can distinguish rare tumors, for morphologically distinct entities even with very limited case numbers (< 50) for training. This study further underlines the enormous potential of AI in pathology which could become a standard tool to aid pathologists in routine diagnostics in the foreseeable future. The final diagnostic responsibility will remain with the pathologist. ● Establishment of a algorithm for histological analysis in a multi-center study. ● The algorithm distinguishes the group of less common cutaneous adnexal tumors (CAT). ● The algorithm distinguishes 14 CAT from basal cell carcinoma and seborrheic keratosis. ● The total accuracy for classifying samples into these 16 diagnoses was 89.92 %. [ABSTRACT FROM AUTHOR]