Diagnostic Performance of Deep Learning Algorithms Applied to Three Common Diagnoses in Dermatopathology

Abstract

Background:Artificial intelligence is advancing at an accelerated pace into clinical applications, providing opportunities for increased efficiency, improved accuracy, and cost savings through computer-aided diagnostics. Dermatopathology, with emphasis on pattern recognition, offers a unique opportunity for testing deep learning algorithms.Aims:This study aims to determine the accuracy of deep learning algorithms to diagnose three common dermatopathology diagnoses.Methods:Whole slide images (WSI) of previously diagnosed nodular basal cell carcinomas (BCCs), dermal nevi, and seborrheic keratoses were annotated for areas of distinct morphology. Unannotated WSIs, consisting of five distractor diagnoses of common neoplastic and inflammatory diagnoses, were included in each training set. A proprietary fully convolutional neural network was developed to train algorithms to classify test images as positive or negative relative to ground truth diagnosis.Results:Artificial intelligence system accurately classified 123/124 (99.45%) BCCs (nodular), 113/114 (99.4%) dermal nevi, and 123/123 (100%) seborrheic keratoses.Conclusions:Artificial intelligence using deep learning algorithms is a potential adjunct to diagnosis and may result in improved workflow efficiencies for dermatopathologists and laboratories.

Osteoid Metaplasia in Femoral Artery Plaques Is Associated With the Clinical Severity of Lower Extremity Artery Disease in Men

“…The use of digital microscopy is becoming increasingly frequent in the field of medicine, especially pathology, and it enables the use of machine learning algorithms in the analysis of tissue samples. Previously, DL-based AI algorithms have been successfully used to analyze samples of tumor and dermatological tissues ( 6 , 26 ). The analysis conducted with the help of the DL algorithms can achieve similar levels of accuracy as those achieved through visual assessments performed by pathologists ( 6 , 27 ).…”

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

“…For example, Arevalo et al described a system that analyzes histopathological images and can classify basal cell carcinoma with 98.1% accuracy (67). Olsen et al described a system that diagnosed dermal nevi and seborrheic keratosis with high accuracies and may serve as a future method to increase the efficiency of analyzing these prevalent benign tumors (72). Algorithms have also been described that can identify predictive genes and biomarkers for diseases (73)(74)(75)(76)(77)(78)(79)(80)(81)(82)(83).…”

Semi-Supervised Nests of Melanocytes Segmentation Method Using Convolutional Autoencoders

“…There are only a few works in the literature which cover automatic processing of histopathological whole slide images of skin specimens stained with hematoxylin and eosin (H&E), the standard stain in histopathology. Some notable examples include an automated algorithm for the diagnostics of melanocytic tumors by Xu et al [40] (based on the melanocyte detection technique described in [41] and the epidermis segmentation approach described in [42]), a method capable of differentiating squamous cell carcinoma in situ from actinic keratosis by Noroozi and Zakerolhosseini [43] and a method for classifying histopathological skin images of three common skin lesions: basal cell carcinomas, dermal nevi, and seborrheic keratoses by Olsen et al [44]. The first two methods are based on classic algorithms for image processing and machine learning, whereas the last one uses deep neural networks.…”