Dermal epidermal junction detection for full-field optical coherence tomography data of human skin by deep learning
Journal
Computerized Medical Imaging and Graphics
Journal Volume
87
Date Issued
2021
Author(s)
Abstract
Full-field optical coherence tomography (FF-OCT) has been developed to obtain three-dimensional (3D) OCT data of human skin for early diagnosis of skin cancer. Detection of dermal epidermal junction (DEJ), where melanomas and basal cell carcinomas originate, is an essential step for skin cancer diagnosis. However, most existing DEJ detection methods consider each cross-sectional frame of the 3D OCT data independently, leaving the relationship between neighboring frames unexplored. In this paper, we exploit the continuity of 3D OCT data to enhance DEJ detection. In particular, we propose a method for noise reduction of the training data and a multi-directional convolutional neural network to predict the probability of epidermal pixels in the 3D OCT data, which is more stable than one-directional convolutional neural network for DEJ detection. Our crosscheck refinement method also exploits the domain knowledge to generate a smooth DEJ surface. The average mean error of the entire DEJ detection system is approximately 6 μm. ? 2020 Elsevier Ltd
Subjects
Convolution; Convolutional neural networks; Dermatology; Diagnosis; Diseases; Noise abatement; Optical tomography; Tomography; Basal cell carcinoma; Dermal-epidermal junctions; Detection methods; Detection system; Domain knowledge; Full-field optical coherence tomographies; Refinement methods; Threedimensional (3-d); Deep learning; article; convolutional neural network; deep learning; dermoepidermal junction; human; human experiment; noise reduction; optical coherence tomography; probability
SDGs
Other Subjects
Convolution; Convolutional neural networks; Dermatology; Diagnosis; Diseases; Noise abatement; Optical tomography; Tomography; Basal cell carcinoma; Dermal-epidermal junctions; Detection methods; Detection system; Domain knowledge; Full-field optical cohe
Type
journal article