Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis.

BACKGROUND: Application of deep-learning technology to skin cancer classification can potentially improve the sensitivity and specificity of skin cancer screening, but the number of training images required for such a system is thought to be extremely large. OBJECTIVES: To determine whether deep-learning technology could be used to develop an efficient skin cancer classification system with a relatively small dataset of clinical images. METHODS: A deep convolutional neural network (DCNN) was trained using a dataset of 4867 clinical images obtained from 1842 patients diagnosed with skin tumours at the University of Tsukuba Hospital from 2003 to 2016. The images consisted of 14 diagnoses, including both malignant and benign conditions. Its performance was tested against 13 board-certified dermatologists and nine dermatology trainees. RESULTS: The overall classification accuracy of the trained DCNN was 76·5%. The DCNN achieved 96·3% sensitivity (correctly classified malignant as malignant) and 89·5% specificity (correctly classified benign as benign). Although the accuracy of malignant or benign classification by the board-certified dermatologists was statistically higher than that of the dermatology trainees (85·3% ± 3·7% and 74·4% ± 6·8%, P < 0·01), the DCNN achieved even greater accuracy, as high as 92·4% ± 2·1% (P < 0·001). CONCLUSIONS: We have developed an efficient skin tumour classifier using a DCNN trained on a relatively small dataset. The DCNN classified images of skin tumours more accurately than board-certified dermatologists. Collectively, the current system may have capabilities for screening purposes in general medical practice, particularly because it requires only a single clinical image for classification.

Increased halogenated tyrosine levels are useful markers of human skin ageing, reflecting proteins denatured by past skin inflammation.

BACKGROUND: Photoageing of skin is thought to be caused by protein denaturation, which can be induced by ultraviolet radiation. Previous studies have also reported that inflammation is related to protein denaturation; however, the influence of inflammation on skin ageing has not been explored in detail. AIM: To investigate the possible connection between inflammation and protein denaturation, which might lead to skin ageing, we focused on halogenated tyrosine as a denatured substance produced during the inflammation process. METHODS: We measured halogenated tyrosine in aged human skin. Inflammatory cells and halogenated tyrosine were detected by immunohistochemistry using antibodies to mast-cell tryptase, neutrophilic myeloperoxidase and halogenated tyrosine. Finally, using elastic van Gieson (EVG) staining, we investigated whether the sites of halogenated tyrosine coincided with the sites at which proteins were denatured. RESULTS: Immunohistochemical analysis indicated that both inflammatory cells and halogenated tyrosines increased with ageing in both photoexposed and photoprotected skin. EVG staining confirmed that the localization of halogenated tyrosine was close to the sites at which protein was denatured. CONCLUSIONS: Our investigations indicate a possible connection between skin ageing and inflammation, suggesting that halogenated tyrosine could be a useful marker of ageing skin.