Artificial Intelligence in Multiphoton Tomography: Atopic Dermatitis Diagnosis

Abstract

The diagnostic possibilities of multiphoton tomography (MPT) in dermatology have already been demonstrated. Nevertheless, the analysis of MPT data is still time-consuming and operator dependent. We propose a fully automatic approach based on convolutional neural networks (CNNs) to fully realize the potential of MPT. In total, 3,663 MPT images combining both morphological and metabolic information were acquired from atopic dermatitis (AD) patients and healthy volunteers. These were used to train and tune CNNs to detect the presence of living cells, and if so, to diagnose AD, independently of imaged layer or position. The proposed algorithm correctly diagnosed AD in 97.0 ± 0.2% of all images presenting living cells. The diagnosis was obtained with a sensitivity of 0.966 ± 0.003, specificity of 0.977 ± 0.003 and F-score of 0.964 ± 0.002. Relevance propagation by deep Taylor decomposition was used to enhance the algorithm's interpretability. Obtained heatmaps show what aspects of the images are important for a given classification. We showed that MPT imaging can be combined with artificial intelligence to successfully diagnose AD. The proposed approach serves as a framework for the automatic diagnosis of skin disorders using MPT.

Translation of two-photon microscopy to the clinic: multimodal multiphoton CARS tomography of in vivo human skin

“…For that case, we started to employ artificial intelligence/deep learning procedures. 39,40 We hope that multimodal MPT will provide a new insight into pathological effects on a molecular and subcellular scale in-vivo and may lead to a future noninvasive, rapid, and label-free diagnostic procedure.…”

Skin Barriers in Dermal Drug Delivery: Which Barriers Have to Be Overcome and How Can We Measure Them?

“…The development of the combined multiphoton/CARS microscope could be considered as an important step towards a clinical application of Raman spectroscopy [ 163 ]; yet, further quenching of background signals and automatized image analysis is required to grant a close implementation into routine examination in dermatology. Further progress in the development of user-friendly devices and automatized image acquisition and analysis will open a broader usage of Raman spectroscopy in (trans)dermal drug delivery research [ 164 ].…”

“…The combination of mentioned non-invasive spectroscopic and microscopic techniques such as CARS/Raman spectroscopy, MPM and associated techniques provide a huge potential for the investigation of the skin barrier and the related impact on dermal or even transdermal drug delivery. Sophisticated image analysis through artificial intelligence may open up the broad application of high-resolution skin microscopy in skin research and clinics [ 164 ].…”

Acompanhamento Domiciliar De Uma Família Refugiada Da Venezuela: Um Relato De Caso

“…potencial da IA na medicina clínica é amplo e foi impulsionado nos últimos anos pelo aumento da disponibilidade de grandes conjuntos de dados de saúde devido à digitalização dos registros de saúde, juntamente com o compartilhamento de dados de saúde. A IA para diagnóstico usando dados de imagem tem potencial em diversos campos, como diagnóstico No entanto, a análise dos dados do MPT ainda é demorada e depende do operador Guimarães et al, 2020,. propuseram uma abordagem totalmente automática baseada em redes neurais convolucionais (CNNs) para realizar plenamente o potencial do MPT.…”