Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images

Objective To compare the application value of the binary classification model based on dermoscopic images of convolutional neural network (CNN) in the diagnosis of mycosis fungoides (MF) and inflammatory dermatosis. Methods Patients diagnosed with early MF or inflammatory dermatosis with similar...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	LIU Zhaorui, ZHANG Yilan, XIE Fengying, LIU Jie
Formato:	article
Lenguaje:	ZH
Publicado:	Editorial Office of Medical Journal of Peking Union Medical College Hospital 2021
Materias:	early mycosis fungoides inflammatory dermatosis dermoscopic image convolutional neural network Medicine R
Acceso en línea:	https://doaj.org/article/23505d9bb90f48a5ac459de601803368
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:23505d9bb90f48a5ac459de601803368
record_format	dspace
spelling	oai:doaj.org-article:23505d9bb90f48a5ac459de6018033682021-12-01T01:43:05ZEarly Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images1674-908110.12290/xhyxzz.2021-0496https://doaj.org/article/23505d9bb90f48a5ac459de6018033682021-10-01T00:00:00Zhttps://xhyxzz.pumch.cn/en/article/doi/10.12290/xhyxzz.2021-0496https://doaj.org/toc/1674-9081Objective To compare the application value of the binary classification model based on dermoscopic images of convolutional neural network (CNN) in the diagnosis of mycosis fungoides (MF) and inflammatory dermatosis. Methods Patients diagnosed with early MF or inflammatory dermatosis with similar clinical manifestations in the dermatology clinic of Peking Union Medical College Hospital from January 2016 to December 2020 were retrospectively included. The patients were divided into the training set and the test set at a ratio of 4∶1. Six classical network structures were trained by using the dermoscopic images of patients in the training set, and the CNN binary classification model was constructed by using transfer learning. At the same time, in the test set, 1 image of each patient that was randomly selected, together with clinical images of the skin lesions, was interpreted by 13 dermatologists. Compare the CNN binary classification model with dermatologists in the differential diagnosis of early MF and inflammatory dermatosis in the test set. The results were expressed in terms of area under the curve (AUC), sensitivity, specificity, Kappa coefficient, etc., and receiver operating characteristic (ROC) curve was used for visual analysis. Results A total of 48 patients with early MF (402 dermoscopic images) and 96 patients with inflammatory dermatosis (557 dermoscopic images) were included. Among them, there were 117 cases in the training set (772 dermoscopic images), and 27 cases in the test set (187 dermoscopic images). In the test set, the sensitivity and specificity of dermatologists in the differential diagnosis of early MF and inflammatory dermatosis were 70.19% (95% CI: 59.68%-80.70%) and 94.74% (95% CI: 91.77%-97.71%) respectively, and the Kappa coefficient is 0.677(95% CI: 0.566-0.789). When classified by the single image, the AUC of the CNN binary classification model for the differential diagnosis of early MF and inflammatory dermatosis was 0.87 (95% CI: 0.84-0.89); the sensitivity and specificity were 75.02% (95% CI: 70.19%-79.85%) and 82.02% (95% CI: 79.30%-84.87%), respectively; the Kappa coefficient was 0.563(95% CI: 0.507-0.620). When classified by cases, the AUC of the CNN binary classification model for the differential diagnosis of early MF and inflammatory dermatosis was 0.97 (95% CI: 0.95-0.99); the sensitivity and specificity were 87.50% (95% CI: 78.55%-96.45%) and 93.85% (95% CI: 88.93%-98.77%), respectively; the Kappa coefficient was 0.920(95% CI: 0.884-0.954). The ROC curve showed that the AUC of the CNN binary classification model with EfficientNet-B0 for diagnosing MF was 0.99 when classified by cases, the sensitivity and specifity were 88.9% and 100%, and the corresponding point of the average diagnostic sensitivity and specificity of 13 dermatologists were at the lower right of the curve. Conclusions The CNN binary classification model based on the intelligent analysis of dermoscopic images can accurately classify early MF and inflammatory dermatosis, and its ability of differential diagnosis is better than the average level of dermatologists.LIU ZhaoruiZHANG YilanXIE FengyingLIU JieEditorial Office of Medical Journal of Peking Union Medical College Hospitalarticleearly mycosis fungoidesinflammatory dermatosisdermoscopic imageconvolutional neural networkMedicineRZHXiehe Yixue Zazhi, Vol 12, Iss 5, Pp 689-697 (2021)
institution	DOAJ
collection	DOAJ
language	ZH
topic	early mycosis fungoides inflammatory dermatosis dermoscopic image convolutional neural network Medicine R
spellingShingle	early mycosis fungoides inflammatory dermatosis dermoscopic image convolutional neural network Medicine R LIU Zhaorui ZHANG Yilan XIE Fengying LIU Jie Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images
description	Objective To compare the application value of the binary classification model based on dermoscopic images of convolutional neural network (CNN) in the diagnosis of mycosis fungoides (MF) and inflammatory dermatosis. Methods Patients diagnosed with early MF or inflammatory dermatosis with similar clinical manifestations in the dermatology clinic of Peking Union Medical College Hospital from January 2016 to December 2020 were retrospectively included. The patients were divided into the training set and the test set at a ratio of 4∶1. Six classical network structures were trained by using the dermoscopic images of patients in the training set, and the CNN binary classification model was constructed by using transfer learning. At the same time, in the test set, 1 image of each patient that was randomly selected, together with clinical images of the skin lesions, was interpreted by 13 dermatologists. Compare the CNN binary classification model with dermatologists in the differential diagnosis of early MF and inflammatory dermatosis in the test set. The results were expressed in terms of area under the curve (AUC), sensitivity, specificity, Kappa coefficient, etc., and receiver operating characteristic (ROC) curve was used for visual analysis. Results A total of 48 patients with early MF (402 dermoscopic images) and 96 patients with inflammatory dermatosis (557 dermoscopic images) were included. Among them, there were 117 cases in the training set (772 dermoscopic images), and 27 cases in the test set (187 dermoscopic images). In the test set, the sensitivity and specificity of dermatologists in the differential diagnosis of early MF and inflammatory dermatosis were 70.19% (95% CI: 59.68%-80.70%) and 94.74% (95% CI: 91.77%-97.71%) respectively, and the Kappa coefficient is 0.677(95% CI: 0.566-0.789). When classified by the single image, the AUC of the CNN binary classification model for the differential diagnosis of early MF and inflammatory dermatosis was 0.87 (95% CI: 0.84-0.89); the sensitivity and specificity were 75.02% (95% CI: 70.19%-79.85%) and 82.02% (95% CI: 79.30%-84.87%), respectively; the Kappa coefficient was 0.563(95% CI: 0.507-0.620). When classified by cases, the AUC of the CNN binary classification model for the differential diagnosis of early MF and inflammatory dermatosis was 0.97 (95% CI: 0.95-0.99); the sensitivity and specificity were 87.50% (95% CI: 78.55%-96.45%) and 93.85% (95% CI: 88.93%-98.77%), respectively; the Kappa coefficient was 0.920(95% CI: 0.884-0.954). The ROC curve showed that the AUC of the CNN binary classification model with EfficientNet-B0 for diagnosing MF was 0.99 when classified by cases, the sensitivity and specifity were 88.9% and 100%, and the corresponding point of the average diagnostic sensitivity and specificity of 13 dermatologists were at the lower right of the curve. Conclusions The CNN binary classification model based on the intelligent analysis of dermoscopic images can accurately classify early MF and inflammatory dermatosis, and its ability of differential diagnosis is better than the average level of dermatologists.
format	article
author	LIU Zhaorui ZHANG Yilan XIE Fengying LIU Jie
author_facet	LIU Zhaorui ZHANG Yilan XIE Fengying LIU Jie
author_sort	LIU Zhaorui
title	Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images
title_short	Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images
title_full	Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images
title_fullStr	Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images
title_full_unstemmed	Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images
title_sort	early diagnosis model of mycosis fungoides based on intelligent analysis of dermoscopic images
publisher	Editorial Office of Medical Journal of Peking Union Medical College Hospital
publishDate	2021
url	https://doaj.org/article/23505d9bb90f48a5ac459de601803368
work_keys_str_mv	AT liuzhaorui earlydiagnosismodelofmycosisfungoidesbasedonintelligentanalysisofdermoscopicimages AT zhangyilan earlydiagnosismodelofmycosisfungoidesbasedonintelligentanalysisofdermoscopicimages AT xiefengying earlydiagnosismodelofmycosisfungoidesbasedonintelligentanalysisofdermoscopicimages AT liujie earlydiagnosismodelofmycosisfungoidesbasedonintelligentanalysisofdermoscopicimages
_version_	1718405947996504064

Early Diagnosis Model of Mycosis Fungoides Based on Intelligent Analysis of Dermoscopic Images

Ejemplares similares