Assistant Diagnosis of Basal Cell Carcinoma and Seborrheic Keratosis in Chinese Population Using Convolutional Neural Network

Huang, Kai; He, Xiaoyu; Jin, Z.; Wu, Lisha; Zhao, Xinyu; Wu, Zhe; Wang, Xian; Xie, Yang; Wan, Miaojian; Li, Fangfang; Liu, Dihui; Yu, Nianzhou; Li, Mingjia; Su, Juan; Chen, Xiang

doi:10.1155/2020/1713904

Cited by 7 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A previous study reported an artificial intelligence-assisted decision making system for skin tumors with a recognition rate of 91.2% for [17]. Additionally, in rosacea, psoriasis, eczema, and atopic dermatitis, deep learning has been proven to have excellent diagnostic or classification capabilities [18][19][20][21].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

An Intelligent Diagnostic Model for Melasma Based on Deep Learning and Multimode Image Input

Liu

Chen

Xue

et al. 2022

Dermatol Ther (Heidelb)

View full text Add to dashboard Cite

Introduction:The diagnosis of melasma is often based on the naked-eye judgment of physicians. However, this is a challenge for inexperienced physicians and non-professionals, and incorrect treatment might have serious consequences. Therefore, it is important to develop an accurate method for melasma diagnosis. The objective of this study is to develop and validate an intelligent diagnostic system based on deep learning for melasma images. Methods: A total of 8010 images in the VISIA system, comprising 4005 images of patients with melasma and 4005 images of patients without melasma, were collected for training and testing. Inspired by four high-performance structures (i.e., DenseNet, ResNet, Swin Transformer, and MobileNet), the performances of deep learning models in melasma and nonmelasma binary classifiers were evaluated. Furthermore, considering that there were five modes of images for each shot in VISIA, we fused these modes via multichannel image input in different combinations to explore whether multimode images could improve network performance. Results: The proposed network based on Den-seNet121 achieved the best performance with an accuracy of 93.68% and an area under the curve (AUC) of 97.86% on the test set for the melasma classifier. The results of the Gradientweighted Class Activation Mapping showed that it was interpretable. In further experiments, for the five modes of the VISIA system,

show abstract

Section: Discussionmentioning

confidence: 99%

“…used a convolutional neural network to grade the severity of facial images of patients with acne, and obtained the best classification accuracy of 67% [ 17 ]. Additionally, in rosacea, psoriasis, eczema, and atopic dermatitis, deep learning has been proven to have excellent diagnostic or classification capabilities [ 18 – 21 ].…”

Section: Discussionmentioning

confidence: 99%

An Intelligent Diagnostic Model for Melasma Based on Deep Learning and Multimode Image Input

Liu

Chen

Xue

et al. 2022

Dermatol Ther (Heidelb)

View full text Add to dashboard Cite

show abstract

“…In the field of skin oncology, we have studied less. According to other studies, there has been the first dataset of skin tumors of BCC and SK races in China [ 28 ]. In the following research, we will continue to make progress and update our analytical conclusions.…”

Section: Discussionmentioning

confidence: 99%

Basic Pan-Cancer Analysis of the Carcinogenic Effects of Cyclin-Dependent Kinase 4 (CDK4) in Human Surface Tumors

Deng

Huang

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Although the evidence based on current human, animal, or molecular biology can explain some of the relationships between CDK4 and cancer, there is no pan-cancer analysis of the gene CDK4 in human skin tumors. Therefore, the potential carcinogenic effects of CDK4 in 33 tumors were initially explored in the datasets of the GEO (Gene Expression Omnibus) and the CGA (Cancer Genome Atlas). We found that CDK4 was highly expressed in most cancers and that CDK4 performance levels significantly correlated with the prognosis of cancer patients. These were found in our preliminary exploration. In addition, we used the dataset in tumors such as cutaneous melanoma or lung adenocarcinoma and found increased levels of phosphorylation of r24 l/C/h/s. In addition, fibroblast infiltration associated with CDK4 cancer was observed in head and neck, sarcoma, and melanoma skin. Using this pan-cancer study, our group has provided a comprehensive preliminary demonstration of the oncogenic effects of the CDK4 gene on different human skin tumors.

show abstract

“…All 22 studies were performed between 2002 and 2021 [23][24][25][26][27][28][29][30][31][32], with 11 (50%) studies published between 2020 and 2021 [33][34][35][36][37][38][39][40][41][42][43][44]. An overview of study characteristics is displayed in Table 2.…”

Section: Methodsmentioning

confidence: 99%

Artificial Intelligence for the Classification of Pigmented Skin Lesions in Populations with Skin of Color: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

Background While skin cancers are less prevalent in people with skin of color, they are more often diagnosed at later stages and have a poorer prognosis. The use of artificial intelligence (AI) models can potentially improve early detection of skin cancers, however the lack of skin color diversity in training datasets may only widen the pre-existing racial discrepancies in dermatology. Objective To systematically review the technique, quality, accuracy, and implications of studies using AI models trained or tested in populations with skin of color, for classification of pigmented skin lesions. Methods PubMed was used to identify any studies describing AI models for classification of pigmented skin lesions. Only studies that used training datasets with at least 10% of images from people with skin of color were eligible. Outcomes on study population, design of AI model, accuracy, and quality of the studies were reviewed. Results Twenty-two eligible articles were identified. Majority of studies were trained on datasets obtained from Chinese (7/22), Korean (5/22), and Japanese populations (3/22). Seven studies used diverse datasets containing Fitzpatrick skin type I-III in combination with at least 10% from Black American, Native American, Pacific Islander or Fitzpatrick IV-VI. AI models producing binary outcomes (e.g., benign vs malignant) reported an accuracy ranging from 70% to 99.7%. Accuracy of AI models reporting multiclass outcomes (e.g., specific lesion diagnosis) was lower, ranging from 43% to 93%. Reader studies, where dermatologists’ classification is compared with AI model outcomes, reported similar accuracy in one study, higher AI accuracy in three studies, and higher clinician accuracy in two studies. A quality review revealed that dataset description and variety, benchmarking, public evaluation, and healthcare application were frequently not addressed. Conclusions While this review provides promising evidence of accurate AI models in skin of color populations, there are still large discrepancies remain in the number of AI models developed in populations with skin of color (particularly Fitzpatrick type IV-VI) and those with largely European ancestry. A lack of publicly available datasets from diverse populations is likely a contributing factor, as is the inadequate reporting of patient-level metadata relating to skin color in training datasets.

show abstract