Dataset Information

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

ABSTRACT: Objectives:To evaluate CNN models' performance of identifying the clinical images of basal cell carcinoma (BCC) and seborrheic keratosis (SK) and to compare their performance with that of dermatologists. Methods:We constructed a Chinese skin diseases dataset which includes 1456 BCC and 1843 SK clinical images and the corresponding medical history. We evaluated the performance using four mainstream CNN structures and transfer learning techniques. We explored the interpretability of the CNN model and compared its performance with that of 21 dermatologists. Results:The fine-tuned InceptionResNetV2 achieved the best performance, with an accuracy and area under the curve of 0.855 and 0.919, respectively. Further experimental results suggested that the CNN model was not only interpretable but also had a performance comparable to that of dermatologists. Conclusions:This study is the first on the assistant diagnosis of BCC and SK based on the proposed dataset. The promising results suggested that CNN model's performance was comparable to that of expert dermatologists.

SUBMITTER: Huang K

PROVIDER: S-EPMC7422221 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Huang Kai K He Xiaoyu X Jin Zhentao Z Wu Lisha L Zhao Xinyu X Wu Zhe Z Wu Xian X Xie Yang Y Wan Miaojian M Li Fangfang F Liu Dihui D Yu Nianzhou N Li Mingjia M Su Juan J Zhao Shuang S Chen Xiang X

Journal of healthcare engineering 20200801

<h4>Objectives</h4>To evaluate CNN models' performance of identifying the clinical images of basal cell carcinoma (BCC) and seborrheic keratosis (SK) and to compare their performance with that of dermatologists.<h4>Methods</h4>We constructed a Chinese skin diseases dataset which includes 1456 BCC and 1843 SK clinical images and the corresponding medical history. We evaluated the performance using four mainstream CNN structures and transfer learning techniques. We explored the interpretability of ...[more]

PMID: 32832046

Similar Datasets

Project description:ImportanceMelanomas that clinically mimic seborrheic keratosis (SK) can delay diagnosis and adequate treatment. However, little is known about the value of dermoscopy in recognizing these difficult-to-diagnose melanomas.ObjectiveTo describe the dermoscopic features of SK-like melanomas to understand their clinical morphology.Design, setting, and participantsThis observational retrospective study used 134 clinical and dermoscopic images of histopathologically proven melanomas in 134 patients treated in 9 skin cancer centers in Spain, France, Italy, and Austria. Without knowledge that the definite diagnosis for all the lesions was melanoma, 2 dermoscopy-trained observers evaluated the clinical descriptions and 48 dermoscopic features (including all melanocytic and nonmelanocytic criteria) of all 134 images and classified each dermoscopically as SK or not SK. The total dermoscopy score and the 7-point checklist score were assessed. Images of the lesions and patient data were collected from July 15, 2013, through July 31, 2014.Main outcomes and measuresFrequencies of specific morphologic patterns of (clinically and dermoscopically) SK-like melanomas, patient demographics, and interobserver agreement of criteria were evaluated.ResultsOf the 134 cases collected from 72 men and 61 women, all of whom were white and who had a mean (SD) age of 55.6 (17.5) years, 110 (82.1%) revealed dermoscopic features suggestive of melanoma, including pigment network (74 [55.2%]), blue-white veil (72 [53.7%]), globules and dots (68 [50.7%]), pseudopods or streaks (47 [35.1%]), and blue-black sign (43 [32.3%]). The remaining 24 cases (17.9%) were considered likely SKs, even by dermoscopy. Overall, lesions showed a scaly and hyperkeratotic surface (45 [33.6%]), yellowish keratin (42 [31.3%]), comedo-like openings (41 [30.5%]), and milia-like cysts (30 [22.4%]). The entire sample achieved a mean (SD) total dermoscopy score of 4.7 (1.6) and a 7-point checklist score of 4.4 (2.3), while dermoscopically SK-like melanomas achieved a total dermoscopy score of only 4.2 (1.3) and a 7-point checklist score of 2.0 (1.9), both in the range of benignity. The most helpful criteria in correctly diagnosing SK-like melanomas were the presence of blue-white veil, pseudopods or streaks, and pigment network. Multivariate analysis found only the blue-black sign to be significantly associated with a correct diagnosis, while hyperkeratosis and fissures and ridges were independent risk markers of dermoscopically SK-like melanomas.Conclusions and relevanceSeborrheic keratosis-like melanomas can be dermoscopically challenging, but the presence of the blue-black sign, pigment network, pseudopods or streaks, and/or blue-white veil, despite the presence of other SK features, allows the correct diagnosis of most of the difficult melanoma cases.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets