Dataset Information

Identification of Skin Lesions by Using Single-Step Multiframe Detector.

ABSTRACT: An artificial intelligence algorithm to detect mycosis fungoides (MF), psoriasis (PSO), and atopic dermatitis (AD) is demonstrated. Results showed that 10 s was consumed by the single shot multibox detector (SSD) model to analyze 292 test images, among which 273 images were correctly detected. Verification of ground truth samples of this research come from pathological tissue slices and OCT analysis. The SSD diagnosis accuracy rate was 93%. The sensitivity values of the SSD model in diagnosing the skin lesions according to the symptoms of PSO, AD, MF, and normal were 96%, 80%, 94%, and 95%, and the corresponding precision were 96%, 86%, 98%, and 90%. The highest sensitivity rate was found in MF probably because of the spread of cancer cells in the skin and relatively large lesions of MF. Many differences were found in the accuracy between AD and the other diseases. The collected AD images were all in the elbow or arm and other joints, the area with AD was small, and the features were not obvious. Hence, the proposed SSD could be used to identify the four diseases by using skin image detection, but the diagnosis of AD was relatively poor.

SUBMITTER: Hsiao YP

PROVIDER: S-EPMC7796252 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of Skin Lesions by Using Single-Step Multiframe Detector.

Hsiao Yu-Ping YP Chiu Chih-Wei CW Lu Chih-Wei CW Nguyen Hong Thai HT Tseng Yu Sheng YS Hsieh Shang-Chin SC Wang Hsiang-Chen HC

Journal of clinical medicine 20210104 1

An artificial intelligence algorithm to detect mycosis fungoides (MF), psoriasis (PSO), and atopic dermatitis (AD) is demonstrated. Results showed that 10 s was consumed by the single shot multibox detector (SSD) model to analyze 292 test images, among which 273 images were correctly detected. Verification of ground truth samples of this research come from pathological tissue slices and OCT analysis. The SSD diagnosis accuracy rate was 93%. The sensitivity values of the SSD model in diagnosing t ...[more]

PMID: 33406761

Similar Datasets

Project description:ImportanceThe incidence of skin cancer is increasing and evaluation of the utility of total body skin examination (TBSE) in detecting incidental skin cancers is warranted.ObjectivesTo evaluate the proportion and rate of incidental skin cancer detection in urgent skin cancer clinics and investigate the rate of incidental skin cancer detection in 2 groups based on the degree of clinical suspicion of the index lesion for malignancy.Design, setting, and participantsA multicenter retrospective cohort study with a case note review of consecutive secondary care consultations was conducted using data from 2 urgent suspected skin cancer screening clinics in UK National Health Service trusts. The study was performed from January 1, 2015, to March 31, 2016, and data analysis was performed from October 14, 2018, to February 1, 2019. Patients included those presenting with a skin lesion suspicious of malignancy who were referred to the urgent suspected skin cancer clinic (N = 5944) over 15 months. Patients who accepted and received a TBSE were subsequently included in the analysis.Main outcomes and measuresThe proportion and rate of incidental skin cancer detection through TBSE and whether a clinically suspicious (malignant) index lesion was associated with a higher chance of having a malignant incidental lesion.ResultsOf the 5944 patients referred to the clinic, 4726 individuals (79.5%) were evaluated. In the cohort included in the analyses, the median age was 57 years (interquartile range, 39-73 years); 2567 patients (54.3%) were women. A total of 1117 skin cancers were identified; of these, 242 lesions (21.7%) were detected incidentally through TBSE, including 197 of 570 (34.6%) basal cell carcinomas, 16 of 250 (6.4%) squamous cell carcinomas, and 25 of 215 (11.6%) melanomas. The detection rate of incidental malignant lesions was 5.1 lesions per 100 patients examined (5.1%; 95% CI, 4.5%-5.8%). There was a higher detection rate of histologically confirmed incidental malignant lesions in individuals with clinically suspicious index lesions requiring biopsy (10.9%; 95% CI, 9.5%-12.5%) compared with those presenting with clinically benign index lesions (2.0%; 95% CI, 1.6%-2.5%) (P < .001).Conclusions and relevanceThe findings of this study support the use of TBSE for urgent skin cancer referrals, highlighting the potential harms of solitary lesion assessment in a subgroup. Individuals presenting with a clinically suspicious index lesion requiring biopsy are most likely to benefit from TBSE and should be counseled regarding the benefit.

Project description:Recent studies have demonstrated the usefulness of convolutional neural networks (CNNs) to classify images of melanoma, with accuracies comparable to those achieved by dermatologists. However, the performance of a CNN trained with only clinical images of a pigmented skin lesion in a clinical image classification task, in competition with dermatologists, has not been reported to date. In this study, we extracted 5846 clinical images of pigmented skin lesions from 3551 patients. Pigmented skin lesions included malignant tumors (malignant melanoma and basal cell carcinoma) and benign tumors (nevus, seborrhoeic keratosis, senile lentigo, and hematoma/hemangioma). We created the test dataset by randomly selecting 666 patients out of them and picking one image per patient, and created the training dataset by giving bounding-box annotations to the rest of the images (4732 images, 2885 patients). Subsequently, we trained a faster, region-based CNN (FRCNN) with the training dataset and checked the performance of the model on the test dataset. In addition, ten board-certified dermatologists (BCDs) and ten dermatologic trainees (TRNs) took the same tests, and we compared their diagnostic accuracy with FRCNN. For six-class classification, the accuracy of FRCNN was 86.2%, and that of the BCDs and TRNs was 79.5% (p = 0.0081) and 75.1% (p < 0.00001), respectively. For two-class classification (benign or malignant), the accuracy, sensitivity, and specificity were 91.5%, 83.3%, and 94.5% by FRCNN; 86.6%, 86.3%, and 86.6% by BCD; and 85.3%, 83.5%, and 85.9% by TRN, respectively. False positive rates and positive predictive values were 5.5% and 84.7% by FRCNN, 13.4% and 70.5% by BCD, and 14.1% and 68.5% by TRN, respectively. We compared the classification performance of FRCNN with 20 dermatologists. As a result, the classification accuracy of FRCNN was better than that of the dermatologists. In the future, we plan to implement this system in society and have it used by the general public, in order to improve the prognosis of skin cancer.

Dataset Information

Identification of Skin Lesions by Using Single-Step Multiframe Detector.

Publications

Identification of Skin Lesions by Using Single-Step Multiframe Detector.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure