FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952971376> ?p ?o ?g. }

• W2952971376 endingPage "947" @default.
• W2952971376 startingPage "938" @default.
• W2952971376 abstract "Background Whether machine-learning algorithms can diagnose all pigmented skin lesions as accurately as human experts is unclear. The aim of this study was to compare the diagnostic accuracy of state-of-the-art machine-learning algorithms with human readers for all clinically relevant types of benign and malignant pigmented skin lesions. Methods For this open, web-based, international, diagnostic study, human readers were asked to diagnose dermatoscopic images selected randomly in 30-image batches from a test set of 1511 images. The diagnoses from human readers were compared with those of 139 algorithms created by 77 machine-learning labs, who participated in the International Skin Imaging Collaboration 2018 challenge and received a training set of 10 015 images in advance. The ground truth of each lesion fell into one of seven predefined disease categories: intraepithelial carcinoma including actinic keratoses and Bowen's disease; basal cell carcinoma; benign keratinocytic lesions including solar lentigo, seborrheic keratosis and lichen planus-like keratosis; dermatofibroma; melanoma; melanocytic nevus; and vascular lesions. The two main outcomes were the differences in the number of correct specific diagnoses per batch between all human readers and the top three algorithms, and between human experts and the top three algorithms. Findings Between Aug 4, 2018, and Sept 30, 2018, 511 human readers from 63 countries had at least one attempt in the reader study. 283 (55·4%) of 511 human readers were board-certified dermatologists, 118 (23·1%) were dermatology residents, and 83 (16·2%) were general practitioners. When comparing all human readers with all machine-learning algorithms, the algorithms achieved a mean of 2·01 (95% CI 1·97 to 2·04; p<0·0001) more correct diagnoses (17·91 [SD 3·42] vs 19·92 [4·27]). 27 human experts with more than 10 years of experience achieved a mean of 18·78 (SD 3·15) correct answers, compared with 25·43 (1·95) correct answers for the top three machine algorithms (mean difference 6·65, 95% CI 6·06–7·25; p<0·0001). The difference between human experts and the top three algorithms was significantly lower for images in the test set that were collected from sources not included in the training set (human underperformance of 11·4%, 95% CI 9·9–12·9 vs 3·6%, 0·8–6·3; p<0·0001). Interpretation State-of-the-art machine-learning classifiers outperformed human experts in the diagnosis of pigmented skin lesions and should have a more important role in clinical practice. However, a possible limitation of these algorithms is their decreased performance for out-of-distribution images, which should be addressed in future research. Funding None. Whether machine-learning algorithms can diagnose all pigmented skin lesions as accurately as human experts is unclear. The aim of this study was to compare the diagnostic accuracy of state-of-the-art machine-learning algorithms with human readers for all clinically relevant types of benign and malignant pigmented skin lesions. For this open, web-based, international, diagnostic study, human readers were asked to diagnose dermatoscopic images selected randomly in 30-image batches from a test set of 1511 images. The diagnoses from human readers were compared with those of 139 algorithms created by 77 machine-learning labs, who participated in the International Skin Imaging Collaboration 2018 challenge and received a training set of 10 015 images in advance. The ground truth of each lesion fell into one of seven predefined disease categories: intraepithelial carcinoma including actinic keratoses and Bowen's disease; basal cell carcinoma; benign keratinocytic lesions including solar lentigo, seborrheic keratosis and lichen planus-like keratosis; dermatofibroma; melanoma; melanocytic nevus; and vascular lesions. The two main outcomes were the differences in the number of correct specific diagnoses per batch between all human readers and the top three algorithms, and between human experts and the top three algorithms. Between Aug 4, 2018, and Sept 30, 2018, 511 human readers from 63 countries had at least one attempt in the reader study. 283 (55·4%) of 511 human readers were board-certified dermatologists, 118 (23·1%) were dermatology residents, and 83 (16·2%) were general practitioners. When comparing all human readers with all machine-learning algorithms, the algorithms achieved a mean of 2·01 (95% CI 1·97 to 2·04; p<0·0001) more correct diagnoses (17·91 [SD 3·42] vs 19·92 [4·27]). 27 human experts with more than 10 years of experience achieved a mean of 18·78 (SD 3·15) correct answers, compared with 25·43 (1·95) correct answers for the top three machine algorithms (mean difference 6·65, 95% CI 6·06–7·25; p<0·0001). The difference between human experts and the top three algorithms was significantly lower for images in the test set that were collected from sources not included in the training set (human underperformance of 11·4%, 95% CI 9·9–12·9 vs 3·6%, 0·8–6·3; p<0·0001). State-of-the-art machine-learning classifiers outperformed human experts in the diagnosis of pigmented skin lesions and should have a more important role in clinical practice. However, a possible limitation of these algorithms is their decreased performance for out-of-distribution images, which should be addressed in future research." @default.
• W2952971376 created "2019-06-27" @default.
• W2952971376 creator A5000215116 @default.
• W2952971376 creator A5002939193 @default.
• W2952971376 creator A5004712523 @default.
• W2952971376 creator A5008065839 @default.
• W2952971376 creator A5011182804 @default.
• W2952971376 creator A5011768850 @default.
• W2952971376 creator A5016830138 @default.
• W2952971376 creator A5027450519 @default.
• W2952971376 creator A5030258474 @default.
• W2952971376 creator A5033462323 @default.
• W2952971376 creator A5033515147 @default.
• W2952971376 creator A5034990173 @default.
• W2952971376 creator A5035102732 @default.
• W2952971376 creator A5046618994 @default.
• W2952971376 creator A5050063952 @default.
• W2952971376 creator A5050532754 @default.
• W2952971376 creator A5056955219 @default.
• W2952971376 creator A5063123689 @default.
• W2952971376 creator A5068417011 @default.
• W2952971376 creator A5070127396 @default.
• W2952971376 creator A5072653864 @default.
• W2952971376 creator A5073027533 @default.
• W2952971376 creator A5073937900 @default.
• W2952971376 creator A5079760997 @default.
• W2952971376 creator A5080708228 @default.
• W2952971376 creator A5081297649 @default.
• W2952971376 creator A5086926559 @default.
• W2952971376 creator A5091131544 @default.
• W2952971376 date "2019-07-01" @default.
• W2952971376 modified "2023-10-13" @default.
• W2952971376 title "Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study" @default.
• W2952971376 cites W2006617902 @default.
• W2952971376 cites W2021002036 @default.
• W2952971376 cites W2023191766 @default.
• W2952971376 cites W2033809335 @default.
• W2952971376 cites W2040600853 @default.
• W2952971376 cites W2041914157 @default.
• W2952971376 cites W2112796928 @default.
• W2952971376 cites W2128186581 @default.
• W2952971376 cites W2128756499 @default.
• W2952971376 cites W2164273268 @default.
• W2952971376 cites W2170994840 @default.
• W2952971376 cites W2328176404 @default.
• W2952971376 cites W2488406013 @default.
• W2952971376 cites W2581082771 @default.
• W2952971376 cites W2586172326 @default.
• W2952971376 cites W2591494847 @default.
• W2952971376 cites W2757940437 @default.
• W2952971376 cites W2786147899 @default.
• W2952971376 cites W2800373720 @default.
• W2952971376 cites W2806853752 @default.
• W2952971376 cites W2963059730 @default.
• W2952971376 cites W3102785203 @default.
• W2952971376 cites W4232128237 @default.
• W2952971376 doi "https://doi.org/10.1016/s1470-2045(19)30333-x" @default.
• W2952971376 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8237239" @default.
• W2952971376 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31201137" @default.
• W2952971376 hasPublicationYear "2019" @default.
• W2952971376 type Work @default.
• W2952971376 sameAs 2952971376 @default.
• W2952971376 citedByCount "302" @default.
• W2952971376 countsByYear W29529713762019 @default.
• W2952971376 countsByYear W29529713762020 @default.
• W2952971376 countsByYear W29529713762021 @default.
• W2952971376 countsByYear W29529713762022 @default.
• W2952971376 countsByYear W29529713762023 @default.
• W2952971376 crossrefType "journal-article" @default.
• W2952971376 hasAuthorship W2952971376A5000215116 @default.
• W2952971376 hasAuthorship W2952971376A5002939193 @default.
• W2952971376 hasAuthorship W2952971376A5004712523 @default.
• W2952971376 hasAuthorship W2952971376A5008065839 @default.
• W2952971376 hasAuthorship W2952971376A5011182804 @default.
• W2952971376 hasAuthorship W2952971376A5011768850 @default.
• W2952971376 hasAuthorship W2952971376A5016830138 @default.
• W2952971376 hasAuthorship W2952971376A5027450519 @default.
• W2952971376 hasAuthorship W2952971376A5030258474 @default.
• W2952971376 hasAuthorship W2952971376A5033462323 @default.
• W2952971376 hasAuthorship W2952971376A5033515147 @default.
• W2952971376 hasAuthorship W2952971376A5034990173 @default.
• W2952971376 hasAuthorship W2952971376A5035102732 @default.
• W2952971376 hasAuthorship W2952971376A5046618994 @default.
• W2952971376 hasAuthorship W2952971376A5050063952 @default.
• W2952971376 hasAuthorship W2952971376A5050532754 @default.
• W2952971376 hasAuthorship W2952971376A5056955219 @default.
• W2952971376 hasAuthorship W2952971376A5063123689 @default.
• W2952971376 hasAuthorship W2952971376A5068417011 @default.
• W2952971376 hasAuthorship W2952971376A5070127396 @default.
• W2952971376 hasAuthorship W2952971376A5072653864 @default.
• W2952971376 hasAuthorship W2952971376A5073027533 @default.
• W2952971376 hasAuthorship W2952971376A5073937900 @default.
• W2952971376 hasAuthorship W2952971376A5079760997 @default.
• W2952971376 hasAuthorship W2952971376A5080708228 @default.
• W2952971376 hasAuthorship W2952971376A5081297649 @default.
• W2952971376 hasAuthorship W2952971376A5086926559 @default.
• W2952971376 hasAuthorship W2952971376A5091131544 @default.
• W2952971376 hasBestOaLocation W29529713763 @default.

• next