Predicting the clinical management of skin lesions using deep learning

Abstract Automated machine learning approaches to skin lesion diagnosis from images are approaching dermatologist-level performance. However, current machine learning approaches that suggest management decisions rely on predicting the underlying skin condition to infer a management decision without...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kumar Abhishek, Jeremy Kawahara, Ghassan Hamarneh
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7db5a0869123411895ea4b08b90c398b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7db5a0869123411895ea4b08b90c398b
record_format	dspace
spelling	oai:doaj.org-article:7db5a0869123411895ea4b08b90c398b2021-12-02T14:37:15ZPredicting the clinical management of skin lesions using deep learning10.1038/s41598-021-87064-72045-2322https://doaj.org/article/7db5a0869123411895ea4b08b90c398b2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87064-7https://doaj.org/toc/2045-2322Abstract Automated machine learning approaches to skin lesion diagnosis from images are approaching dermatologist-level performance. However, current machine learning approaches that suggest management decisions rely on predicting the underlying skin condition to infer a management decision without considering the variability of management decisions that may exist within a single condition. We present the first work to explore image-based prediction of clinical management decisions directly without explicitly predicting the diagnosis. In particular, we use clinical and dermoscopic images of skin lesions along with patient metadata from the Interactive Atlas of Dermoscopy dataset (1011 cases; 20 disease labels; 3 management decisions) and demonstrate that predicting management labels directly is more accurate than predicting the diagnosis and then inferring the management decision ( $$13.73 \pm 3.93\%$$ 13.73 ± 3.93 % and $$6.59 \pm 2.86\%$$ 6.59 ± 2.86 % improvement in overall accuracy and AUROC respectively), statistically significant at $$p < 0.001$$ p < 0.001 . Directly predicting management decisions also considerably reduces the over-excision rate as compared to management decisions inferred from diagnosis predictions (24.56% fewer cases wrongly predicted to be excised). Furthermore, we show that training a model to also simultaneously predict the seven-point criteria and the diagnosis of skin lesions yields an even higher accuracy (improvements of $$4.68 \pm 1.89\%$$ 4.68 ± 1.89 % and $$2.24 \pm 2.04\%$$ 2.24 ± 2.04 % in overall accuracy and AUROC respectively) of management predictions. Finally, we demonstrate our model’s generalizability by evaluating on the publicly available MClass-D dataset and show that our model agrees with the clinical management recommendations of 157 dermatologists as much as they agree amongst each other.Kumar AbhishekJeremy KawaharaGhassan HamarnehNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kumar Abhishek Jeremy Kawahara Ghassan Hamarneh Predicting the clinical management of skin lesions using deep learning
description	Abstract Automated machine learning approaches to skin lesion diagnosis from images are approaching dermatologist-level performance. However, current machine learning approaches that suggest management decisions rely on predicting the underlying skin condition to infer a management decision without considering the variability of management decisions that may exist within a single condition. We present the first work to explore image-based prediction of clinical management decisions directly without explicitly predicting the diagnosis. In particular, we use clinical and dermoscopic images of skin lesions along with patient metadata from the Interactive Atlas of Dermoscopy dataset (1011 cases; 20 disease labels; 3 management decisions) and demonstrate that predicting management labels directly is more accurate than predicting the diagnosis and then inferring the management decision ( $$13.73 \pm 3.93\%$$ 13.73 ± 3.93 % and $$6.59 \pm 2.86\%$$ 6.59 ± 2.86 % improvement in overall accuracy and AUROC respectively), statistically significant at $$p < 0.001$$ p < 0.001 . Directly predicting management decisions also considerably reduces the over-excision rate as compared to management decisions inferred from diagnosis predictions (24.56% fewer cases wrongly predicted to be excised). Furthermore, we show that training a model to also simultaneously predict the seven-point criteria and the diagnosis of skin lesions yields an even higher accuracy (improvements of $$4.68 \pm 1.89\%$$ 4.68 ± 1.89 % and $$2.24 \pm 2.04\%$$ 2.24 ± 2.04 % in overall accuracy and AUROC respectively) of management predictions. Finally, we demonstrate our model’s generalizability by evaluating on the publicly available MClass-D dataset and show that our model agrees with the clinical management recommendations of 157 dermatologists as much as they agree amongst each other.
format	article
author	Kumar Abhishek Jeremy Kawahara Ghassan Hamarneh
author_facet	Kumar Abhishek Jeremy Kawahara Ghassan Hamarneh
author_sort	Kumar Abhishek
title	Predicting the clinical management of skin lesions using deep learning
title_short	Predicting the clinical management of skin lesions using deep learning
title_full	Predicting the clinical management of skin lesions using deep learning
title_fullStr	Predicting the clinical management of skin lesions using deep learning
title_full_unstemmed	Predicting the clinical management of skin lesions using deep learning
title_sort	predicting the clinical management of skin lesions using deep learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7db5a0869123411895ea4b08b90c398b
work_keys_str_mv	AT kumarabhishek predictingtheclinicalmanagementofskinlesionsusingdeeplearning AT jeremykawahara predictingtheclinicalmanagementofskinlesionsusingdeeplearning AT ghassanhamarneh predictingtheclinicalmanagementofskinlesionsusingdeeplearning
_version_	1718391015404994560

Predicting the clinical management of skin lesions using deep learning

Ejemplares similares