Volver al buscador
Vista en detalle del documento
Titulo Artículo:
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Resumen:
Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.
Fecha de publicación:
2020.
Autores :
Konstantinos Liopyris;
Noel C F Codella;
Allan C Halpern;
Stephen W Dusza;
David A Gutman ;
Brian Helba;
Aadi Kalloo;
Michael A Marchetti ;
Autor corporativo:
Journal of the American Academy of Dermatology,
Editores:
Medline-PubMed ;
Signatura Topográfica:
3
Idioma:
Inglés
Páginas:
622
ISBN:
1097-6787
Existencias:
627
Palabras claves:
International Skin Imaging Collaboration
International Symposium on Biomedical Imaging
Deep Learning
Melanoma
Skin Cancer
Público objetivo:
Posgrado
Docentes
Investigadores
Educadores Medicos
Titulo Artículo:
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Resumen:
Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.
Fecha de publicación:
2020.
Autores :
Konstantinos Liopyris;
Noel C F Codella;
Allan C Halpern;
Stephen W Dusza;
David A Gutman ;
Brian Helba;
Aadi Kalloo;
Michael A Marchetti ;
Autor corporativo:
Journal of the American Academy of Dermatology,
Editores:
Medline-PubMed ;
Signatura Topográfica:
3
Idioma:
Inglés
Páginas:
622
Existencias:
627
Palabras claves:
International Skin Imaging Collaboration
International Symposium on Biomedical Imaging
Deep Learning
Melanoma
Skin Cancer
Público objetivo:
Posgrado
Docentes
Investigadores
Educadores Medicos
Titulo Artículo:
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Resumen:
Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.
Autores:
Konstantinos Liopyris
,
Noel C F Codella
,
Allan C Halpern
,
Stephen W Dusza
,
David A Gutman
,
Brian Helba
,
Aadi Kalloo
,
Michael A Marchetti
,
.
Titulo Revista:
Journal of the American Academy of Dermatology,
.
Numero:
3
Volumen:
82
Fecha de publicación:
2020.
Base de Datos Bibliográfica:
Medline-PubMed ,
.
Suplemento:
Idioma:
Inglés
Página Inicial:
622
Página Final:
627
ISBN:
1097-6787
Palabras claves:
International Skin Imaging Collaboration
International Symposium on Biomedical Imaging
Deep Learning
Melanoma
Skin Cancer
Público objetivo:
Posgrado
Docentes
Investigadores
Educadores Medicos
Título Medline-PubMed :
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Resumen:
Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.
Autores :
Konstantinos Liopyris;
Noel C F Codella;
Allan C Halpern;
Stephen W Dusza;
David A Gutman ;
Brian Helba;
Aadi Kalloo;
Michael A Marchetti ;
Autor corporativo:
Journal of the American Academy of Dermatology,
Fecha de publicación:
2020.
Tipo :
Medline-PubMed .
Idioma:
Inglés
Palabras claves:
International Skin Imaging Collaboration
International Symposium on Biomedical Imaging
Deep Learning
Melanoma
Skin Cancer
Público objetivo:
Posgrado
Docentes
Investigadores
Educadores Medicos
Título Medline-PubMed :
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Resumen:
Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.
Autores :
Konstantinos Liopyris;
Noel C F Codella;
Allan C Halpern;
Stephen W Dusza;
David A Gutman ;
Brian Helba;
Aadi Kalloo;
Michael A Marchetti ;
Autor corporativo:
Journal of the American Academy of Dermatology,
Fecha de publicación:
2020.
Paginas:
622.
ISBN:
1097-6787.
Idioma:
Inglés
Palabras claves:
International Skin Imaging Collaboration
International Symposium on Biomedical Imaging
Deep Learning
Melanoma
Skin Cancer
Público objetivo:
Posgrado
Docentes
Investigadores
Educadores Medicos
Titulo Artículo:
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Resumen:
Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.
Fecha de publicación:
2020.
Autor corporativo:
Journal of the American Academy of Dermatology,
.
Idioma:
Inglés
Palabras claves:
International Skin Imaging Collaboration
International Symposium on Biomedical Imaging
Deep Learning
Melanoma
Skin Cancer
Público objetivo:
Posgrado
Docentes
Investigadores
Educadores Medicos
Citar
Enviar por correo electrónico
Imprimir
Guardar
Consultar
INGRESE LOS SIGUIENTES DATOS
PARA ENVIAR EL CORREO
Sus nombres:
Sus apellidos:
Su correo electrónico:
Se necesita un valor.
Formato no válido.
Inscribirme al e-boletin de ASCOFAME
Correo electrónico destino:
Se necesita un valor.
Formato no válido.
Hola, encontré este documento en la biblioteca especializada en Educación Médica de ASCOFAME :Konstantinos Liopyris; Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017(2020). Podras consultarlo en el Siguiente link: https://ascofame.org.co/biblioteca/detalle_documento.php?id=2174
INGRESE LOS SIGUIENTES DATOS
PARA RESERVA EN SALA
Sus nombres:
Sus apellidos:
Correo electrónico:
Se necesita un valor.
Formato no válido.
Inscribirme al e-boletin de ASCOFAME
Programar la fecha de su visita:
Programar la hora de su visita:
7:00 AM
8:00 AM
9:00 AM
10:00 AM
11:00 AM
12:00 M
1:00 PM
2:00 PM
3:00 PM
¿Cómo citar este documento?
Seleccionar y copiar el texto.
Konstantinos Liopyris Noel C F Codella Allan C Halpern Stephen W Dusza David A Gutman Brian Helba Aadi Kalloo Michael A Marchetti Konstantinos Liopyris Noel C F Codella Allan C Halpern Stephen W Dusza David A Gutman Brian Helba Aadi Kalloo Michael A Marchetti Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017. 2020; 82Ed. 622.
