Deep Vision for Breast Cancer Classification and Segmentation

(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learni...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lawrence Fulton, Alex McLeod, Diane Dolezel, Nathaniel Bastian, Christopher P. Fulton
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep vision breast cancer machine learning region of interest detection Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/93a512ab233d49478864a87120cc3ad8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:93a512ab233d49478864a87120cc3ad8
record_format	dspace
spelling	oai:doaj.org-article:93a512ab233d49478864a87120cc3ad82021-11-11T15:29:43ZDeep Vision for Breast Cancer Classification and Segmentation10.3390/cancers132153842072-6694https://doaj.org/article/93a512ab233d49478864a87120cc3ad82021-10-01T00:00:00Zhttps://www.mdpi.com/2072-6694/13/21/5384https://doaj.org/toc/2072-6694(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learning classifies 299 × 299 pixel de-noised mammography images as negative or non-negative using models built on 55,890 pre-processed training images and applied to 15,364 unseen test images. A small image representation from the fitted training model is returned to evaluate the portion of the loss function gradient with respect to the image that maximizes the classification probability. This gradient is then re-mapped back to the original images, highlighting the areas of the original image that are most influential for classification (perhaps masses or boundary areas). (3) Results: initial classification results were 97% accurate, 99% specific, and 83% sensitive. Gradient techniques for unsupervised region of interest mapping identified areas most associated with the classification results clearly on positive mammograms and might be used to support clinician analysis. (4) Conclusions: deep vision techniques hold promise for addressing the overdiagnoses and treatment, underdiagnoses, and automated region of interest identification on mammography.Lawrence FultonAlex McLeodDiane DolezelNathaniel BastianChristopher P. FultonMDPI AGarticledeep visionbreast cancermachine learningregion of interest detectionNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENCancers, Vol 13, Iss 5384, p 5384 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep vision breast cancer machine learning region of interest detection Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	deep vision breast cancer machine learning region of interest detection Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Lawrence Fulton Alex McLeod Diane Dolezel Nathaniel Bastian Christopher P. Fulton Deep Vision for Breast Cancer Classification and Segmentation
description	(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learning classifies 299 × 299 pixel de-noised mammography images as negative or non-negative using models built on 55,890 pre-processed training images and applied to 15,364 unseen test images. A small image representation from the fitted training model is returned to evaluate the portion of the loss function gradient with respect to the image that maximizes the classification probability. This gradient is then re-mapped back to the original images, highlighting the areas of the original image that are most influential for classification (perhaps masses or boundary areas). (3) Results: initial classification results were 97% accurate, 99% specific, and 83% sensitive. Gradient techniques for unsupervised region of interest mapping identified areas most associated with the classification results clearly on positive mammograms and might be used to support clinician analysis. (4) Conclusions: deep vision techniques hold promise for addressing the overdiagnoses and treatment, underdiagnoses, and automated region of interest identification on mammography.
format	article
author	Lawrence Fulton Alex McLeod Diane Dolezel Nathaniel Bastian Christopher P. Fulton
author_facet	Lawrence Fulton Alex McLeod Diane Dolezel Nathaniel Bastian Christopher P. Fulton
author_sort	Lawrence Fulton
title	Deep Vision for Breast Cancer Classification and Segmentation
title_short	Deep Vision for Breast Cancer Classification and Segmentation
title_full	Deep Vision for Breast Cancer Classification and Segmentation
title_fullStr	Deep Vision for Breast Cancer Classification and Segmentation
title_full_unstemmed	Deep Vision for Breast Cancer Classification and Segmentation
title_sort	deep vision for breast cancer classification and segmentation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/93a512ab233d49478864a87120cc3ad8
work_keys_str_mv	AT lawrencefulton deepvisionforbreastcancerclassificationandsegmentation AT alexmcleod deepvisionforbreastcancerclassificationandsegmentation AT dianedolezel deepvisionforbreastcancerclassificationandsegmentation AT nathanielbastian deepvisionforbreastcancerclassificationandsegmentation AT christopherpfulton deepvisionforbreastcancerclassificationandsegmentation
_version_	1718435253446508544

Deep Vision for Breast Cancer Classification and Segmentation

Ejemplares similares