High Precision Mammography Lesion Identification From Imprecise Medical Annotations

Breast cancer screening using Mammography serves as the earliest defense against breast cancer, revealing anomalous tissue years before it can be detected through physical screening. Despite the use of high resolution radiography, the presence of densely overlapping patterns challenges the consisten...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ulzee An, Ankit Bhardwaj, Khader Shameer, Lakshminarayanan Subramanian
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	oncology breast cancer computer vision digital health computational diagnosis big data and analytics Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/d7c113d05b6a4ca1a0490b4dfb9b4daf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d7c113d05b6a4ca1a0490b4dfb9b4daf
record_format	dspace
spelling	oai:doaj.org-article:d7c113d05b6a4ca1a0490b4dfb9b4daf2021-12-03T15:54:27ZHigh Precision Mammography Lesion Identification From Imprecise Medical Annotations2624-909X10.3389/fdata.2021.742779https://doaj.org/article/d7c113d05b6a4ca1a0490b4dfb9b4daf2021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fdata.2021.742779/fullhttps://doaj.org/toc/2624-909XBreast cancer screening using Mammography serves as the earliest defense against breast cancer, revealing anomalous tissue years before it can be detected through physical screening. Despite the use of high resolution radiography, the presence of densely overlapping patterns challenges the consistency of human-driven diagnosis and drives interest in leveraging state-of-art localization ability of deep convolutional neural networks (DCNN). The growing availability of digitized clinical archives enables the training of deep segmentation models, but training using the most widely available form of coarse hand-drawn annotations works against learning the precise boundary of cancerous tissue in evaluation, while producing results that are more aligned with the annotations rather than the underlying lesions. The expense of collecting high quality pixel-level data in the field of medical science makes this even more difficult. To surmount this fundamental challenge, we propose LatentCADx, a deep learning segmentation model capable of precisely annotating cancer lesions underlying hand-drawn annotations, which we procedurally obtain using joint classification training and a strict segmentation penalty. We demonstrate the capability of LatentCADx on a publicly available dataset of 2,620 Mammogram case files, where LatentCADx obtains classification ROC of 0.97, AP of 0.87, and segmentation AP of 0.75 (IOU = 0.5), giving comparable or better performance than other models. Qualitative and precision evaluation of LatentCADx annotations on validation samples reveals that LatentCADx increases the specificity of segmentations beyond that of existing models trained on hand-drawn annotations, with pixel level specificity reaching a staggering value of 0.90. It also obtains sharp boundary around lesions unlike other methods, reducing the confused pixels in the output by more than 60%.Ulzee AnAnkit BhardwajKhader ShameerLakshminarayanan SubramanianLakshminarayanan SubramanianFrontiers Media S.A.articleoncologybreast cancercomputer visiondigital healthcomputational diagnosisbig data and analyticsInformation technologyT58.5-58.64ENFrontiers in Big Data, Vol 4 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	oncology breast cancer computer vision digital health computational diagnosis big data and analytics Information technology T58.5-58.64
spellingShingle	oncology breast cancer computer vision digital health computational diagnosis big data and analytics Information technology T58.5-58.64 Ulzee An Ankit Bhardwaj Khader Shameer Lakshminarayanan Subramanian Lakshminarayanan Subramanian High Precision Mammography Lesion Identification From Imprecise Medical Annotations
description	Breast cancer screening using Mammography serves as the earliest defense against breast cancer, revealing anomalous tissue years before it can be detected through physical screening. Despite the use of high resolution radiography, the presence of densely overlapping patterns challenges the consistency of human-driven diagnosis and drives interest in leveraging state-of-art localization ability of deep convolutional neural networks (DCNN). The growing availability of digitized clinical archives enables the training of deep segmentation models, but training using the most widely available form of coarse hand-drawn annotations works against learning the precise boundary of cancerous tissue in evaluation, while producing results that are more aligned with the annotations rather than the underlying lesions. The expense of collecting high quality pixel-level data in the field of medical science makes this even more difficult. To surmount this fundamental challenge, we propose LatentCADx, a deep learning segmentation model capable of precisely annotating cancer lesions underlying hand-drawn annotations, which we procedurally obtain using joint classification training and a strict segmentation penalty. We demonstrate the capability of LatentCADx on a publicly available dataset of 2,620 Mammogram case files, where LatentCADx obtains classification ROC of 0.97, AP of 0.87, and segmentation AP of 0.75 (IOU = 0.5), giving comparable or better performance than other models. Qualitative and precision evaluation of LatentCADx annotations on validation samples reveals that LatentCADx increases the specificity of segmentations beyond that of existing models trained on hand-drawn annotations, with pixel level specificity reaching a staggering value of 0.90. It also obtains sharp boundary around lesions unlike other methods, reducing the confused pixels in the output by more than 60%.
format	article
author	Ulzee An Ankit Bhardwaj Khader Shameer Lakshminarayanan Subramanian Lakshminarayanan Subramanian
author_facet	Ulzee An Ankit Bhardwaj Khader Shameer Lakshminarayanan Subramanian Lakshminarayanan Subramanian
author_sort	Ulzee An
title	High Precision Mammography Lesion Identification From Imprecise Medical Annotations
title_short	High Precision Mammography Lesion Identification From Imprecise Medical Annotations
title_full	High Precision Mammography Lesion Identification From Imprecise Medical Annotations
title_fullStr	High Precision Mammography Lesion Identification From Imprecise Medical Annotations
title_full_unstemmed	High Precision Mammography Lesion Identification From Imprecise Medical Annotations
title_sort	high precision mammography lesion identification from imprecise medical annotations
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/d7c113d05b6a4ca1a0490b4dfb9b4daf
work_keys_str_mv	AT ulzeean highprecisionmammographylesionidentificationfromimprecisemedicalannotations AT ankitbhardwaj highprecisionmammographylesionidentificationfromimprecisemedicalannotations AT khadershameer highprecisionmammographylesionidentificationfromimprecisemedicalannotations AT lakshminarayanansubramanian highprecisionmammographylesionidentificationfromimprecisemedicalannotations AT lakshminarayanansubramanian highprecisionmammographylesionidentificationfromimprecisemedicalannotations
_version_	1718373177316343808

High Precision Mammography Lesion Identification From Imprecise Medical Annotations

Ejemplares similares