Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels

Abstract Reflectance confocal microscopy (RCM) is a non-invasive imaging tool that reduces the need for invasive histopathology for skin cancer diagnoses by providing high-resolution mosaics showing the architectural patterns of skin, which are used to identify malignancies in-vivo. RCM mosaics are...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marissa D’Alonzo, Alican Bozkurt, Christi Alessi-Fox, Melissa Gill, Dana H. Brooks, Milind Rajadhyaksha, Kivanc Kose, Jennifer G. Dy
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/57ace70346f641dd9734c941091b7c3a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:57ace70346f641dd9734c941091b7c3a
record_format	dspace
spelling	oai:doaj.org-article:57ace70346f641dd9734c941091b7c3a2021-12-02T14:11:28ZSemantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels10.1038/s41598-021-82969-92045-2322https://doaj.org/article/57ace70346f641dd9734c941091b7c3a2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-82969-9https://doaj.org/toc/2045-2322Abstract Reflectance confocal microscopy (RCM) is a non-invasive imaging tool that reduces the need for invasive histopathology for skin cancer diagnoses by providing high-resolution mosaics showing the architectural patterns of skin, which are used to identify malignancies in-vivo. RCM mosaics are similar to dermatopathology sections, both requiring extensive training to interpret. However, these modalities differ in orientation, as RCM mosaics are horizontal (parallel to the skin surface) while histopathology sections are vertical, and contrast mechanism, RCM with a single (reflectance) mechanism resulting in grayscale images and histopathology with multi-factor color-stained contrast. Image analysis and machine learning methods can potentially provide a diagnostic aid to clinicians to interpret RCM mosaics, eventually helping to ease the adoption and more efficiently utilizing RCM in routine clinical practice. However standard supervised machine learning may require a prohibitive volume of hand-labeled training data. In this paper, we present a weakly supervised machine learning model to perform semantic segmentation of architectural patterns encountered in RCM mosaics. Unlike more widely used fully supervised segmentation models that require pixel-level annotations, which are very labor-demanding and error-prone to obtain, here we focus on training models using only patch-level labels (e.g. a single field of view within an entire mosaic). We segment RCM mosaics into “benign” and “aspecific (nonspecific)” regions, where aspecific regions represent the loss of regular architecture due to injury and/or inflammation, pre-malignancy, or malignancy. We adopt Efficientnet, a deep neural network (DNN) proven to accurately accomplish classification tasks, to generate class activation maps, and use a Gaussian weighting kernel to stitch smaller images back into larger fields of view. The trained DNN achieved an average area under the curve of 0.969, and Dice coefficient of 0.778 showing the feasibility of spatial localization of aspecific regions in RCM images, and making the diagnostics decision model more interpretable to the clinicians.Marissa D’AlonzoAlican BozkurtChristi Alessi-FoxMelissa GillDana H. BrooksMilind RajadhyakshaKivanc KoseJennifer G. DyNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Marissa D’Alonzo Alican Bozkurt Christi Alessi-Fox Melissa Gill Dana H. Brooks Milind Rajadhyaksha Kivanc Kose Jennifer G. Dy Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
description	Abstract Reflectance confocal microscopy (RCM) is a non-invasive imaging tool that reduces the need for invasive histopathology for skin cancer diagnoses by providing high-resolution mosaics showing the architectural patterns of skin, which are used to identify malignancies in-vivo. RCM mosaics are similar to dermatopathology sections, both requiring extensive training to interpret. However, these modalities differ in orientation, as RCM mosaics are horizontal (parallel to the skin surface) while histopathology sections are vertical, and contrast mechanism, RCM with a single (reflectance) mechanism resulting in grayscale images and histopathology with multi-factor color-stained contrast. Image analysis and machine learning methods can potentially provide a diagnostic aid to clinicians to interpret RCM mosaics, eventually helping to ease the adoption and more efficiently utilizing RCM in routine clinical practice. However standard supervised machine learning may require a prohibitive volume of hand-labeled training data. In this paper, we present a weakly supervised machine learning model to perform semantic segmentation of architectural patterns encountered in RCM mosaics. Unlike more widely used fully supervised segmentation models that require pixel-level annotations, which are very labor-demanding and error-prone to obtain, here we focus on training models using only patch-level labels (e.g. a single field of view within an entire mosaic). We segment RCM mosaics into “benign” and “aspecific (nonspecific)” regions, where aspecific regions represent the loss of regular architecture due to injury and/or inflammation, pre-malignancy, or malignancy. We adopt Efficientnet, a deep neural network (DNN) proven to accurately accomplish classification tasks, to generate class activation maps, and use a Gaussian weighting kernel to stitch smaller images back into larger fields of view. The trained DNN achieved an average area under the curve of 0.969, and Dice coefficient of 0.778 showing the feasibility of spatial localization of aspecific regions in RCM images, and making the diagnostics decision model more interpretable to the clinicians.
format	article
author	Marissa D’Alonzo Alican Bozkurt Christi Alessi-Fox Melissa Gill Dana H. Brooks Milind Rajadhyaksha Kivanc Kose Jennifer G. Dy
author_facet	Marissa D’Alonzo Alican Bozkurt Christi Alessi-Fox Melissa Gill Dana H. Brooks Milind Rajadhyaksha Kivanc Kose Jennifer G. Dy
author_sort	Marissa D’Alonzo
title	Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
title_short	Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
title_full	Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
title_fullStr	Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
title_full_unstemmed	Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
title_sort	semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/57ace70346f641dd9734c941091b7c3a
work_keys_str_mv	AT marissadalonzo semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT alicanbozkurt semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT christialessifox semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT melissagill semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT danahbrooks semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT milindrajadhyaksha semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT kivanckose semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels AT jennifergdy semanticsegmentationofreflectanceconfocalmicroscopymosaicsofpigmentedlesionsusingweaklabels
_version_	1718391842675884032

Semantic segmentation of reflectance confocal microscopy mosaics of pigmented lesions using weak labels

Ejemplares similares