Aggregation of cohorts for histopathological diagnosis with deep morphological analysis

Abstract There have been substantial efforts in using deep learning (DL) to diagnose cancer from digital images of pathology slides. Existing algorithms typically operate by training deep neural networks either specialized in specific cohorts or an aggregate of all cohorts when there are only a few...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jeonghyuk Park, Yul Ri Chung, Seo Taek Kong, Yeong Won Kim, Hyunho Park, Kyungdoc Kim, Dong-Il Kim, Kyu-Hwan Jung
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/cc3a6ff7b5f74169a3a27530a75eb747
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cc3a6ff7b5f74169a3a27530a75eb747
record_format	dspace
spelling	oai:doaj.org-article:cc3a6ff7b5f74169a3a27530a75eb7472021-12-02T14:06:12ZAggregation of cohorts for histopathological diagnosis with deep morphological analysis10.1038/s41598-021-82642-12045-2322https://doaj.org/article/cc3a6ff7b5f74169a3a27530a75eb7472021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-82642-1https://doaj.org/toc/2045-2322Abstract There have been substantial efforts in using deep learning (DL) to diagnose cancer from digital images of pathology slides. Existing algorithms typically operate by training deep neural networks either specialized in specific cohorts or an aggregate of all cohorts when there are only a few images available for the target cohort. A trade-off between decreasing the number of models and their cancer detection performance was evident in our experiments with The Cancer Genomic Atlas dataset, with the former approach achieving higher performance at the cost of having to acquire large datasets from the cohort of interest. Constructing annotated datasets for individual cohorts is extremely time-consuming, with the acquisition cost of such datasets growing linearly with the number of cohorts. Another issue associated with developing cohort-specific models is the difficulty of maintenance: all cohort-specific models may need to be adjusted when a new DL algorithm is to be used, where training even a single model may require a non-negligible amount of computation, or when more data is added to some cohorts. In resolving the sub-optimal behavior of a universal cancer detection model trained on an aggregate of cohorts, we investigated how cohorts can be grouped to augment a dataset without increasing the number of models linearly with the number of cohorts. This study introduces several metrics which measure the morphological similarities between cohort pairs and demonstrates how the metrics can be used to control the trade-off between performance and the number of models.Jeonghyuk ParkYul Ri ChungSeo Taek KongYeong Won KimHyunho ParkKyungdoc KimDong-Il KimKyu-Hwan JungNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jeonghyuk Park Yul Ri Chung Seo Taek Kong Yeong Won Kim Hyunho Park Kyungdoc Kim Dong-Il Kim Kyu-Hwan Jung Aggregation of cohorts for histopathological diagnosis with deep morphological analysis
description	Abstract There have been substantial efforts in using deep learning (DL) to diagnose cancer from digital images of pathology slides. Existing algorithms typically operate by training deep neural networks either specialized in specific cohorts or an aggregate of all cohorts when there are only a few images available for the target cohort. A trade-off between decreasing the number of models and their cancer detection performance was evident in our experiments with The Cancer Genomic Atlas dataset, with the former approach achieving higher performance at the cost of having to acquire large datasets from the cohort of interest. Constructing annotated datasets for individual cohorts is extremely time-consuming, with the acquisition cost of such datasets growing linearly with the number of cohorts. Another issue associated with developing cohort-specific models is the difficulty of maintenance: all cohort-specific models may need to be adjusted when a new DL algorithm is to be used, where training even a single model may require a non-negligible amount of computation, or when more data is added to some cohorts. In resolving the sub-optimal behavior of a universal cancer detection model trained on an aggregate of cohorts, we investigated how cohorts can be grouped to augment a dataset without increasing the number of models linearly with the number of cohorts. This study introduces several metrics which measure the morphological similarities between cohort pairs and demonstrates how the metrics can be used to control the trade-off between performance and the number of models.
format	article
author	Jeonghyuk Park Yul Ri Chung Seo Taek Kong Yeong Won Kim Hyunho Park Kyungdoc Kim Dong-Il Kim Kyu-Hwan Jung
author_facet	Jeonghyuk Park Yul Ri Chung Seo Taek Kong Yeong Won Kim Hyunho Park Kyungdoc Kim Dong-Il Kim Kyu-Hwan Jung
author_sort	Jeonghyuk Park
title	Aggregation of cohorts for histopathological diagnosis with deep morphological analysis
title_short	Aggregation of cohorts for histopathological diagnosis with deep morphological analysis
title_full	Aggregation of cohorts for histopathological diagnosis with deep morphological analysis
title_fullStr	Aggregation of cohorts for histopathological diagnosis with deep morphological analysis
title_full_unstemmed	Aggregation of cohorts for histopathological diagnosis with deep morphological analysis
title_sort	aggregation of cohorts for histopathological diagnosis with deep morphological analysis
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/cc3a6ff7b5f74169a3a27530a75eb747
work_keys_str_mv	AT jeonghyukpark aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT yulrichung aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT seotaekkong aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT yeongwonkim aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT hyunhopark aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT kyungdockim aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT dongilkim aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis AT kyuhwanjung aggregationofcohortsforhistopathologicaldiagnosiswithdeepmorphologicalanalysis
_version_	1718392050176491520

Aggregation of cohorts for histopathological diagnosis with deep morphological analysis

Ejemplares similares