Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

Abstract Fast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Young-Gon Kim, Sungchul Kim, Cristina Eunbee Cho, In Hye Song, Hee Jin Lee, Soomin Ahn, So Yeon Park, Gyungyub Gong, Namkug Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/3dd13c442152495286bae88305d66b5a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3dd13c442152495286bae88305d66b5a
record_format	dspace
spelling	oai:doaj.org-article:3dd13c442152495286bae88305d66b5a2021-12-02T12:42:17ZEffectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections10.1038/s41598-020-78129-02045-2322https://doaj.org/article/3dd13c442152495286bae88305d66b5a2020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78129-0https://doaj.org/toc/2045-2322Abstract Fast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.Young-Gon KimSungchul KimCristina Eunbee ChoIn Hye SongHee Jin LeeSoomin AhnSo Yeon ParkGyungyub GongNamkug KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-9 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Young-Gon Kim Sungchul Kim Cristina Eunbee Cho In Hye Song Hee Jin Lee Soomin Ahn So Yeon Park Gyungyub Gong Namkug Kim Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
description	Abstract Fast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.
format	article
author	Young-Gon Kim Sungchul Kim Cristina Eunbee Cho In Hye Song Hee Jin Lee Soomin Ahn So Yeon Park Gyungyub Gong Namkug Kim
author_facet	Young-Gon Kim Sungchul Kim Cristina Eunbee Cho In Hye Song Hee Jin Lee Soomin Ahn So Yeon Park Gyungyub Gong Namkug Kim
author_sort	Young-Gon Kim
title	Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
title_short	Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
title_full	Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
title_fullStr	Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
title_full_unstemmed	Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
title_sort	effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/3dd13c442152495286bae88305d66b5a
work_keys_str_mv	AT younggonkim effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT sungchulkim effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT cristinaeunbeecho effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT inhyesong effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT heejinlee effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT soominahn effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT soyeonpark effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT gyungyubgong effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections AT namkugkim effectivenessoftransferlearningforenhancingtumorclassificationwithaconvolutionalneuralnetworkonfrozensections
_version_	1718393679731752960

Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

Ejemplares similares