Building Efficient CNN Architectures for Histopathology Images Analysis: A Case-Study in Tumor-Infiltrating Lymphocytes Classification

Página do item simplificado
dc.creatorAndré L. S. Meirelles
dc.creatorTahsin Kurc
dc.creatorJun Kong
dc.creatorRenato Antonio Celso Ferreira
dc.creatorJoel H. Saltz
dc.creatorGeorge Teodoro
dc.date.accessioned2023-11-16T21:23:05Z
dc.date.accessioned2025-09-09T00:26:48Z
dc.date.available2023-11-16T21:23:05Z
dc.date.issued2022-05-31
dc.description.sponsorshipCNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico
dc.description.sponsorshipFAPEMIG - Fundação de Amparo à Pesquisa do Estado de Minas Gerais
dc.description.sponsorshipCAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
dc.format.mimetypepdf
dc.identifier.doihttps://doi.org/10.3389/fmed.2022.894430
dc.identifier.issn2296-858X
dc.identifier.urihttps://hdl.handle.net/1843/61019
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofFrontiers in Medicine
dc.rightsAcesso Aberto
dc.subjectApendizado do computador
dc.subjectTumores
dc.subjectLinfócitos
dc.subjectAprendizado profundo (Aprendizado do computador)
dc.subject.otherDigital pathology
dc.subject.otherDeep learning
dc.subject.otherCNN simplification
dc.subject.otherTumor-infiltrating lymphocytes
dc.subject.otherEfficient CNNs
dc.titleBuilding Efficient CNN Architectures for Histopathology Images Analysis: A Case-Study in Tumor-Infiltrating Lymphocytes Classification
dc.typeArtigo de periódico
local.citation.epage10
local.citation.spage894430
local.citation.volume9
local.description.resumoBackground: Deep learning methods have demonstrated remarkable performance in pathology image analysis, but they are computationally very demanding. The aim of our study is to reduce their computational cost to enable their use with large tissue image datasets. Methods: We propose a method called Network Auto-Reduction (NAR) that simplifies a Convolutional Neural Network (CNN) by reducing the network to minimize the computational cost of doing a prediction. NAR performs a compound scaling in which the width, depth, and resolution dimensions of the network are reduced together to maintain a balance among them in the resulting simplified network. We compare our method with a state-of-the-art solution called ResRep. The evaluation is carried out with popular CNN architectures and a real-world application that identifies distributions of tumor-infiltrating lymphocytes in tissue images. Results: The experimental results show that both ResRep and NAR are able to generate simplified, more efficient versions of ResNet50 V2. The simplified versions by ResRep and NAR require 1.32× and 3.26× fewer floating-point operations (FLOPs), respectively, than the original network without a loss in classification power as measured by the Area under the Curve (AUC) metric. When applied to a deeper and more computationally expensive network, Inception V4, NAR is able to generate a version that requires 4× lower than the original version with the same AUC performance. Conclusions: NAR is able to achieve substantial reductions in the execution cost of two popular CNN architectures, while resulting in small or no loss in model accuracy. Such cost savings can significantly improve the use of deep learning methods in digital pathology. They can enable studies with larger tissue image datasets and facilitate the use of less expensive and more accessible graphics processing units (GPUs), thus reducing the computing costs of a study.
local.identifier.orcidhttps://orcid.org/0000-0002-4372-8996
local.publisher.countryBrasil
local.publisher.departmentICEX - INSTITUTO DE CIÊNCIAS EXATAS
local.publisher.departmentICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO
local.publisher.initialsUFMG
local.url.externahttps://www.frontiersin.org/articles/10.3389/fmed.2022.894430/full

Arquivos

Pacote original

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
Building Efficient CNN Architectures for Histopathology Images Analysis_ A Case-Study in Tumor-Infiltrating Lymphocytes Classification.pdf
Tamanho:
648.18 KB
Formato:
Adobe Portable Document Format
Baixar

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
1.99 KB
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG