1. Repositório Institucional da UFMG
2. Publicações Científicas e Culturais
3. Artigo de Periódico

Type:	Artigo de Periódico
Title:	Building Efficient CNN Architectures for Histopathology Images Analysis: A Case-Study in Tumor-Infiltrating Lymphocytes Classification
Authors:	André L. S. Meirelles Tahsin Kurc Jun Kong Renato Antonio Celso Ferreira Joel H. Saltz George Teodoro
Abstract:	Background: 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.
Subject:	Apendizado do computador Tumores Linfócitos Aprendizado profundo (Aprendizado do computador)
language:	eng
metadata.dc.publisher.country:	Brasil
Publisher:	Universidade Federal de Minas Gerais
Publisher Initials:	UFMG
metadata.dc.publisher.department:	ICEX - INSTITUTO DE CIÊNCIAS EXATAS ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO
Rights:	Acesso Aberto
metadata.dc.identifier.doi:	https://doi.org/10.3389/fmed.2022.894430
URI:	http://hdl.handle.net/1843/61019
Issue Date:	31-May-2022
metadata.dc.url.externa:	https://www.frontiersin.org/articles/10.3389/fmed.2022.894430/full
metadata.dc.relation.ispartof:	Frontiers in Medicine
Appears in Collections:	Artigo de Periódico

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.