Please use this identifier to cite or link to this item: https://observatorio.fm.usp.br/handle/OPI/40292
Title: Multi-View Ensemble Convolutional Neural Network to Improve Classification of Pneumonia in Low Contrast Chest X-Ray Images
Authors: FERREIRA JUNIOR, Jose RanieryCARDENAS, Diego Armando CardonaMORENO, Ramon AlfredoREBELO, Marina de Fatima de SaKRIEGER, Jose EduardoGUTIERREZ, Marco Antonio
Citation: 42ND ANNUAL INTERNATIONAL CONFERENCES OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY: ENABLING INNOVATIVE TECHNOLOGIES FOR GLOBAL HEALTHCARE EMBC'20, p.1238-1241, 2020
Abstract: Pneumonia is one of the leading causes of childhood mortality worldwide. Chest x-ray (CXR) can aid the diagnosis of pneumonia, but in the case of low contrast images, it is important to include computational tools to aid specialists. Deep learning is an alternative because it can identify patterns automatically, even in low-resolution images. We propose herein a convolutional neural network (CNN) architecture with different training strategies towards detecting pneumonia on CXRs and distinguishing its subforms of bacteria and virus. We also evaluated different image pre-processing methods to improve the classification. This study used CXRs from pediatric patients from a public pneumonia CXR dataset. The pre-processing methods evaluated were image cropping and histogram equalization. To classify the images, we adopted the VGG16 CNN and replaced its fully-connected layers with a customized multilayer perceptron. With this architecture, we proposed and evaluated four different training strategies: original CXR image (baseline), chest-cavity-cropped image (A), and histogram-equalized segmented image (B). The last strategy method (C) implemented is based on ensemble between strategies A and B. The performance was assessed by the area under the ROC curve (AUC) with 95% confidence interval (CI), accuracy, sensitivity, specificity, and F1-score. The ensemble model C yielded the highest performances: AUC of 0.97 (CI: 0.96-0.99) to classify pneumonia vs. normal, and AUC of 0.91 (CI: 0.88-0.94) to classify bacterial vs. viral cases. All models that used pre-processed images showed higher AUC than baseline, which used the original CXR image. Image cropping and histogram equalization reduced irrelevant information from the exam, enhanced contrast, and was able to identify fine CXR texture details. The proposed ensemble model increased the representation of inflammatory patterns from bacteria and viruses with few epochs to train the deep CNNs.
Appears in Collections:

Comunicações em Eventos - FM/MCP
Departamento de Cardio-Pneumologia - FM/MCP

Comunicações em Eventos - HC/InCor
Instituto do Coração - HC/InCor

Comunicações em Eventos - LIM/13
LIM/13 - Laboratório de Genética e Cardiologia Molecular

Comunicações em Eventos - LIM/65
LIM/65 - Laboratório de Investigação Médica em Bioengenharia


Files in This Item:
File Description SizeFormat 
art_FERREIRA JUNIOR_MultiView_Ensemble_Convolutional_Neural_Network_to_Improve_Classification_2020.PDF
  Restricted Access
publishedVersion (English)1.21 MBAdobe PDFView/Open Request a copy

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