Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box

Early pulmonary nodule detection is very important in lung cancer diagnosis and screening. Most state-of-the-art lung nodule detection models are based on Faster Region-based Convolutional Neural Network (Faster R-CNN) due to its superior performance. However, this object detection approach faces di...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chi Cuong Nguyen, Giang Son Tran, Van Thi Nguyen, Jean-Christophe Burie, Thi Phuong Nghiem
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Pulmonary nodules CT~images deep learning faster R-CNN anchor box Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/2f1d402462bb4f639d64987fa105086c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2f1d402462bb4f639d64987fa105086c
record_format	dspace
spelling	oai:doaj.org-article:2f1d402462bb4f639d64987fa105086c2021-11-25T00:00:52ZPulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box2169-353610.1109/ACCESS.2021.3128942https://doaj.org/article/2f1d402462bb4f639d64987fa105086c2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9619980/https://doaj.org/toc/2169-3536Early pulmonary nodule detection is very important in lung cancer diagnosis and screening. Most state-of-the-art lung nodule detection models are based on Faster Region-based Convolutional Neural Network (Faster R-CNN) due to its superior performance. However, this object detection approach faces difficulties with the variety of nodule sizes in training datasets. In this paper, we propose a novel Computer-Aided Detection (CAD) system based on Faster R-CNN model with adaptive anchor box for lung nodule detection. Our method employs ground-truth nodule sizes in the training dataset to generate adaptive anchor box sizes of Faster R-CNN. Learned anchors are used as hyper-parameter to boost Faster R-CNN’s detection performance. A residual convolutional neural network is proposed to reduce false positives from Faster R-CNN’s output. Our method is trained and tested on the largest publicly available LUNA16 dataset. Experiments show that our proposed system achieves a high sensitivity of 95.64% at 1.72 false positives per scan, and a Competition Performance Metric (CPM) score of 88.2%, which outperforms other recent state-of-the-art detection methods. The false positive reduction network achieves a sensitivity of 93.8%, specificity of 97.6% and accuracy of 95.7%. An additional evaluation on a completely independent SPIE-AAPM dataset demonstrates the generalization of our proposed model with 89.3% sensitivity.Chi Cuong NguyenGiang Son TranVan Thi NguyenJean-Christophe BurieThi Phuong NghiemIEEEarticlePulmonary nodulesCT~imagesdeep learningfaster R-CNNanchor boxElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 154740-154751 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Pulmonary nodules CT~images deep learning faster R-CNN anchor box Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Pulmonary nodules CT~images deep learning faster R-CNN anchor box Electrical engineering. Electronics. Nuclear engineering TK1-9971 Chi Cuong Nguyen Giang Son Tran Van Thi Nguyen Jean-Christophe Burie Thi Phuong Nghiem Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
description	Early pulmonary nodule detection is very important in lung cancer diagnosis and screening. Most state-of-the-art lung nodule detection models are based on Faster Region-based Convolutional Neural Network (Faster R-CNN) due to its superior performance. However, this object detection approach faces difficulties with the variety of nodule sizes in training datasets. In this paper, we propose a novel Computer-Aided Detection (CAD) system based on Faster R-CNN model with adaptive anchor box for lung nodule detection. Our method employs ground-truth nodule sizes in the training dataset to generate adaptive anchor box sizes of Faster R-CNN. Learned anchors are used as hyper-parameter to boost Faster R-CNN’s detection performance. A residual convolutional neural network is proposed to reduce false positives from Faster R-CNN’s output. Our method is trained and tested on the largest publicly available LUNA16 dataset. Experiments show that our proposed system achieves a high sensitivity of 95.64% at 1.72 false positives per scan, and a Competition Performance Metric (CPM) score of 88.2%, which outperforms other recent state-of-the-art detection methods. The false positive reduction network achieves a sensitivity of 93.8%, specificity of 97.6% and accuracy of 95.7%. An additional evaluation on a completely independent SPIE-AAPM dataset demonstrates the generalization of our proposed model with 89.3% sensitivity.
format	article
author	Chi Cuong Nguyen Giang Son Tran Van Thi Nguyen Jean-Christophe Burie Thi Phuong Nghiem
author_facet	Chi Cuong Nguyen Giang Son Tran Van Thi Nguyen Jean-Christophe Burie Thi Phuong Nghiem
author_sort	Chi Cuong Nguyen
title	Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
title_short	Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
title_full	Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
title_fullStr	Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
title_full_unstemmed	Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box
title_sort	pulmonary nodule detection based on faster r-cnn with adaptive anchor box
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/2f1d402462bb4f639d64987fa105086c
work_keys_str_mv	AT chicuongnguyen pulmonarynoduledetectionbasedonfasterrcnnwithadaptiveanchorbox AT giangsontran pulmonarynoduledetectionbasedonfasterrcnnwithadaptiveanchorbox AT vanthinguyen pulmonarynoduledetectionbasedonfasterrcnnwithadaptiveanchorbox AT jeanchristopheburie pulmonarynoduledetectionbasedonfasterrcnnwithadaptiveanchorbox AT thiphuongnghiem pulmonarynoduledetectionbasedonfasterrcnnwithadaptiveanchorbox
_version_	1718414687015534592

Pulmonary Nodule Detection Based on Faster R-CNN With Adaptive Anchor Box

Ejemplares similares