Detection and Semantic Segmentation of Rib Fractures using a Convolutional Neural Network Approach

Zineddine N. Haitaamar; Nidhal Abdulaziz

doi:10.1109/TENSYMP52854.2021.9550883

Detection and Semantic Segmentation of Rib Fractures using a Convolutional Neural Network Approach

Zineddine N. Haitaamar
, Nidhal Abdulaziz

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

Rib Fractures are one of the most common bone injuries that can occur. Over 3 million cases are diagnosed in the United States alone yearly making it a very common fracture. Causes are usually from chest trauma such as falls and sports accidents. The detection of Rib Fractures is a common task in clinics and a labor-intensive such that a specialist radiologist is required to detect rib fractures. The proposed solution looks at processing CT Scans containing rib fractures with an Attention U-Net CNN Architecture. The system achieved a segmentation dice of 77.46% and an IoU of 63.21% with an improvement of 5.96% and 7.61% respectively from the currently published paper.

Original language	English
Title of host publication	2021 IEEE Region 10 Symposium
Publisher	IEEE
ISBN (Electronic)	9781665400268
DOIs	https://doi.org/10.1109/TENSYMP52854.2021.9550883
Publication status	Published - 4 Oct 2021
Event	2021 IEEE Region 10 Symposium - Jeju, Korea, Republic of Duration: 23 Aug 2021 → 25 Aug 2021

Conference

Conference	2021 IEEE Region 10 Symposium
Abbreviated title	TENSYMP 2021
Country/Territory	Korea, Republic of
City	Jeju
Period	23/08/21 → 25/08/21

Keywords

Bone Fracture
Convolutional Neural Networks
Image Processing
Rib Fracture
U-Net

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems and Management
Computer Networks and Communications
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/TENSYMP52854.2021.9550883

Cite this

@inproceedings{e9e628ec6e734ba7adf72191cb16e75a,

title = "Detection and Semantic Segmentation of Rib Fractures using a Convolutional Neural Network Approach",

abstract = "Rib Fractures are one of the most common bone injuries that can occur. Over 3 million cases are diagnosed in the United States alone yearly making it a very common fracture. Causes are usually from chest trauma such as falls and sports accidents. The detection of Rib Fractures is a common task in clinics and a labor-intensive such that a specialist radiologist is required to detect rib fractures. The proposed solution looks at processing CT Scans containing rib fractures with an Attention U-Net CNN Architecture. The system achieved a segmentation dice of 77.46\% and an IoU of 63.21\% with an improvement of 5.96\% and 7.61\% respectively from the currently published paper.",

keywords = "Bone Fracture, Convolutional Neural Networks, Image Processing, Rib Fracture, U-Net",

author = "Haitaamar, \{Zineddine N.\} and Nidhal Abdulaziz",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Region 10 Symposium, TENSYMP 2021 ; Conference date: 23-08-2021 Through 25-08-2021",

year = "2021",

month = oct,

day = "4",

doi = "10.1109/TENSYMP52854.2021.9550883",

language = "English",

booktitle = "2021 IEEE Region 10 Symposium",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Detection and Semantic Segmentation of Rib Fractures using a Convolutional Neural Network Approach

AU - Haitaamar, Zineddine N.

AU - Abdulaziz, Nidhal

PY - 2021/10/4

Y1 - 2021/10/4

N2 - Rib Fractures are one of the most common bone injuries that can occur. Over 3 million cases are diagnosed in the United States alone yearly making it a very common fracture. Causes are usually from chest trauma such as falls and sports accidents. The detection of Rib Fractures is a common task in clinics and a labor-intensive such that a specialist radiologist is required to detect rib fractures. The proposed solution looks at processing CT Scans containing rib fractures with an Attention U-Net CNN Architecture. The system achieved a segmentation dice of 77.46% and an IoU of 63.21% with an improvement of 5.96% and 7.61% respectively from the currently published paper.

AB - Rib Fractures are one of the most common bone injuries that can occur. Over 3 million cases are diagnosed in the United States alone yearly making it a very common fracture. Causes are usually from chest trauma such as falls and sports accidents. The detection of Rib Fractures is a common task in clinics and a labor-intensive such that a specialist radiologist is required to detect rib fractures. The proposed solution looks at processing CT Scans containing rib fractures with an Attention U-Net CNN Architecture. The system achieved a segmentation dice of 77.46% and an IoU of 63.21% with an improvement of 5.96% and 7.61% respectively from the currently published paper.

KW - Bone Fracture

KW - Convolutional Neural Networks

KW - Image Processing

KW - Rib Fracture

KW - U-Net

UR - https://www.scopus.com/pages/publications/85117523499

U2 - 10.1109/TENSYMP52854.2021.9550883

DO - 10.1109/TENSYMP52854.2021.9550883

M3 - Conference contribution

AN - SCOPUS:85117523499

BT - 2021 IEEE Region 10 Symposium

PB - IEEE

T2 - 2021 IEEE Region 10 Symposium

Y2 - 23 August 2021 through 25 August 2021

ER -

Detection and Semantic Segmentation of Rib Fractures using a Convolutional Neural Network Approach

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this