Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward

<b>Background/Objectives:</b> The accurate assessment of aortic diameter (AoD) is essential in managing patients with traumatic hemorrhage, particularly during interventions such as resuscitative endovascular balloon occlusion of the aorta (REBOA). Manual AoD measurements are time-consum...

Full description

Saved in:
Bibliographic Details
Main Authors: Yoonjung Heo, Go-Eun Lee, Jungchan Cho, Sang-Il Choi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/11/1312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160461105856512
author Yoonjung Heo
Go-Eun Lee
Jungchan Cho
Sang-Il Choi
author_facet Yoonjung Heo
Go-Eun Lee
Jungchan Cho
Sang-Il Choi
author_sort Yoonjung Heo
collection DOAJ
description <b>Background/Objectives:</b> The accurate assessment of aortic diameter (AoD) is essential in managing patients with traumatic hemorrhage, particularly during interventions such as resuscitative endovascular balloon occlusion of the aorta (REBOA). Manual AoD measurements are time-consuming and subject to inter-observer variability. This study aimed to develop and validate a deep learning (DL) model for automated AoD measurement in trauma patients requiring massive transfusion. <b>Methods:</b> Abdominal CT scans from 300 adult patients were retrospectively analyzed. A Shallow Attention Network was trained on 444 manually annotated axial CT images to segment the aorta and measure its diameter. An ellipse-based calibration method was employed for enhanced measurement accuracy. <b>Results:</b> The model achieved a mean Dice coefficient of 0.865 and an intersection over union of 0.9988. After calibration, the mean discrepancy between predicted and ground truth diameters was 2.11 mm. The median diaphragmatic AoD was 22.59 mm (interquartile range: 20.18–24.74 mm). <b>Conclusions:</b> The proposed DL model with ellipse-based calibration demonstrated robust performance in automated AoD measurement and may facilitate timely planning of aortic interventions in trauma care.
format Article
id doaj-art-3e914f9fb9bc4853a210e4583e40e82b
institution OA Journals
issn 2075-4418
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-3e914f9fb9bc4853a210e4583e40e82b2025-08-20T02:23:08ZengMDPI AGDiagnostics2075-44182025-05-011511131210.3390/diagnostics15111312Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path ForwardYoonjung Heo0Go-Eun Lee1Jungchan Cho2Sang-Il Choi3Division of Trauma Surgery, Department of Surgery, Dankook University College of Medicine, Cheonan-si 31116, Republic of KoreaDepartment of Computer Science and Engineering, Dankook University, Yongin-si 16890, Republic of KoreaDepartment of Computing, Gachon University, Seongnam-si 13120, Republic of KoreaDepartment of Computer Science and Engineering, Dankook University, Yongin-si 16890, Republic of Korea<b>Background/Objectives:</b> The accurate assessment of aortic diameter (AoD) is essential in managing patients with traumatic hemorrhage, particularly during interventions such as resuscitative endovascular balloon occlusion of the aorta (REBOA). Manual AoD measurements are time-consuming and subject to inter-observer variability. This study aimed to develop and validate a deep learning (DL) model for automated AoD measurement in trauma patients requiring massive transfusion. <b>Methods:</b> Abdominal CT scans from 300 adult patients were retrospectively analyzed. A Shallow Attention Network was trained on 444 manually annotated axial CT images to segment the aorta and measure its diameter. An ellipse-based calibration method was employed for enhanced measurement accuracy. <b>Results:</b> The model achieved a mean Dice coefficient of 0.865 and an intersection over union of 0.9988. After calibration, the mean discrepancy between predicted and ground truth diameters was 2.11 mm. The median diaphragmatic AoD was 22.59 mm (interquartile range: 20.18–24.74 mm). <b>Conclusions:</b> The proposed DL model with ellipse-based calibration demonstrated robust performance in automated AoD measurement and may facilitate timely planning of aortic interventions in trauma care.https://www.mdpi.com/2075-4418/15/11/1312aortatraumahemorrhagecomputed tomographydeep learningimage segmentation
spellingShingle Yoonjung Heo
Go-Eun Lee
Jungchan Cho
Sang-Il Choi
Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward
Diagnostics
aorta
trauma
hemorrhage
computed tomography
deep learning
image segmentation
title Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward
title_full Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward
title_fullStr Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward
title_full_unstemmed Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward
title_short Deep Learning-Based Aortic Diameter Measurement in Traumatic Hemorrhage Using Shallow Attention Network: A Path Forward
title_sort deep learning based aortic diameter measurement in traumatic hemorrhage using shallow attention network a path forward
topic aorta
trauma
hemorrhage
computed tomography
deep learning
image segmentation
url https://www.mdpi.com/2075-4418/15/11/1312
work_keys_str_mv AT yoonjungheo deeplearningbasedaorticdiametermeasurementintraumatichemorrhageusingshallowattentionnetworkapathforward
AT goeunlee deeplearningbasedaorticdiametermeasurementintraumatichemorrhageusingshallowattentionnetworkapathforward
AT jungchancho deeplearningbasedaorticdiametermeasurementintraumatichemorrhageusingshallowattentionnetworkapathforward
AT sangilchoi deeplearningbasedaorticdiametermeasurementintraumatichemorrhageusingshallowattentionnetworkapathforward