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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |