Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation
Thoracic injuries account for a high percentage of combat casualty mortalities, with 80% of preventable deaths resulting from abdominal or thoracic hemorrhage. An effective method for detecting and triaging thoracic injuries is point-of-care ultrasound (POCUS), as it is a cheap and portable noninvas...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/7/222 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849246319097413632 |
|---|---|
| author | Austin J. Ruiz Sofia I. Hernández Torres Eric J. Snider |
| author_facet | Austin J. Ruiz Sofia I. Hernández Torres Eric J. Snider |
| author_sort | Austin J. Ruiz |
| collection | DOAJ |
| description | Thoracic injuries account for a high percentage of combat casualty mortalities, with 80% of preventable deaths resulting from abdominal or thoracic hemorrhage. An effective method for detecting and triaging thoracic injuries is point-of-care ultrasound (POCUS), as it is a cheap and portable noninvasive imaging method. POCUS image interpretation of pneumothorax (PTX) or hemothorax (HTX) injuries requires a skilled radiologist, which will likely not be available in austere situations where injury detection and triage are most critical. With the recent growth in artificial intelligence (AI) for healthcare, the hypothesis for this study is that deep learning (DL) models for classifying images as showing HTX or PTX injury, or being negative for injury can be developed for lowering the skill threshold for POCUS diagnostics on the future battlefield. Three-class deep learning classification AI models were developed using a motion-mode ultrasound dataset captured in animal study experiments from more than 25 swine subjects. Cluster analysis was used to define the “population” based on brightness, contrast, and kurtosis properties. A MobileNetV3 DL model architecture was tuned across a variety of hyperparameters, with the results ultimately being evaluated using images captured in real-time. Different hyperparameter configurations were blind-tested, resulting in models trained on filtered data having a real-time accuracy from 89 to 96%, as opposed to 78–95% when trained without filtering and optimization. The best model achieved a blind accuracy of 85% when inferencing on data collected in real-time, surpassing previous YOLOv8 models by 17%. AI models can be developed that are suitable for high performance in real-time for thoracic injury determination and are suitable for potentially addressing challenges with responding to emergency casualty situations and reducing the skill threshold for using and interpreting POCUS. |
| format | Article |
| id | doaj-art-5d9a7e0148ec487290c6ff9cd9d68003 |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-5d9a7e0148ec487290c6ff9cd9d680032025-08-20T03:58:31ZengMDPI AGJournal of Imaging2313-433X2025-07-0111722210.3390/jimaging11070222Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image InterpretationAustin J. Ruiz0Sofia I. Hernández Torres1Eric J. Snider2Organ Support and Automation Technologies Group, U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USAOrgan Support and Automation Technologies Group, U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USAOrgan Support and Automation Technologies Group, U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USAThoracic injuries account for a high percentage of combat casualty mortalities, with 80% of preventable deaths resulting from abdominal or thoracic hemorrhage. An effective method for detecting and triaging thoracic injuries is point-of-care ultrasound (POCUS), as it is a cheap and portable noninvasive imaging method. POCUS image interpretation of pneumothorax (PTX) or hemothorax (HTX) injuries requires a skilled radiologist, which will likely not be available in austere situations where injury detection and triage are most critical. With the recent growth in artificial intelligence (AI) for healthcare, the hypothesis for this study is that deep learning (DL) models for classifying images as showing HTX or PTX injury, or being negative for injury can be developed for lowering the skill threshold for POCUS diagnostics on the future battlefield. Three-class deep learning classification AI models were developed using a motion-mode ultrasound dataset captured in animal study experiments from more than 25 swine subjects. Cluster analysis was used to define the “population” based on brightness, contrast, and kurtosis properties. A MobileNetV3 DL model architecture was tuned across a variety of hyperparameters, with the results ultimately being evaluated using images captured in real-time. Different hyperparameter configurations were blind-tested, resulting in models trained on filtered data having a real-time accuracy from 89 to 96%, as opposed to 78–95% when trained without filtering and optimization. The best model achieved a blind accuracy of 85% when inferencing on data collected in real-time, surpassing previous YOLOv8 models by 17%. AI models can be developed that are suitable for high performance in real-time for thoracic injury determination and are suitable for potentially addressing challenges with responding to emergency casualty situations and reducing the skill threshold for using and interpreting POCUS.https://www.mdpi.com/2313-433X/11/7/222ultrasound imagingartificial intelligencedeep learningthoracicemergency medicinetrauma |
| spellingShingle | Austin J. Ruiz Sofia I. Hernández Torres Eric J. Snider Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation Journal of Imaging ultrasound imaging artificial intelligence deep learning thoracic emergency medicine trauma |
| title | Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation |
| title_full | Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation |
| title_fullStr | Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation |
| title_full_unstemmed | Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation |
| title_short | Development of Deep Learning Models for Real-Time Thoracic Ultrasound Image Interpretation |
| title_sort | development of deep learning models for real time thoracic ultrasound image interpretation |
| topic | ultrasound imaging artificial intelligence deep learning thoracic emergency medicine trauma |
| url | https://www.mdpi.com/2313-433X/11/7/222 |
| work_keys_str_mv | AT austinjruiz developmentofdeeplearningmodelsforrealtimethoracicultrasoundimageinterpretation AT sofiaihernandeztorres developmentofdeeplearningmodelsforrealtimethoracicultrasoundimageinterpretation AT ericjsnider developmentofdeeplearningmodelsforrealtimethoracicultrasoundimageinterpretation |