Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma
Abstract The study aimed to develop an AI-assisted ultrasound model for early liver trauma identification, using data from Bama miniature pigs and patients in Beijing, China. A deep learning model was created and fine-tuned with animal and clinical data, achieving high accuracy metrics. In internal...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-91900-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238373728780288 |
|---|---|
| author | Qing Song Xuelei He Yanjie Wang Hanjing Gao Li Tan Jun Ma Linli Kang Peng Han Yukun Luo Kun Wang |
| author_facet | Qing Song Xuelei He Yanjie Wang Hanjing Gao Li Tan Jun Ma Linli Kang Peng Han Yukun Luo Kun Wang |
| author_sort | Qing Song |
| collection | DOAJ |
| description | Abstract The study aimed to develop an AI-assisted ultrasound model for early liver trauma identification, using data from Bama miniature pigs and patients in Beijing, China. A deep learning model was created and fine-tuned with animal and clinical data, achieving high accuracy metrics. In internal tests, the model outperformed both Junior and Senior sonographers. External tests showed the model’s effectiveness, with a Dice Similarity Coefficient of 0.74, True Positive Rate of 0.80, Positive Predictive Value of 0.74, and 95% Hausdorff distance of 14.84. The model’s performance was comparable to Junior sonographers and slightly lower than Senior sonographers. This AI model shows promise for liver injury detection, offering a valuable tool with diagnostic capabilities similar to those of less experienced human operators. |
| format | Article |
| id | doaj-art-82a44416f4274065856bd1de6f2d9cac |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-82a44416f4274065856bd1de6f2d9cac2025-08-20T04:01:36ZengNature PortfolioScientific Reports2045-23222025-07-011511910.1038/s41598-025-91900-5Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver traumaQing Song0Xuelei He1Yanjie Wang2Hanjing Gao3Li Tan4Jun Ma5Linli Kang6Peng Han7Yukun Luo8Kun Wang9Department of Ultrasound, First Medical Center of General Hospital of Chinese PLASchool of Information Sciences and Technology, Northwest UniversityDepartment of Ultrasound, Shandong Province Maternal and Child Health Care HospitalDepartment of Ultrasound, Second Medical Center, General Hospital of Chinese PLABeijing Da Wang Lu Emergency HospitalDepartment of Ultrasound, First Medical Center of General Hospital of Chinese PLADepartment of Ultrasound, First Medical Center of General Hospital of Chinese PLADepartment of Ultrasound, First Medical Center of General Hospital of Chinese PLADepartment of Ultrasound, First Medical Center of General Hospital of Chinese PLACAS Key Laboratory of Molecular Imaging, State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of SciencesAbstract The study aimed to develop an AI-assisted ultrasound model for early liver trauma identification, using data from Bama miniature pigs and patients in Beijing, China. A deep learning model was created and fine-tuned with animal and clinical data, achieving high accuracy metrics. In internal tests, the model outperformed both Junior and Senior sonographers. External tests showed the model’s effectiveness, with a Dice Similarity Coefficient of 0.74, True Positive Rate of 0.80, Positive Predictive Value of 0.74, and 95% Hausdorff distance of 14.84. The model’s performance was comparable to Junior sonographers and slightly lower than Senior sonographers. This AI model shows promise for liver injury detection, offering a valuable tool with diagnostic capabilities similar to those of less experienced human operators.https://doi.org/10.1038/s41598-025-91900-5Liver contusionsLacerationsDeep learningArtificial intelligenceAnimal modelsPredictive value of tests |
| spellingShingle | Qing Song Xuelei He Yanjie Wang Hanjing Gao Li Tan Jun Ma Linli Kang Peng Han Yukun Luo Kun Wang Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma Scientific Reports Liver contusions Lacerations Deep learning Artificial intelligence Animal models Predictive value of tests |
| title | Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma |
| title_full | Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma |
| title_fullStr | Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma |
| title_full_unstemmed | Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma |
| title_short | Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma |
| title_sort | clinical validation of ai assisted animal ultrasound models for diagnosis of early liver trauma |
| topic | Liver contusions Lacerations Deep learning Artificial intelligence Animal models Predictive value of tests |
| url | https://doi.org/10.1038/s41598-025-91900-5 |
| work_keys_str_mv | AT qingsong clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT xueleihe clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT yanjiewang clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT hanjinggao clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT litan clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT junma clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT linlikang clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT penghan clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT yukunluo clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma AT kunwang clinicalvalidationofaiassistedanimalultrasoundmodelsfordiagnosisofearlylivertrauma |