A deep-learning algorithm could improve the imaging quality of Focused Assessment with Sonography in Trauma (FAST) among novice users, according to a report published March 28 in JAMA Network Open.
A team led by Dr. I-Min Chiu from National Sun Yat-sen University in Kaohsiung, Taiwan, found that artificial intelligence (AI) guidance improved FAST image quality scores among novices but also led to longer imaging times.
"Although initially it may take longer to complete an examination with AI guidance, it is expected that the learning curve will be lower for novices practicing FAST," Chiu and colleagues wrote.
FAST could help with shorter time to operative care, shortened hospital length of stay, and lower medical costs as indicated in previous reports. However, the researchers pointed out ultrasound's high operator dependence, as well as FAST being "among the hardest protocols" for interpreting the acquired images.
Chiu and colleagues wanted to see if AI guidance could lead to higher quality of FAST exams as performed by novice ultrasonography users.
They recruited 30 operators for the study. These included 10 registered nurses, 10 nurse practitioners, and 10 emergency medical technicians (EMTs) without prior experience in performing ultrasonography. After receiving training on how to perform the FAST exam, the participants were randomized to a group that included or did not include AI guidance. The operators were told to perform FAST examination over the Morrison pouch in 10 healthy patients in the same order to obtain a five-second clip of the standard view within three minutes.
The operators created a total of 300 ultrasonography scans. The researchers reported that the intraclass correlation coefficient (ICC) for diagnostic quality scores was 0.97, indicating "excellent" reliability. The team found that AI guidance led to higher quality scores among operators.
| Performance of operators working on FAST exam with vs. without AI guidance | |||
| Without AI guidance | With AI guidance | p-value | |
| Median quality score | 4 | 5 | 0.02 |
| Average rate of acceptable quality score | 102 | 126 | 0.002 |
The team also found that AI guidance was tied to a higher quality score with an odds ratio (OR) of 0.40 (p = 0.005), as well as a higher rate of acceptable quality with an OR of 3.82 (p < 0.001).
Additionally, it also found that AI guidance was significantly associated with longer examination time with an OR of 14.36 (p = 0.02). The researchers noted that this trend was "mostly observed" in the first few rounds of operations.
Finally, in subgroup analysis, nurse practitioners and EMTs benefitted most from AI guidance. Both groups had acceptable quality rates exceeding 0.8 on a 0-to-1 scale. These subgroups without AI guidance each had quality rates just above 0.6. Although the nurses showed slight improvement with AI guidance, this did not achieve statistical significance.
The study authors called for further research in clinical deployment, writing that this will help fully evaluate AI's potential benefits in helping manage patients with traumatic injury.
![Examples of ultrasound findings and techniques. (A) Images in a 39-year-old male patient with a mass in the left thigh. The mass is heterogeneous on the B-mode US image (compared with the patient in D) and showed increased microvascularity (superb microvascular imaging [SMI]) and shear-wave elastography (SWE) values. Undifferentiated pleomorphic sarcoma was diagnosed at biopsy (with pleomorphic rhabdomyosarcoma in surgical specimen). (B) Images in an 18-year-old male patient with a mass in the left leg. The mass is hypoechoic on the B-mode image, with no other findings suggestive of malignancy. The lesion is in contact with the cortex of the tibia, which is slightly irregular. CT revealed a doubtful anteromedial tibial erosion. The microvascular study demonstrated high vascularization, suggestive of malignancy. Periosteal Ewing sarcoma was diagnosed with both histologic and immunohistochemical confirmation. (C) Images in a 69-year-old female patient with a lump growing on the outside of the left leg. Multiple SWE examinations were performed (please note the high values obtained in the measurements, whereas the color map highlights the stiffness relative to adjacent tissues). SMI showed areas of increased vascularization to target for sampling. Undifferentiated spindle cell sarcoma was diagnosed at biopsy, with residual leiomyosarcoma in the surgical specimen after neoadjuvant therapy. (D) Images in a 56-year-old female patient with a mass in the right thigh. The mass is heterogeneous at both B-mode ultrasound (similar to patient A) and MRI (coronal T2-weighted spectral attenuated inversion recovery [SPAIR]; T1-weighted pre-contrast and postcontrast imaging), which even shows uptake after the administration of paramagnetic contrast material, which is traditionally suggestive of malignancy. Low values at SMI and elastography are suggestive of benignity. Spindle cell lipoma was diagnosed at biopsy, with atypical spindle cell lipomatous tumor in the surgical specimen.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/08/images-radiol250278fig2.APCFLSvX6p.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
