FDA Clears ThinkSono’s Ultrasound AI Guidance Software to Evaluate Suspected DVT

July 29, 2026—ThinkSono announced that the company’s ThinkSono Guidance software has received FDA 510(k) clearance that provides real-time guidance to nonultrasound-trained health care professionals during the acquisition of vascular ultrasound images. The company is preparing for commercial availability in the United States.

According to the company, ThinkSono Guidance is indicated for adult patients who require a lower extremity compression ultrasound examination for the evaluation of suspected deep vein thrombosis (DVT). The device received FDA Breakthrough Device designation in February 2026.

ThinkSono Guidance, which is available by prescription only, operates with the compatible FDA-cleared Clarius handheld point-of-care ultrasound scanner (Clarius Mobile Health), noted the company.

The mobile app connects to the scanner and uses an artificial intelligence algorithm to guide the operator in real time through probe positioning and the recording of venous compression cine-loops, so the anatomic sites relevant to lower extremity DVT are consistently imaged.

As noted in the press release, operators in clinical studies performed examinations after 60 to 90 minutes of standardized training. Recorded cine-loops were transmitted to the ThinkSono Guidance dashboard, where a remote qualified clinician grades image quality and assesses vein compressibility.

ThinkSono Guidance does not assist in the interpretation of ultrasound images, and all clinical decisions remain under the authority of the qualified clinician, advised the company.

The company stated that the clearance is supported by prospective, double-blinded, multicenter clinical investigations comparing ThinkSono Guidance examinationss performed by non-ultrasound-trained operators against reference-standard specialist duplex ultrasound.

In total, 1,691 patients were recruited across 24 United States and international sites, including 157 with confirmed DVTs. The pivotal United States study enrolled 594 patients across five sites.

The company also reported that findings from a pooled analysis showed the following:

• Examinations achieved adequate diagnostic image quality in 87.1% of cases, with a sensitivity of 92.9% (95% CI, 86.3-96.4%) and a prioritization specificity of 97.1% (95% CI, 94.6-98.5%).
• Median operator scan time was 5 minutes 24 seconds.
• Median remote review time was 2 minutes 13 seconds.
• Performance was consistent across demographic subgroups, including age, sex, body mass index, and race/ethnicity.