Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning

Kainz B, Heinrich MP, Makropoulos A, Oppenheimer J, Mandegaran R, Sankar S, Deane C, Mischkewitz S, Al-Noor F, Rawdin AC, Ruttloff A, Klein-Weigel PF, Stevenson MD, Curry N (2021)

Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2021


Book Volume: 4

Pages Range: 1-20

Article Number: 137

Journal Issue: 1


DOI: 10.1038/s41746-021-00503-7

Open Access Link:


Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to have a DVT, resulting in long referral waiting times for patients and a large clinical burden for specialists. Thus, diagnosis at the point of care by non-specialists is desired. We collect images in a pre-clinical study and investigate a deep learning approach for the automatic interpretation of compression ultrasound images. Our method provides guidance for free-hand ultrasound and aids non-specialists in detecting DVT. We train a deep learning algorithm on ultrasound videos from 255 volunteers and evaluate on a sample size of 53 prospectively enrolled patients from an NHS DVT diagnostic clinic and 30 prospectively enrolled patients from a German DVT clinic. Algorithmic DVT diagnosis performance results in a sensitivity within a 95% CI range of (0.82, 0.94), specificity of (0.70, 0.82), a positive predictive value of (0.65, 0.89), and a negative predictive value of (0.99, 1.00) when compared to the clinical gold standard. To assess the potential benefits of this technology in healthcare we evaluate the entire clinical DVT decision algorithm and provide cost analysis when integrating our approach into diagnostic pathways for DVT. Our approach is estimated to generate a positive net monetary benefit at costs up to 72 pound to 175 pound per software-supported examination, assuming a willingness to pay of 20,000 pound/QALY.

Authors with CRIS profile

Involved external institutions

How to cite


Kainz, B., Heinrich, M.P., Makropoulos, A., Oppenheimer, J., Mandegaran, R., Sankar, S.,... Curry, N. (2021). Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. npj Digital Medicine, 4(1), 1-20.


Kainz, Bernhard, et al. "Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning." npj Digital Medicine 4.1 (2021): 1-20.

BibTeX: Download