What is DVT?
Deep vein thrombosis (DVT) is a blood clot that forms within the deep vein in the body, most commonly in the leg. This can be potentially fatal if parts of the clot breaks off, travels through the body and becomes lodged in the lungs, this is known as a pulmonary embolism (PE).
PE and DVT together is called venous thromboembolism (VTE), and is considered a major cause of morbidity and mortality worldwide.
The current DVT diagnostic pathway is slow and inefficient. The standard way to detect a DVT is through a compression ultrasound exam, usually carried out by an expert (sonographer or radiologist).
However patients typically have multiple appointments, including a blood test and long wait times before they see the expert. Additionally, more than 80% of patients come back negative when investigated for DVT. This results in higher diagnostic costs and lower patient outcomes.
ThinkSono AI Solution
AutoDVT aims to enable non-radiology staff to also detect DVT by automatically guiding them through a compression ultrasound exam. The whole exam takes between 5 and 15 minutes using only a handheld device and a mobile phone.
With ThinkSono AI, the diagnosis can be done at the point of care, within 15minutes, and by non-radiology trained staff. This results in a shorter clinical pathway, lower diagnostic cost and improved patient outcomes.
Our Scientific Publications
Medical Image Computing and Computer Assisted Interventions – 2018
AutoDVT: Joint Real-time Classification for Vein Compressibility Analysis in Deep Vein Thrombosis Ultrasound Diagnostics.
Abstract: We propose a dual-task convolutional neural network (CNN) to fully automate the real-time diagnosis of deep vein thrombosis (DVT). DVT can be reliably diagnosed through evaluation of vascular compressibility at anatomically defined landmarks in streams of ultrasound (US) images.
Nature Digital Medicine (NPJ) – 2021
Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning
Abstract: 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 to £175 per software-supported examination, assuming a willingness to pay of £20,000/QALY.