Arthritis is a chronic inflammatory disease affecting around 1% of the population. The cardinal symptom of the disease is affection by swelling and pain from especially the joints of the hands and feet. Fast disease control and monitoring is essential as active disease can cause damage, disability and decreased quality of life for the patient.
This platform will ensure systematic and uniform method to perform ultrasound scans, thereby ensuring physicians the best possible starting point for the determination of treatment. Ultrasound scans are highly operator dependent such a systematic method of scanning is not currently possible.
Deep Vein Thrombosis (DVT) is a condition where thromboses (blood clots) form in the legs or pelvis. The incidence of DVT is 1 – 2 per 1000 citizens per year, increasing with age.
We are developing a robot platform for automating Deep Vein Thrombosis (DVT) diagnosis. Using a robotic platform we hope to achieve a higher scan consistency and increase the hospitals capacity for performing the scans.
This paper investigates the possibility of using feature extraction with a convolutional neural network for classification of power Doppler ultrasound images of RA.
An accuracy of 75.0 % was achieved for 4-class classification. An accuracy of 86.9 %, a sensitivity of 87.5 %, and a specificity of 86.4 % was achieved for binary classification.