Output details

ATD: a multi-platform for semi-automatic 3D detection of kidneys and their pathology in real-time

This research outlines an integrated system combining two distinct platforms: the first uses “DoctorEye” to accurately identify kidneys in an abdominal set of MRIs; the second focuses on their pathology, identifying any abnormalities found and providing real metrics on tumours and cysts that can later be used to simulate the effect of cancer therapy. The system makes use of “Templates” that clinicians originally create to accurately detect organs and custom-made image processing algorithms capable of swiftly identifying renal pathologies. The system was tested in over 500 MRI images and yields an average accuracy of 97.2%, outperforming all existing systems.