Augmented patient‐specific functional medical imaging by implicit manifold learning. (6th March 2020)

• Record Type: Journal Article
• Authors: Rapadamnaba, Robert; Nicoud, Franck; Mohammadi, Bijan
• Is Part Of: International journal for numerical methods in biomedical engineering. Volume 36:Number 5(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-03-06
• Subjects: convolutional neural network -- hemodynamic problems -- machine learning -- noninvasive pressure estimation -- transfer learning; Biomedical engineering -- Periodicals; Imaging systems in medicine -- Periodicals; Numerical analysis -- Periodicals; Engineering mathematics -- Periodicals; 610.28
• DOI: 10.1002/cnm.3325
• Languages: English
• ISSNs: 2040-7939

Abstract

Abstract: This paper uses machine learning to enrich magnetic resonance angiography and magnetic resonance imaging acquisitions. A convolutional neural network is built and trained over a synthetic database linking geometrical parameters and mechanical characteristics of the arteries to blood flow rates and pressures in an arterial network. Once properly trained, the resulting neural network can be used in order to predict blood pressure in cerebral arteries noninvasively in nearly real‐time. One challenge here is that not all input variables present in the synthetic database are known from patient‐specific medical data. To overcome this challenge, a learning technique, which we refer to as implicit manifold learning, is employed: in this view, the input and output data of the neural network are selected based on their availability from medical measurements rather than being defined from the mechanical description of the arterial system. The results show the potential of the method and that machine learning is an alternative to costly ensemble based inversion involving sophisticated fluid structure models. Abstract : Machine learning used together with Convolutional Neural Networks (CNNs) is a good alternative to ensemble Kalman Filter based technique for patient‐specific blood pressure estimation in cerebral arteries in nearly real‐time. The implicit CNN proposed here is dedicated to dealing with small data and has above all the advantage of eliminating the need for some blood flow model input parameters, difficult to measure, in the procedure of patient‐specific blood pressure estimation. It is able to manage data, which is either rare, incomplete, expensive, or simply dangerous to obtain so that it can recover a target output of a blood flow model without using the explicit knowledge of all the model input parameters.