MSB Online Seminar: Differentiable Deconvolution for Improved Stroke Perfusion Analysis

, Events

Titel: Differentiable Deconvolution for Improved Stroke Perfusion Analysis

Sprecher:  Ezequiel de la Rosa, GCB Doktorand in einem Forschungsprojekt des ITN Netzwerks TRABIT (Translational Brain Imaging Training Network), Prof. Menze / Prof. Kirschke

Datum und Uhrzeit: Dienstag, 27. April 2021, 13:00 Uhr

Abstract: Perfusion imaging is the current gold standard for acute ischemic stroke analysis. It allows quantification of the salvageable and non-salvageable tissue regions (penumbra and core areas respectively). In clinical settings, the singular value decomposition (SVD) deconvolution is one of the most accepted and used approaches for generating interpretable and physically meaningful maps. Though this method has been widely validated in experimental and clinical settings, it might produce suboptimal results because the chosen inputs to the model cannot guarantee optimal performance. For the most critical input, the arterial input function (AIF), it is still controversial how and where it should be chosen even though the method is very sensitive to this input. In this work we propose an AIF selection approach that is optimized for maximal core lesion segmentation performance. The AIF is regressed by a neural network optimized through a differentiable SVD deconvolution, aiming to maximize core lesion segmentation agreement with ground truth data. To our knowledge, this is the first work exploiting a differentiable deconvolution model with neural networks. We show that our approach is able to generate AIFs without any manual annotation, and hence avoiding manual rater’s influences. The method achieves manual expert performance in the ISLES18 dataset. We conclude that the methodology opens new possibilities for improving perfusion imaging quantification with deep neural networks.


This semester, the MSB Seminar will take place online (Zoom). Please register via email (katharina.scholz(at) and we are happy to provide the access data.


4 May 2021 1:00 pm Theodor Cheslerean-Boghiu Lasser Group Dual Domain Neural Networks for Sparse X-ray Computed Tomography.
11 May 2021 1:00 pm Mirko Riedel Herzen Group High Resolution Phase-Contrast Imaging at the PETRA III Synchrotron.
18 May 2021 1:00 pm Christian Sigl Dietz Group Programmable Icosahedral Shell System Based on the Principle of Viral Capsids.
25 May 2021 1:00 pm Erdal Pekel Lasser Group Robotic X-ray CT Imaging.
1 June 2021 1:00 pm Lukas Hiendlmeier Wolfrum Group 4D Printing and Self-Folding - A Possbility to Enhance an Electrical Nerve Interface.
8 june 2021 1:00 pm Jonas Geißdörfer Hemmert Group Simulation of the Electric Excitability of Auditory Nerve Fibers Stimulated with Multipolar Cochlear Implant Electrode Configurations.
15 June 2021 1:00 pm Max Weirather Gleich Group Modular EMG Amplifier.
22 June 2021 1:00 pm Philipp Braun Gleich Group Inductive Stimulation of the Phrenic Nerve.
29 June 2021 1:00 pm Lukas Driendl Hemmert Group Modeling of Neural Adaption in Auditory Nerve Fibers.
6 July 2021 1:00 pm Nico Linhart Gleich Group Development of a Testing System for an Invasive Blood Pressure Measurement Module.
13 July 2021 1:00 pm tbd    
20 July 2021 1:00 pm tbd