[Forschungsseminar-BSV] Forschungsseminar Computergrafik, Bildverarbeitung und Visualisierung

[Vanessa Kretzschmar]

Für alle virtuell interessierten, hier der Link zum BBB: https://conf.fmi.uni-leipzig.de/b/van-bwb-jil-vk2

(Verbindung im Raum ist schlecht d.h. es kann zum Abbruch oder Unterbrechungen kommen)

Viele Grüße
Vanessa Kretzschmar 

On October 5, 2022 11:06:24 AM GMT+02:00, Vanessa Kretzschmar <kretzschmar at informatik.uni-leipzig.de> wrote:
>E I N L A D U N G
>
>======================================================================
>
>zum Forschungsseminar 'Computergrafik, Bildverarbeitung und Visualisierung'
>
>    am Mittwoch, den 12. Oktober 2022, 13:15 Uhr,
>    im Raum SG 3-10 im Seminargebäude an der Universitätsstraße.
>
>======================================================================
>
>Wir hören einen Vortrag von
>
>    Lucas Peter
>
>mit dem Titel:
>
>    'Predicting Stroke Lesions from CT Imaging and Clinical Information using UNets'
>
>zum Inhalt:
>
>    Strokes are one of the leading causes of disability worldwide. The
>    resulting disabilities are caused by regions of abnormal brain tissue
>    that are a result of a blockage in the blood circulation of the brain.
>    To accurately and effectively treat these abnormalities, a precise
>    prediction of where the lesion will form is of huge benefit, as medical
>    personnel would be able to more effectively determine which parts of the
>    brain need to be recanalized. One approach to generate these predictions
>    that has gained popularity recently, has been to use Artificial Neural
>    Networks, that are trained on Magnetic resonance imaging (MRI)- or
>    computer tomography (CT)-Scans of patients. Such an approach is presented
>    here in this work. Specifically, a type of Convolutional Neural Network
>    called a UNet is trained on a comparatively large dataset and different
>    values for multiple hyperparameters are tested and their efficacy is
>    compared. In doing so, a model is trained that generates results that
>    are comparable to the state-of-the-art in multiple performance metrics.
>    Furthermore, the importance of the used imaging and auxiliary clinical
>    modalities is determined and a novel technique to generate the salvageable
>    tissue is discussed.
>
>======================================================================
>
>Alle Interessierten sind im Namen von Professor Dr. Scheuermann herzlich
>eingeladen.
>
>Mit freundlichen Grüßen
>Vanessa Kretzschmar
-- 
Sent from my Android device with K-9 Mail. Please excuse my brevity.
-------------- nächster Teil --------------
Ein Dateianhang mit HTML-Daten wurde abgetrennt...
URL: <http://lists.informatik.uni-leipzig.de/pipermail/forschungsseminar-bsv/attachments/20221012/a4430024/attachment.html>