BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//BioMedIA - ECPv6.15.11//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:BioMedIA
X-ORIGINAL-URL:https://biomedia.doc.ic.ac.uk
X-WR-CALDESC:Events for BioMedIA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20140101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20160519T160000
DTEND;TZID=UTC:20160519T170000
DTSTAMP:20260529T153226
CREATED:20160427T184136Z
LAST-MODIFIED:20160512T210610Z
UID:2744-1463673600-1463677200@biomedia.doc.ic.ac.uk
SUMMARY:BioMedIA Talk: Ioannis Katramados (COSMONiO)
DESCRIPTION:Title: The challenges of developing an active deep-learning platform \nAbstract:\nDeep learning is usually linked to Big Data. However\, there are several scientific\, engineering and medical imaging problems with limited data available (e.g. rare medical conditions). Can Deep Learning prove a useful tool in such cases? COSMONiO is designing NOUS\, an active deep learning platform that aims to make high-accuracy predictions using significantly smaller training datasets. NOUS aims to allow experts from any field to train neural networks without any prior experience. We will discuss the main challenges and how we address them.
URL:https://biomedia.doc.ic.ac.uk/event/biomedia-talk-ioannis-katramados-cosmonio/
LOCATION:Huxley 144
CATEGORIES:Talks & Seminars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20160518T120000
DTEND;TZID=UTC:20160518T130000
DTSTAMP:20260529T153226
CREATED:20160427T184017Z
LAST-MODIFIED:20160512T210704Z
UID:2743-1463572800-1463576400@biomedia.doc.ic.ac.uk
SUMMARY:BioMedIA Talk: Enzo Ferrante
DESCRIPTION:Title: Graph-based deformable registration: slice-to-volume mapping and context specific methods \nAbstract: Image registration methods\, which aim at aligning two or more images into one coordinate system\, are among the oldest and most widely used algorithms in computer vision. A particular type of registration algorithm\, known as graph-based deformable registration\, has become popular during the last decade given its robustness\, scalability\, efficiency and theoretical simplicity. In this thesis\, we extend this flexible framework to new scenarios\, and propose novel methodological contributions. \nWe start by formulating\, within the graph-based deformable registration framework\, the challenging slice-to-volume registration problem. We introduce a scalable\, modular and flexible formulation accommodating low-rank and high order terms\, which simultaneously selects the plane and estimates the in-plane deformation through a single shot optimization approach. The other two contributions included in this thesis are related to how semantic information can be encompassed within the registration process. Currently\, most of the methods rely on a single metric function explaining the similarity between the source and target images. We argue that incorporating semantic information to guide the registration process will further improve the accuracy of the results\, particularly in the presence of semantic labels making the registration a domain specific problem.
URL:https://biomedia.doc.ic.ac.uk/event/biomedia-talk-enzo-ferrante/
LOCATION:Huxley 144
CATEGORIES:Talks & Seminars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20151216T110000
DTEND;TZID=UTC:20151216T120000
DTSTAMP:20260529T153226
CREATED:20151214T193635Z
LAST-MODIFIED:20151214T193756Z
UID:2465-1450263600-1450267200@biomedia.doc.ic.ac.uk
SUMMARY:BioMedIA talk: William M. Wells
DESCRIPTION:Sandy Wells is giving a talk on Wednesday 16 Dec\, 11:00\, in Huxley 218. He will be talking about his registration work and will give an overview of projects in image-guided therapy in his lab.
URL:https://biomedia.doc.ic.ac.uk/event/biomedia-talk-william-m-wells/
LOCATION:Huxley 218
CATEGORIES:Talks & Seminars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20151113T140000
DTEND;TZID=UTC:20151113T150000
DTSTAMP:20260529T153226
CREATED:20151109T132417Z
LAST-MODIFIED:20151109T132439Z
UID:2225-1447423200-1447426800@biomedia.doc.ic.ac.uk
SUMMARY:BioMedIA talk: Eugenio Iglesias
DESCRIPTION:Building brain atlases and segmentation tools with ex vivo MRI and histology: application to hippocampus\, amygdala and beyond \nAbstract: Ex vivo modalities make it possible to obtain manual delineations of brain anatomy with very high precision. These delineations can be used to build accurate atlases at very high resolution\, which can in turn be applied to the segmentation of brain substructures in in vivo MRI scans. While analyzing the brain at the substructure level holds promise to increase our understanding of such a complex organ (both in health and in disease)\, it also poses a number of modeling challenges. In this talk\, I will first describe the construction of a probabilistic atlas of the hippocampal subfields using a combination of in vivo and ex vivo MRI. Then\, I will present some results on in vivo MRI segmented with the atlas. Next\, I will present an extension of the atlas to the amygdaloid nuclei. And finally\, I will discuss the extension of the framework to the thalamus and other brain structures using histology – a modality that yields excellent contrast and resolution\, but also introduces additional difficulties. \nBio: Juan Eugenio Iglesias holds an MSc in Telecom Engineering from the University of Seville (Spain)\, an MSc in Electrical Engineering from the Royal Institute of Technology (Stockholm\, Sweden)\, and a PhD in Biomedical Engineering from the University of California\, Los Angeles (USA). He has also been a postdoctoral researcher at the Martinos Center for Biomedical Imaging (Massachusetts General Hospital / Harvard Medical School)\, and is currently a Marie Curie postdoctoral fellow at the Basque Center on Cognition\, Brain and Language (San Sebastian\, Spain). His main research interest is exploring generative models for brain MRI segmentation.
URL:https://biomedia.doc.ic.ac.uk/event/biomedia-talk-eugenio-iglesias/
LOCATION:Huxley 342
CATEGORIES:Talks & Seminars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20151110T160000
DTEND;TZID=UTC:20151110T170000
DTSTAMP:20260529T153226
CREATED:20151109T132204Z
LAST-MODIFIED:20151110T121237Z
UID:2223-1447171200-1447174800@biomedia.doc.ic.ac.uk
SUMMARY:BioMedIA talk: Francois Rousseau
DESCRIPTION:On early brain development from MRI data \nAbstract: The development of ultrafast 2D acquisition sequences has led to significant improvements in the clinical utility of fetal MRI. However\, the slice acquisition time is still very critical and has to be as short as possible to reduce the impact of fetal and maternal motion on the exam. Since 2005 there has been a series of techniques coming from computer vision that have been developed to address these limitations in fetal MRI. These motion-correction methods provide a new window into early human brain growth study. I will present in this talk an overview of the current research into fetal brain MRI processing for early brain development studies. I will focus on temporal analysis\, and more particularly on cortical folding.
URL:https://biomedia.doc.ic.ac.uk/event/biomedia-talk-francois-rousseau/
LOCATION:Huxley 503
CATEGORIES:Talks & Seminars
END:VEVENT
END:VCALENDAR