Our work on using Deep Learning techniques for endoluminal image analysis was presented as example at NVIDIA’s GPU Technical Conference (http://www.gputechconf.com/).

a

Dr. Francesco Ciompi has received a Diplom recognizing his work for being 1 of the finalists in the deliberation process of the best PhD thesis of 2014 of the University of Barcelona. His thesis is called: “MultiClass Learning for Vessel Characterization in Intravascular Ultrasound”, c-supervised by Dr. Petia Radeva and Dr. Oriol Pujol.

El CST rep una beca per la investigació en malalties neurodegeneratives“, terassadigital.cot, 31 d’Octubre, 2014.

Our project on Lifelogging: “A Cognitive Training Tool Based on life- logging Mild Cognitive Impairment in (Re -memory)” has been awarded by the “La Marató de TV3”, edition of 2014.

Last week (22, 23 & 24 of October 2014) the Dissetè Congrés Internacional de l’Associació Catalana d’Intel·ligència Artificial (CCIA 2014) just finished,  (http://www.maia.ub.edu/~ccia2014/). Excellent organizations and conference! Congratulations to the whole team and mainly to the Program Chair (President del Comité Organitzador), Oriol Pujol.

Our Consolidated Research Group (2014 SGR 1219) has been recognized and sponsored by the Generalitat de Catalunya. Congratulations to all! It will last from 2014-2018.

  • Laura Igual received the AMDO 2014 Honourable Mention for the paper “Multiclass Dictionary Learning for MRI Segmentation” presented at the conference AMDO’2014.

Next autumn, BCNPCL will perform a series of “lightning talks”. A lightning talk is a very short presentation given at a conference or similar forum. Unlike other presentations, lightning talks last only a few minutes and several will usually be delivered in a single period by different speakers.

We propose to run 5 minute lightning talks per doctor proposing one or several open research topics where we look for collaboration. After the talks we will open a discussion to enquire more details.

Calendar:

September, 17th:

    • Michal Drozdzal: TBA
    • Laura Igual: Problems in Neuroimaging
    • David Masip: Emotion classification: Deep features and dynamics

November, 5th:

    • Jordi Vitrià: Zero-shot learning of food
    • Oriol Pujol: TBA
    • Petia Radeva: Lifelogging: a problem to solve.
    • Xevi Baró: TBA
    • Simone Balocco: TBA

Universitat de Barcelona’s Data Science and Big Data course offers students a program that covers the concepts and tools you will need throughout the entire data science pipeline: asking the right questions; wrangling and cleaning data; generating hypothesis; making inferences; visualizing data; assessing solutions; and building data products.

Schedule: October 2, 2014 – May 30, 2015, Thursday 18h-21h

Estimated workload: 6 hours per week (including lectures and homework)

Location: Edifici Històric de la Universitat de Barcelona, Gran Via de les Corts Catalanes 585, 08007, Barcelona

More informacion: LinkedIn | Tweeter | Web | datascience@ub.edu

“Una de las pruebas más desagradables a las que se someten los pacientes va mejorando cada año gracias a los avances de la tecnología. La endoscopia, que consiste en la introducción de una cámara con un cable dentro del aparato digestivo, entre otros, para hacer diagnósticos, se ha reconvertido en los últimos tiempos en un quebradero de cabeza menor en algunos hospitales que han incorporado la solución no invasiva de la empresa israelí Given Imaging: una cápsula endoscópica (PillCam) que el paciente ingiere y expulsa horas después y que graba de forma autónoma su recorrido por el intestino delgado y colon, generando alrededor de ocho horas de vídeo con entre 30.000 y 50.000 imágenes.

Sin embargo, no podemos imaginar que un médico pueda pasar varias horas delante de una pantalla por cada paciente que se realiza la prueba. Así que doctores del hospital Vall d’Hebron de Barcelona, centro que usa la cápsula, pidieron ayuda al Centro de Visión por Computador (CVC), cuyo grupo liderado por la doctora Petia Radeva y el doctor Jordi Vitrià lleva siete años trabajando en un software de comercialización muy próxima que ayuda a procesar las imágenes y extraer la información sobre la motilidad intestinal….”

Published by “El Mundo”, on April, 4th, 2014. Read more…

 

Research Coordinators and Contact Information

E-MAIL: bcnpcl@gmail.com
Petia Radeva & Jordi Vitrià
Dept. de Matemàtica Aplicada i Anàlisi
Facultat de Matemàtiques
Universitat de Barcelona
Gran Via 585, 08007 Barcelona
Catalonia, Spain
(How to arrive)
Are you in Barcelona? Come and visit our lab, but don't forget the city and its attractions!


Research Consortia

Follow

Get every new post delivered to your Inbox.