close
CVC News

Announcement of the awards of GIANA Sub-challenge on Gastrointestinal Image Analysis

Winners 1 GIANA

GIANA 2017 Sub-challenge on Gastrointestinal Image Analysis took part on September 10th during MICCAI 2017 conference, held in Quebec, Canada. It was part of the MICCAI 2017 EndoVis challenge, which comprised 4 different categories this year: Gastrointestinal Image ANAlysis, Surgical Workflow Analysis in the SensorOR, Robotic Instrument Segmentation and Kidney Boundary Detection.

GIANA 2017 Sub-challenge was jointly organized by 4 different institutions from Spain and France: Computer Vision Center/Universitat Autònoma de Barcelona (CVC-UAB), ETIS laboratory at Ecole nationale supérieure de l’Electronique et de ses Applications (ETIS-ENSEA), Hospital Clinic de Barcelona (HCB) and Hôpital Saint-Antoine AP-HP (HAS). Main organizers of the sub-challenge were Jorge Bernal from CVC-UAB and Prof. Aymeric Histace from ETIS-ENSEA.

GIANA Sub-challenge is the continuation of previous challenges (ISBI 2015 and MICCAI 2015) on polyp detection. This year the sub-challenge consisted of three main different tasks: polyp detection and localization in videocolonoscopy, polyp segmentation in colonoscopy images and angiodysplasia detection and localization in wireless capsule endoscopy images. Completely new databases and annotations were provided for each of the tasks thanks to the collaboration with our clinical partners, led by PhD MD Gloria Fernández-Esparrach from HCB and PhD MD Xavier Dray from HAS.

A total of 57 different research teams were interested in the different data provided in the sub-challenge and finally, 12 of them took part in the actual challenge: 1) TU/e  – VCA research group from Technology University of Eindhoven (TU/e-VCA), 2) CUEndo from The Chinese University of Hong Kong (CUEndo), 3) National Institute of Informatics Shin’ichi Satoh Laboratory (NII-Satoh), 4) Laboratoire d’Informatique de Paris 6 (LIP6), 5) Computer Vision and Machine Learning group from University of Central Lancashire (CVML), 6) Norwegian University of Science and Technology (NTNU), 7) University College of London (UCL), 8) GastroView group from Politechnika GDanska (GastroView), 9) The Medical Image Analysis Lab at Simon Fraser University  (SFU), 10) TrueAccord and Massachusets Institute of Technology (TA-MIT), 11) CMEMS group from University of Minho (UMinho), 12) Konica Minolta (KM).

Teams had access to annotated training data from June 5th and testing data was released on July 20th. Final submission data of the results was August 29th. All information related to the challenge was released in GIANA official website though data was only accessible after registering on the website and acceptance of the rules for participation.

Awards for the challenge were sponsored by Société Française d’Endoscopie Digestive (SFED), which provided with 12 different prizes for a total of 2000 €. The following categories were defined: 1) Polyp Detection and Localization, 2) Polyp Segmentation (SD and HD images), 3) Angiodysplasia Detection and Localization and 4) Overall Participation award, which considered only the teams that took part in all 3 previous categories.

With respect to Polyp Detection and Localization category, the first prize (250 €) was awarded to TA-MIT team, composed by Vladimir Iglovikov and Alexey Shvets. Second prize (150 €) was awarded to UCL team composed by Patrick Brandao and Danail Stoyanov. Third prize (100 €) was awarded to NTNU team composed by Younghak Shin, Hemin Ali Qadir and Ilangko Balasingham.

Winners of Polyp Detection and Localization awards. From left to right, Vladimir Iglovikov (TA-MIT, 1st prize), Danail Stoyanov (UCL, 2nd prize) and Younghak Shin (NTNU, 3rd prize).

The winner of the Polyp Segmentation category (250 €) was CVML team, composed by Yun Bo Guo, Pedro Henriquez and Bogdan J. Matuszewski. Second prize (150 €) was awarded to SFU team composed by Saeed Izadi and Ghassan Hamarneh. As a result of a tie in the results, third prize (100 €) was awarded to UCL team composed by Patrick Brandao and Danail Stoyanov and to TA-MIT team, composed by Vladimir Iglovikov and Alexey Shvets.

Winners of Polyp Segmentation awards. From left to right, Bogdan J. Matuszewski (CVML. 1st prize), Aïcha Bentaieb (SFU, 2nd prize), Vladimir Iglovikov (TA-MIT, 3rd prize) and Danail Stoyanov (UCL, 3rd prize).

The winner of the Angiodysplasia Detection and Localization category (250 €) was TA-MIT team, composed by Vladimir Iglovikov and Alexey Shvets. Second prize (150 €) was awarded to to NTNU team composed by Younghak Shin, Hemin Ali Qadir and Ilangko Balasingham. Third prize (100 €) was awarded to TU/e-VCA team composed by Farhad Ghazvinian Zanjani and Joost van der Putten.

Winners of Angiodysplasia Detection and Localization awards. From left to right, Vladimir Iglovikov (TA-MIT, 1st prize), Joost van der Putten (TU/e-VCA, 3rd prize) and Younghak Shin (NTNU, 2nd prize).

Finally and with respect to the Overall Participation award, only two teams took part in all the different tasks of the challenge therefore only two awards were given. First prize (250 €) was awarded to TA-MIT team, composed by Vladimir Iglovikov and Alexey Shvets and second prize (150 €) was awarded to UCL team composed by Patrick Brandao and Danail Stoyanov.

Winners of the Overall Participation task. From left to right, Vladimir Iglovikov (TA-MIT, 1st prize) and Danail Stoyanov (UCL, 2nd prize).

We want to acknowledge the quality of the contributions from all the teams. Slides presented in the challenge detailing the results, along with details of each of the methodology, will be published later this week. Additionally, we aim to publish journal publications summarizing the results of the challenge. We also want to deeply thank the main organizers of EndoVis challenge (Stefanie Speidel, Lena Maier-Hein and Danail Stoyanov) for their help and support during challenge preparation. We look forward to organize future iterations of this sub-challenge in the following years.

Nuria Martínez

The author Nuria Martínez