Residual Motion Improves Deep Learning Performance for Surgical Actions in Gynecologic Laparoscopy

In a recent work, presented at the 31st IEEE International Symposium on Computer-Based Medical Systems (CBMS2018), we could show that the inclusion of Residual Motion improves classification performance of surgical actions in videos from gynecologic laparoscopy significantly (resulting in a boost of Recall and Precision of 5% and 9% with the GoogLeNet CNN architecture). This performance can be improved even further (to a boost of 13% and 25% in terms of Recall and Precision) by using a late fusion approach for frame classification in the videos. The corresponding paper can be found here.

diveXplore Interactive Video Retrieval System

We have created a video of the diveXplore system, which we used for the Video Browser Showdown in 2017 and 2018 (as well as for the Lifelog Search Challenge 2018 in slightly modified form) quite successfully (2nd place in all three competitions). The video shows the different features of the system when applied to the IACC.3 dataset that consists of 600 hours of video content (around 300000 shots):

Cataract-101 Video Dataset

The ITEC Cataract-101 Dataset is available under here:

It consists of videos from 101 cataract surgeries, annotated with different operation phases that were performed by four different surgeons over a period of 9 months. These surgeons are grouped into moderately experienced and highly experienced surgeons (assistant vs. senior physicians), providing the basis for experience-based video analytics, as described in detail in the corresponding paper presented at MMSYS 2018.

LapGyn4 Gynecologic Laparoscopy Dataset

The ITEC LapGyn4 Gynecologic Laparoscopy Image Dataset is available under here:

It comprises four individual datasets (surgical actions, anatomical structures, actions on anatomy, and instrument count) taken from 500+ gynecologic laparoscopic surgeries for the task of automatic content analysis, as described in detail in the corresponding paper presented at MMSYS 2018.

ITEC @ Lange Nacht der Forschung 2018

On April 13, 2018 the ‘Lange Nacht der Forschung 2018‘ (long research night) took place again in Austria and the medical multimedia research group of ITEC did also participate in this exciting event that communicates research works to the public. Our booth at Klagenfurt University showed ‘How neural networks can help surgeons to improve surgical quality‘ and it was a great success: several thousands of people came to see our research efforts and they were stunned by our interesting demos and hands-on experiences: real-time instruments detection, real-time smoke detection (with dry ice), and several laparoscopic operation simulator boxes where visitors could test their surgical skills (we also had an original KARL STORZ Endoscope with corresponding laparoscopic instruments).

First six photos by photo riccio.

Best Demo Award at MMM 2018

We are very happy that we received the Best Demo Award at the 24th International Conference on Multimedia Modeling (MMM 2018) for our demo on “Video Browsing on a Circular Timeline“.

Medical Image and Video Analysis Using Deep Learning – Deadline Extended!

The submission deadline for our Special Track on Medical Image and Video Analysis using Deep Learning at the 31st IEEE CBMS International Symposium on Computer-Based Medical Systems (CBMS 2018), to be held in Karlstad, Sweden from June 18-21, 2018, has been extended until March 5, 2018! Find more information here.

Results of the VBS 2018

The 7th Video Browser Showdown (2018) at the 24th International Conference on Multimedia Modeling (MMM 2018), held from February 5-7, 2018 in Bangkok, Thailand was a great and entertaining event! We had 9 very competitive teams from 8 different countries that challenged each other for several hours and performed 20 tasks in the public session (as well as 8 training tasks in the private session on February 4th). The novices in the Novice Run were highly active and performed very well! Moreover, we had hard-working judges that performed live-judgement for more than 1500 submissions (that couldn’t be found in the TRECVID groundtruth). Congratulations to the SIRET team from Czech Republic that won the VBS 2018! We are also very happy that Klagenfurt University (ITEC-1 and ITEC-2) scored very well with place 2 and 3. Here are all the details and results of this year’s VBS.

 

Medical Image and Video Analysis using Deep Learning – Deadline Extended!

We are happy to announce that our Special Track on Medical Image and Video Analysis using Deep Learning at the 31st IEEE CBMS International Symposium on Computer-Based Medical Systems, to be held in Karlstad, Sweden from June 18-21, 2018, has been accepted!

Topics of interest include (but are not limited to):

  • Novel approaches for medical image/exam classification, object/lesion classification, organ/region/landmark localization, object/lesion detection, organ/substructure segmentation, lesion segmentation, and medical image registration using deep learning;
  • Content-Based Image Retrieval (CBIR) of medical images using deep learning;
  • Medical image content understanding using deep learning;
  • Medical image generation and enhancement methods using deep learning;
  • Multimodal (image/text) analysis using deep learning;
  • Organ-specific, modality-specific, and disease-specific image analysis using deep learning;
  • Applications of deep learning for digital pathology and microscopy.

Please find the Call-for-Papers here. We are looking forward to your submissions!

  • Abstract submission deadline: February 5, 2018
  • Full paper submission deadline: February 19, 2018
  • Notification of acceptance: April 25, 2018
  • Final paper submission deadline: May 7, 2018

Medical Multimedia Information Systems

The slides of our tutorial on Medical Multimedia Information Systems, held together with Bernd Münzer, Paal Halvorsen, and Michael Riegler at the 25th ACM International Conference on Multimedia 2017 (ACMMM17) can be found on slideshare: