Prof. Radu Prodan

Prof. Radu Prodan participated at the PhD examination of Dr. Yang Hu and Dr. Huan Zhou at the University of Amsterdam, Netherlands.

, , ,

Prof. Radu Prodan participated at the PhD examination of Dr. Yang Hu and Dr. Huan Zhou at the University of Amsterdam, Netherlands.

With: Prof. Peter van Emde Boas, Prof. Cees de Laat, Prof. Henri E. Bal, Dr. Paola Grosso, Dr. Zhiming Zhao, Prof. Rob van Nieuwpoort, Prof. Pieter Adriaans, Dr. Adam S.Z. Belloum

Sabrina Kletz presented her work at the MIAR Workshop @ MICCAI 2019


Sabrina Kletz presented the paper “Learning the Representation of Instrument Images in Laparoscopy Video” at the MIAR Workshop @ MICCAI 2019 in Shenzhen, China.

Authors: Sabrina Kletz, Klaus Schoeffmann, Heinrich Husslein

Abstract: Automatic recognition of instruments in laparoscopy videos poses many challenges that need to be addressed like identifying multiple instruments appearing in various representations and in different lighting conditions which in turn may be occluded by other instruments, tissue, blood or smoke. Considering these challenges it may be beneficial for recognition approaches that instrument frames are first detected in a sequence of video frames for further investigating only these frames. This pre-recognition step is also relevant for many other classification tasks in laparoscopy videos such as action recognition or adverse event analysis. In this work, we address the task of binary classification to recognize video frames as either instrument or non-instrument images. We examine convolutional neural network models to learn the representation of instrument frames in videos and take a closer look at learned activation patterns. For this task, GoogLeNet together with batch normalization is trained and validated using a publicly available dataset for instrument count classifications. We compare transfer learning with learning from scratch and evaluate on datasets from cholecystectomy and gynecology. The evaluation shows that fine-tuning a pre-trained model on the instrument and non-instrument images is much faster and more stable in learning than training a model from scratch.

Conference: 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), October 13–17, 2018, Shenzhen, China

Track: Medical Imaging and Augmented Reality (MIAR) Workshop @MICCAI

Mathias Lux

Hüttenjam 2019 is over and it has been a hugely successful event

The Hüttenjam 2019 is over and it has been a hugely successful event. 26 participants jammed for two days and two nights in four chalets at Marktlalm, on Turracher Höhe. Six games have been developed matching the topic “Can’t see the wood for the trees”. Games ranged from multiplayer hide and seek, to simulations, platformers, stealth, and puzzle games. All games can be found on [1]. Besides working on the games we could socialize and network with joint breakfast and lunches and trips to the Nockiflitzer and Panoramaalm. For the motivated participants, there were running sessions in the morning and a hike to Rinsennock. 

General feedback by the participants indicated that people wanted to have a second edition next year. Responses on social networks like Twitter, Facebook and Instagram indicated that many more people are interested beyond the ones already attending. For Twitter top tweets had more than 70 likes [2], with the initial Facebook video we reached more than 700 people within a month, with the latest video we reached more than 70 people in a day [3]. 

Thanks a lot to all the sponsors who made this possible: Bitmovin, Förderverein Technische Fakultät, and Technische Fakultät der Universität Klagenfurt. If you want to spread the word about the event, feel free to use any photos or video from [4].

[1] All games online:

[2] Hüttenjam on Twitter

[3] Gamebert on Facebook

[4] Photos and videos:

Christian Timmerer

5GPlayground-Eröffnung mit ITEC-Use-Case “Virtual Realities”


Mit dem 5G Summit Carinthia, ein Kurzsymposium zur neuen Mobilfunktechnologie 5G, wurde heute der 5G Playground Carinthia feierlich eröffnet. Der 5G Playground Carinthia ist österreichweit die erste Serviceeinrichtung für die Erforschung und Weiterentwicklung von 5G-spezifischen Anwendungen, Services und Geschäftsmodellen. Das Bundesministerium für Verkehr, Innovation und Technology (BMVIT) sowie das Land Kärnten finanzieren dieses einzigartige Forschungslabor im Süden Österreichs. A1 Telekom Austria stellt die technische Infrastruktur zur Verfügung.

Der 5G Playground Carinthia bietet allen Forschungs-, Innovations- und Bildungseinrichtungen sowie KMUs und Start Ups die einzigartige Möglichkeit ihre Produkte und Anwendungen mit dieser neuen Technologie zu testen und im Echtbetrieb zu erproben.

Die Alpen-Adria-Universität Klagenfurt und insbesondere das Institut für Informationstechnologie beteiligt sich an dem 5GPlayground mit einen Use-Case über “Virtual Realities”. Das Projekt erforscht, entwickelt, erprobt und evaluiert ausgewählte VR-Anwendungen über 5G-Netze, z.B. Streaming von 360°-Videos und von neuen Formen immersiver Medien, etwa von volumetrischen Daten (Point Clouds). Diese Anwendungen erfordern und testen sowohl die hohen Datenraten als auch die extrem geringen Verzögerungszeiten von 5G-Netzen, im Downlink (Streaming zu einer VR-Brille) wie auch im Uplink (Streaming von Live-Inhalten von einer 360°-Kamera weg). Darüber hinaus werden Edge-Computing-Komponenten genutzt, die 5G vorsieht, um höhere Präsentationsqualität und raschere Reaktionszeiten des VR-Systems bei Bewegung/Interaktion eines Nutzers zu erreichen. Es werden VR-Systeme entwickelt, welche die Leistungsfähigkeit von 5G zu demonstrieren erlauben.


Prof. Radu Prodan @ EU High level Social Media Symposium Panel Discussion

, , ,

Read more about the High level Symposium.

Blockchain course in WS 2019 – Assoc.-Prof. Dr. Antorweep Chakravorty

BlockchainITEC is delighted to announce the next speaker in our guest lecture series – Dr. Antorweep Chakravorty from University of Stavanger and bitYoga, Norway. The course will take place from November 18 – 29, 2019

This course presents an introduction and further information about the high-interest topic blockchains. Please register at the course 623.714.

Further information is available HERE.

3rd ARTICONF technical meeting in Porto.

, , ,

The first H2020 ASPIDE technical meeting took place in Klagenfurt

, , ,

The Klagenfurt University hosted the first ASPIDE technical meeting (30th September – 2nd October), which aims on designing scalable software solutions for exascale computing.

2019 ASPIDE Meeting Klagenfurt

ASPIDE Meeting at Klagenfurt University

2019 ASPIDE Meeting Klagenfurt Social Event

2019 ASPIDE Meeting Klagenfurt (Social Event)

Natalia Sokolova

MMM’20: Evaluating the Generalization Performance of Instrument Classification in Cataract Surgery Videos


Our paper has been accepted for publication at the MMM 2020 Conference on Multimedia Modeling. The work was conducted in the context of the ongoing OVID project.

Authors: Natalia Sokolova, Klaus Schoeffmann, Mario Taschwer (AAU Klagenfurt); Doris
Putzgruber-Adamitsch, Yosuf El-Shabrawi (Klinikum Klagenfurt)

In the field of ophthalmic surgery, many clinicians nowadays record their microscopic procedures with a video camera and use the recorded footage for later purpose, such as forensics, teaching, or training. However, in order to efficiently use the video material after surgery, the video content needs to be analyzed automatically. Important semantic content to be analyzed and indexed in these short videos are operation instruments, since they provide an indication of the corresponding operation phase and surgical action. Related work has already shown that it is possible to accurately detect instruments in cataract surgery videos. However, their underlying dataset (from the CATARACTS challenge) has very good visual quality, which is not reflecting the typical quality of videos acquired in general hospitals. In this paper, we therefore analyze the generalization performance of deep learning models for instrument recognition in terms of dataset change. More precisely, we trained such models as ResNet-50, Inception v3 and NASNet Mobile using a dataset of high visual quality (CATARACT) and test it on another dataset with low visual quality (Cataract-101), and vice versa. Our results show that the generalizability is rather low in general, but clearly worse for the model trained on the high-quality dataset. Another important observation is the fact that the trained models are able to detect similar instruments in the other dataset even if their appearance is different.