The invention relates to a method for determining a pose of an object in its surroundings, wherein by means of an optical detection device, the object and its surroundings detected as current recording (x) and by means of an optical image analysis, the pose of the object is determined, and wherein by means of a neural network (1) determining the pose of the object as output of the neural network (1), the neural network (1) using multi-task learning (L) through use of pose regression (L) and descriptor learning (L) is taught by using a triplet-wise-loss function (L) and a pair-wise-loss-function (L), whereby the posse-regression (L) by means of quaternions, the triplet-wise-loss-function (L ) depending on a dynamic margin term (m) and the pair-wise-loss function (L) can only be determined as an anchoring function.

Die Erfindung betrifft ein Verfahren zum Ermöglichen einer tomographischen Rekonstruktion, mit den Schritten:
- Emittieren eines Röntgenstrahls (5) durch eine Röntgeneinheit (1),
- Ermitteln einer Dämpfung des Röntgenstrahls (5) beim Transmittieren des Objekts (4), welches sich in einem Strahlengang des Röntgenstrahls (5) der Röntgeneinheit (1) befindet,
- Ermitteln von Strukturdaten des Objekts (4) anhand der Dämpfung des Röntgenstrahls (5),
Um eine verbesserte tomographische Rekonstruktion des Objekts zu ermöglichen, ist vorgesehen, dass
- anhand eines digitalen Modells des Objekts (4) sowie anhand der Dämpfung des Röntgenstrahls (5) eine Pose der Röntgeneinheit (1) relativ zu dem Objekt (4) zum Ermöglichen der tomographischen Rekonstruktion ermittelt wird.

We got the best paper award at MIAR conference for our paper "CathNets: Detection and Single-View Depth Prediction of Catheter Electrodes" by C. Baur, S. Albarqouni, S. Demirci, N. Navab, P. Fallavollita.

It is really an interesting experience. It was the first course in Robotics field offered to the Undergraduate students in our department.

Today's clinical procedures often generate a large amount of digital images requiring close inspection. Manual examination by physicians is time-consuming and machine learning in computer vision and pattern recognition is playing an increasing role in medical applications. In contrast to pure machine learning methods, crowdsourcing can be used for processing big data sets, utilising the collective brainpower of huge crowds. Since individuals in the crowd are usually no medical experts, preparation of medical data as well as an appropriate visualization to the user becomes indispensable. The concept of gamification typically allows for embedding non-game elements in a serious game environment, providing an incentive for persistent engagement to the crowd. Medical image analysis empowered by the masses is still rare and only a few applications successfully use the crowd for solving medical problems. The goal of this thesis is the development and implementation of a medical game for the crowd, targeting the challenge of mitosis count, i.e. correctly identifying the number of mitoses within a given histological patch. The game should enable users to recognize mitotic figures and support the decision making process. Based on actions of the crowd, probabilities for mitotic figure locations and the mitosis count on a single patch are to be generated.

In this project which is offered in MLMI course for BMC Students, we would like to implement kind of Supervised Dictionary Learning incorporating the global consistency, discriminative labeling, and the Transformation-invariant.

DAAD-RISE Program for Exchange, which is restricted for Undergraduate students from US, Canada and UK.

For more details on Application procedure: https://www.daad.de/rise/en/11638/index.html
Our Offer: https://www.daad.de/app-rise/rise/offer/offer?id=26943

This is a senior project done by talent students, it was a Web Application system that should be able to support emergency services in Gaza Strip-Palestine, which encounter a serious problem in the delivery of health services, especially in Crisis Events. The current emergency system is very primitive, and lacks coordination between other healthcare and emergency officers. The Proposed System is a part of my research interest on Establishing Telemedicine Center in Palestine, and preparing a Framework of an Electronic Emergency System in Gaza Strip, the proposed system is based on Web 2.0 Application.

Modeling X-ray images as well as improving the image quality of ultra-low dose X-ray images using analytical- and learning-based methods

The goal is to apple AI and Big Data technology in Ophthalmology

Cryo-ET has recently emerged as a leading technique to investigate the three-dimensional(3D) structure of biological specimens at close-to-native state. It also bridges the gap between low-resolution imaging techniques (e.g. light microscopy) and high-resolution techniques (e.g. single particle electron microscopy). The technique consists of acquiring many two-dimensional (2D) projections of the structure under scrutiny at various tilt angles under cryogenic conditions. The 3D structure is recovered through a number of steps including projection alignment, reconstruction and de-nosing. The resolution of the reconstructed tomogram, however, is aaffected by the low signal to noise ratio (SNR) of the projection images (typically 0.1 to 0.01) and the limited angular coverage (typically 60 to 70 ) resulting in wedge-shaped missing information in Fourier space, the so-called missing wedge; making the reconstruction process very challenging and demanding. In this project, we are aiming to develop image processing techniques including 3d reconstruction together with noise-reduction that are suitable for this technology.

Today's clinical procedures often generate a large amount of digital images requiring close inspection. Manual examination by physicians is time-consuming and machine learning in computer vision and pattern recognition is playing an increasing role in medical applications. In contrast to pure machine learning methods, crowdsourcing can be used for processing big data sets, utilising the collective brainpower of huge crowds. Since individuals in the crowd are usually no medical experts, preparation of medical data as well as an appropriate visualization to the user becomes indispensable. In this project, we are aiming to develop a concept of gamification typically allows for embedding non-game elements in a serious game environment, providing an incentive for persistent engagement to the crowd. Medical image analysis empowered by the masses is still rare and only a few applications successfully use the crowd for solving medical problems. The goal of this project is to bring the gamification and crowdsourcing to the Medical Imaging community.