Scientific Advisor: BMC Master of TUM in Singapore
Learning and Understanding in 3D Point Clouds (Video1)Video Length:
We present a revised pipe-line of the existing 3D object detection and pose estimation framework based on point pair feature matching. In particular, we propose to couple the object detection with a coarse-to-fine segmentation, where each segment is subject to disjoint pose estimation. During matching, we apply a weighted Hough voting and an interpolated recovery of pose parameters. Finally, all the generated hypotheses are tested via an occlusion-aware ranking and sorted. We argue that such a combined pipeline simultaneously boosts the detection rate and reduces the complexity, while improving the accuracy of the resulting pose.
19 November 2019, TranslaTUM? auditorium Invited Talk by Dr. Bernhard Kainz Artificial Narrow Intelligence (ANI) including Machine Learning (ML) has the controversial potential to replace healthcare professionals in their jobs. ANI/ML technology has already the capacity to augment, educate and democratize expertise for medical front-line personnel, freeing up their time for difficult cases while making them better at their tasks in modern precision medicine. ANI/ML can make the quality of an individual's work better, resulting in better decision making in healthcare, faster diagnosis, improved patient communication, more efficient training and less mistakes. In this talk I will shed some light on the looming AI bubble in Healthcare, discuss the potential of ML to complement human decision making in clinical applications and will provide an outlook for selected ML applications that have the potential to survive the coming AI winter. We will explore ML methods for population screening, where lack of training and limited expertise lead to missed early treatment opportunities and a high burden on patients and the healthcare system through the 'refer if unsure' approach. Our ML methods also show promising results for complementing sparse data in a meaningful way. I will briefly discuss the impact of ML on image reconstruction tasks that go beyond human capabilities and will conclude with an outlook into the future of autonomous agents in medical imaging, which have the potential to revolutionise patient monitoring and population screening through guided image acquisition.
5 July 2019, MI 03.13.010 The Coronary Atlas The coronary atlas is the largest collection of processed coronary angiogram images. Together with computational modelling, shape analysis and benchtop experiments these can reveal unique insights into our individual differences and why generic coronary artery disease treatment methods won’t always work. This thus not only forms a platform for optimising existing strategies but opens entire new pathways for preventive strategies through early prediction with medical biomarkers.
24 May 2019, MI 03.13.010 Invited Talk by Danielle Pace This work addresses the need for whole heart segmentation to individually label the cardiac chambers and great vessels for patients with congenital heart disease. Our main challenges are extreme anatomical variability and very limited training data. We demonstrate an iterative segmentation method, implemented as a recurrent neural network (RNN), in which a user provides a single landmark per structure, and a segmentation is evolved over multiple steps until reaching a stopping point that can be user-defined or automatically determined. The model grows segmentations in a predictable way that is defined during training. We show that a loss function that evaluates the entire sequence of output segmentations can be optimized using training images alongside input-output pairs of partial segmentations. Our experiments demonstrate that, compared to conventional models that segment an image in one step, the iterative segmentation offers better generalization to patients with the most severe heart malformations.
17 January 2019, MI HS 2 Invited Talk by Prof. Oliver Bimber Digital images play an essential role in our life. Advanced imaging systems, image processing methods, and visualization techniques are today fundamental to many professions. Medical imaging is certainly a good example. However, when mapping complex (possibly multidimensional) data to 2D, information is lost. What if the notion of digital images would change once and forever? What if instead of capturing, storing, processing and displaying only a single color per pixel, each pixel would consist of individual colors for each emitting direction? Digital images would no longer be two-dimensional matrices but four-dimensional ones (storing spatial information in two dimensions, and directional information in the other two dimensions). This is called a light field. I will introduce the fundamentals of light fields, explain how light fields are captured, processed, and displayed, and present several applications of light-field technology in various application domains, such as microscopy, sensors, and aerial scanning.
6 July 2018, MI 03.13.010 Invited Talk by Prof. William (Sandy) Wells Segmentation is a fundamental task for extracting semantically meaningful regions from an image. The goal of segmentation algorithms is to accurately assign object labels to each image location. However, image-noise, shortcomings of algorithms, and image ambiguities cause uncertainty in label assignment. Estimating the uncertainty in label assignment is important in multiple application domains, such as segmenting tumors from medical images for radiation treatment planning. One way to estimate these uncertainties is through the computation of posteriors of Bayesian models, which is computationally prohibitive for many practical applications. On the other hand, most computationally efficient methods fail to estimate label uncertainty. [...]
5 December 2019, CAMP/CM@TUM offer up to 5 International Undergraduate Excellence Awards in 2020 to the best international undergraduate applicants The Chair for Computer Aided Medical Procedures (CAMP) and the Chair for Connected Mobility would like to offer up to 5 research awards to strongly motivated international undergraduate students interested in improving their research skills in machine learning, medical imaging, computer vision, augmented reality, Internet of Things, and/or Edge Computing. The students are required to pursue their undergraduate studies outside Germany. The first two awards amount to 4500 Euros and the second three awards to 4000 Euros. These awards will provide financial support for the awardees during their research stay at CAMP for a period of up to three months between June 2020 and October 2020.
4 December 2019, FMI-Building, Room 01.06.020 PhD Defense by Aslı Okur Kuru Radioguided surgery is a well-established clinical discipline. However, the devices or systems are not necessarily optimized for the particular needs of the target clinical application. This thesis addresses several challenges associated with the deployment of new technologies or concepts for radioguided surgery in different clinical scenarios on the concrete example of Freehand SPECT, a novel 3D nuclear imaging and navigation system. This includes the analysis of the clinical workflow, definition of the supporting functions of the technology and its modification towards integrated applications.
13 November 2019, FMI-Building, Room 00.12.019 PhD Defense by Marco Esposito In this dissertation, we explore innovative techniques for intraoperative medical imaging. First, we augment ultrasound-guided needle biopsy with functional information provided by a collaborative robotic arm holding a gamma camera. We evaluate its effectivness for sentinel lymph node biopsy in the axilla. Second, we propose a novel Riemannian regularization method for decreasing the jitter present in the output of electromagnetic tracking systems, which are standard for freehand 3D ultrasound.
25 July 2019, Seoul, Korea 9 papers accepted at ICCV 2019 We are happy to announce that 8 papers of our chair will be presented at the International Conference on Computer Vision (ICCV 2019) in Seoul, Korea, October 27 - November 2, 2019.
6 July 2019, Shenzhen, China 13 papers accepted at MICCAI 2019 We are happy to announce that 13 papers of our chair will be presented at the 22nd International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2019) in Shenzhen, China, October 13-17, 2019.
28 February 2019, London, UK 1 paper accepted at MIDL 2019 We are happy to announce that one paper from our Chair will be presented at the International Conference on Medical Imaging with Deep Learning MIDL 2019, which will take place in London, July 8-9, 2019.
26 February 2019, Hong Kong 2 papers accepted at IPMI 2019 We are happy to announce that two papers from our Chair will be presented at the International Conference on Information Processing in Medical Imaging, IPMI 2019, which will take place in Hong Kong, June 2-7, 2019.
25 February 2019, Long Beach, CA, USA 5 papers accepted at CVPR 2019 We are happy to announce that five papers from our Chair will be presented at the International Conference on Computer Vision and Pattern Recognition, CVPR 2019, which will take place in Long Beach, CA, USA on June 16-20, 2019.