arXiv subjects

Matthias Kirsch

Publications and source records attributed to Matthias Kirsch.

3 recordsLinked to original sources

arXiv2020

Visualisation of Medical Image Fusion and Translation for Accurate Diagnosis of High Grade Gliomas

The medical image fusion combines two or more modalities into a single view while medical image translation synthesizes new images and assists in data augmentation. Together, these methods help in faster diagnosis of high grade malignant gliomas. However, they might be untrustworthy due to which neurosurgeons demand a robust visualisation tool to verify the reliability of the fusion and translation results before they make pre-operative surgical decisions. In this paper, we propose a novel approach to compute a confidence heat map between the source-target image pair by estimating the information transfer from the source to the target image using the joint probability distribution of the two images. We evaluate several fusion and translation methods using our visualisation procedure and showcase its robustness in enabling neurosurgeons to make finer clinical decisions.

cs.CV↗

arXiv2019

Structural Similarity based Anatomical and Functional Brain Imaging Fusion

Multimodal medical image fusion helps in combining contrasting features from two or more input imaging modalities to represent fused information in a single image. One of the pivotal clinical applications of medical image fusion is the merging of anatomical and functional modalities for fast diagnosis of malignant tissues. In this paper, we present a novel end-to-end unsupervised learning-based Convolutional Neural Network (CNN) for fusing the high and low frequency components of MRI-PET grayscale image pairs, publicly available at ADNI, by exploiting Structural Similarity Index (SSIM) as the loss function during training. We then apply color coding for the visualization of the fused image by quantifying the contribution of each input image in terms of the partial derivatives of the fused image. We find that our fusion and visualization approach results in better visual perception of the fused image, while also comparing favorably to previous methods when applying various quantitative assessment metrics.

eess.IV↗

arXiv2005

The PAX Toolkit and its Applications at Tevatron and LHC

At the CHEP03 conference we launched the Physics Analysis eXpert (PAX), a C++ toolkit released for the use in advanced high energy physics (HEP) analyses. This toolkit allows to define a level of abstraction beyond detector reconstruction by providing a general, persistent container model for HEP events. Physics objects such as particles, vertices and collisions can easily be stored, accessed and manipulated. Bookkeeping of relations between these objects (like decay trees, vertex and collision separation, etc.) including deep copies is fully provided by the relation management. Event container and associated objects represent a uniform interface for algorithms and facilitate the parallel development and evaluation of different physics interpretations of individual events. So-called analysis factories, which actively identify and distinguish different physics processes and study systematic uncertainties, can easily be realized with the PAX toolkit. PAX is officially released to experiments at Tevatron and LHC. Being explored by a growing user community, it is applied in a number of complex physics analyses, two of which are presented here. We report the successful application in studies of t-tbar production at the Tevatron and Higgs searches in the channel t-tbar-Higgs at the LHC and give a short outlook on further developments.

physics.data-an↗