A5057378251- Radiomics and Machine Learning in Medical Imaging
- Prostate Cancer Diagnosis and Treatment
- Medical Image Segmentation Techniques
- MRI in cancer diagnosis
- Advanced MRI Techniques and Applications
- Prostate Cancer Treatment and Research
- Advanced Radiotherapy Techniques
- Advanced Neuroimaging Techniques and Applications
- Computational Geometry and Mesh Generation
- Image and Signal Denoising Methods
- Tensor decomposition and applications
- Urinary Bladder and Prostate Research
- Colorectal Cancer Surgical Treatments
- Cell Image Analysis Techniques
- Robotics and Sensor-Based Localization
- Advanced Fluorescence Microscopy Techniques
- Image Processing Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Medical Imaging and Analysis
- Advanced X-ray and CT Imaging
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Advanced Image Processing Techniques
- Blind Source Separation Techniques
- AI in cancer detection
University of Bergen
2007-2020
Haukeland University Hospital
2017-2020
University Hospital Carl Gustav Carus
2020
OncoRay
2020
Johns Hopkins University
2020
Technische Universität Dresden
2020
National Center for Tumor Diseases
2020
German Cancer Research Center
2020
Helmholtz-Zentrum Dresden-Rossendorf
2020
The image biomarker standardisation initiative (IBSI) is an independent international collaboration which works towards standardising the extraction of biomarkers from acquired imaging for purpose high-throughput quantitative analysis (radiomics). Lack reproducibility and validation studies considered to be a major challenge field. Part this lies in scantiness consensus-based guidelines definitions process translating into biomarkers. IBSI therefore seeks provide nomenclature definitions,...
To investigate whether magnetic resonance (MR) radiomic features combined with machine learning may aid in predicting extraprostatic extension (EPE) high- and non-favorable intermediate-risk patients prostate cancer.To the diagnostic performance of radiomics to detect EPE.MR were extracted from 228 patients, whom 86 diagnosed EPE, using lesion segmentations. Prediction models built Random Forest. Further, EPE was also predicted a clinical nomogram routine radiological interpretation assessed...
Background and purposeHigh-risk prostate cancer patients are frequently treated with external-beam radiotherapy (EBRT). Of all receiving EBRT, 15–35% will experience biochemical recurrence (BCR) within five years. Magnetic resonance imaging (MRI) is commonly acquired as part of the diagnostic procedure imaging-derived features have shown promise in tumour characterisation prediction. We investigated value extracted from pre-treatment T2w anatomical MRI to predict year high-risk...
Purpose To validate the MRI grading system proposed by Mehralivand et al in 2019 (the "extraprostatic extension [EPE] grade") an independent cohort and to compare EPE with interpretation on basis of a five-point Likert score ("EPE Likert"). Materials Methods A total 310 consecutive patients underwent multiparametric according standardized institutional protocol before radical prostatectomy was performed using same 1.5-T unit at single institution between 2010 2012. Two radiologists blinded...
To improve preoperative risk stratification for prostate cancer (PCa) by incorporating multiparametric MRI (mpMRI) features into tools PCa, CAPRA and D'Amico.807 consecutive patients operated on robot-assisted radical prostatectomy at our institution during the period 2010-2015 were followed to identify biochemical recurrence (BCR). 591 eligible final analysis. We employed stepwise backward likelihood methodology penalised Cox cross-validation most significant predictors of BCR including...
A fast and accurate segmentation of organs at risk, such as the healthy colon, would be benefit for planning radiotherapy, in particular an adaptive scenario. For treatment pelvic tumours, a great challenge is most adjacent sensitive parts gastrointestinal tract, sigmoid descending colon. We propose semi-automated method to segment these bowel using marching (FM) method. Standard 3D computed tomography (CT) image data obtained from routine radiotherapy were used. Our pre-processing steps...
ORIGINAL RESEARCH article Front. Neuroinform., 26 July 2013 Volume 7 - | https://doi.org/10.3389/fninf.2013.00013
High resolution (HR) volume reconstruction is a collection of post-processing algorithms applied to enhance out-of-plane or sub-voxel image quality. In this work, we use HR combine three orthogonal magnetic resonance (MR) acquisitions the prostate, i.e. axial, sagittal and coronal. The MR volumes are first resampled, registered intensity-corrected. Then reconstruct using maximum posteriori (MAP) approach with Markov-Random-Field-based (MRF) regularization. Our preliminary results promising...
T2-weighted magnetic resonance images (T2W MRI) of prostate cancer are usually acquired with a large slice thickness compared to in-plane voxel dimensions and the minimal significant malignant tumour size. This causes negative partial volume effect, decreasing precision volumetry complicating 3D texture analysis images. At same time, three orthogonal, anisotropic acquisitions overlapping fields view often allow insight into from different anatomical planes. It is desirable reconstruct an...
In this paper, we present a new unsupervised prostate cancer (PCa) localization algorithm for the peripheral zone (PZ), utilizing well-established rules used in clinical PCa diagnosis from mpMRI data. We perform clustering on ADC and DWI images accompanied by T2W examination of clustered regions then combined with DCE findings. For each 10 analysed patients, obtain likelihood map showing suspicious areas. evaluate our method comparison against radiological MR tumor segmentations delineations...
Traditionally, analysis of Dynamic Contrast-Enhanced Magnetic Resonance Images (DCE MRI) requires pharmacokinetic modelling to derive quantitative physiological parameters the tissue. Modelling, however, is a complex task and many competing models contrast agent kinetics tissue structure were proposed. Alternatively, raw DCE data could be analysed find correlation with pathology in or other desired effects, for example by clustering. In this paper, we propose new method MRI timeseries We...