A5063892307- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Prostate Cancer Diagnosis and Treatment
- MRI in cancer diagnosis
- Explainable Artificial Intelligence (XAI)
- Advanced Radiotherapy Techniques
- Medical Image Segmentation Techniques
- Advanced MRI Techniques and Applications
- Image Retrieval and Classification Techniques
- Prostate Cancer Treatment and Research
- Advanced Neural Network Applications
- Medical Imaging and Analysis
- Medical Imaging Techniques and Applications
University of Freiburg
2020-2025
University Medical Center Freiburg
2020-2025
MathWorks (United States)
2022
German Cancer Research Center
2020
Deutschen Konsortium für Translationale Krebsforschung
2020
Abstract Automatic prostate tumor segmentation is often unable to identify the lesion even if multi-parametric MRI data used as input, and output difficult verify due lack of clinically established ground truth images. In this work we use an explainable deep learning model interpret predictions a convolutional neural network (CNN) for segmentation. The CNN uses U-Net architecture which was trained on from 122 patients automatically segment gland lesions. addition, co-registered whole mount...
Abstract Background Automatic tumor segmentation based on Convolutional Neural Networks (CNNs) has shown to be a valuable tool in treatment planning and clinical decision making. We investigate the influence of 7 MRI input channels CNN with respect performance head&neck cancer. Methods Head&neck cancer patients underwent multi-parametric including T2w, pre- post-contrast T1w, T2*, perfusion (k trans , v e ) diffusion (ADC) measurements at 3 time points before during...
Abstract Background In this work, we compare input level, feature level and decision data fusion techniques for automatic detection of clinically significant prostate lesions (csPCa). Methods Multiple deep learning CNN architectures were developed using the Unet as baseline. The CNNs use both multiparametric MRI images (T2W, ADC, High b-value) quantitative clinical (prostate specific antigen (PSA), PSA density (PSAD), gland volume & gross tumor (GTV)), only mp-MRI ( n = 118), input....
MR guidance is used during therapy to detect and compensate for lesion motion. T2 -weighted MRI often has a superior contrast in comparison T1 real-time imaging. The purpose of this work was design fast sequence capable simultaneously acquiring two orthogonal slices, enabling tracking lesions.To generate slices simultaneously, (Ortho-SFFP-Echo) designed that samples the spin echo (S- ) signal TR-interleaved acquisition slices. Slice selection phase-encoding directions are swapped between...
Cross modal image syntheses is gaining significant interests for its ability to estimate target images of a different modality from given set source images,like estimating MR MR, CT, CT PET etc, without the need an actual acquisition.Though they show potential applications in radiation therapy planning,image super resolution, atlas construction, segmentation etc.The synthesis results are not as accurate acquisition.In this paper,we address problem multi by proposing fully convolutional deep...
Abstract Automatic prostate tumor segmentation is often unable to identify the lesion even if in multi-parametric MRI data used as input, and output difficult verify due lack of clinically established ground truth images. In this work we use an explainable deep learning model interpret predictions a convolutional neural network (CNN) for segmentation. The CNN uses U-Net architecture which was trained on from 122 patients automatically segment gland lesions. addition, co-registered whole...
A convolutional neural network was implemented to automatically segment tumors in multi-parametric MRI data. The influence of the variability ground truth data evaluated for automated prostate tumor segmentation. Therefore, agreement between predictions CNN measured with co-registered whole mount histopathology images and contours drawn by an expert radio-oncologist. results indicate that can discriminate from healthy tissue rather than mimicking radiologist.
Background/Aim: We examined the prognostic value of intraprostatic gross tumour volume (GTV) as measured by multiparametric MRI (mpMRI) in patients with prostate cancer following (primary) external beam radiation therapy (EBRT). Patients and Methods: In a retrospective monocentric study, we analysed (PCa) after EBRT. GTV was delineated pre-treatment mpMRI (GTV-MRI) using T2-weighted images. Cox-regression analyses were performed considering biochemical failure recurrence-free survival (BRFS)...