A5057543570- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Glioma Diagnosis and Treatment
- Hepatocellular Carcinoma Treatment and Prognosis
- AI in cancer detection
- Medical Imaging and Analysis
- Liver Disease Diagnosis and Treatment
- Sarcoma Diagnosis and Treatment
- Brain Tumor Detection and Classification
- MRI in cancer diagnosis
- Geophysical Methods and Applications
- Salivary Gland Tumors Diagnosis and Treatment
- Advanced MRI Techniques and Applications
Fraunhofer Institute for Digital Medicine
2015-2022
University of Bremen
2019-2022
Brigham and Women's Hospital
2019-2022
Harvard University
2019-2022
Knowledge of the exact tumor location and structures at risk in its vicinity are crucial for neurosurgical interventions. Neuronavigation systems support navigation within patient's brain, based on preoperative MRI (preMRI). However, increasing tissue deformation during course resection reduces accuracy preMRI. Intraoperative ultrasound (iUS) is therefore used as real-time intraoperative imaging. Registration preMRI iUS remains a challenge due to different or varying contrasts Here, we...
We aimed to develop a predictive model of disease severity for cirrhosis using MRI-derived radiomic features the liver and spleen compared it existing metrics MELD score clinical decompensation. The is compiled solely by blood parameters, so far, was not investigated if extracted image-based have potential reflect potentially complement calculated score.This retrospective study eligible patients with ([Formula: see text]) who underwent contrast-enhanced MR screening protocol hepatocellular...
Radiomics extracts quantitative image features to identify biomarkers for characterizing disease. Our aim was characterize the ability of radiomic extracted from magnetic resonance (MR) imaging liver and spleen detect cirrhosis by comparing patients with those without cirrhosis.This retrospective study compared MR-derived between undergoing hepatocellular carcinoma screening intraductal papillary mucinous neoplasm surveillance 2015 2018 using same protocol. Secondary analyses stratified...
Segmentation of anatomical structures in intraoperative ultrasound (iUS) images during image-guided interventions is challenging. Anatomical variances and the uniqueness each procedure impede robust automatic image analysis. In addition, acquisition itself, especially acquired freehand by multiple physicians, subject to major variability. this paper we present a fully neural-network-based segmentation central brain on B-mode images. For our study used iUS data sets from 18 patients,...