A5083196840- Advanced Radiotherapy Techniques
- Medical Imaging Techniques and Applications
- Radiation Therapy and Dosimetry
- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- Medical Imaging and Analysis
- Advanced X-ray and CT Imaging
- Medical Image Segmentation Techniques
- Radiation Detection and Scintillator Technologies
- Nuclear Physics and Applications
- Radiation Dose and Imaging
- AI in cancer detection
- Digital Radiography and Breast Imaging
- Advanced Vision and Imaging
- Atomic and Subatomic Physics Research
- Surgical Simulation and Training
- Augmented Reality Applications
- Breast Cancer Treatment Studies
- Anatomy and Medical Technology
- Photoacoustic and Ultrasonic Imaging
- Head and Neck Cancer Studies
- Optical Systems and Laser Technology
- Advances in Oncology and Radiotherapy
- Prostate Cancer Diagnosis and Treatment
Ludwig-Maximilians-Universität München
2018-2025
Bayer (Germany)
2023-2024
LMU Klinikum
2022-2024
Politecnico di Milano
2010-2019
National Center for Oncological Hadrontherapy
2011-2016
University of Wollongong
2012-2016
University of Wisconsin–Madison
2016
Ingham Institute
2016
European Institute of Oncology
2015-2016
University Hospital Heidelberg
2016
Purpose: Intensity modulated proton therapy (IMPT) of head and neck (H&N) cancer patients may be improved by plan adaptation. The decision to adapt the treatment based on a dose recalculation current anatomy requires diagnostic quality computed tomography (CT) scan patient. As gantry‐mounted cone beam CT (CBCT) scanners are currently being offered vendors, they offer daily or weekly updates patient anatomy. CBCT image not sufficient for accurate calculation it is likely necessary perform...
Abstract Objectives Deep learning-based auto-segmentation of head and neck cancer (HNC) tumors is expected to have better reproducibility than manual delineation. Positron emission tomography (PET) computed (CT) are commonly used in tumor segmentation. However, current methods still face challenges handling whole-body scans where a selection bounding box may be required. Moreover, different institutions might apply guidelines for This study aimed at exploring the auto-localization...
In-room cine-MRI guidance can provide non-invasive target localization during radiotherapy treatment. However, in order to cope with finite imaging frequency and system latencies between dose delivery, tumour motion prediction is required. This work proposes a framework for dedicated guidance, aiming at quantifying the geometric uncertainties introduced by this process both tracking beam gating. The position, identified through scale invariant features detected slices, estimated...
Abstract Objective. Gated beam delivery is the current clinical practice for respiratory motion compensation in MR-guided radiotherapy, and further research ongoing to implement tracking. To manage intra-fractional using multileaf collimator tracking total system latency needs be accounted real-time. In this study, long short-term memory (LSTM) networks were optimized prediction of superior–inferior tumor centroid positions extracted from clinically acquired 2D cine MRIs. Approach. We used...
Purpose : The goal of this study is to investigate the advantages large scale optimization methods vs conventional classification techniques in predicting acute toxicity for urinary bladder and rectum due prostate irradiation. Methods Clinical dosimetric data 321 patients undergoing conformal radiotherapy were recorded. Gastro-intestinal genito-urinary toxicities scored according Radiation Therapy Oncology Group/European Organization Research Treatment Cancer (RTOG/EORTC) scale. Patients...
Adaptive radiation therapy (ART) aims at compensating for anatomic and pathological changes to improve delivery along a treatment fraction sequence. Current ART protocols require time-consuming manual updating of all volumes interest on the images acquired during treatment. Deformable image registration (DIR) contour propagation stand as state method automate process, but lack DIR quality control methods hinder an introduction into clinical practice. We investigated scale invariant feature...
Purpose: Four‐dimensional magnetic resonance imaging (4DMRI) is an emerging technique in radiotherapy treatment planning for organ motion quantification. In this paper, the authors present a novel 4DMRI retrospective image‐based sorting method, providing reduced artifacts than using standard monodimensional external respiratory surrogate. Methods: Serial interleaved 2D multislice MRI data were acquired from 24 liver cases (6 volunteers + 18 patients) to test proposed sorting. Image...
The ability to perform dose recalculation on the anatomy of day is important in context adaptive proton therapy.The objective this study was investigate use deformable image registration (DIR) and cone beam CT (CBCT) imaging generate daily stopping power distribution patient.We investigated deformation planning scan (pCT) onto CBCT images a virtual (vCT) using phantom designed for head neck (H & N) region.The imaged at scanner configuration, yielding pCT deformed, treatment reference...
In-room MRI is a promising image guidance strategy in external beam radiotherapy to acquire volumetric information for moving targets. However, limitations spatio-temporal resolution led several authors use 2D orthogonal images guidance. The aim of this work present method concurrently compensate non-rigid tumour motion and provide an approach 3D reconstruction from cine-MRI slices MRI-guided treatments.Free-breathing sagittal/coronal interleaved were acquired addition pre-treatment volume...
Real-time optical surface imaging systems offer a non-invasive way to monitor intra-fraction motion of patient's thorax during radiotherapy treatments. Due lack point correspondence in dynamic acquisition, such cannot currently provide 3D tracking at specific landmarks, as available technologies based on passive markers. We propose apply deformable mesh registration extract trajectories from markerless imaging, thus yielding multi-dimensional breathing traces. The investigated approach is...
Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient's image and perform a binary classification occurrence given clinical endpoint. In this work, 2D-CNN 3D-CNN distant metastasis (DM) in head neck patients were extended time-to-event analysis. newly built CNNs incorporate censoring information...