A5008015416- Advanced Radiotherapy Techniques
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Management of metastatic bone disease
- Medical Imaging and Analysis
- Glioma Diagnosis and Treatment
- Radiation Therapy and Dosimetry
- Head and Neck Cancer Studies
- Brain Tumor Detection and Classification
- Dental Radiography and Imaging
- Radiation Effects and Dosimetry
- Medical Image Segmentation Techniques
- Brain Metastases and Treatment
- Advances in Oncology and Radiotherapy
- Lung Cancer Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- Radiation Detection and Scintillator Technologies
- AI in cancer detection
- Spine and Intervertebral Disc Pathology
- Nuclear Physics and Applications
- Hip and Femur Fractures
- Material Properties and Applications
- Colorectal Cancer Surgical Treatments
- Innovations in Concrete and Construction Materials
The University of Texas MD Anderson Cancer Center
2018-2025
University of Houston
2019-2022
The University of Texas Health Science Center at Houston
2018-2021
Dongnam Institute of Radiological & Medical Sciences
2013-2016
Dong-A University
2015
Duke University
2013-2014
Yonsei University
2000-2007
Severance Hospital
2004
Advanced Materials Technology (United States)
1989
University of Washington
1989
To develop a head and neck normal structures autocontouring tool that could be used to automatically detect the errors in autocontours from clinically validated tool.An based on convolutional neural networks (CNN) was developed for 16 of tested identify contour multiatlas-based system (MACS). The computed tomography (CT) scans clinical contours 3495 patients were semiautomatically curated train validate CNN-based tool. final accuracy evaluated by calculating Sørensen-Dice similarity...
Purpose Radiation therapy treatment planning is a time‐consuming and iterative manual process. Consequently, plan quality varies greatly between within institutions. Artificial intelligence shows great promise in improving reducing times. This technical note describes our participation the American Association of Physicists Medicine Open Knowledge‐Based Planning Challenge (OpenKBP), competition to accurately predict radiation dose distributions. Methods A three‐dimensional (3D) densely...
To develop a tool for the automatic contouring of clinical treatment volumes (CTVs) and normal tissues radiotherapy planning in cervical cancer patients.
To develop a deep learning model that generates consistent, high-quality lymph node clinical target volumes (CTV) contours for head and neck cancer (HNC) patients, as an integral part of fully automated radiation treatment planning workflow.
Accurate clinical target volume (CTV) delineation is essential to ensure proper tumor coverage in radiation therapy. This a particularly difficult task for head-and-neck cancer patients where detailed knowledge of the pathways microscopic spread necessary. paper proposes solution auto-segment these volumes oropharyngeal using two-channel 3D U-Net architecture. The first channel feeds network with patient's CT image providing anatomical context, whereas second provides location and...
To develop an automated workflow for rectal cancer three-dimensional conformal radiotherapy treatment planning that combines deep-learning(DL) aperture predictions and forward-planning algorithms. We designed algorithm to automate the clinical with field-in-field. DL models were trained, validated, tested on 555 patients automatically generate shapes primary boost fields. Network inputs digitally reconstructed radiography, gross tumor volume(GTV), nodal GTV. A physician scored each 20 a...
Abstract Manually delineating upper abdominal organs at risk (OARs) is a time-consuming task. To develop deep-learning-based tool for accurate and robust auto-segmentation of these OARs, forty pancreatic cancer patients with contrast-enhanced breath-hold computed tomographic (CT) images were selected. We trained three-dimensional (3D) U-Net ensemble that automatically segments all organ contours concurrently the self-configuring nnU-Net framework. Our tool’s performance was assessed on...
Objective.To establish an open framework for developing plan optimization models knowledge-based planning (KBP).Approach.Our includes radiotherapy treatment data (i.e. reference plans) 100 patients with head-and-neck cancer who were treated intensity-modulated radiotherapy. That also high-quality dose predictions from 19 KBP that developed by different research groups using out-of-sample during the OpenKBP Grand Challenge. The input to four fluence-based mimicking form 76 unique pipelines...
Abstract Purpose Pediatric patients with medulloblastoma in low‐ and middle‐income countries (LMICs) are most treated 3D‐conformal photon craniospinal irradiation (CSI), a time‐consuming, complex treatment to plan, especially resource‐constrained settings. Therefore, we developed tested CSI autoplanning tool for varying patient lengths. Methods materials Autocontours were generated deep learning model trained:tested (80:20 ratio) on 143 pediatric CT scans (patient ages: 2–19 years, median =...
To determine the most accurate similarity metric when using an independent system to verify automatically generated contours.A reference autocontouring (primary create clinical contours) and a verification (secondary test primary were used generate pair of 6 female pelvic structures (UteroCervix [uterus + cervix], CTVn [nodal target volume (CTV)], PAN [para-aortic lymph nodes], bladder, rectum, kidneys) on 49 CT scans from our institution 38 other institutions. Additionally, clinically...
PurposeComplicating factors such as time pressures, anatomic variants in the spine, and similarities adjacent vertebrae are associated with incorrect level treatments of spine. The purpose this work was to mitigate challenges by fully automating treatment planning process for diagnostic simulation computed tomography (CT) scans.Methods MaterialsVertebral bodies labeled on CT scans any length using 2 intendent deep-learning models—mirroring different experts labeling Then, a U-Net++...
Background/Objectives: Stereotactic body radiation therapy (SBRT) for skull base reirradiation is particularly challenging, as patients have already received substantial doses to the region, and nearby normal organs may approached their tolerance limit from prior treatments. In this study, we reviewed characteristics capabilities of four advanced external beam delivery systems modern treatment planning evaluated plan quality each technique using patient cases. Methods: SBRT plans were...
Pancreatic gross tumor volume (GTV) delineation is challenging due to their variable morphology and uncertain ground truth. Previous deep learning-based auto-segmentation methods have struggled handle tasks with truth not accommodated stylistic customizations. We aim develop a human-in-the-loop pancreatic GTV segmentation tool using Tversky ensembles by leveraging uncertainty estimation techniques. In this study, we utilized total of 282 patients from the pancreas task Medical Segmentation...
Abstract Background Hippocampal avoidance whole‐brain radiotherapy (HA‐WBRT) is designed to spare cognitive function by reducing radiation dose the hippocampus during treatment of brain metastases. Current manual planning methods can be time‐consuming and may vary in quality, necessitating development automated approaches streamline process ensure consistency. Purpose To automate hippocampal planning. Methods Our algorithm automatically contours organs‐at‐risk (OARs) hippocampal‐avoidance...
Accurate delineation of orodental structures on radiotherapy CT images is essential for dosimetric assessments and dental decisions. We propose a deep-learning auto-segmentation framework individual teeth mandible/maxilla sub-volumes aligned with the ClinRad ORN staging system. Mandible maxilla were manually defined, differentiating between alveolar basal regions, labelled individually. For each task, DL segmentation model was independently trained. A Swin UNETR-based used mandible...
To develop an automated workflow for rectal cancer three-dimensional conformal radiotherapy (3DCRT) treatment planning that combines deep learning (DL) aperture predictions and forward-planning algorithms.We designed algorithm to automate the clinical 3DCRT with field creations field-in-field (FIF) planning. DL models (DeepLabV3+ architecture) were trained, validated, tested on 555 patients automatically generate shapes primary (posterior-anterior [PA] opposed laterals) boost fields. Network...
To fully automate CT-based cervical cancer radiotherapy by automating contouring and planning for three different treatment techniques.We automated techniques locally advanced cancer: 2D 4-field-box (4-field-box), 3D conformal (3D-CRT), volumetric modulated arc therapy (VMAT). These auto-planning algorithms were combined with a previously developed auto-contouring system. improve the quality of 3D-CRT plans, we used an in-house, field-in-field (FIF) automation program. Thirty-five plans...