A5100783879- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Machine Learning in Healthcare
- Medical Imaging Techniques and Applications
- COVID-19 diagnosis using AI
- COVID-19 Clinical Research Studies
- Advanced Radiotherapy Techniques
- Artificial Intelligence in Healthcare and Education
- Advanced X-ray and CT Imaging
- Esophageal Cancer Research and Treatment
- Gastric Cancer Management and Outcomes
- Lung Cancer Diagnosis and Treatment
- MRI in cancer diagnosis
- Statistical Methods in Clinical Trials
- Colorectal Cancer Screening and Detection
- 3D Shape Modeling and Analysis
- Microbial Applications in Construction Materials
- Endometrial and Cervical Cancer Treatments
- Explainable Artificial Intelligence (XAI)
- Advanced Chemical Sensor Technologies
- Spectroscopy and Chemometric Analyses
- Mental Health Research Topics
- Management of metastatic bone disease
- Cancer Mechanisms and Therapy
- Parkinson's Disease Mechanisms and Treatments
University of Maryland, Baltimore
2025
Human Genome Sciences (United States)
2025
Maastricht University
2020-2024
Cleveland Clinic
2024
Jadavpur University
2011-2024
Ramakrishna Mission Vivekananda Educational and Research Institute
2024
McGill University Health Centre
2017-2022
Montreal General Hospital
2022
McGill University
2018-2022
Icometrix (Belgium)
2022
Abstract Traditional radiomics involves the extraction of quantitative texture features from medical images in an attempt to determine correlations with clinical endpoints. We hypothesize that convolutional neural networks (CNNs) could enhance performance traditional radiomics, by detecting image patterns may not be covered a radiomic framework. test this hypothesis training CNN predict treatment outcomes patients head and neck squamous cell carcinoma, based solely on their pre-treatment...
Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires ability to integrate clinical features extracted from acquired by different scanners protocols improve stability robustness. Previous studies have described various computational approaches fuse single modality datasets. However, these surveys rarely focused on evaluation metrics lacked checklist for harmonisation studies. In this systematic review, we...
Background Stratifying high-risk histopathologic features in endometrial carcinoma is important for treatment planning. Radiomics analysis at preoperative MRI holds potential to identify phenotypes. Purpose To evaluate the performance of multiparametric three-dimensional radiomics-based machine learning models differentiating low- from markers—deep myometrial invasion (MI), lymphovascular space (LVSI), and high-grade status—and advanced-stage carcinoma. Materials Methods This dual-center...
Purpose: The distribution of a radiomic feature can differ between two institutions due to, for example, different image acquisition parameters, imaging systems, and contouring (i.e., tumor delineation) variations clinicians. We aimed to develop effective statistical methods successfully apply radiomics-based predictive model an external dataset. Theory: Two common normalization methods, rescaling standardization, were evaluated suitability in reducing variability institutions....
Abstract Purpose: Small cell lung cancer (SCLC) is a highly aggressive and deadly malignancy. Two major factors contributing to the high mortality of SCLC are early metastasis rapid development therapy resistance. Recent research suggests upregulation epithelial-mesenchymal transition (EMT) program EMT transcription factor Twist1 correlated with accelerated tumor progression chemoradiation (CRT) resistance in SCLC. However, causal relationship between these aspects biology has not been...
This retrospective study investigated the value of pretreatment contrast-enhanced Magnetic Resonance Imaging (MRI)-based radiomics for prediction pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients. A total 292 patients, with 320 tumors, who were treated neo-adjuvant and underwent a MRI exam enrolled. As data collected two different hospitals five scanners varying acquisition protocols, three strategies split training validation datasets used....
Objective To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such could be precursor to implementing smart lockdowns vaccine distribution strategies. Methods The training cohort comprised 2337 inpatients from nine hospitals in Netherlands. clinical outcome was death within 21 days of being discharged. features were derived electronic health records collected during admission....
In this paper, we propose a novel computer vision technique to measure respiration rate by counting the periodic thoracoabdominal motion in real-time using an inexpensive consumer grade camera. We compute component of optical flow parallel image gradient at each pixel, which is computationally operation. Then, find principal field gathering information over many frames. Subsequently, frame, along capture motion. Our method very simple, easy implement and needs no specialized hardware. This...
Purpose: Radiomic studies, where correlations are drawn between patients' medical image features and patient outcomes, often deal with small datasets. Consequently, results can suffer from lack of replicability stability. This paper establishes a methodology to assess reduce the impact statistical fluctuations that may occur in Such lead false discoveries, particularly when applying feature selection or machine learning (ML) methods commonly used radiomics literature. Methods: Two were...
Machine learning techniques are becoming increasingly popular in radiomics studies. They can handle high dimensional sets of features with higher robustness than usual statistical analyses, by capturing complex interactions between themselves and feature combinations clinical endpoints under investigation order to build efficient prognostic/predictive models. However, there is no "one fits all" solution deciding which algorithm the most accurate for a given application not always...
There is a cumulative risk of 20-40% developing brain metastases (BM) in solid cancers. Stereotactic radiotherapy (SRT) enables the application high focal doses radiation to volume and often used for BM treatment. However, SRT can cause adverse effects (ARE), such as necrosis, which sometimes irreversible damage brain. It therefore clinical interest identify patients at ARE. We hypothesized that models trained with radiomics features, deep learning (DL) patient characteristics or their...
Despite radical intent therapy for patients with stage III non-small-cell lung cancer (NSCLC), cumulative incidence of brain metastases (BM) reaches 30%. Current risk stratification methods fail to accurately identify these patients. As radiomics features have been shown predictive value, this study aims develop a model combining clinical factors BM development in radically treated NSCLC.Retrospective analysis two prospective multicentre studies. Inclusion criteria: adequately staged...
The aim of this study was to develop and evaluate a proof-of-concept open-source individualized Patient Decision Aid (iPDA) with group patients, physicians, computer scientists. iPDA developed based on the International Standards (IPDAS). A previously published questionnaire adapted used test user-friendliness content iPDA. contained 40 multiple-choice questions, answers were given 5-point Likert Scale (1–5) ranging from “strongly disagree” agree.” In addition questionnaire, semi-structured...