A5057262083- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Radiation Dose and Imaging
- Artificial Intelligence in Healthcare and Education
- Medical Imaging and Analysis
- AI in cancer detection
- Radiology practices and education
- COVID-19 diagnosis using AI
- Renal cell carcinoma treatment
- Aortic aneurysm repair treatments
- Ovarian cancer diagnosis and treatment
- Aortic Disease and Treatment Approaches
- Cardiac Imaging and Diagnostics
- Spine and Intervertebral Disc Pathology
Humanitas University
2022-2024
IRCCS Humanitas Research Hospital
2022-2024
Istituti di Ricovero e Cura a Carattere Scientifico
2021
Vita-Salute San Raffaele University
2021
Abstract Purpose To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research of radiomics studies. Methods We conducted an online modified Delphi study with group international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members identify the items be voted; Stage#3, four rounds exercise by panelists determine eligible for METRICS their weights. The...
To investigate the intra- and inter-rater reliability of total radiomics quality score (RQS) reproducibility individual RQS items' in a large multireader study.
This article's main contributions are twofold: 1) to demonstrate how apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice domain of healthcare and 2) investigate research question what does "trustworthy AI" mean at time COVID-19 pandemic. To this end, we present results a post-hoc self-assessment evaluate trustworthiness an system predicting multiregional score conveying degree lung compromise patients, developed verified by...
Abstract Background Differentiating radionecrosis from neoplastic progression after stereotactic radiosurgery (SRS) for brain metastases is a diagnostic challenge. Previous studies have often been limited by datasets lacking histologically confirmed diagnoses. This study aimed to develop automated models distinguishing disease on MRI, utilizing cases with definitive histopathological confirmation. Methods multi-center retrospective included patients who underwent surgical resection suspected...
To evaluate the methodological rigor of radiomics-based studies using noninvasive imaging in ovarian setting.Multiple medical literature archives (PubMed, Web Science, and Scopus) were searched to retrieve original focused on computed tomography (CT), magnetic resonance (MRI), ultrasound (US), or positron emission (PET) radiomics for disorders' assessment. Two researchers consensus evaluated each investigation quality score (RQS). Subgroup analyses performed assess whether total RQS varied...
Abstract Radiomics features (RFs) studies have showed limitations in the reproducibility of RFs different acquisition settings. To date, using CT images mainly rely on phantoms, due to harness patient exposure X-rays. The provided CadAIver dataset has aims evaluating how scanner parameters effect radiomics cadaveric donor. comprises 112 unique acquisitions a truck acquired 3 scanners varying KV, mA, field-of-view, and reconstruction kernel Technical validation comprehensive univariate...
Radiomics features (RFs) serve as quantitative metrics to characterize shape, density/intensity, and texture patterns in radiological images. Despite their promise, RFs exhibit reproducibility challenges across acquisition settings, thus limiting implementation into clinical practice. In this investigation, we evaluate the effects of different CT scanners protocols (KV, mA, field-of-view, reconstruction kernel settings) on extracted from lumbar vertebrae a cadaveric trunk. Employing...
Aortic injury represents a rare but potentially fatal complication of invasive coronary angiography. The authors present series four patients with aortic after angiography and intervention (mean age, 71 years; three women). In patients, CT showed subintimal staining from undiluted contrast media (CM) in the root no communication to lumen. Short-term follow-up resolution CM all patients. Classic dissection occurred one patient, false lumen root. Preliminary evidence suggests that iatrogenic...