A5080623230- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Colorectal Cancer Surgical Treatments
- Hepatocellular Carcinoma Treatment and Prognosis
- Colorectal and Anal Carcinomas
- Advanced MRI Techniques and Applications
- Colorectal Cancer Treatments and Studies
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Pancreatic and Hepatic Oncology Research
- Genetic factors in colorectal cancer
- Gastric Cancer Management and Outcomes
- Colorectal Cancer Screening and Detection
- Occupational and environmental lung diseases
- Lung Cancer Diagnosis and Treatment
- Radiology practices and education
- Radiation Dose and Imaging
- Bacterial Infections and Vaccines
- Bone and Joint Diseases
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Pelvic floor disorders treatments
- Hematological disorders and diagnostics
- Advanced Neuroimaging Techniques and Applications
- Bone health and treatments
- Lung Cancer Research Studies
Institute of Cancer Research
2023-2025
Royal Marsden Hospital
2022-2025
Oncode Institute
2020-2024
The Netherlands Cancer Institute
2020-2024
Royal Marsden NHS Foundation Trust
2023-2024
Brescia University
2023
University of Brescia
2020-2023
To investigate sources of variation in a multicenter rectal cancer MRI dataset focusing on hardware and image acquisition, segmentation methodology, radiomics feature extraction software.
Abstract Purpose To evaluate intra-patient and interobserver agreement in patients who underwent liver MRI with gadoxetic acid using two different multi-arterial phase (AP) techniques. Methods A total of 154 prospectively enrolled clinical acid-enhanced twice within 12 months, algorithms: CAIPIRINHA-VIBE TWIST-VIBE. For every patient, breath-holding time, body mass index, sex, age were recorded. The without contrast media the APs independently evaluated by radiologists quantified Gibbs...
Abstract Purpose Pre-treatment knowledge of the anticipated response rectal tumors to neoadjuvant chemoradiotherapy (CRT) could help further optimize treatment. Van Griethuysen et al. proposed a visual 5-point confidence score predict likelihood on baseline MRI. Aim was evaluate this in multicenter and multireader study setting compare it two simplified (4-point 2-point) adaptations terms diagnostic performance, interobserver agreement (IOA), reader preference. Methods Twenty-two...
To compare relative fat fraction (rFF) of active bone lesions from breast, prostate and myeloma malignancies normal marrow; to assess its inter-reader agreement.Patients with breast (n = 26), 32) cancer 52) were retrospectively evaluated. 110 baseline rFF maps whole-body MRI reviewed by two radiologists. Regions interest for up four focal in each patient drawn on maps, one at the cervicothoracic spine, lumbosacral pelvis extremity. The mean standard deviation recorded. marrow was measured...
As the management of gastrointestinal malignancy has evolved, tumor response assessment expanded from size-based assessments to those that include enhancement, in addition functional data such as derived PET and diffusion-weighted imaging. Accurate interpretation therefore requires knowledge imaging modalities used malignancy, anticancer therapies, biology. Targeted therapies immunotherapy pose additional considerations due unique patterns drug toxicity; a consequence, criteria have been...
Abstract Background Microsatellite instability (MSI) status is a strong predictor of response to immunotherapy colorectal cancer. Radiogenomic approaches promise the ability gain insight into underlying tumor biology using non-invasive routine clinical images. This study investigates association between morphology and MSI versus microsatellite stability (MSS), validating novel radiomic signature on an external multicenter cohort. Methods Preoperative computed tomography scans with matched...
Introduction The spleen is a lymphoid organ and we hypothesize that clinical benefit to immunotherapy may present with an increase in splenic volume during treatment. purpose of this study was investigate whether changes could be observed those showing versus not pembrolizumab treatment non-small cell lung cancer (NSCLC) patients. Materials methods In study, 70 patients locally advanced or metastatic NSCLC treated pembrolizumab; who underwent baseline CT scan within 2 weeks before follow-up...
Abstract Objectives Diffusion-weighted imaging (DWI) with simultaneous multi-slice (SMS) acquisition and advanced processing can accelerate time improve MR image quality. This study evaluated the quality apparent diffusion coefficient (ADC) measurements of free-breathing DWI acquired from patients liver metastases using a prototype SMS-DWI (with/without an option) conventional DWI. Methods Four schemes were compared in pilot 5-patient cohort; three further assessed 24-patient cohort. Two...
Abstract Background The purpose of this case report is to emphasize the importance curing any clinical radiological elements in historical period, especially area endemic coronavirus disease 19 (COVID-19) such as Lombardy and stress management asymptomatic patient, their crucial role spread contagion. Case presentation We reported incidental diagnosis interstitial pneumonia by first finding on whole-body MR (WB-MR) patient affected multiple myeloma (MM), with a negative respiratory symptoms...
Motivation: Deep learning (DL) reconstructions can improve image quality and/or reduce acquisition time in diffusion-weighted imaging (DWI). Goal(s): This study aims to assess, quantitatively and qualitatively, DL-accelerated DWI 50 patients with colorectal cancer undergoing liver examinations. Approach: Three series are compared: a moderately-accelerated DL-DWI, corresponding standard reconstruction highly-accelerated DL-DWI. Results: The DL method provides better than reconstruction. Its...
Motivation: With increasing AI adoption in MR-reconstructions, robust quality assessment becomes paramount. This study aims to ensure that AI-techniques meet clinical requirements at implementation and longitudinally. Goal(s): 1) Compare image of AI-imaging with standard techniques anorectal cancer. 2) Develop longitudinal control (QC) assessments capable detecting changes AI-reconstructions without resource-intensive evaluations. Approach: A prospective involving 40 patients utilised...
Purpose: Pleural plaques (PPs) are morphologic manifestations of long-term asbestos exposure. The relationship between PP and lung function is not well understood, whereas the time-consuming nature delineation to obtain volume impedes research. To automate laborious task delineation, we aimed develop automatic artificial intelligence (AI)–driven segmentation PP. Moreover, explore pleural plaque (PPV) pulmonary tests. Materials Methods: Radiologists manually delineated PPs retrospectively in...
An advanced reconstruction method, which employs a neural network trained on high resolution data to conduct interpolation, combined with iterative denoising, was applied in contrast-enhanced liver imaging patients receiving hepatocyte-specific contrast agent. The provides improved image quality, better contrast-to-noise ratio, vessel edge sharpness, and lesion sharpness compared the standard using zero-filling interpolation without reconstruction. improvement quality also observed faster...