A5029636345- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Advanced Radiotherapy Techniques
- Sarcoma Diagnosis and Treatment
- Prostate Cancer Treatment and Research
- Digital Radiography and Breast Imaging
- Health Systems, Economic Evaluations, Quality of Life
- BIM and Construction Integration
- Radiation Dose and Imaging
- Prostate Cancer Diagnosis and Treatment
- Numerical methods in inverse problems
- Statistical Methods in Clinical Trials
- Cardiac, Anesthesia and Surgical Outcomes
- MRI in cancer diagnosis
- Lanthanide and Transition Metal Complexes
- Advanced MRI Techniques and Applications
- Optical and Acousto-Optic Technologies
- Biochemical Analysis and Sensing Techniques
- Geophysics and Sensor Technology
- Cancer Diagnosis and Treatment
- Gastric Cancer Management and Outcomes
- Healthcare Policy and Management
Istituto Oncologico Veneto
2019-2025
Istituti di Ricovero e Cura a Carattere Scientifico
2019-2025
University of Padua
2021-2024
University Hospital Carl Gustav Carus
2024
Helmholtz-Zentrum Dresden-Rossendorf
2024
Cardiff University
2024
TU Dresden
2024
National Center for Tumor Diseases
2024
University of Pennsylvania
2024
German Cancer Research Center
2024
Background The translation of radiomic models into clinical practice is hindered by the limited reproducibility features across software and studies. Standardization needed to accelerate this process bring radiomics closer deployment. Purpose To assess standardization level seven programs investigate agreement as a function built-in image preprocessing (eg, interpolation discretization), feature aggregation methods, morphological characteristics (ie, volume shape) region interest (ROI)....
In this study, we tested and compared radiomics deep learning-based approaches on the public LUNG1 dataset, for prediction of 2-year overall survival (OS) in non-small cell lung cancer patients. Radiomic features were extracted from gross tumor volume using Pyradiomics, while bi-dimensional slices by convolutional autoencoder. Both radiomic fed to 24 different pipelines formed combination four feature selection/reduction methods six classifiers. Direct classification through neural networks...
Purpose Interest in the field of radiomics is rapidly growing because its potential to characterize tumor phenotype and provide predictive prognostic information. Nevertheless, reproducibility robustness studies are hampered by lack standardization feature definition calculation. In context image biomarker initiative (IBSI), we investigated grade compliance explorer (IBEX), a free open‐source radiomic software, developed validated standardized‐IBEX (S‐IBEX), an adaptation IBEX IBSI. Methods...
Abstract Purpose A recently introduced commercial tool is tested to assess whether it able reduce the complexity of a treatment plan and improve deliverability without compromising overall quality. Methods Ten prostate ten oropharynx plans previously treated patients were reoptimized using aperture shape controller (ASC) in Eclipse TPS (Varian Medical Systems, Palo Alto, CA). The performance ASC was assessed terms quality metric, reduction through analysis 14 most common metrics, change 3D...
To study the feasibility of radiomic analysis baseline [18F]fluoromethylcholine positron emission tomography/computed tomography (PET/CT) for prediction biochemical recurrence (BCR) in a cohort intermediate and high-risk prostate cancer (PCa) patients.Seventy-four patients were prospectively collected. We analyzed three gland (PG) segmentations (i.e., PGwhole: whole PG; PG41%: having standardized uptake value - SUV > 0.41*SUVmax; PG2.5: 2.5) together with discretization steps 0.2, 0.4, 0.6)....
Abstract Background The application of semi-conductor detectors such as cadmium–zinc–telluride (CZT) in nuclear medicine improves extrinsic energy resolution and count sensitivity due to the direct conversion gamma photons into electric signals. A 3D-ring pixelated CZT system named StarGuide was recently developed implemented by GE HealthCare for SPECT acquisition. consists 12 detector columns with seven modules 16 × crystals, each an integrated parallel-hole tungsten collimator. axial...
The objective of this study was to evaluate a set radiomics-based advanced textural features extracted from 18F-FLT-PET/CT images predict tumor response neoadjuvant chemotherapy (NCT) in patients with locally breast cancer (BC).Patients operable (T2-T3, N0-N2, M0) or (T4, BC were enrolled. All underwent (six cycles every 3 weeks). Surgery performed within 4 weeks the end NCT. MD Anderson Residual Cancer Burden calculator used pathological response. 2 before start NCT and approximately after...
PET imaging is a pivotal tool for biomarker research aimed at personalized medicine. Leveraging the quantitative nature of requires knowledge plasma radiotracer concentration. Typically, arterial input function (AIF) obtained through cannulation, an invasive and technically demanding procedure. A less alternative, especially [18F]FDG, image-derived (IDIF), which, however, often correction partial volume effect (PVE), usually performed via venous blood samples. The aim this paper to present...
Abstract In radiology and oncology, radiomic models are increasingly employed to predict clinical outcomes, but their deployment has been hampered by lack of standardisation. This hindrance driven the international Image Biomarker Standardisation Initiative (IBSI) define guidelines for image pre-processing, standardise formulation nomenclature 169 features share two benchmark digital phantoms software calibration. However, better assess concordance tools, more heterogeneous needed. We...
e18000 Background: Radiomics is the computerized extraction of quantitative features from medical images, beyond level detail accessible to an unaided human eye. Several studies on radiomic analysis have been carried out identify predictive, prognostic and diagnostic biomarkers for diverse tumor types including HNSCC. Radiomic proved be effective in predicting outcomes patients with locally advanced The aim present study was dentify predictive platinum-refractory HNSCC recurrent and/or...