Unsupervised clustering analysis-based characterization of spatial profiles of inaccuracy in apparent diffusion coefficient values with varying acquisition plan orientation and diffusion weighting gradient direction - a large multicenter phantom study.

This large multicenter study of 37 magnetic resonance imaging scanners aimed at characterizing, for the first time, spatial profiles of inaccuracy (namely, Δ-profiles) in apparent diffusion coefficient (ADC) values with varying acquisition plan orientation and diffusion weighting gradient direction, using a statistical approach exploiting unsupervised clustering analysis. A diffusion-weighted imaging (DWI) protocol (b-value: 0-200-400-600-800-1000 s mm) with different combinations of acquisition plan orientation (axial/sagittal/coronal) and diffusion weighting gradient direction (anterior-posterior/left-right/feet-head) was acquired on a standard water phantom. For each acquisition setup, Δ-profiles along the 3 main orthogonal directions were characterized by fitting data with a second order polynomial function ().

Robust machine learning challenge: An AIFM multicentric competition to spread knowledge, identify common pitfalls and recommend best practice.

Purpose: A novel and unconventional approach to a machine learning challenge was designed to spread knowledge, identify robust methods and highlight potential pitfalls about machine learning within the Medical Physics community.

Methods: A public dataset comprising 41 radiomic features and 535 patients was employed to assess the potential of radiomics in distinguishing between primary lung tumors and metastases. Each participant developed two classification models using: (i) all features (base model); (ii) only robust features (robust model).

Developing an ensemble machine learning study: Insights from a multi-center proof-of-concept study.

Background: To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance.

Test-retest repeatability of myocardial radiomic features from quantitative cardiac magnetic resonance T1 and T2 mapping.

Radiomics of cardiac magnetic resonance (MR) imaging has proved to be potentially useful in the study of various myocardial diseases. Therefore, assessing the repeatability degree in radiomic features measurement is of fundamental importance. The aim of this study was to assess test-retest repeatability of myocardial radiomic features extracted from quantitative T1 and T2 maps.