Dataset Information

Minimising multi-centre radiomics variability through image normalisation: a pilot study.

ABSTRACT: Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features' variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 ± 0.08 and 0.79 ± 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 ± 0.28 and 0.60 ± 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.

SUBMITTER: Campello VM

PROVIDER: S-EPMC9307565 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:INTRODUCTION:Progress tests provide students feedback on their level of proficiency over the course of their medical studies. Peer-assisted learning and competency-based education have become increasingly important in medical education. Although progress tests have been proven to be useful as a longitudinal feedback instrument, there are currently no progress tests that have been created in cooperation with students or that focus on competency in medical education. In this study, we investigated the extent to which students can be included in the development of a progress test and demonstrated that aspects of knowledge related to competency can be represented on a competency-based progress test. METHODS:A two-dimensional blueprint for 144 multiple-choice questions (MCQs) covering groups of medical subjects and groups of competency areas was generated by three expert groups for developing the competency-based progress test. A total of 31 students from seven medical schools in Germany actively participated in this exercise. After completing an intensive and comprehensive training programme, the students generated and reviewed the test questions for the competency-based progress test using a separate platform of the ItemManagementSystem (IMS). This test was administered as a formative test to 469 students in a pilot study in November 2013 at eight medical schools in Germany. The scores were analysed for the overall test and differentiated according to the subject groups and competency areas. RESULTS:A pool of more than 200 MCQs was compiled by the students for pilot use, of which 118 student-generated MCQs were used in the progress test. University instructors supplemented this pool with 26 MCQs, which primarily addressed the area of scientific skills. The post-review showed that student-generated MCQs were of high quality with regard to test statistic criteria and content. Overall, the progress test displayed a very high reliability. When the academic years were compared, the progress test mapped out over the course of study not only by the overall test but also in terms of the subject groups and competency areas. OUTLOOK:Further development in cooperation with students will be continued. Focus will be on compiling additional questions and test formats that can represent competency at a higher skill level, such as key feature questions, situational judgement test questions and OSCE. In addition, the feedback formats will be successively expanded. The intention is also to offer the formative competency-based progress test online.

Dataset Information

Minimising multi-centre radiomics variability through image normalisation: a pilot study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets