IRMA: Machine learning-based harmonization of

• Tác giả: D Arnaldi, M Biehl, N Bregman, G Carli, R Dierckx, K L Leenders, S S Lövdal, P Mattioli, S K Meles, S Morbelli, R Orad, B Orso, R J Renken, T Shiner, R van Veen
• Ngôn ngữ: eng
• Ký hiệu phân loại: 353.5332 *Administration of social welfare
• Thông tin xuất bản: Germany : European journal of nuclear medicine and molecular imaging , 2025
• Bộ sưu tập: NCBI
• ID: 187359

Tóm tắt

PURPOSE: Center-specific effects in PET brain scans arise due to differences in technical and procedural aspects. This restricts the merging of data between centers and introduces source-specific bias. METHODS: We demonstrate the use of the recently proposed machine learning method Iterated Relevance Matrix Analysis (IRMA) for harmonization of center-specific effects in brain RESULTS: At the initial IRMA iteration, the system was able to determine the center origin of the four HC cohorts almost perfectly. The method required six iterations, corresponding to a six-dimensional subspace CONCLUSION: IRMA can be used to learn and disregard center-specific information in features extracted from brain