Ass.-Prof. Dr. Sepideh Hatamikia was invited by the Computational and Structural Biotechnology Journal (CSBJ) to publish her research in this journal.
The paper entitled “Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy – How are they affected by variations in tumor delineation?” was recently published at CSBJ, which was a collaboration between Danube Private University (DPU) and ACMIT.
The main goal of the study was to apply mathematical operations to the original volume of interests (VOI) delineated by experts to simulate variations of segmentation masks for breast tumors in MR images. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. This study demonstrated that differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for the development of standardized radiomics research.
For more information, please visit:
