Segmentation and classification
Participated in an ongoing doctoral research project entitled “Predictive value of tumor-infiltrating lymphocytes (TILs), lymph nodes, and breast MRI in patients with early HER2-positive and Triple-Negative Breast Cancer: a retrospective study.” The aim was to assess whether imaging, pathological, and radiomic features could help predict response to neoadjuvant therapy. My tasks included DICOM image review, tumor segmentation, image annotation and classification, radiomic feature extraction, database creation, and feature selection using advanced statistical methods. Quality measures included standardized segmentation procedures, structured data labeling, review of annotations.