Publications by authors named "Klarisa Elena Szilagyi"
Article Synopsis
- The study aimed to create machine learning models to predict pathological complete response (pCR) in breast cancer patients after neoadjuvant chemotherapy using data from FDG PET/CT scans.
- 52 newly diagnosed breast cancer patients had their tumors and lymph node metastases segmented, and various features, both clinical and radiomic, were collected and analyzed.
- The results indicated that models using radiomic features from PET scans, particularly when including data from lymph nodes, performed better in predicting pCR compared to those based on clinical or CT data alone.
Purpose: To characterise the impact of Precise Image (PI) deep learning reconstruction algorithm on image quality, compared to filtered back-projection (FBP) and iDose iterative reconstruction for brain computed tomography (CT) phantom images.
Methods: Catphan-600 phantom was acquired with an Incisive CT scanner using a dedicated brain protocol, at six different dose levels (volume computed tomography dose index (CTDI): 7/14/29/49/56/67 mGy). Images were reconstructed using FBP, levels 2/5 of iDose, and PI algorithm (Sharper/Sharp/Standard/Smooth/Smoother).