ESTRO 2024 - Abstract Book

S2912

Interdiscplinary - Other

ESTRO 2024

1 Hong Kong Polytechnic University, Department of Health Technology and Informatics, Hong Kong, Hong Kong. 2 Queen Elizabeth Hospital, Department of Clinical Oncology, Hong Kong, Hong Kong

Purpose/Objective:

Magnetic Resonance Imaging (MRI) plays a pivotal role in the accurate delineation of tumors for radiotherapy. However, conventional MRI sequences often show inconsistencies in tumor contrast across patients. This study aimed to assess the potential of a novel multi-model image fusion method, the Pixelwise Gradient Model for Image Fusion (PGMIF), to improve MRI tumor contrast and its consistency across patients.

Material/Methods:

We utilized T1-w and T2-w MR images from a cohort of 80 patients. The proposed PGMIF was based on a pixelwise gradient to capture the shape of the input images and a Generative Adversarial Network (GAN) term for capturing image contrast. It was compared with other fusion algorithms: Gradient Model with Maximum Comparison Among Images (GMMCI), Deep Learning Model with Weighted Loss (DLMWL), Pixelwise Weighted Average (PWA), and Maximum of Images (MoI). All images underwent pre-processing: registration, normalization, and re-scaling. Two metrics were used to test the fusion methods' performance: Tumor Contrast-to-Noise Ratio (CNR) and a refined Sobel Operator Analysis to measure the edge sharpness.

Results:

PGMIF surpassed in both metrics, registering a CNR of 1.237 ± 0.100. This marked a significant enhancement compared to T1-w (0.976 ± 0.052) and T2-w MR images (1.077 ± 0.087). PGMIF also outperformed other models including GMMCI, DLMWL, PWA, and MoI. In the Sobel Operator Analysis, PGMIF again showed the highest Sigmoid of Sobel Metric values for T1-w and T2-w MR images comparisons, demonstrating the contrast amplification and edge acuity.

Conclusion:

The novel PGMIF method shows its potential to enhance MRI tumor contrast while retaining the anatomical structures from the source images. Its implementation could be useful in NPC tumor delineation.

Keywords: MRI fusion, nasopharyngeal carcinoma

1497

Digital Poster

Analysis of group consensus peer review process in MR-Linac patients: outcomes and feasibility

Yew Sin 1 , Vikneswary Batumalai 2,3 , Jeremy de Leon 2 , Eugene Leong 4,5 , Kasri Rahim 4,5 , Farshad Kasraei 2 , Monique Heinke 2 , Charles Tran 2 , Tommy Liang 4 , Urszula Jelen 2 , Nicolle Dunkerley 2 , Katrina Biggerstaff 4 , Laura McKenzie 2 , Nicole Hug 4 , Amrinder Chhabra 4 , Kathryn Hird 1 , Hendrick Tan 4,5