Generation of multimodal realistic computational phantoms as a test-bed for validating deep learning-based cross-modality synthesis techniques.
Authors
Affiliations (8)
Affiliations (8)
- Department of Electronics, Information, and Bioengineering, Politecnico Di Milano, Milan, Italy. [email protected].
- Department of Electronics, Information, and Bioengineering, Politecnico Di Milano, Milan, Italy.
- Medical Physics Unit, Clinical Department, CNAO National Center of Oncological Hadrontherapy, Pavia, Italy.
- Radiation Oncology Unit, Clinical Department, CNAO National Center of Oncological Hadrontherapy, Pavia, Italy.
- Department of Internal Medicine and Therapeutics, University of Pavia, Pavia, Italy.
- Bioengineering Unit, Clinical Department, CNAO National Center of Oncological Hadrontherapy, Pavia, Italy.
- Department of Clinical, Surgical, Diagnostic,and Pediatric Sciences, University of Pavia, Pavia, Italy.
- Department of Medical Physics, Ludwig-Maximilians-Universität München, Garching, Germany.
Abstract
The validation of multimodal deep learning models for medical image translation is limited by the lack of high-quality, paired datasets. We propose a novel framework that leverages computational phantoms to generate realistic CT and MRI images, enabling reliable ground-truth datasets for robust validation of artificial intelligence (AI) methods that generate synthetic CT (sCT) from MRI, specifically for radiotherapy applications. Two CycleGANs (cycle-consistent generative adversarial networks) were trained to transfer the imaging style of real patients onto CT and MRI phantoms, producing synthetic data with realistic textures and continuous intensity distributions. These data were evaluated through paired assessments with original phantoms, unpaired comparisons with patient scans, and dosimetric analysis using patient-specific radiotherapy treatment plans. Additional external validation was performed on public CT datasets to assess the generalizability to unseen data. The resulting, paired CT/MRI phantoms were used to validate a GAN-based model for sCT generation from abdominal MRI in particle therapy, available in the literature. Results showed strong anatomical consistency with original phantoms, high histogram correlation with patient images (HistCC = 0.998 ± 0.001 for MRI, HistCC = 0.97 ± 0.04 for CT), and dosimetric accuracy comparable to real data. The novelty of this work lies in using generated phantoms as validation data for deep learning-based cross-modality synthesis techniques.