In the field of knee imaging, the incorporation of MR-based pseudo-CT synthesis holds the potential to mitigate the need for separate CT scans, simplifying workflows, enhancing patient comfort, and reducing radiation exposure. In this work, we present a novel DL framework, grounded in the development of the Cycle-Consistent Generative Adversarial Network (CycleGAN) method, tailored specifically for the synthesis of pseudo-CT images in knee imaging to surmount the limitations of current methods. Upon visually examining the outcomes, it is evident that the synthesized pseudo-CTs show an excellent quality and high robustness. Despite the limited dataset employed, the method is able to capture the particularities of the bone contours in the resulting image. The experimental Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Zero-Normalized Cross Correlation (ZNCC), Mutual Information (MI), Relative Change (RC), and absolute Relative Change (|RC|) report values of 30.4638 ± 7.4770, 28.1168 ± 1.5245, 0.9230 ± 0.0217, 0.9807 ± 0.0071, 0.8548 ± 0.1019, 0.0055 ± 0.0265, and 0.0302 ± 0.0218 (median ± median absolute deviation), respectively. The voxel-by-voxel correlation plot shows an excellent correlation between pseudo-CT and ground-truth CT Hounsfield units (m = 0.9785; adjusted $R^2$ = 0.9988; $\rho$ = 0.9849; p < 0.001). The Bland–Altman plot shows that the average of the differences is low (($H{U}_{CT}-H{U}_{pseudo-CT}$ = 0.7199 ± 35.2490; 95% confidence interval [−68.3681, 69.8079]). This study represents the first reported effort in the field of MR-based knee pseudo-CT synthesis, shedding light to significantly advance the field of knee imaging.

Radiomics is a growing field in medical imaging that transforms images into high-dimensional quantitative data, offering insights into disease diagnosis, prognosis, and treatment planning. Using advanced computational techniques, radiomics uncovers patterns invisible to the human eye, playing a key role in precision medicine. However, the adoption of radiomics faces several barriers, including a lack of standardization, reproducibility challenges, and difficulties in clinical implementation. To address these challenges, a practical 10-step recipe is proposed to guide researchers in conducting effective radiomic studies: (1) identify a genuine clinical need and application; (2) establish a comprehensive database; (3) implement robust quality assurance and preprocessing; (4) ensure accurate image segmentation; (5) extract quantitative imaging features; (6) prioritize feature selection and dimension reduction; (7) consider integration of clinical and multi-omics data; (8) construct predictive models with machine learning techniques; (9) evaluate model performance using appropriate metrics; (10) translate models into clinical practice and workflow integration. This recipe emphasizes research rationale and methodologies, ensuring that the studies are aligned with real clinical needs, employing advanced techniques, and promoting reproducibility. By addressing these challenges through a structured approach, radiomics can transition from a research discipline to a clinical tool, contributing to more personalized and effective patient care. Relevance statement: A structured 10-step framework is proposed to guide radiomic research, addressing key challenges in standardization and implementation. This practical guide supports any professional aiming to start in radiomics or adopt best practices, promoting reproducibility and clinical relevance in precision imaging workflows. Key Points: Radiomics extracts quantitative data from medical images for improved diagnosis and treatment. Reproducibility, standardization issues, and clinical implementation barriers are among the main challenges of the technique. Data quality, feature selection, and machine learning are key to meaningful analysis. A structured 10-step guide for conducting reliable radiomic studies is proposed, taking a step toward a standardized workflow. Graphical