×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerRecently, three-dimensional models 3DM in the prosthetics field gained popularity, especially in the context of residual limb shape creation resulting from collecting medical images in Digital Imaging and Communications in Medicine DICOM format from a magnetic resonance imaging MRI after image processing accurately. In this study, a three-dimensional model of the residual limb for a patient with transtibial amputation was realized with the integration of artificial intelligence and a computer vision approach demonstrating the benefits of AI segmentation tools and artificial algorithms to generate higher accuracy three-dimensional model before prosthetic socket design or in case of comparison the 3D model generated from MRI with another 3D model generated from another technique, where a residual limb of a 23 years old male patient with amputation in the left leg wearing a prosthetic socket liner, and having 62 kg weight, 168 cm height, with high activity level. The patient was scanned using GE Medical Systems, 1,5 Tesla Signa Excite. MRI images in DICOM format were read to retrieve essential metadata such as pixel spacing and slice thickness. These images were processed to obtain a model that reflects the real shape of the residual limb using a specific algorithm, and the 3D model was extracted using AI segmentation tools. The obtained 3D model result with high resolution proves the potential of the artificial intelligence approach with deep learning to reconstruct 3D models concluding that AI has an instrumental role in medical image analysis, particularly in the areas of organ and tissue classification and segmentation., thus generating automatic and repetitive a 3D model.
The standardization and preprocessing decisions determine the performance, reproducibility and generalizability of Artificial Intelligence (AI) models in cervical spine Magnetic Resonance Imaging (MRI). In this research, the author suggests a six-step standardized preprocessing pipeline that can help with the reliable analysis of heterogeneous MRI data using AI. It is obtained by the pipeline based on recurrent methodological patterns found in the literature, focusing on the operations reported to stabilize image intensity distribution and reduce unwanted sources of variability. A systematic literature review was screened on 2,882 records, and 43 articles were included per the inclusion criteria. Due to the large variability of imaging procedures, preprocessing plans, and reported outcomes metrics, no quantitative meta-analysis was performed and a qualitative synthesis was done. Basic methods such as segmentation, denoising, intensity normalization, augmentation, bias-field correction were consistently reported to improve AI performance. Studies evaluating tasks such as normalization and automated segmentation reported accuracies of 94% to 99.95%. Moreover, less-specific harmonization methods like Combatting Batch Effects (ComBat), z-score normalization and histogram matching, and Generative Adversarial Network (GAN)-based ones were also often attributed with lower scanner- and site-based variations. Regardless of these improvements, the AI workflow remains unstable because of the irregularity of predefined parameters, unequal standards of acquisition, and lack of methodological reporting. In efforts to deal with such challenges, the current work proposes a methodical six-stage preprocessing model that consists of quality control, noise removal, intensity normalization, anatomical segmentation, harmonization and validation. The suggested workflow model offers a practical and transparent basis of clinically translatable AI usage in cervical spine MRI based on conventional mathematical equations and clear documentation.