Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.

Scaffolds are critical in regenerative medicine, particularly in bone tissue engineering, where they mimic the extracellular matrix to support tissue regeneration. Scaffold efficacy depends on precise control of 3D printing parameters, which determine geometric and mechanical properties, including Young’s modulus. This study examines the impact of nozzle temperature, printing speed, and feed rate on the Young’s modulus of polylactic acid (PLA) scaffolds. Using a Prusa MINI+ 3D printer (Prusa Research a.s., Prague, Czech Republic), systematic experiments are conducted to explore these correlations. Results show that higher nozzle temperatures decrease Young’s modulus due to reduced viscosity and weaker interlayer bonding, likely caused by thermal degradation and reduced crystallinity. Printing speed exhibits an optimal range, with Young’s modulus peaking at moderate speeds (around 2100 mm/min), suggesting a balance that enhances crystallinity and bonding. Material feed rate positively correlates with Young’s modulus, with increased material deposition improving scaffold density and strength. The integration of an Artificial Neural Network (ANN) model further optimized the printing parameters, successfully predicting the maximum Young’s modulus while maintaining geometric constraints. Notably, the Young’s modulus achieved falls within the typical range for cancellous bone, indicating the model’s potential to meet specific clinical requirements. These findings offer valuable insights for designing patient-specific bone scaffolds, potentially improving clinical outcomes in bone repair.

Cardiovascular stents are widely applied in the treatment of arterial stenosis, but conventional metallic stents present limitations such as permanent implantation, hypersensitivity reactions, and late restenosis. Biodegradable polymer stents offer a promising alternative, though their translation is restricted by structural design challenges and inadequate mechanical performance. In this study, eight representative stent architectures were computationally evaluated with respect to radial elastic recoil, foreshortening, dogboning, and radial support force. Stents were fabricated from polylactide (PLA) via fused deposition modelling (FDM), and the effects of nozzle temperature, layer height, and printing speed were systematically assessed on PLA dogbone specimens to determine optimised process parameters. Computational analysis revealed that only type B and type F stents met clinical deformation requirements, with radial elastic recoil <6 %, foreshortening <10 %, and dogboning <10 %, while other designs exhibited values exceeding these thresholds. Parallel compression tests further quantified radial support capacity at 50 % compression. Fabrication and dimensional evaluation showed that, although all stent designs could be produced using optimised FDM parameters, manufacturing-induced geometric deviations at thin struts and unit connection regions were unavoidable. As a result, the finite-element simulations should be regarded as providing idealised mechanical responses for comparative design evaluation rather than exact predictions of fabricated prototypes. Overall, these findings provide structural and process design guidelines for the development of mechanically reliable 3D-printed biodegradable PLA cardiovascular stents, while emphasising the importance of manufacturing fidelity when translating computationally optimised designs into physical devices.