Search

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.

The complexity of urban road scenes at night and the inadequacy of visible light imaging in such conditions pose significant challenges. To address the issues of insufficient color information, texture detail, and low spatial resolution in infrared imagery, we propose an enhanced infrared detection model called LFIR-YOLO, which is built upon the YOLOv8 architecture. The primary goal is to improve the accuracy of infrared target detection in nighttime traffic scenarios while meeting practical deployment requirements. First, to address challenges such as limited contrast and occlusion noise in infrared images, the C2f module in the high-level backbone network is augmented with a Dilation-wise Residual (DWR) module, incorporating multi-scale infrared contextual information to enhance feature extraction capabilities. Secondly, at the neck of the network, a Content-guided Attention (CGA) mechanism is applied to fuse features and re-modulate both initial and advanced features, catering to the low signal-to-noise ratio and sparse detail features characteristic of infrared images. Third, a shared convolution strategy is employed in the detection head, replacing the decoupled head strategy and utilizing shared Detail Enhancement Convolution (DEConv) and Group Norm (GN) operations to achieve lightweight yet precise improvements. Finally, loss functions, PIoU v2 and Adaptive Threshold Focal Loss (ATFL), are integrated into the model to better decouple infrared targets from the background and to enhance convergence speed. The experimental results on the FLIR and multispectral datasets show that the proposed LFIR-YOLO model achieves an improvement in detection accuracy of 4.3% and 2.6%, respectively, compared to the YOLOv8 model. Furthermore, the model demonstrates a reduction in parameters and computational complexity by 15.5% and 34%, respectively, enhancing its suitability for real-time deployment on resource-constrained edge devices.

Electroactive biomaterials are fascinating for tissue engineering applications because of their ability to deliver electrical stimulation directly to cells, tissue, and organs. One particularly attractive conductive filler for electroactive biomaterials is silver nanoparticles (AgNPs) because of their high conductivity, antibacterial activity, and ability to promote bone healing. However, production of AgNPs involves a toxic reducing agent which would inhibit biological scaffold performance. This work explores facile and green synthesis of AgNPs using extract of Cilembu sweet potato and studies the effect of baking and precursor concentrations (1, 10 and 100 mM) on AgNPs’ properties. Transmission electron microscope (TEM) results revealed that the smallest particle size of AgNPs (9.95 ± 3.69 nm) with nodular morphology was obtained by utilization of baked extract and ten mM AgNO3. Polycaprolactone (PCL)/AgNPs scaffolds exhibited several enhancements compared to PCL scaffolds. Compressive strength was six times greater (3.88 ± 0.42 MPa), more hydrophilic (contact angle of 76.8 ± 1.7°), conductive (2.3 ± 0.5 × 10−3 S/cm) and exhibited anti-bacterial properties against Staphylococcus aureus ATCC3658 (99.5% reduction of surviving bacteria). Despite the promising results, further investigation on biological assessment is required to obtain comprehensive study of this scaffold. This green synthesis approach together with the use of 3D printing opens a new route to manufacture AgNPs-based electroactive with improved anti-bacterial properties without utilization of any toxic organic solvents.

Oxygen vacancies (OVs) have critical effects on the photoelectric characterizations and photocatalytic activity of nanoceria, but the contributions of surface OVs on the promoted photocatalytic properties are not clear yet. In this work, we synthesized ceria nanopolyhedron (P-CeO2), ceria nanocube (C-CeO2) and ceria nanorod (R-CeO2), respectively, and annealed them at 600 °C in air, 30%, 60% or pure H2. After annealing, the surface OVs concentration of ceria elevates with the rising of H2 concentration. Photocatalytic activity of annealed ceria is promoted with the increasing of surface OVs, the methylene blue photodegradation ratio with pure hydrogen annealed of P-CeO2, C-CeO2 or R-CeO2 is 93.82%, 85.15% and 90.09%, respectively. Band gap of annealed ceria expands first and then tends to narrow slightly with the rising of surface OVs, while the valence band (VB) and conductive band (CB) of annealed ceria changed slightly. Both of photoluminescence spectra and photocurrent results indicate that the separation efficiency of photoinduced electron-hole pairs is significantly enhanced with the increasing of the surface OVs concentration. The notable weakened recombination of photogenerated carrier is suggested to attribute a momentous contribution on the enhanced photocatalytic activity of ceria which contains surface OVs.

In this study, the phytochemical profiles, total and cellular antioxidant activities of five different Chinese chestnut (Castanea mollissima BL.) cultivars were analyzed. Phenolics, flavonoids as well as phytochemical compounds in five cultivars of chestnut kernels were determined. Results showed that the free forms played a dominant role in total phenolics, flavonoids and antioxidant activities of all five cultivars of chestnut kernels. The cultivar ‘Fyou’ showed the highest total and free phenolic contents, ‘Heguoyihao’ showed the highest total and free flavonoids contents, and ‘Chushuhong’ showed the highest total and cellular antioxidant activities. Eight phenolic compounds were detected, and chlorogenic acid, gallic acid, and quercetin were shown as three predominant components in all five cultivars. These results provide valuable information which may be a guidance for selection of good chestnut variety to be used as functional food.

The intention of this study was to investigate the effect of steaming processing on phenolic profiles and antioxidant activities in chestnuts. Steaming processing at different times and temperatures depicted diverse impacts on free and bound fractions. Though, bound phenolics were stable but long time steaming at higher temperatures tended to improve the levels of phenolics, flavonoids as well as antioxidant activities in chestnut kernels, by up to 60.11% of the original value. Seven phenolic compounds including ferulic acid, chlorogenic acid, gallic acid, vanillic acid, syringate, p-coumaric acid and quercetin were found to change during thermal processes. Significant relationships (p < 0.05) were identified between total phenolics and total antioxidant activities. However, the consistency of chlorogenic acid (p < 0.01) only with cellular antioxidant activity indicated poor bio-accessibility of the phytochemicals in chestnuts. However, this situation could be partly improved by steaming. Steaming could improve the cellular accessibility of free phytochemicals, particularly, increasing the bio-accessibility by 41.96%. This study provided valuable information on dynamic changes of phenolic profiles and antioxidant activity of chestnuts under a steaming process, which could offer possible guidance for the chestnut processing industry in the future.