Medical image segmentation plays a critical role in the field of medical image processing. Precisely delineating brain tumor areas from multimodal MRI scans is crucial for clinical diagnosis and predicting patient outcomes. However, challenges arise from similar intensity patterns, varying tumor shapes, and indistinct boundaries, which complicate brain tumor segmentation. Traditional segmentation networks like UNet face difficulties in capturing comprehensive long-range dependencies within the feature space due to the limitations of CNN receptive fields. This limitation is particularly significant in tasks requiring detailed predictions such as brain tumor segmentation. Inspired by these constraints, this study suggests incorporating EfficientNet as an encoder within UNet, with a thorough reassessment of its fundamental components: the encoder, bottleneck, and skip connections. EfficientNet replaces UNet’s encoder, initially frozen to retain learned features from pre-trained weights, adept at extracting detailed features crucial for precise segmentation like brain tumors from MRI scans. Preserving UNet’s bottleneck compresses EfficientNet’s outputs, while skip connections maintain spatial integrity during decoder upsampling. The decoder reconstructs the original image size by merging encoder-decoder features, refining boundaries with convolutional layers for accurate clinical insights.The study conducted multiclass operations on the Brain-Tumor.npy dataset from Kaggle, consisting of 3064 T1-weighted contrast-enhanced images from 233 patients with meningioma (708 slices), glioma (1426 slices), and pituitary tumor (930 slices). Experimental findings in brain tumor segmentation tasks show that the proposed model achieves performance on par with or better than recent CNN or Transformer models. Specifically, the model achieves an accuracy of 0.9925 and a loss of 0.2991 on the dataset.

In the present paper, we study the transmission of the two-dimensional photonic crystal (PC) superellipse ring resonator. The fast growing applications of optomechanical systems lead to strong demands in new sensing mechanism in order to design the sensing elements to nanometer scale. The photonic crystal based resonator has been investigated as promising solutions because the band gap structure and resonator characteristics are extremely sensitive to the deformation and position shift of rod / cavity in PC resonators. This structure opens a single channel filter. The study is extended for tuning of channel filter’s wavelength with a temperature of this structure. The transmission of the channel filter shows a red shift with temperature linearly. This wavelength shift of the channel filter is used for the sensor application. The sensitivity for the proposed structure is found to be 65.3 pm/°C. The outstanding sensing capability renders PC resonators as a promising optomechanical sensing element to be integrated into various transducers for temperature sensing applications.

<!-- *** Custom HTML *** --> The interference method is used to achieve all-optical logic gate operations. This has been realized with a single design of photonic crystal ring resonator at different wavelengths rather than designing separate for all the logic gates. Such a single design can be used to perform all optical operations as AND, OR, and XOR logic gates at different wavelengths. Further operating wavelength, contrast ratio (CR), response time (RT), and bit rate have been analyzed for all three logic gates. The highest CR is obtained as about 22.06 dB with fast RT about 0.14 ps and high bit rate of 7.14 Tb / s for proposed XOR logic gate in comparison to all the other logic gates with single-design structure, which may lead us to construct on-chip logic circuits.

We study the two-dimensional photonic crystal (PC) square lattice structure to design a channel drop filter. The channel drop filter (CDF) is designed using a PC ring resonator structure because of its better response. The variation in the shape of scatterer rods causes the shift in resonant wavelength and also shows an improvement in quality factor as well as dropping efficiency. The dropping efficiency is improved from 92.7% to 99.5% for a particular wavelength at 1531 nm, which is especially used in telecommunication. The designed CDF structure is useful for coarse wavelength division multiplexer. The size of the device is very small, so these devices can play an important role in optical communication networks and photonic integrated circuits.

This manuscript presents a ring-core Bragg Fiber (RC-BF) for orbital angular momentum (OAM) modes propagation and supercontinuum generation. The proposed RC-BF is composed of alternating layers of soft glasses SF57 and LLF1 to render high nonlinearity to the fiber. Mode analysis using full-vectorial finite element method resulted in obtaining HE/EH modes to support vector modes as well as orbital angular momentum modes. The optimized fiber supports 22 OAM modes and exhibits a zero-dispersion wavelength (ZDW). The small effective area of Fiber 3 aided in achieving the highest nonlinearity, γ = 91.51 W ^-1 km ^-1 . A near-infrared supercontinuum is generated with a 35 dB flatness over a bandwidth of ~1087 - 2024 nm in a 20 cm long RC-BF using a chirp-free hyperbolic secant pulse of width 200 fs and peak power of 5 kW.

In this paper, a new work on channel drop filters (CDFs) based on photonic crystals ring resonators (PCRRs) is presented. The filter characteristics for single-ring configurations based on two dimensional (2D) square lattice photonic crystal (PC) silicon rods have been investigated by using the two-dimensional (2D) finite-difference time-domain (FDTD) method. The CDF we designed can easily separate the light with four different wavelengths simultaneously with high drop efficiency. Among the CWDM system communication wavelengths these are the wavelengths of 1.471, 1.491, 1.511 and 1.531 μm which are the main communication wavelengths with corresponding dielectric constant of silicon materials as 10.24, 10.59, 11.05 and 12.04 are dropped respectively. It is superior to the CDFs reported before and can be used extensively in optical communication systems.