Xunan Huang

Hyperspectral images are high-dimensional data containing rich spatial, spectral, and radiometric information, widely used in geological mapping, urban remote sensing, and other fields. However, due to the characteristics of hyperspectral remote sensing images—such as high redundancy, strong correlation, and large data volumes—the classification and recognition of these images present significant challenges. In this paper, we propose a band selection method (GE-AP) based on multi-feature extraction and the Affine Propagation Clustering (AP) algorithm for dimensionality reduction of hyperspectral images, aiming to improve classification accuracy and processing efficiency. In this method, texture features of the band images are extracted using the Gray-Level Co-occurrence Matrix (GLCM), and the Euclidean distance between bands is calculated. A similarity matrix is then constructed by integrating multi-feature information. The AP algorithm clusters the bands of the hyperspectral images to achieve effective band dimensionality reduction. Through simulation and comparison experiments evaluating the overall classification accuracy (OA) and Kappa coefficient, it was found that the GE-AP method achieves the highest OA and Kappa coefficient compared to three other methods, with maximum increases of 8.89% and 13.18%, respectively. This verifies that the proposed method outperforms traditional single-information methods in handling spatial and spectral redundancy between bands, demonstrating good adaptability and stability.

The prostate tissue structure is complex, the shape and size change is relatively large, and the surrounding anatomical structure is complex, so the task of segmenting prostate and prostate cancer is somewhat challenging. In this paper, the idea of deformable convolution is combined with the U-net algorithm widely used in medical image segmentation. By using the deformable convolution module at a specific position in the ordinary U-Net network structure, additional offsets can be added to the convolution operator and the spatial sampling position can be changed by learning the offset of the target segmentation area. The fixed receptive field of the traditional convolution operator is shifted to an adaptive receptive field that can feel the change of features, and the segmentation accuracy of the target area is improved. Experiments show that the algorithm can improve the accuracy of prostate segmentation. In this paper, the segmentation model trained with healthy prostate data is transferred to the prostate cancer data set for secondary training by simulating the way doctors read pictures. Experiments show that the segmentation effect of the lesion area is significantly improved compared with the network model trained directly with small sample prostate cancer data. The research results can provide further exploration ideas for the application of medical domain knowledge in deep learning models.

Purpose The Corona Virus Disease 2019 (COVID-19) was first reported in December 2019 from an outbreak of unexplained pneumonia in Wuhan (Hubei, China) that subsequently spread rapidly around the world. Because of the public health emergency, chest CT has been widely used for sensitive detection and diagnosis, monitoring the changes of lesions and also for treatment evaluation. The purpose of this study was to investigate radiation dose and image quality of chest CT scans received by COVID-19 patients and to evaluate the oncogenic risk of multiple chest CT examinations. Methods A retrospective review of 33 patients with RT-PCR confirmed COVID-19 infection was performed from January 31, 2020 to February 19, 2020. The date of each CT exam and respective radiation dose for each exam was recorded for all patients. Multiple pulmonary CT scans were obtained during diagnosis and treatment procedure. Scan frequency, total scan times, radiation dose, and image quality were determined. Results Thirty-three patients (15 males and 18 females, age 21–82 years) with confirmed COVID-19 pneumonia underwent a total of 143 chest CT scans. The number of CT scans per patient was 4 ± 1, with a range of 2–6. The time interval between two consecutive chest CT scans was 3 ± 1 days. The average effective dose from a single chest CT scan was 1.21 ± 0.10 mSv, with a range of 1.02–1.44 mSv. The average cumulative effective dose per patient was 5.25 ± 1.52 mSv, with a range of 2.24–7.48 mSv. The maximum cumulative effective dose was 7.48 mSv for six CT examinations during COVID-19 treatment. Based on subjective image quality analysis, the visual scoring of CT findings was 11.23 ± 1.35 points out of 15 points. Conclusions The frequency, total number and image quality of chest CT scans should be reviewed carefully to guarantee minimally required CT scans during the COVID-19 management.

Medical image fusion technology has been widely used in clinical practice by doctors to better understand lesion regions through the fusion of multiparametric medical images. This paper proposes an automated fusion method based on a U-Net. Through neural network learning, a weight distribution is generated based on the relationship between the image feature information and the multifocus training target. The MRI image pair of prostate cancer (axial T2-weighted and ADC map) is fused using a strategy based on local similarity and Gaussian pyramid transformation. Experimental results show that the fusion method can enhance the appearance of prostate cancer in terms of both visual quality and objective evaluation.