This research was to explore the accuracy of ultrasonic diagnosis based on artificial intelligence algorithm in the diagnosis of pregnancy complicated with brain tumors. In this study, 18 patients with pregnancy complicated with brain tumor confirmed by pathology were selected as the research object. Ultrasound contrast based on artificial bee colony algorithm was performed and diagnosed by experienced clinicians. Ultrasonic image will be reconstructed by artificial bee colony algorithm to improve its image display ability. The pathological diagnosis will be handed over to the physiological pathology laboratory of the hospital for diagnosis. The doctor’s ultrasonic diagnosis results were compared with the pathological diagnosis stage results of patients, and the results were analyzed by statistical analysis to evaluate its diagnostic value. The comparison results showed that the number and classification of benign tumors were the same, while in malignant tumors, the number diagnosis was the same, but there was one patient with diagnostic error in classification. One case of mixed glial neuron tumor was diagnosed as glial neuron tumor, and the diagnostic accuracy was 94.44% and the K value was 0.988. The diagnostic results of the two were in excellent agreement. The results show that, in the ultrasonic image diagnosis of patients with brain tumors during pregnancy based on artificial intelligence algorithm, most of them are benign and have obvious symptoms. Ultrasound has a good diagnostic accuracy and can be popularized in clinical diagnosis. The results can provide experimental data for the clinical application of ultrasonic image feature analysis based on artificial intelligence as the diagnosis of pregnancy complicated with brain tumors.

Echo signals in different regions in the k-space of magnetic resonance imaging (MRI) data possess different amplitudes. The signal-to-noise ratio (SNR) of a received signal can be improved by differentially setting the receiving gain (RG) parameter in different areas of the k-space. Previously, the k-space data splicing method and the gain normalization implementation method were not specifically investigated; however, this study focuses on this aspect. Specifically, to improve the SNR, three RGs and MRI scans are herein designed for each gain parameter using the gradient echo sequence to obtain one group of k-space data. Subsequently, the three groups of experimental k-space data obtained using MRI scans are spliced into one group of k-space data. For the splicing process, a method for gain and phase correction and compensation is developed that normalizes different RG parameters in the k-space. The experimental results indicate that the developed methods improve the SNR by 5–13%. When the RGs are set to other combinations, the k-space data splicing and gain normalization methods presented in this paper are still applicable.

BACKGROUND: Addressing intensity inhomogeneity is critical in magnetic resonance imaging (MRI) because associated errors can adversely affect post-processing and quantitative analysis of images (i.e., segmentation, registration, etc.), as well as the accuracy of clinical diagnosis. Although several prior methods have been proposed to eliminate or correct intensity inhomogeneity, some significant disadvantages have remained, including alteration of tissue contrast, poor reliability and robustness of algorithms, and prolonged acquisition time. OBJECTIVE: In this study, we propose an intensity inhomogeneity correction method based on volume and surface coils simultaneous reception (VSSR). METHODS: The VSSR method comprises of two major steps: 1) simultaneous image acquisition from both volume and surface coils and 2) denoising of volume coil images and polynomial surface fitting of bias field. Extensive in vivo experiments were performed considering various anatomical structures, acquisition sequences, imaging resolutions, and orientations. In terms of correction performance, the proposed VSSR method was comparatively evaluated against several popular methods, including multiplicative intrinsic component optimization and improved nonparametric nonuniform intensity normalization bias correction methods. RESULTS: Experimental results show that VSSR is more robust and reliable and does not require prolonged acquisition time with the volume coil. CONCLUSION: The VSSR may be considered suitable for general implementation.