Head CT Image Segmentation and Three-Dimensional Reconstruction Technology Based on Human Anatomy

Wu, Zhenyu; Wang, Lin; Li, Yifei; Dai, Shuhui; Zhang, Dongliang

doi:10.1155/2022/7091476

Cited by 4 publications

(2 citation statements)

References 16 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the continuous development of imaging technology, its application domains have been expanding to include medical imaging, material imaging, space detection, security monitoring, and so on [1][2][3][4][5]. However, when an object passes through a scattering medium, the imaging information is degraded, making it difficult to obtain the original image directly.…”

Section: Introductionmentioning

confidence: 99%

Study on transfer learning-based cross-spectral speckle image reconstruction method

Zhao,

Zhang,

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

In recent years, convolutional neural networks (CNNs) have been successfully applied to reconstruct images from speckle patterns generated as objects pass through scattering media. To achieve this objective, a large amount of data is collected for training the CNN. However, in certain cases, the characteristics of light passing through the scattering medium may vary. In such situations, it is necessary to collect a substantial amount of new data to re-train the CNN and achieve image reconstruction. To address this challenge, transfer learning techniques are introduced in this study. Specifically, we propose a novel Residual U-Net Generative Adversarial Network, denoted as ResU-GAN. The network is initially pre-trained using a large amount of data collected from either visible or non-visible light sources, and subsequently fine-tuned using a small amount of data collected from non-visible or visible light sources. Experimental results demonstrate the outstanding reconstruction performance of the ResU-GAN network. Furthermore, by combining transfer learning techniques, the network enables the reconstruction of speckle images across different datasets. The findings presented in this paper provide a more generalized approach for utilizing CNNs in cross-spectral speckle imaging.

show abstract

Section: Introductionmentioning

confidence: 99%

Study on transfer learning-based cross-spectral speckle image reconstruction method

Zhao,

Zhang,

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…The standardized three-dimensional reconstruction of head CT scans holds tremendous utility for various post-processing applications. These include tasks such as the segmentation of reconstructed results to isolate structures such as the brain and skull [31], the extraction of specific features or landmarks from the three-dimensional reconstruction-identifying specific anatomical structures or lesions to facilitate further analysis or clinical decision-making [32]. Furthermore, they aid in the execution of quantitative measurements on the 3D reconstruction, including determining the volume of a tumor or quantifying the length and angle of certain anatomical structures [33], and embarking on 3D medical image registration [34], which aligns two or more 3D images within a shared spatial domain.…”

Section: E Discussionmentioning

confidence: 99%

Deep learning for lung cancer on computed tomography: early detection and prognostic prediction

Zheng¹

View full text Add to dashboard Cite

Three-dimensional (3D) reconstruction of head Computed Tomography (CT) images elucidates the intricate spatial relationships of tissue structures, thereby assisting in accurate diagnosis. Nonetheless, securing an optimal head CT scan without deviation is challenging in clinical settings, owing to poor positioning by technicians, patient's physical constraints, or CT scanner tilt angle restrictions. Manual formatting and reconstruction not only introduce subjectivity but also strain time and labor resources. To address these issues, we propose an efficient automatic head CT images 3D reconstruction method, improving accuracy and repeatability, as well as diminishing manual intervention. Our approach employs a deep learningbased object detection algorithm, identifying and evaluating orbitomeatal line landmarks to automatically reformat the images prior to reconstruction. Given the dearth of existing evaluations of object detection algorithms in the context of head CT images, we compared ten methods from both theoretical and experimental perspectives. By exploring their precision, efficiency, and robustness, we singled out the lightweight YOLOv8 as the aptest algorithm for our task, with an mAP of 92.91% and impressive robustness against class imbalance. Our qualitative evaluation of standardized reconstruction results demonstrates the clinical practicability and validity of our method.

show abstract

Self-similarity study based on the particle sizes of coal-series diatomite

Cheng,

Wang,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Coal-series diatomite (CSD) is widely distributed in China and has poor functional and structural properties and exhibits limited utilization of high value-added materials, resulting in a serious waste of resources and tremendous pressure on the environment. Moreover, due to differences in the mineralogical characteristics of CSD, different particle size scales (PSSs) have different functional structures and exhibit different self-similarities. In this study, we took CSD as the research object and PSS as the entry point and carried out a self-similarity study based on gas adsorption and an image processing method to illustrate the microstructures and self-similarities of different PSSs. The results showed that the pore structure of the CSD was dominated by mesopores and macropores and basically lacked micropores. The fractal dimensions were calculated with the Frenkel-Haisey-Hill (FHH) model and Menger model, and the DF1 values for − 0.025 mm and − 2 mm were 2.51 and 2.48, respectively, and the DM1 values were 3.75 and 3.79, respectively, indicating that the mesopore structure of the fine PSS was complex, whereas macropores were present in the coarse PSS. MATLAB was programmed to obtain grayscale thresholds, binarized images, grayscale histograms, three-dimensional (3D) reconstruction images and box dimensions, which enabled us to observe the microstructures and self-similarities of the CSD. Self-similarity studies based on particle sizes are very important for functional application of CSD.Please note that article title mismatch between MS and JS we have followed MS, kindly check and cofirm.Yes, I have checked and confirmed.Kindly check and confirm corresponding author mail id are correctly identified.Yes, I have checked and confirmed.

show abstract

Head CT Image Segmentation and Three-Dimensional Reconstruction Technology Based on Human Anatomy

Cited by 4 publications

References 16 publications

Study on transfer learning-based cross-spectral speckle image reconstruction method

Study on transfer learning-based cross-spectral speckle image reconstruction method

Deep learning for lung cancer on computed tomography: early detection and prognostic prediction

Self-similarity study based on the particle sizes of coal-series diatomite

Contact Info

Product

Resources

About