Journal of X-Ray Science and Technology最新文献

Background: The emergence of deep learning (DL) techniques has revolutionized tumor detection and classification in medical imaging, with multimodal medical imaging (MMI) gaining recognition for its precision in diagnosis, treatment, and progression tracking.

Objective: This review comprehensively examines DL methods in transforming tumor detection and classification across MMI modalities, aiming to provide insights into advancements, limitations, and key challenges for further progress.

Methods: Systematic literature analysis identifies DL studies for tumor detection and classification, outlining methodologies including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and their variants. Integration of multimodality imaging enhances accuracy and robustness.

Results: Recent advancements in DL-based MMI evaluation methods are surveyed, focusing on tumor detection and classification tasks. Various DL approaches, including CNNs, YOLO, Siamese Networks, Fusion-Based Models, Attention-Based Models, and Generative Adversarial Networks, are discussed with emphasis on PET-MRI, PET-CT, and SPECT-CT.

Future directions: The review outlines emerging trends and future directions in DL-based tumor analysis, aiming to guide researchers and clinicians toward more effective diagnosis and prognosis. Continued innovation and collaboration are stressed in this rapidly evolving domain.

Conclusion: Conclusions drawn from literature analysis underscore the efficacy of DL approaches in tumor detection and classification, highlighting their potential to address challenges in MMI analysis and their implications for clinical practice.

Background: Dental health issues are on the rise, necessitating prompt and precise diagnosis. Automated dental condition classification can support this need.

Objective: The study aims to evaluate the effectiveness of deep learning methods and multimodal feature fusion techniques in advancing the field of automated dental condition classification.

Methods and materials: A dataset of 11,653 clinically sourced images representing six prevalent dental conditions-caries, calculus, gingivitis, tooth discoloration, ulcers, and hypodontia-was utilized. Features were extracted using five Convolutional Neural Network (CNN) models, then fused into a matrix. Classification models were constructed using Support Vector Machines (SVM) and Naive Bayes classifiers. Evaluation metrics included accuracy, recall rate, precision, and Kappa index.

Results: The SVM classifier integrated with feature fusion demonstrated superior performance with a Kappa index of 0.909 and accuracy of 0.925. This significantly surpassed individual CNN models such as EfficientNetB0, which achieved a Kappa of 0.814 and accuracy of 0.847.

Conclusions: The amalgamation of feature fusion with advanced machine learning algorithms can significantly bolster the precision and robustness of dental condition classification systems. Such a method presents a valuable tool for dental professionals, facilitating enhanced diagnostic accuracy and subsequently improved patient outcomes.

Background: Typical propagation-based X-ray phase contrast imaging (PB-PCI) experiments using polyenergetic sources are tested in very ideal conditions: low-energy spectrum (mainly characteristic X-rays), small thickness and homogeneous materials considered weakly absorbing objects, large object-to-detector distance, long exposure times and non-clinical detector.

Objective: Explore PB-PCI features using boundary conditions imposed by a low power polychromatic X-ray source (X-ray spectrum without characteristic X-rays), thick and heterogenous materials and a small area imaging detector with high low-detection radiation threshold, elements commonly found in a clinical scenario.

Methods: A PB-PCI setup implemented using a microfocus X-ray source and a dental imaging detector was characterized in terms of different spectra and geometric parameters on the acquired images. Test phantoms containing fibers and homogeneous materials with close attenuation characteristics and animal bone and mixed soft tissues (bio-sample models) were analyzed. Contrast to Noise Ratio (CNR), system spatial resolution and Kerma values were obtained for all images.

Results: Phase contrast images showed CNR up to 15% higher than conventional contact images. Moreover, it is better seen when large magnifications (>3) and object-to-detector distances (>13 cm) were used. The influence of the spectrum was not appreciable due to the low efficiency of the detector (thin scintillator screen) at high energies.

Conclusions: Despite the clinical boundary condition used in this work, regarding the X-ray spectrum, thick samples, and detection system, it was possible to acquire phase contrast images of biological samples.

Background: To reduce radiation dose and subsequent risks, several legislative documents in different countries describe the need for Diagnostic Reference Levels (DRLs). Spinal radiography is a common and high-dose examination. Therefore, the aim of this work was to establish the DRL for Computed Tomography (CT) examinations of the spine in healthcare institutions across Jordan.

Methods: Data was retrieved from the picture archiving and communications system (PACS), which included the CT Dose Index (CTDI (vol) ) and Dose Length Product (DLP). The median radiation dose values of the dosimetric indices were calculated for each site. DRL values were defined as the 75th percentile distribution of the median CTDI (vol)  and DLP values.

Results: Data was collected from 659 CT examinations (316 cervical spine and 343 lumbar-sacral spine). Of the participants, 68% were males, and the patients' mean weight was 69.7 kg (minimum = 60; maximum = 80, SD = 8.9). The 75th percentile for the DLP of cervical and LS-spine CT scans in Jordan were 565.2 and 967.7 mGy.cm, respectively.

Conclusions: This research demonstrates a wide range of variability in CTDI (vol)  and DLP values for spinal CT examinations; these variations were associated with the acquisition protocol and highlight the need to optimize radiation dose in spinal CT examinations.

Purpose: To compare image quality, iodine intake, and radiation dose in overweight and obese patients undergoing abdominal computed tomography (CT) enhancement using different scanning modes and contrast medium.

Methods: Ninety overweight and obese patients (25 kg/m2≤body mass index (BMI)< 30 kg/m2 and BMI≥30 kg/m2) who underwent abdominal CT-enhanced examinations were randomized into three groups (A, B, and C) of 30 each and scanned using gemstone spectral imaging (GSI) +320 mgI/ml, 100 kVp + 370 mgI/ml, and 120 kVp + 370 mgI/ml, respectively. Reconstruct monochromatic energy images of group A at 50-70 keV (5 keV interval). The iodine intake and radiation dose of each group were recorded and calculated. The CT values, contrast-to-noise ratios (CNRs), and subjective scores of each subgroup image in group A versus images in groups B and C were by using one-way analysis of variance or Kruskal-Wallis H test, and the optimal keV of group A was selected.

Results: The dual-phase CT values and CNRs of each part in group A were higher than or similar to those in groups B and C at 50-60 keV, and similar to or lower than those in groups B and C at 65 keV and 70 keV. The subjective scores of the dual-phase images in group A were lower than those of groups B and C at 50 keV and 55 keV, whereas no significant difference was seen at 60-70 keV. Compared to groups B and C, the iodine intake in group A decreased by 12.5% and 13.3%, respectively. The effective doses in groups A and B were 24.7% and 25.8% lower than those in group C, respectively.

Conclusion: GSI +320 mgI/ml for abdominal CT-enhanced in overweight patients satisfies image quality while reducing iodine intake and radiation dose, and the optimal keV was 60 keV.

Background: Connectome is understanding the complex organization of the human brain's structural and functional connectivity is essential for gaining insights into cognitive processes and disorders.

Objective: To improve the prediction accuracy of brain disorder issues, the current study investigates dysconnected subnetworks and graph structures associated with schizophrenia.

Method: By using the proposed structural connectivity-deep graph neural network (sc-DGNN) model and compared with machine learning (ML) and deep learning (DL) models.This work attempts to focus on eighty-eight subjects of diffusion magnetic resonance imaging (dMRI), three classical ML, and five DL models.

Result: The structural connectivity-deep graph neural network (sc-DGNN) model is proposed to effectively predict dysconnectedness associated with schizophrenia and exhibits superior performance compared to traditional ML and DL (GNNs) methods in terms of accuracy, sensitivity, specificity, precision, F1-score, and Area under receiver operating characteristic (AUC).

Conclusion: The classification task on schizophrenia using structural connectivity matrices and experimental results showed that linear discriminant analysis (LDA) performed 72% accuracy rate in ML models and sc-DGNN performed at a 93% accuracy rate in DL models to distinguish between schizophrenia and healthy patients.

Background: An efficient deep convolutional neural network (DeepCNN) is proposed in this article for the classification of Covid-19 disease.

Objective: A novel structure known as the Pointwise-Temporal-pointwise convolution unit is developed incorporated with the varying kernel-based depth wise temporal convolution before and after the pointwise convolution operations.

Methods: The outcome is optimized by the Slap Swarm algorithm (SSA). The proposed Deep CNN is composed of depth wise temporal convolution and end-to-end automatic detection of disease. First, the datasets SARS-COV-2 Ct-Scan Dataset and CT scan COVID Prediction dataset are preprocessed using the min-max approach and the features are extracted for further processing.

Results: The experimental analysis is conducted between the proposed and some state-of-art works and stated that the proposed work effectively classifies the disease than the other approaches.

Conclusion: The proposed structural unit is used to design the deep CNN with the increasing kernel sizes. The classification process is improved by the inclusion of depth wise temporal convolutions along with the kernel variation. The computational complexity is reduced by the introduction of stride convolutions are used in the residual linkage among the adjacent structural units.

Background: The polychromatic X-rays generated by a linear accelerator (Linac) often result in noticeable hardening artifacts in images, posing a significant challenge to accurate defect identification. To address this issue, a simple yet effective approach is to introduce filters at the radiation source outlet. However, current methods are often empirical, lacking scientifically sound metrics.

Objective: This study introduces an innovative filter design method that optimizes filter performance by balancing the impact of ray intensity and energy on image quality.

Materials and methods: Firstly, different spectra under various materials and thicknesses of filters were obtained using GEometry ANd Tracking (Geant4) simulation. Subsequently, these spectra and their corresponding incident photon counts were used as input sources to generate different reconstructed images. By comprehensively comparing the intensity differences and noise in images of defective and non-defective regions, along with considering hardening indicators, the optimal filter was determined.

Results: The optimized filter was applied to a Linac-based X-ray computed tomography (CT) detection system designed for identifying defects in graphite materials within high-temperature gas-cooled reactor (HTR), with defect dimensions of 2 mm. After adding the filter, the hardening effect reduced by 22%, and the Defect Contrast Index (DCI) reached 3.226.

Conclusion: The filter designed based on the parameters of Average Difference (AD) and Defect Contrast Index (DCI) can effectively improve the quality of defect images.

Background: The coronavirus disease 2019 is a serious and highly contagious disease caused by infection with a newly discovered virus, named severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Objective: A Computer Aided Diagnosis (CAD) system to assist physicians to diagnose Covid-19 from chest Computed Tomography (CT) slices is modelled and experimented.

Methods: The lung tissues are segmented using Otsu's thresholding method. The Covid-19 lesions have been annotated as the Regions of Interest (ROIs), which is followed by texture and shape extraction. The obtained features are stored as feature vectors and split into 80:20 train and test sets. To choose the optimal features, Whale Optimization Algorithm (WOA) with Support Vector Machine (SVM) classifier's accuracy is employed. A Multi-Layer Perceptron (MLP) classifier is trained to perform classification with the selected features.

Results: Comparative experimentations of the proposed system with existing eight benchmark Machine Learning classifiers using real-time dataset demonstrates that the proposed system with 88.94% accuracy outperforms the benchmark classifier's results. Statistical analysis namely, Friedman test, Mann Whitney U test and Kendall's Rank Correlation Coefficient Test has been performed which indicates that the proposed method has a significant impact on the novel dataset considered.

Conclusion: The MLP classifier's accuracy without feature selection yielded 80.40%, whereas with feature selection using WOA, it yielded 88.94%.