Journal of X-Ray Science and Technology最新文献

Purpose: The explore the added value of peri-calcification regions on contrast-enhanced mammography (CEM) in the differential diagnosis of breast lesions presenting as only calcification on routine mammogram.

Methods: Patients who underwent CEM because of suspicious calcification-only lesions were included. The test set included patients between March 2017 and March 2019, while the validation set was collected between April 2019 and October 2019. The calcifications were automatically detected and grouped by a machine learning-based computer-aided system. In addition to extracting radiomic features on both low-energy (LE) and recombined (RC) images from the calcification areas, the peri-calcification regions, which is generated by extending the annotation margin radially with gradients from 1 mm to 9 mm, were attempted. Machine learning (ML) models were built to classify calcifications into malignant and benign groups. The diagnostic matrices were also evaluated by combing ML models with subjective reading.

Results: Models for LE (significant features: wavelet-LLL_glcm_Imc2_MLO; wavelet-HLL_firstorder_Entropy_MLO; wavelet-LHH_glcm_DifferenceVariance_CC; wavelet-HLL_glcm_SumEntropy_MLO;wavelet-HLH_glrlm_ShortRunLowGray LevelEmphasis_MLO; original_firstorder_Entropy_MLO; original_shape_Elongation_MLO) and RC (significant features: wavelet-HLH_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_10Percentile_CC; original_firstorder_Maximum_MLO; wavelet-HHH_glcm_Autocorrelation_MLO; original_shape_Elongation_MLO; wavelet-LHL_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_RootMeanSquared_MLO) images were set up with 7 features. Areas under the curve (AUCs) of RC models are significantly better than those of LE models with compact and expanded boundary (RC v.s. LE, compact: 0.81 v.s. 0.73, p < 0.05; expanded: 0.89 v.s. 0.81, p < 0.05) and RC models with 3 mm boundary extension yielded the best performance compared to those with other sizes (AUC = 0.89). Combining with radiologists' reading, the 3mm-boundary RC model achieved a sensitivity of 0.871 and negative predictive value of 0.937 with similar accuracy of 0.843 in predicting malignancy.

Conclusions: The machine learning model integrating intra- and peri-calcification regions on CEM has the potential to aid radiologists' performance in predicting malignancy of suspicious breast calcifications.

In the medical field, diagnostic tools that make use of deep neural networks have reached a level of performance never before seen. A proper diagnosis of a patient's condition is crucial in modern medicine since it determines whether or not the patient will receive the care they need. Data from a sinus CT scan is uploaded to a computer and displayed on a high-definition monitor to give the surgeon a clear anatomical orientation before endoscopic sinus surgery. In this study, a unique method is presented for detecting and diagnosing paranasal sinus disorders using machine learning. The researchers behind the current study designed their own approach. To speed up diagnosis, one of the primary goals of our study is to create an algorithm that can accurately evaluate the paranasal sinuses in CT scans. The proposed technology makes it feasible to automatically cut down on the number of CT scan images that require investigators to manually search through them all. In addition, the approach offers an automatic segmentation that may be used to locate the paranasal sinus region and crop it accordingly. As a result, the suggested method dramatically reduces the amount of data that is necessary during the training phase. As a result, this results in an increase in the efficiency of the computer while retaining a high degree of performance accuracy. The suggested method not only successfully identifies sinus irregularities but also automatically executes the necessary segmentation without requiring any manual cropping. This eliminates the need for time-consuming and error-prone human labor. When tested with actual CT scans, the method in question was discovered to have an accuracy of 95.16 percent while retaining a sensitivity of 99.14 percent throughout.

Objective: To explore the value of body composition changes (BCC) measured by quantitative computed tomography (QCT) for evaluating the survival of patients with locally advanced cervical cancer (LACC) underwent concurrent chemoradiotherapy (CCRT), nomograms combined BCC with clinical prognostic factors (CPF) were constructed to predict overall survival (OS) and progression-free survival (PFS).

Methods: Eighty-eight patients with LACC were retrospectively selected. All patients underwent QCT scans before and after CCRT, bone mineral density (BMD), subcutaneous fat area (SFA), visceral fat area (VFA), total fat area (TFA), paravertebral muscle area (PMA) were measured from two sets of computed tomography (CT) images, and change rates of these were calculated.

Results: Multivariate Cox regression analysis showed ΔBMD, ΔSFA, SCC-Ag, LNM were independent factors for OS (HR = 3.560, 5.870, 2.702, 2.499, respectively, all P < 0.05); ΔPMA, SCC-Ag, LNM were independent factors for PFS (HR = 2.915, 4.291, 2.902, respectively, all P < 0.05). Prognostic models of BCC combined with CPF had the highest predictive performance, and the area under the curve (AUC) for OS and PFS were 0.837, 0.846, respectively. The concordance index (C-index) of nomograms for OS and PFS were 0.834, 0.799, respectively. Calibration curves showed good agreement between the nomograms' predictive and actual OS and PFS, decision curve analysis (DCA) showed good clinical benefit of nomograms.

Conclusion: CT-based body composition changes and CPF (SCC-Ag, LNM) were associated with survival in patients with LACC. The prognostic nomograms combined BCC with CPF were able to predict the OS and PFS in patients with LACC reliably.

Background: Early diagnosis of breast cancer is crucial to perform effective therapy. Many medical imaging modalities including MRI, CT, and ultrasound are used to diagnose cancer.

Objective: This study aims to investigate feasibility of applying transfer learning techniques to train convoluted neural networks (CNNs) to automatically diagnose breast cancer via ultrasound images.

Methods: Transfer learning techniques helped CNNs recognise breast cancer in ultrasound images. Each model's training and validation accuracies were assessed using the ultrasound image dataset. Ultrasound images educated and tested the models.

Results: MobileNet had the greatest accuracy during training and DenseNet121 during validation. Transfer learning algorithms can detect breast cancer in ultrasound images.

Conclusions: Based on the results, transfer learning models may be useful for automated breast cancer diagnosis in ultrasound images. However, only a trained medical professional should diagnose cancer, and computational approaches should only be used to help make quick decisions.

Background: A coded aperture X-ray diffraction (XRD) imaging system can measure the X-ray diffraction form factor from an object in three dimensions -X, Y and Z (depth), broadening the potential application of this technology. However, to optimize XRD systems for specific applications, it is critical to understand how to predict and quantify system performance for each use case.

Objective: The purpose of this work is to present and validate 3D spatial resolution models for XRD imaging systems with a detector-side coded aperture.

Methods: A fan beam coded aperture XRD system was used to scan 3D printed resolution phantoms placed at various locations throughout the system's field of view. The multiplexed scatter data were reconstructed using a model-based iterative reconstruction algorithm, and the resulting volumetric images were evaluated using multiple resolution criteria to compare against the known phantom resolution. We considered the full width at half max and Sparrow criterion as measures of the resolution and compared our results against analytical resolution models from the literature as well as a new theory for predicting the system resolution based on geometric arguments.

Results: We show that our experimental measurements are bounded by the multitude of theoretical resolution predictions, which accurately predict the observed trends and order of magnitude of the spatial and form factor resolutions. However, we find that the expected and observed resolution can vary by approximately a factor of two depending on the choice of metric and model considered. We observe depth resolutions of 7-16 mm and transverse resolutions of 0.6-2 mm for objects throughout the field of view. Furthermore, we observe tradeoffs between the spatial resolution and XRD form factor resolution as a function of sample location.

Conclusion: The theories evaluated in this study provide a useful framework for estimating the 3D spatial resolution of a detector side coded aperture XRD imaging system. The assumptions and simplifications required by these theories can impact the overall accuracy of describing a particular system, but they also can add to the generalizability of their predictions. Furthermore, understanding the implications of the assumptions behind each theory can help predict performance, as shown by our data's placement between the conservative and idealized theories, and better guide future systems for optimized designs.

Introduction: Intensity modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT) are the main radiotherapy techniques for treating and managing rectal cancer. Collimator rotation is one of the crucial parameters in radiotherapy planning, and its alteration can cause dosimetric variations. This study assessed the effect of collimator rotation on the dosimetric results of various IMRT and VMAT plans for rectal cancer.

Materials and methods: Computed tomography (CT) images of 20 male patients with rectal cancer were utilized for IMRT and VMAT treatment planning with various collimator angles. Nine different IMRT techniques (5, 7, and 9 coplanar fields with collimator angles of 0°, 45°, and 90°) and six different VMAT techniques (1 and 2 full coplanar arcs with collimator angles of 0°, 45°, and 90°) were planned for each patient. The dosimetric results of various treatment techniques for target tissue (conformity index [CI] and homogeneity index [HI]) and organs at risk (OARs) sparing (parameters obtained from OARs dose-volume histograms [DVH]) as well as radiobiological findings were analyzed and compared.

Results: The 7-fields IMRT technique demonstrated lower bladder doses (V40Gy, V45Gy), unaffected by collimator rotation. The 9-fields IMRT and 2-arcs VMAT (excluding the 90-degree collimator) had the lowest V35Gy and V45Gy. A 90-degree collimator rotation in 2-arcs VMAT significantly increased small bowel and bladder V45Gy, femoral head doses, and HI values. Radiobiologically, the 90-degree rotation had adverse effects on small bowel NTCP (normal tissue complication probability). No superiority was found for a 45-degree collimator rotation over 0 or 30 degrees in VMAT techniques.

Conclusion: Collimator rotation had minimal impact on dosimetric parameters in IMRT planning but is significant in VMAT techniques. A 90-degree rotation in VMAT, particularly in a 2-full arc technique, adversely affects PTV homogeneity index, bladder dose, and small bowel NTCP. Other evaluated collimator angles did not significantly affect VMAT dosimetrical or radiobiological outcomes.

Background: By providing both functional and anatomical information from a single scan, digital imaging technologies like PET/CT and PET/MRI hybrids are gaining popularity in medical imaging industry. In clinical practice, the median value (SUVmed) receives less attention owing to disagreements surrounding what defines a lesion, but the SUVmax value, which is a semi-quantitative statistic used to analyse PET and PET/CT images, is commonly used to evaluate lesions.

Objective: This study aims to build an image processing technique with the purpose of automatically detecting and isolating lesions in PET/CT images, as well as measuring and assessing the SUVmed.

Methods: The pictures are separated into their respective lesions using mathematical morphology and the crescent region, which are both part of the image processing method. In this research, a total of 18 different pictures of lesions were evaluated.

Results: The findings of the study reveal that the threshold is satisfied by both the SUVmax and the SUVmed for most of the lesion types. However, in six instances, the SUVmax and SUVmed values are found to be in different courts.

Conclusion: The new information revealed by this study needs to be further investigated to determine if it has any practical value in diagnosing and monitoring lesions. However, results of this study suggest that SUVmed should receive more attention in the evaluation of lesions in PET and CT images.

Background: The Chinese population ranks among the highest globally in terms of stroke prevalence. In the clinical diagnostic process, radiologists utilize computed tomography angiography (CTA) images for diagnosis, enabling a precise assessment of collateral circulation in the brains of stroke patients. Recent studies frequently combine imaging and machine learning methods to develop computer-aided diagnostic algorithms. However, in studies concerning collateral circulation assessment, the extracted imaging features are primarily composed of manually designed statistical features, which exhibit significant limitations in their representational capacity. Accurately assessing collateral circulation using image features in brain CTA images still presents challenges.

Methods: To tackle this issue, considering the scarcity of publicly accessible medical datasets, we combined clinical data with imaging data to establish a dataset named RadiomicsClinicCTA. Moreover, we devised two collateral circulation assessment models to exploit the synergistic potential of patients' clinical information and imaging data for a more accurate assessment of collateral circulation: data-level fusion and feature-level fusion. To remove redundant features from the dataset, we employed Levene's test and T-test methods for feature pre-screening. Subsequently, we performed feature dimensionality reduction using the LASSO and random forest algorithms and trained classification models with various machine learning algorithms on the data-level fusion dataset after feature engineering.

Results: Experimental results on the RadiomicsClinicCTA dataset demonstrate that the optimized data-level fusion model achieves an accuracy and AUC value exceeding 86%. Subsequently, we trained and assessed the performance of the feature-level fusion classification model. The results indicate the feature-level fusion classification model outperforms the optimized data-level fusion model. Comparative experiments show that the fused dataset better differentiates between good and bad side branch features relative to the pure radiomics dataset.

Conclusions: Our study underscores the efficacy of integrating clinical and imaging data through fusion models, significantly enhancing the accuracy of collateral circulation assessment in stroke patients.

 An automated system for acquiring microscopic-resolution radiographic images of biological samples was developed. Mass-produced, low-cost, and easily automated components were used, such as Commercial-Off-The-Self CMOS image sensors (CIS), stepper motors, and control boards based on Arduino and RaspberryPi. System configuration, imaging protocols, and Image processing (filtering and stitching) were defined to obtain high-resolution images and for successful computational image reconstruction. Radiographic images were obtained for animal samples including the widely used animal models zebrafish (Danio rerio) and the fruit-fly (Drosophila melanogaster), as well as other small animal samples. The use of phosphotungstic acid (PTA) as a contrast agent was also studied. Radiographic images with resolutions of up to (7±0.6)μm were obtained, making this system comparable to commercial ones. This work constitutes a starting point for the development of more complex systems such as X-ray attenuation micro-tomography systems based on low-cost off-the-shelf technology. It will also bring the possibility to expand the studies that can be carried out with small animal models at many institutions (mostly those working on tight budgets), particularly those on the effects of ionizing radiation and absorption of heavy metal contaminants in animal tissues.