Optimized Backprojection Filtration Algorithm for Postoperative Reduction and Analysis of Respiratory Infection-Related Factors of Pelvic Fractures by CT Imaging

To explore the computed tomography (CT) imaging characteristics and BPF algorithm fine lung CT image efficiency for the diagnosis of pelvic fracture patients and assist clinicians to carry out the disease care and treatment, CT images based on optimized back-projection filtering (BPF) algorithm were utilized to diagnose postoperative reduction of pelvic fractures and penetrating lung infection caused by long-term bed rest. A total of 100 patients with pelvic fracture were selected and all of them underwent pelvic fracture surgery and were rolled into conventional CT diagnosis group (conventional group) and BPF algorithm optimized CT image diagnosis group (BPF group). One group used conventional CT images to guide pelvic reduction and detect lung infections, and the other used BPF algorithm to optimize the images. The results showed that the BPF group was superior to the conventional CT group in both image clarity and shadow area, and the peak signal-to-noise ratio (PSNR) was significantly better than that of the conventional group ( P < 0.05 ). Nine more cases were detected in the algorithm group than in the conventional group, and the incidence of complications was 48% in the conventional group and 28% in the BPF group, with a statistical difference of 20% between the two groups ( P < 0.05 ). In addition, the satisfaction of returning patients was 96% in the BPF group and 77% in the conventional group ( P < 0.05 ). The diagnosis of pulmonary infection was more obvious in the BPF group, indicating that BPF optimization of the CT image was suitable for clinical diagnosis and had a practical application value.

Download Full-text

Assessment of CT Imaging Protocols Impacts on Calculation of Point Dose in Water Phantom Using Radiotherapy Treatment Planning System

Frontiers in Biomedical Technologies ◽

10.18502/fbt.v7i2.3857 ◽

2020 ◽

Author(s):

Gholamreza Fallah Mohammadi ◽

Ehsan Mihandoost

Keyword(s):

Treatment Planning ◽

Photon Energy ◽

Dose Calculation ◽

Ct Images ◽

Ct Imaging ◽

Planning System ◽

Treatment Planning System ◽

Ct Image ◽

Water Phantom ◽

Imaging Protocols

Purpose: Point dose calculation in the Treatment Planning System (TPS) is performed using Computed Tomography (CT) images because CT images data have the tissue electron density information. The effect of CT imaging protocols on the calculation of point doses in TPS is one of the most important subjects that was evaluated in this study. Materials and Methods: CT scan imaging was performed from cylindrical water phantom using three scanner systems and different imaging technical parameters. The CT images data were irradiated in TPS to delivering a 200 cGy radiation dose to the center of the phantom with 6 and 15MV X-Ray photon energy with multiple radiation fields and Monitor Unit (MU) were separately calculated. In the TPS, a virtual water phantom with the same characteristic as CT image phantom was simulated and irradiated with similar conditions. The difference in MU values obtained from two irradiation methods in TPS was compared with Wilcoxon nonparametric test. Results: Variations of mA, kV, Pitch, slice thickness, and kernel as CT imaging parameters have not significantly affected radiotherapy point dose calculation (<2%). CT imaging protocols as a thin slice, 80 kV, and sharp kernel have the greatest difference between CT image-based calculation and designed phantom calculation in TPS where wedge field and 6 MV photon energy were used. Conclusion: The use of CT images obtained with multiple protocols can be used without having a significant effect on the dose calculations of the treatment planning system.

Download Full-text

Study on the Relationship Between the Imaging Characteristics of Inflammatory Infection and the Expression of Serum Cytokines in Patients with Blood Tumor

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3368 ◽

2021 ◽

Vol 11 (2) ◽

pp. 648-653

Author(s):

Feibo Zhu ◽

Chenglong Sun ◽

Yongwei Hong ◽

Jinhu Li ◽

Yuhong Zhou

Keyword(s):

Ct Imaging ◽

Control Group ◽

Imaging Features ◽

Ct Image ◽

Spearman Correlation ◽

Ct Diagnosis ◽

Tumor Patients ◽

Serum Cytokines ◽

Imaging Characteristics ◽

The Relationship

To study the relationship between the CT image characteristics of inflammatory infection in patients with blood tumor and expression of serum cytokines in patients, and provide a theoretical basis for the application of CT imaging in the diagnosis of inflammation in clinical hematologic tumor patients in the future, 110 patients with inflammatory infection of blood tumor admitted to the hospital from October 30, 2017 to December 30, 2019 were selected as experimental group (EG), and 80 patients without infection in the general blood tumor department were selected as control group (CG). CT imaging was performed on both groups of patients, and two senior doctors read the imaging features and recorded the infection. At the same time, with flow cytometry, levels of IL2, IL-4, IL-6, IL-10, IFN-γ, and TNF-α in serum were detected. Cytokines levels and CT diagnosis results were analyzed by the working characteristic curve of the subjects. Kappa was used to test the consistency of the two physicians, and Spearman correlation was used to analyze the correlation between cytokines and CT diagnosis results. The results demonstrated that IL-6 level, IL-10 level, and TNF-α level in EG were obviously higher than those in CG (P < 0.05), and there was no obvious difference in levels of IL-2, IL-4, and IFN-γ (P > 0.05). The consistency coefficient of kappa test was 0.82. In the EG, sensitivity (Se) and specificity (Spe) of IL-6, IL-10, TNF-α, and CT diagnosis were 53.5% and 76.8%, 53.5% and 80.8%, 53.5% and 72.0%, 86.7% and 72.8%, respectively. Area under curve (AUC) was 0.686, 0.747, 0.657 and 0.859. Spearman correlation analysis (SCA) indicated obvious positive correlation between CT diagnosis results and levels of serum cytokines IL-6, IL-10, and TNF-α in both groups (P < 0.05). The results showed that the levels of IL-6, IL-10 and TNF-α in patients with inflammatory infection were obviously higher than those in patients with common blood tumor. Se and AUC area of CT image diagnosis are the highest, which has a better diagnostic value in inflammatory infection of blood tumor patients. Moreover, it is obviously correlated with cytokines levels, including IL-6, IL-10, and TNF-α, in serum.

Download Full-text

CT Image Analysis of Gastrointestinal Tumors Based on Simple Linear Iterative Cluster Algorithm

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2019.2778 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1770-1775

Author(s):

Wentao Huang ◽

Danhua Zhou ◽

Dawei Liu ◽

Baolong Li

Keyword(s):

Gastrointestinal Cancer ◽

Malignant Tumors ◽

Ct Scanning ◽

Ct Imaging ◽

Gastrointestinal Tumors ◽

Common Disease ◽

Imaging Features ◽

Ct Image ◽

Texture Information ◽

Imaging Characteristics

Objective: Gastrointestinal cancer is a very common disease at present. The purpose of this experiment is to use CT scanning technology and Simple Linear Iterative Cluster (SLIC) algorithm to analyze and fuse the scanning results, to explore the imaging characteristics of gastrointestinal neuroendocrine tumors by CT scanning and its application value in gastrointestinal tumors. Methods: The medical records of 25 patients with gastrointestinal tumors were selected as samples and analyzed retrospectively. Texture information fusion of CT image based on SLIC algorithm. This algorithm can fuse the texture information in the image, and then propose more targeted treatment for gastrointestinal tumors in different periods. Results: It was found that the diameter of malignant gastrointestinal tumors was more than 5 cm, and most of them occurred in the intestinal tract and the edge. The specific manifestations are blurred or lobulated, uneven density, invasion of surrounding structures and combined transfer rate. Therefore, it can be concluded that there are significant differences in CT features between benign and malignant gastrointestinal tumors. CT examination is helpful to differentiate benign and malignant tumors. Conclusion: Based on CT imaging, it can be found that the main cause of gastric neurosecretory tumors is blood-rich lesions. Gastrointestinal cancer cells of different pathological grades have different CT imaging features. CT imaging has certain value for preliminary judgment of pathological grading of patients.

Download Full-text

CT Image Examination Based on Virtual Reality Analysis in Clinical Diagnosis of Gastrointestinal Stromal Tumors

Journal of Healthcare Engineering ◽

10.1155/2021/9996565 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Zhiying Wang ◽

Qiaoyan Qu ◽

Ke Cai ◽

Ting Xu

Keyword(s):

Virtual Reality ◽

Lymph Nodes ◽

Clinical Diagnosis ◽

Gastrointestinal Stromal Tumors ◽

Ct Images ◽

Ct Imaging ◽

Ct Image ◽

Average Difference ◽

Stromal Tumors ◽

Imaging Examination

With the advancement and development of medical equipment, CT images have become a common lung examination tool. This article mainly studies the application of CT imaging examination based on virtual reality analysis in the clinical diagnosis of gastrointestinal stromal tumors. Before extracting suspected lymph nodes from a CT image of the stomach, the CT image sequence is preprocessed first, which can reduce the cumbersomeness of subsequent extraction of suspected lymph nodes and speed up the subsequent processing. According to medical knowledge, CT images of the stomach show that lymph nodes mainly exist in the adipose tissue around the gastric wall, but there are no lymph nodes in the subcutaneous fat outside the chest. The most basic gray value in the image and the neighborhood average difference feature related to gray level are used as the primary features of visual attention detection. When extracting the neighborhood average difference feature, we use a 3 ∗ 3 sliding window method to traverse each point of the pixel matrix in the image, thereby calculating the feature value of each pixel in the image. After the feature extraction is completed, it is necessary to calibrate the data and make a training data set. The SP immunohistochemical staining method was used. The specimens were fixed with 10% formaldehyde, routinely embedded in paraffin, sectioned, and stained with HE. The tumor tissue was determined by immunohistochemistry, and the reagents were products of Maixin Company. All patients were followed up by regular outpatient review, letters, and visits or phone calls. The data showed that immunohistochemical tumor cells showed positive staining for CD117 (14/15, 93.3%) and CD34 (10/15, 66.7%). The results show that the application of virtual reality technology to CT imaging examination can significantly improve the diagnostic accuracy of gastrointestinal stromal tumors.

Download Full-text

Clinical Manifestations and Radiological Characteristics on Rosai-Dorfman Disease: A Retrospective Observational Study

Medical & Clinical Research ◽

10.33140/mcr.05.05.005 ◽

2020 ◽

Vol 5 (5) ◽

Keyword(s):

Blood Vessels ◽

Abdominal Cavity ◽

Clinical Manifestations ◽

Ct Images ◽

High Signal ◽

Radiological Features ◽

Imaging Characteristics ◽

Rosai Dorfman Disease ◽

Heterogeneous Enhancement ◽

The Masses

Background and Objective: Rosai-Dorfman disease (RDD) are usually misdiagnosed because of rarity and nonspecific clinical and radiological features. The aim of our study is to explore the clinical and imaging characteristics of RDD to improve diagnostic accuracy. Methods: Clinical and imaging data in 10 patients with RDD were retrospectively analyzed. 7 patients were underwent CT scanning and 3 patients were underwent MR examination. Results: 8 (8/10) patients presented with painless enlarged lymph nodes (LNs) or mass. 3 cases were involved with LNs, 5 cases were involved with extra-nodal tissues, and the remaining 2 cases were involved with LNs and extra-nodal tissue simultaneously. In enhanced CT images, enlarged LNs displayed mild or moderate enhancement, and 2 cases showed heterogeneous ring-enhancement. MR features of 3 patients with extra-nodal RDD, 2 cases showed a mass located in the subcutaneous and anterior abdominal wall respectively, and 1 case showed an intracranial mass. Besides, all lesions showed high signal foci on DWI images, and were characterized by marked heterogeneous enhancement with blurred edge. The dural/fascia tail sign and dilated blood vessels could be seen around all the lesions on enhanced MRI. Radiological features of 2 cases with LN and extranodal tissue involved, one case presented with the swelling and thickening of pharyngeal lymphoid ring and nasopharynx, meanwhile with enlarged LNs in bilateral submandibular area, neck and abdominal cavity, and also companied with osteolytic lesion in right proximal humerus. All these LNs displayed mild and moderate enhancement on CT images. Another case showed enlarged LNs in bilateral neck accompanied with soft tissue mass in the sinuses. Conclusions: RDD occurred commonly in young and middle-aged men and presented with painless enlarged LNs or mass.RDD had a huge diversity of imaging findings, which varied with different location. The radiological features, such as small patches of high signal foci in the masses on DWI images, heterogeneous enhancement and blood vessels around the masses, are helpful in diagnosis of extranodal RDD.

Download Full-text

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

10.2196/preprints.19407 ◽

2020 ◽

Author(s):

Jinseok Lee

Keyword(s):

Deep Learning ◽

Diagnostic Performance ◽

Ct Images ◽

Chest Ct ◽

University Hospital ◽

Detection Accuracy ◽

Ct Image ◽

Test Dataset ◽

Learning Framework ◽

Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

Download Full-text

Integrating Machine/Deep Learning Methods and Filtering Techniques for Reliable Mineral Phase Segmentation of 3D X-ray Computed Tomography Images

Energies ◽

10.3390/en14154595 ◽

2021 ◽

Vol 14 (15) ◽

pp. 4595

Author(s):

Parisa Asadi ◽

Lauren E. Beckingham

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Random Forest ◽

Ct Images ◽

Ct Imaging ◽

Learning Method ◽

Learning Methods ◽

X Ray ◽

Machine Learning Methods ◽

Filtering Techniques

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.

Download Full-text

Epidemiology and aetiology of male and female sexual dysfunctions related to pelvic ring injuries: a systematic review

International Orthopaedics ◽

10.1007/s00264-021-05153-8 ◽

2021 ◽

Author(s):

Giuseppe Rovere ◽

Andrea Perna ◽

Luigi Meccariello ◽

Domenico De Mauro ◽

Alessandro Smimmo ◽

...

Keyword(s):

Sexual Dysfunction ◽

Sexual Function ◽

Pelvic Fracture ◽

Pelvic Ring ◽

Pelvic Fractures ◽

Sexual Dysfunctions ◽

Fracture Type ◽

Ring Fracture ◽

Male And Female ◽

Pelvic Ring Injuries

Abstract Introduction Pelvic ring injuries, frequently caused by high energy trauma, are associated with high rates of morbidity and mortality (5–33%), often due to significant blood loss and disruption of the lumbosacral plexus, genitourinary system, and gastrointestinal system. The aim of the present study is to perform a systematic literature review on male and female sexual dysfunctions related to traumatic lesions of the pelvic ring. Methods Scopus, Cochrane Library MEDLINE via PubMed, and Embase were searched using the keywords: “Pelvic fracture,” “Pelvic Ring Fracture,” “Pelvic Ring Trauma,” “Pelvic Ring injury,” “Sexual dysfunction,” “Erectile dysfunction,” “dyspareunia,” and their MeSH terms in any possible combination. The following questions were formulated according to the PICO (population (P), intervention (I), comparison (C), and outcome (O)) scheme: Do patients suffering from pelvic fracture (P) report worse clinical outcomes (C), in terms of sexual function (O), when urological injury occurs (I)? Is the sexual function (O) influenced by the type of fracture (I)? Results After screening 268 articles by title and abstract, 77 were considered eligible for the full-text analysis. Finally 17 studies that met inclusion criteria were included in the review. Overall, 1364 patients (902 males and 462 females, M/F ratio: 1.9) suffering from pelvic fractures were collected. Discussion Pelvic fractures represent challenging entities, often concomitant with systemic injuries and subsequent morbidity. Anatomical consideration, etiology, correlation between sexual dysfunction and genitourinary lesions, or pelvic fracture type were investigated. Conclusion There are evidences in the literature that the gravity and frequency of SD are related with the pelvic ring fracture type. In fact, patients with APC, VS (according Young-Burgess), or C (according Tile) fracture pattern reported higher incidence and gravity of SD. Only a week association could be found between GUI and incidence and gravity of SD, and relationship between surgical treatment and SD. Electrophysiological tests should be routinely used in patient suffering from SD after pelvic ring injuries.

Download Full-text

Multi-Cycle-Consistent Adversarial Networks for Edge Denoising of Computed Tomography Images

ACM Journal on Emerging Technologies in Computing Systems ◽

10.1145/3462328 ◽

2021 ◽

Vol 17 (4) ◽

pp. 1-16

Author(s):

Xiaowe Xu ◽

Jiawei Zhang ◽

Jinglan Liu ◽

Yukun Ding ◽

Tianchen Wang ◽

...

Keyword(s):

Computed Tomography ◽

Image Denoising ◽

Ct Images ◽

High Dose ◽

Ct Image ◽

Paired Data ◽

High Quality ◽

Computed Tomography Images ◽

Significant Difference ◽

Global Cycle

As one of the most commonly ordered imaging tests, the computed tomography (CT) scan comes with inevitable radiation exposure that increases cancer risk to patients. However, CT image quality is directly related to radiation dose, and thus it is desirable to obtain high-quality CT images with as little dose as possible. CT image denoising tries to obtain high-dose-like high-quality CT images (domain Y ) from low dose low-quality CT images (domain X ), which can be treated as an image-to-image translation task where the goal is to learn the transform between a source domain X (noisy images) and a target domain Y (clean images). Recently, the cycle-consistent adversarial denoising network (CCADN) has achieved state-of-the-art results by enforcing cycle-consistent loss without the need of paired training data, since the paired data is hard to collect due to patients’ interests and cardiac motion. However, out of concerns on patients’ privacy and data security, protocols typically require clinics to perform medical image processing tasks including CT image denoising locally (i.e., edge denoising). Therefore, the network models need to achieve high performance under various computation resource constraints including memory and performance. Our detailed analysis of CCADN raises a number of interesting questions that point to potential ways to further improve its performance using the same or even fewer computation resources. For example, if the noise is large leading to a significant difference between domain X and domain Y , can we bridge X and Y with a intermediate domain Z such that both the denoising process between X and Z and that between Z and Y are easier to learn? As such intermediate domains lead to multiple cycles, how do we best enforce cycle- consistency? Driven by these questions, we propose a multi-cycle-consistent adversarial network (MCCAN) that builds intermediate domains and enforces both local and global cycle-consistency for edge denoising of CT images. The global cycle-consistency couples all generators together to model the whole denoising process, whereas the local cycle-consistency imposes effective supervision on the process between adjacent domains. Experiments show that both local and global cycle-consistency are important for the success of MCCAN, which outperforms CCADN in terms of denoising quality with slightly less computation resource consumption.

Download Full-text