Clinical Computed Tomography Images Research Articles

An image-based metal artifact reduction technique utilizing forward projection in computed tomography.

The projection data generated via the forward projection of a computed tomography (CT) image (FP-data) have useful potentials in cases where only image data are available. However, there is a question of whether the FP-data generated from an image severely corrupted by metal artifacts can be used for the metal artifact reduction (MAR). The aim of this study was to investigate the feasibility of a MAR technique using FP-data by comparing its performance with that of a conventional robust MAR using projection data normalization (NMARconv). The NMARconv was modified to make use of FP-data (FPNMAR). A graphics processing unit was used to reduce the time required to generate FP-data and subsequent processes. The performances of FPNMAR and NMARconv were quantitatively compared using a normalized artifact index (AIn) for two cases each of hip prosthesis and dental fillings. Several clinical CT images with metal artifacts were processed by FPNMAR. The AIn values of FPNMAR and NMARconv were not significantly different from each other, showing almost the same performance between these two techniques. For all the clinical cases tested, FPNMAR significantly reduced the metal artifacts; thereby, the images of the soft tissues and bones obscured by the artifacts were notably recovered. The computation time per image was ~ 56ms. FPNMAR, which can be applied to CT images without accessing the projection data, exhibited almost the same performance as that of NMARconv, while consuming significantly shorter processing time. This capability testifies the potential of FPNMAR for wider use in clinical settings.

Software development to anonymize patient information from clinical computed tomography images

A free software for digital imaging and communications in medicine (DICOM) image anonymization is needed to protect patient information from third parties. This study aimed to develop a software for the anonymization of patient information in computed tomography (CT) image. There was a total of 17 informations to be anonymized, such as Patient’s Name, Other Patient Names, Patient’s ID, Patient’s Birth Date, Patient’s Sex, Patient’s Age, Study ID, Study Description, Series Description, Institution Name, Institution Adress, Referring Phisician’s Name, Consulting Physician’s Name, Performing Physician’s Name, Name of Physician(s) Reading Study, Operator’s Name, and Protocol Name. In every information, its initial value was replaced with a dummy value with the string value of "N/A". For testing, patient CT images from four different hospitals with different scanners were collected. It is found that each scanner had different information stored in DICOM information. However, the anonymization process in the four hospitals works well with accuracy of 100%. The developed software can anonymize DICOM images flexibly and successfully. This software can be used for anonymization of patient information in order to protect patient information.

SMARCA4-deficient non-small cell lung carcinoma: clinicodemographic, computed tomography, and positron emission tomography-computed tomography features.

SMARCA4-deficient non-small cell lung carcinoma (SD-NSCLC) is a relatively rare tumor, which occurs in 5-10% of NSCLC. Based on World Health Organization thoracic tumor classification system, SMARCA4-deficient undifferentiated tumor (SD-UT) is recognized as a separate entity from SD-NSCLC. Differentiation between SD-NSCLC and SD-UT is often difficult due to shared biological continuum, but often required for choosing appropriate treatment regimen. Therefore, the aim of our study was to identify the clinicopathologic, computed tomography (CT), and positron emission tomography (PET)-CT imaging features of SD-NSCLC. Nine patients of pathologically confirmed SD-NSCLC were included in our analysis. We reviewed electronic medical records for clinical information, demographic features, CT, and PET-CT imaging features were analyzed. Smoking history and male predominance are observed in all patients with SD-NSCLC (n=9). On CT, SD-NSCLC appeared as relatively well-defined masses with lobulated contour (n=8) and peripheral location (n=7). Invasion of adjacent pleura or chest wall (n=7) were frequently observed, regardless of small tumor size. Four cases showed lymph node metastases. Among nine patients, three patients showed multiple bone metastases, and one patient showed lung-to-lung metastases. In patient with SD-NSCLC, there was tendency for male smokers, peripheral location and invasion of adjacent pleural or chest wall invasion regardless of small tumor size, when compared to SD-UT.

A convolutional neural network-based method for the generation of super-resolution 3D models from clinical CT images

Background and objectiveThe accurate evaluation of bone mechanical properties is essential for predicting fracture risk based on clinical computed tomography (CT) images. However, blurring and noise in clinical CT images can compromise the accuracy of these predictions, leading to incorrect diagnoses. Although previous studies have explored enhancing trabecular bone CT images to super-resolution (SR), none of these studies have examined the possibility of using clinical CT images from different instruments, typically of lower resolution, as a basis for analysis. Additionally, previous studies rely on 2D SR images, which may not be sufficient for accurate mechanical property evaluation, due to the complex nature of the 3D trabecular bone structures. The objective of this study was to address these limitations. MethodsA workflow was developed that utilizes convolutional neural networks to generate SR 3D models across different clinical CT instruments. The morphological and finite-element-derived mechanical properties of these SR models were compared with ground truth models obtained from micro-CT scans. ResultsA significant improvement in analysis accuracy was demonstrated, where the new SR models increased the accuracy by up to 700 % compared with the low-resolution data, i.e. clinical CT images. Additionally, we found that the mixture of different CT image datasets may improve the SR model performance. ConclusionsSR images, generated by convolutional neural networks, outperformed clinical CT images in the determination of morphological and mechanical properties. The developed workflow could be implemented for fracture risk prediction, potentially leading to improved diagnoses and subsequent clinical decision making.

Ultrasonography, computed tomography and magnetic resonance imaging of the dromedary camel distal limbs

BackgroundLameness associated with the distal limb region in dromedary camels is quiet prevalent. The diagnosis of lameness relies on a comprehensive orthopedic examination conjugated with an appropriate imaging modality to achieve a decisive diagnosis. Using of modern imaging tools provoked a significant breakthrough in the diagnosis of lameness. Ultrasonography (US) is widely established in dromedaries, whereas computed tomography (CT) and magnetic resonance imaging (MRI) are gaining popularity. CT provides a considerably higher bone detail than any other imaging modality. US and MRI continue to be the best options for soft tissue imaging. A truthful assessment of the clinical US, CT and MRI images dictates a comprehensive familiarity with the standard US, CT and MRI tissue deviations. Accordingly, our purposes were to present a full MRI protocol for investigating the dromedary camel distal limbs as well as comparing and illustrating the merits of using MRI, CT and US for evaluation of the front and hind distal limbs in 10 healthy lameness free dromedary camel cadavers. The limbs were scanned via a high-field 1.5 Tesla MRI magnet and a multi-detector CT scanner then subjected to a systematic US examination in both longitudinal and transverse planes. The obtained MRI, CT and US images were evaluated, correlated and compared.ResultsCT and MRI eliminated the structural superimposition in the dromedary camel distal limbs and afforded assessment of minute ligamentous and tendentious structures that were inaccessible by US including the axial collateral ligaments, ligaments supporting the proximal sesamoid bones and the palmar/plantar aspects of the inter-phalangeal joints. US and MRI were appreciated for the assessment of the articular cartilage that was not visible on the plain CT images.ConclusionsCT and MRI accurately identified and characterized bones and soft tissues constituting the dromedary camel distal limbs. US was appreciated for assessment of soft tissues, articular cartilage and bone contours. CT and MRI may be considered when US results are inconclusive or to evaluate the unreachable parts of the camel distal limbs. Images presented in this study could be used as a reference standard for evaluating dromedary camel distal limb diseases.

PND-Net: Physics-inspired Non-local Dual-domain Network for Metal Artifact Reduction.

Metal artifacts caused by the presence of metallic implants tremendously degrade the quality of reconstructed computed tomography (CT) images and therefore affect the clinical diagnosis or reduce the accuracy of organ delineation and dose calculation in radiotherapy. Although various deep learning methods have been proposed for metal artifact reduction (MAR), most of them aim to restore the corrupted sinogram within the metal trace, which removes beam hardening artifacts but ignores other components of metal artifacts. In this paper, based on the physical property of metal artifacts which is verified via Monte Carlo (MC) simulation, we propose a novel physics-inspired non-local dual-domain network (PND-Net) for MAR in CT imaging. Specifically, we design a novel non-local sinogram decomposition network (NSD-Net) to acquire the weighted artifact component and develop an image restoration network (IR-Net) to reduce the residual and secondary artifacts in the image domain. To facilitate the generalization and robustness of our method on clinical CT images, we employ a trainable fusion network (F-Net) in the artifact synthesis path to achieve unpaired learning. Furthermore, we design an internal consistency loss to ensure the data fidelity of anatomical structures in the image domain and introduce the linear interpolation sinogram as prior knowledge to guide sinogram decomposition. NSD-Net, IR-Net, and F-Net are jointly trained so that they can benefit from one another. Extensive experiments on simulation and clinical data demonstrate that our method outperforms state-of-the-art MAR methods.

Case report of septic pulmonary embolism caused by Staphylococcus aureus combined with multidrug-resistant pulmonary tuberculosis and bronchial tuberculosis

This case report describes the presence of septic pulmonary embolism (SPE) in an older woman with diabetes whose initial manifestation was acute sepsis. She underwent computed tomography (CT) imaging, blood metagenomic next-generation sequencing (mNGS), and bronchoscopy, and was diagnosed with SPE secondary to Staphylococcus aureus-positive bacterial infection, combined with multidrug-resistant pulmonary tuberculosis and bronchial tuberculosis. In this case report, we focused on the clinical presentation and CT imaging features of SPE, and the application value of mNGS. This case study suggests that CT combined with mNGS has value in the timely diagnosis and management of SPE in patients with diabetes with severe pneumonia caused by mixed infection with multiple pathogenic pathogens.

CT-based deep learning model for predicting hospital discharge outcome in spontaneous intracerebral hemorrhage.

To predict the functional outcome of patients with intracerebral hemorrhage (ICH) using deep learning models based on computed tomography (CT) images. A retrospective, bi-center study of ICH patients was conducted. Firstly, a custom 3D convolutional model was built for predicting the functional outcome of ICH patients based on CT scans from randomly selected ICH patients in H training dataset collected from H hospital. Secondly, clinical data and radiological features were collected at admission and the Extreme Gradient Boosting (XGBoost) algorithm was used to establish a second model, named the XGBoost model. Finally, the Convolution model and XGBoost model were fused to build the third "Fusion model." Favorable outcome was defined as modified Rankin Scale score of 0-3 at discharge. The prognostic predictive accuracy of the three models was evaluated using an H test dataset and an external Y dataset, and compared with the performance of ICH score and ICH grading scale (ICH-GS). A total of 604 patients with ICH were included in this study, of which 450 patients were in the H training dataset, 50 patients in the H test dataset, and 104 patients in the Y dataset. In the Y dataset, the areas under the curve (AUCs) of the Convolution model, XGBoost model, and Fusion model were 0.829, 0.871, and 0.905, respectively. The Fusion model prognostic performance exceeded that of ICH score and ICH-GS (p = 0.043 and p = 0.045, respectively). Deep learning models have good accuracy for predicting functional outcome of patients with spontaneous intracerebral hemorrhage. The proposed deep learning Fusion model may assist clinicians in predicting functional outcome and developing treatment strategies, thereby improving the survival and quality of life of patients with spontaneous intracerebral hemorrhage. • Integrating clinical presentations, CT images, and radiological features to establish deep learning model for functional outcome prediction of patients with intracerebral hemorrhage. • Deep learning applied to CT images provides great help in prognosing functional outcome of intracerebral hemorrhage patients. • The developed deep learning model performs better than clinical prognostic scores in predicting functional outcome of patients with intracerebral hemorrhage.

Self-Assembled Nano-CT Contrast Agent Leveraging Size Aggregation for Improved In Vivo Tumor CT Imaging.

Computed tomography (CT) is a widely utilized noninvasive diagnostic tool in clinical practice. However, the commonly employed small molecular iodinated contrast agents (ICAs) in clinical CT imaging have limitations such as nonspecific distribution in body, rapid clearance through kidneys, etc., leading to a narrow imaging time window. In contrast, existing nano-sized ICAs face challenges like structural uncertainty, poor reproducibility, low iodine content, and uniformity issues. In this study, a novel approach is presented utilizing the aggregation-induced emission luminogen (AIEgen) to design and fabricate a kind of monocomponent nano-sized ICA (namely, BioDHU-CT NPs) that exhibits a unique aggregation effect upon activation. The small sized BioDHU-CT nanoparticles exhibit excellent tumor targeting capabilities and can release ICA modified with AIEgen with a high release efficiency up to 88.45%, under the activation of reactive oxygen species highly expressed in tumor regions. The released ICA performs in situ aggregation capability in the tumor region, which can enhance the retention efficiency of CT contrast agents, extending the imaging time window and improving the imaging quality in tumor regions.

Deep learning-based age estimation from clinical Computed Tomography image data of the thorax and abdomen in the adult population.

Aging is an important risk factor for disease, leading to morphological change that can be assessed on Computed Tomography (CT) scans. We propose a deep learning model for automated age estimation based on CT- scans of the thorax and abdomen generated in a clinical routine setting. These predictions could serve as imaging biomarkers to estimate a "biological" age, that better reflects a patient's true physical condition. A pre-trained ResNet-18 model was modified to predict chronological age as well as to quantify its aleatoric uncertainty. The model was trained using 1653 non-pathological CT-scans of the thorax and abdomen of subjects aged between 20 and 85 years in a 5-fold cross-validation scheme. Generalization performance as well as robustness and reliability was assessed on a publicly available test dataset consisting of thorax-abdomen CT-scans of 421 subjects. Score-CAM saliency maps were generated for interpretation of model outputs. We achieved a mean absolute error of 5.76 ± 5.17 years with a mean uncertainty of 5.01 ± 1.44 years after 5-fold cross-validation. A mean absolute error of 6.50 ± 5.17 years with a mean uncertainty of 6.39 ± 1.46 years was obtained on the test dataset. CT-based age estimation accuracy was largely uniform across all age groups and between male and female subjects. The generated saliency maps highlighted especially the lumbar spine and abdominal aorta. This study demonstrates, that accurate and generalizable deep learning-based automated age estimation is feasible using clinical CT image data. The trained model proved to be robust and reliable. Methods of uncertainty estimation and saliency analysis improved the interpretability.

An Innovative Metal Artifact Reduction Algorithm based on Res-U-Net GANs

During X-ray computed tomography (CT) scans, the metal implants in the patient's body will produce severe artifacts, which reduce the image quality and interferes with the doctor's judgment. Therefore, it is necessary to develop an algorithm for removing metal artifacts in CT images and reconstructing high-quality images. In this paper, we proposed a generative adversarial networks (GANs)-based metal artifact reduction algorithm for the image domain, Res-U-Net GANs. This method can effectively suppress noise and remove metal artifacts in CT images. Our new approach includes a generator and a discriminator. The generator contains several residual blocks, a U-Net structure and skip connections. And a weighted joint loss function is also used for training. These structures can reduce metal artifacts in images, improve image quality, and restore implant details. We use SSIM, PSNR and RMSE to evaluate the performance of the proposed method. The mean SSIM, PSNR and RMSE of the testing set images are 0.977, 39.044 and 0.011, respectively. And the trained model which is compiled and encapsulated, also show excellent performance in processing clinical data sets, which can remove metal artifacts in clinical CT images. We consider that the proposed algorithm can remove metal artifacts in CT images and restore image details, which is very helpful for radiologists.

Predicting the Probability of the Incidence of Maxillary Sinus Fungus Ball in Patients Using Nomogram Models.

Maxillary sinus fungal ball (MSFB) is the most common type of non-invasive fungal rhinosinusitis. Since MSFB requires a unique treatment strategy and is associated with potentially severe complications, timely and precise diagnosis is crucial. Computed tomography (CT) is the first-line imaging tool for evaluating chronic rhinosinusitis. Accordingly, we aimed to investigate the clinical and CT imaging characteristics of MSFB. We retrospectively enrolled 97 patients with unilateral MSFB and 158 with unilateral non-fungal maxillary rhinosinusitis. The clinical characteristics, laboratory data, and CT imaging features of participants were evaluated. Older age, female sex, lower white blood cell and neutrophil counts, and CT imaging features (including an irregular surface, erosion of the medial sinus wall, sclerosis of the lateral sinus wall, and intralesional hyperdensity) were significantly associated with MSFB. The presence of adjacent maxillary odontogenic pathology was associated with a decreased likelihood of the incidence of MSFB in unilateral maxillary rhinosinusitis. Separate nomograms were created for patients, without and with the use of CT scan, to predict the probabilities of MSFB in patients with unilateral maxillary rhinosinusitis. We proposed two nomograms based on the clinical and CT characteristics of patients with MSFB. These could serve as evaluation tools to assist clinicians in determining the need for undergoing CT and facilitate the accurate and timely diagnosis of MSFB.

Observer- and radiomics model-based computed tomography classification of suppurative versus tuberculous lymphadenitis complicated with nodal necrosis of the neck in children.

Computed tomography (CT) can be used for the early detection of lymphadenitis. Radiomics is able to identify a large amount of hidden information from images. However, few CT-based radiomics studies on cervical lymphadenitis in children have been published. This study aimed to investigate the role of visual CT analysis and CT radiomics in differentiating cervical suppurative node necrosis from tuberculous node necrosis in pediatric patients. A total of 101 patients with cervical suppurative lymphadenitis (n=52) or cervical tuberculous lymphadenitis (n=49) were included. Clinical data and CT images were retrieved for analysis. For visual observation, 11 major CT features were identified for univariate and multivariate analyses. For radiomics analysis, image segmentation, feature value extraction, and dimension reduction, feature selection and the construction of radiomics-based models were performed through the RadCloud platform. For the visual observation, significant differences were found between the two groups, including the short diameter of the largest necrotic lymph node (P=0.03), sharp border of the node (P=0.02), fusion of nodes (P=0.02), regular silhouette of the necrotic area (P=0.001), multilocular necrotic area (P=0.02), node calcification (P=0.004), and enhancement degree of the nodal nonnecrotic area (P=0.01). No feature was found to be an independent predictor for suppurative or tuberculous lymphadenitis (P>0.05 for all features). Concerning the radiomics analysis, after feature value extraction and dimension reduction, nine related features were selected. The support vector machine classifier achieved high diagnostic performance in distinguishing suppurative from tuberculous lymphadenitis. The area under the curve, accuracy, sensitivity, and specificity of the support vector machine model test set were 0.89 (95% confidence interval: 0.72-1.00), 0.88, 0.78, and 0.90, respectively. Compared to observer-based CT image analyses, radiomics model-based CT image analyses exhibit better performance in the differential diagnosis of cervical suppurative and tuberculous lymphadenitis complicated with nodal necrosis in children.

Triple contrast computed tomography reveals site-specific biomechanical differences in the human knee joint-A proof of concept study.

Cartilage and synovial fluid are challenging to observe separately in native computed tomography (CT). We report the use of triple contrast agent (bismuth nanoparticles [BiNPs], CA4+, and gadoteridol) to image and segment cartilage in cadaveric knee joints with a clinical CT scanner. We hypothesize that BiNPs will remain in synovial fluid while the CA4+ and gadoteridol will diffuse into cartilage, allowing (1) segmentation of cartilage, and (2) evaluation of cartilage biomechanical properties based on contrast agent concentrations. To investigate these hypotheses, triple contrast agent was injected into both knee joints of a cadaver (N = 1), imaged with a clinical CT at multiple timepoints during the contrast agent diffusion. Knee joints were extracted, imaged with micro-CT (µCT), and biomechanical properties of the cartilage surface were determined by stress-relaxation mapping. Cartilage was segmented and contrast agent concentrations (CA4+ and gadoteridol) were compared with the biomechanical properties at multiple locations (n = 185). Spearman's correlation between cartilage thickness from clinical CT and reference µCT images verifies successful and reliable segmentation. CA4+ concentration is significantly higher in femoral than in tibial cartilage at 60 min and further timepoints, which corresponds to the higher Young's modulus observed in femoral cartilage. In this pilot study, we show that (1) large BiNPs do not diffuse into cartilage, facilitating straightforward segmentation of human knee joint cartilage in a clinical setting, and (2) CA4+ concentration in cartilage reflects the biomechanical differences between femoral and tibial cartilage. Thus, the triple contrast agent CT shows potential in cartilage morphology and condition estimation in clinical CT.

Early Identification of Sacroiliitis in Patients with Suspected Spondyloarthritis: A Challenging Task.

The purpose of this study was to assess the performance of computed tomography (CT) scan and magnetic resonance imaging (MRI) for detecting sacroiliitis in nonradiographic SpA (nr-SpA). This cross-sectional monocentric double-blind study included 63 patients consulting for symptoms suggestive of SpA between February 2014 and February 2017. Patients with conventional radiographs showing a confirmed sacroiliitis (grade 3 or 4) were not included. Eligible patients underwent CT and MRI of sacroiliac joints (SIJ). CT and MR images were interpreted by 2 experienced musculoskeletal radiologists blinded to clinical and laboratory data. Two professors in rheumatology blinded to radiologists' conclusions analyzed clinical data, laboratory tests, HLA typing, X-rays, CT and MRI images, and divided the patients into 2 groups: confirmed nr-SpA or no SpA. This classification was considered the gold standard when analyzing the results. 46 women and 17 men were included in this study. 47 patients were classified as confirmed nr-SpA (74.6%) and 16 patients as no SpA (25.4%). Sensitivity, specificity, and positive and negative predictive values of CT and MRI for detecting sacroiliitis were, respectively, estimated at 71.7%, 71.4%, 89.2%, 43.5%, and 51.2%, 100%, 100%, and 40%. CT and MRI findings were found to be statistically associated (p<0.001). SIJ MRI is a highly specific method in the detection of sacroiliitis, but with a moderate sensitivity. SIJ CT scan, usually known as the third option after radiography and MRI, has much greater diagnostic utility than it has been documented previously.

Age estimation by modified Suchey-Brooks method using three-dimensional reconstructed CT images of Chinese Han population

The method proposed by Suchey-Brooks for adult age estimation based on the surface morphology of the pubic symphysis has been widely accepted. The applicability of the method varies considerably in different populations. The present study established a virtual reference sample and aimed to develop population-specific criteria that can be used for age estimation in different skeletal samples. First, The dry bone specimens from 100 individuals were compared with their corresponding three-dimensional (3D) reconstruction model and showed high inter-method agreement (k = 0.743–0.811), suggesting that the virtual bone model and physical bone specimens have comparable performances in describing the surface morphology of the pubic symphysis. We retrospectively collected clinical computed tomography (CT) data from 895 Chinese patients to create a virtual reference sample of the pubic symphysis. Based on the original Suchey-Brooks method, each of the 895 reference samples was assigned a phase, for each sex and phase, data on the mean age, standard deviation, and 95% age range of the corresponding sample were obtained, which was then used as the “method modified for Chinese” (modified method) and compared to the “SB method”. Compared to the SB method, modified method had a lower inaccuracy in dry bones for males over 35 years and females over 45 years, in dry bone CT test sample for males over 55 years and females over 45 years, and in postmortem CT test sample for males over 35 years and females over 55 years. The modified method can improve the accuracy of age estimation for older samples over 40 years. It has shown considerable reliability when applied as a population-specific criterion, but its accuracy is still not sufficient, and caution is needed when using it.

A novel protocol for abdominal low-dose CT scans adapted with a model-based iterative reconstruction method.

This study aims to introduce a novel low-dose abdominal computed tomography (CT) protocol adapted with model-based iterative reconstruction (MBIR), To validate the adaptability of this protocol, objective image quality and subjective clinical scores of low-dose MBIR images are compared with the normal-dose images. Normal-dose abdominal CT images of 58 patients and low-dose abdominal CT images of 52 patients are reconstructed using both conventional filtered back projection (FBP) and MBIR methods with and without smooth applying. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) are used to compare image quality between the normal-dose and low-dose CT scans. CT dose indices (CTDI) of normal-dose and low-dose abdominal CT images on post-contrast venous phase are also compared. The SNR, CNR and clinical score of low-dose MBIR images all show significant higher values (Bonferroni p < 0.05) than those of normal-dose images with conventional FBP method. A total of around 40% radiation dose reduction (CTDI: 5.3 vs 8.7 mGy) could be achieved via our novel abdominal CT protocol. With the higher SNR/CNR and clinical scores, the low-dose CT abdominal imaging protocol with MBIR could effectively reduce the radiation for patients and provide equal or even higher image quality and also its adaptability in clinical abdominal CT image diagnosis.

Combined CT and serum CA19-9 for stratifying risk for progression in patients with locally advanced pancreatic cancer receiving intraoperative radiotherapy.

The aim of this study was to evaluate the significance of baseline computed tomography (CT) imaging features and carbohydrate antigen 19-9 (CA19-9) in predicting prognosis of locally advanced pancreatic cancer (LAPC) receiving intraoperative radiotherapy (IORT) and to establish a progression risk nomogram that helps to identify the potential beneficiary of IORT. A total of 88 LAPC patients with IORT as their initial treatment were enrolled retrospectively. Clinical data and CT imaging features were analyzed. Cox regression analyses were performed to identify the independent risk factors for progression-free survival (PFS) and to establish a nomogram. A risk-score was calculated by the coefficients of the regression model to stratify the risk of progression. Multivariate analyses revealed that relative enhanced value in portal-venous phase (REV-PVP), peripancreatic fat infiltration, necrosis, and CA19-9 were significantly associated with PFS (all p < 0.05). The nomogram was constructed according to the above variables and showed a good performance in predicting the risk of progression with a concordance index (C-index) of 0.779. Our nomogram stratified patients with LAPC into low- and high-risk groups with distinct differences in progression after IORT (p < 0.001). The integrated nomogram would help clinicians to identify appropriate patients who might benefit from IORT before treatment and to adapt an individualized treatment strategy.

CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center.

Deep learning (DL) is more and more widely used in children's medical treatment. In this study, we have developed a computed tomography (CT)-based DL model for identifying undiagnosed non-Wilms tumors (nWTs) from pediatric renal tumors. This study collected and analyzed the preoperative clinical data and CT images of pediatric renal tumor patients diagnosed by our center from 2008 to 2020, and established a DL model to identify nWTs noninvasively. A total of 364 children who had been confirmed by histopathology with renal tumors from our center were enrolled, including 269 Wilms tumors (WTs) and 95 nWTs. For DL model development, all cases were randomly allocated to training set (218 cases), validation set (73 cases), and test set (73 cases). In the test set, the DL model achieved area under the curve of 0.831 (95% CI: 0.712-0.951) in discriminating WTs from nWTs, with the accuracy, sensitivity, and specificity of 0.781, 0.563, and 0.842, respectively. The sensitivity of our model was higher than a radiologist with 15 years of experience. We presented a DL model for identifying undiagnosed nWTs from pediatric renal tumors, with the potential to improve the image-based diagnosis. Deep learning model was used for the first time to identify pediatric renal tumors in this study. Deep learning model can identify non-Wilms tumors from pediatric renal tumors. Deep learning model based on computed tomography images can improve tumor diagnosis rate.

Evaluation of cortical bone density using clinical computed tomography images: Detection of cortical porosity areas or transitional zones in human femoral diaphyses.

Age-related changes in human trabecular bone and cortical bone are known to vary. Although the porosity of cortical bone has been suggested to increase the risk of bone fracture, most of the currently available instruments for osteoporosis testing target trabecular bone. In this study, we evaluated cortical bone density using clinical computed tomography (CT) and compared the reliability of the cortical bone density index (CDI) with that of a polished male femoral bone from the same region. CDI images revealed that the porous area of cortical bone was extended in low CDI values. Moreover, this method was used to semi-quantitatively evaluate the cortical bones of the diaphysis of male femur specimens (n=46). We found that there was a significant relationship (r=0.70, p < 0.01) between the value of the cortical index (the ratio of cortical bone area to the cross-sectional area of the femoral diaphysis) and the average of CDI in the low signal area. Our findings suggest that the smaller the cortical bone occupancy, the more areas of consequential bone density loss were present. This may be the first step toward using clinical CT to assess cortical bone density.