CT Imaging Signs Research Articles

Clinical characteristics of HIV-associated tracheobronchial Talaromyces marneffei infection in seven patients in Guangxi, China.

Tracheobronchial Talaromyces marneffei (T. marneffei) infections among HIV-infected patients are rare. To improve understanding, we analyzed the clinical features, immune mechanisms, treatment, and prognosis of these patients. We collected clinical information from HIV-positive patients with talaromycosis admitted to the Fourth People's Hospital of Nanning from January 2015 to June 2022. Patients who presented with culture and/or histopathological proof of tracheobronchial T. marneffei infection were included. A total of 108 patients with respiratory infections who underwent bronchoscopy were enrolled. Seven patients with tracheobronchial T. marneffei infection, all of whom were men with a median age of 48 years (range 39-50 years), were analyzed. Cough, sputum, fever, and weight loss were the most common symptoms. The total white blood cell count was normal or decreased, and all lymphocyte counts were decreased. All patients had reduced CD4+ T-cell counts, with values less than 50 cells/µL. The chest CT imaging signs included patchy signals or large areas of exudation, bronchial stenosis and occlusion. This was different from the lack of bronchial involvement. Endoscopically, the trachea and bronchial mucosa showed congestion, edema, surface attachment, nodules, lumen stenosis, obstruction, etc. T. marneffei spores were found via bronchial mucosal pathology in all 7 patients. Five patients were initially treated with intravenous infusion of amphotericin B for 2 weeks, followed by oral itraconazole capsules (200mg) twice daily, and two patients were initially treated with itraconazole. Six patients were remission, and 1 died. The clinical features of trachea invasion and nontracheal invasion are not unique, but chest CT reveals manifestations such as masses, solid shadows, and bronchial stenosis/obstruction. Bronchoscopy should be performed if possible, and the presence or absence of trachea T. marneffei infection should be confirmed. Antiviral therapy combined with antifungal therapy can improve patient prognosis.

Quantitative radiomics analysis of imaging features in adults and children Mycoplasma pneumonia.

This study aims to explore the value of clinical features, CT imaging signs, and radiomics features in differentiating between adults and children with Mycoplasma pneumonia and seeking quantitative radiomic representations of CT imaging signs. In a retrospective analysis of 981 cases of mycoplasmal pneumonia patients from November 2021 to December 2023, 590 internal data (adults:450, children: 140) randomly divided into a training set and a validation set with an 8:2 ratio and 391 external test data (adults:121; children:270) were included. Using univariate analysis, CT imaging signs and clinical features with significant differences (p < 0.05) were selected. After segmenting the lesion area on the CT image as the region of interest, 1,904 radiomic features were extracted. Then, Pearson correlation analysis (PCC) and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomic features. Based on the selected features, multivariable logistic regression analysis was used to establish the clinical model, CT image model, radiomic model, and combined model. The predictive performance of each model was evaluated using ROC curves, AUC, sensitivity, specificity, accuracy, and precision. The AUC between each model was compared using the Delong test. Importantly, the radiomics features and quantitative and qualitative CT image features were analyzed using Pearson correlation analysis and analysis of variance, respectively. For the individual model, the radiomics model, which was built using 45 selected features, achieved the highest AUCs in the training set, validation set, and external test set, which were 0.995 (0.992, 0.998), 0.952 (0.921, 0.978), and 0.969 (0.953, 0.982), respectively. In all models, the combined model achieved the highest AUCs, which were 0.996 (0.993, 0.998), 0.972 (0.942, 0.995), and 0.986 (0.976, 0.993) in the training set, validation set, and test set, respectively. In addition, we selected 11 radiomics features and CT image features with a correlation coefficient r greater than 0.35. The combined model has good diagnostic performance for differentiating between adults and children with mycoplasmal pneumonia, and different CT imaging signs are quantitatively represented by radiomics.

Transformation with Yolo Tiny Network Architecture for Multimodal Fusion in Lung Disease Classification

This article focuses on the crucial task of identifying lung diseases through the analysis and processing of medical images, aiming to aid medical professionals in the diagnostic process. Image fusion technologies, employed in prospective remedies, enhance diagnostic precision and reliability by amalgamating radiological information from diverse sources. The study introduces a Yolo Tiny network-based medical imaging fusion technique, yielding fused images with enhanced clarity and diverse physical information. The proposed method involves the integration of an adaptive pre-processing module, YOLO Tiny for efficient classification, discrete wavelet transform for feature combination, and a novel adaptive image fusion technique based on a classifier, contributing to improved diagnostic accuracy. Addressing challenges like uneven illumination and poor contrast in medical images, the comprehensive workflow enhances image quality, facilitating effective classification in medical imaging. Experimental results showcase the efficacy of the proposed scheme in CT imaging signs retrieval and classification, specifically for lung nodule detection. The system exhibits high accuracy, specificity, sensitivity, and recall, outperforming existing systems in terms of SSIM, PSNR, MSE, and overall accuracy for both single-modal and multi-modal datasets. The incorporation of YOLO and YOLO Tiny networks underscores improved performance in image processing and classification tasks across diverse medical imaging modalities. The hybrid model, suggested in this study, effectively preserves rich specific information from source images, yielding esthetically pleasing visuals for medical practitioners and enhancing the diagnostic process.

Analysis of enhanced CT imaging signs and clinicopathological prognostic factors in hepatoid adenocarcinoma of stomach patients with radical surgery: a retrospective study

BackgroundTo investigate the association between CT signs and clinicopathological features and disease recurrence in patients with hepatoid adenocarcinoma of stomach (HAS).MethodsForty nine HAS patients undergoing radical surgery were retrospectively collected. Association between CT and clinicopathological features and disease recurrence was analyzed. Multivariate logistic model was constructed and evaluated for predicting recurrence by using receiver operating characteristic (ROC) curve. Survival curves between model-defined risk groups was compared using Kaplan–Meier method.Results24(49.0%) patients developed disease recurrence. Multivariate logistic analysis results showed elevated serum CEA level, peritumoral fatty space invasion and positive pathological vascular tumor thrombus were independent factors for disease recurrence. Odds ratios were 10.87 (95%CI, 1.14–103.66), 6.83 (95%CI, 1.08–43.08) and 42.67 (95%CI, 3.66–496.85), respectively. The constructed model showed an area under ROC of 0.912 (95%CI,0.825–0.999). The model-defined high-risk group showed poorer overall survival and recurrence-free survival than the low-risk group (both P < 0.001).ConclusionsPreoperative CT appearance of peritumoral fatty space invasion, elevated serum CEA level, and pathological vascular tumor thrombus indicated poor prognosis of HAS patients.

Evaluation of recurrence risk for patients with stage I invasive lung adenocarcinoma manifesting as solid nodules based on 18F-FDG PET/CT, imaging signs, and clinicopathological features

BackgroundStage I lung adenocarcinoma is a heterogeneous group. Previous studies have shown the prognostic evaluation value of PET/CT in this cohort; however, few studies focused on stage I invasive adenocarcinoma manifesting as solid nodules. This study aimed to evaluate the recurrence risk for patients with stage I invasive lung adenocarcinoma manifesting as solid nodules based on 18F-FDG PET/CT, CT imaging signs, and clinicopathological parameters.MethodsWe retrospectively enrolled 230 patients who underwent 18F-FDG PET/CT examination between January 2013 and July 2019. Metabolic parameters: maximum standard uptake value (SUVmax), mean standard uptake value, tumor metabolic volume (MTV), and total tumor glucose digestion were collected. Kaplan–Meier method was used to evaluate recurrence-free survival (RFS), and the multivariate Cox proportional hazards model was used to determine the independent risk factors associated with RFS. The time-dependent receiver operating characteristic curve (ROC) method was used to calculate the optimal cutoff value of metabolic parameters.ResultsThe 5-year RFS rate for all patients was 71.7%. Multivariate Cox analysis revealed that the International Association for the Study of Lung Cancer Pathology Committee (IASLC) pathologic grade 3 [Hazard ratio (HR), 3.96; 95% Confidence interval (CI), 1.11–14.09], the presence of cavity sign (HR 5.38; 95% CI 2.23–12.96), SUVmax (HR 1.23; 95% CI 1.13–1.33), and MTV (HR 1.05; 95% CI 1.01–1.08) were potential independent prognostic factors for RFS. Patients with IASLC grade 3, the presence of cavity sign, SUVmax > 3.9, or MTV > 5.4 cm3 were classified as high risk, while others were classified as low risk. There was a significant difference in RFS between the high-risk and low-risk groups (HR 6.04; 95% CI 2.17–16.82, P < 0.001), and the 5-year RFS rate was 94.1% for the low-risk group and 61.3% for the high-risk group.ConclusionsWe successfully evaluate the recurrence risk of patients with stage I invasive adenocarcinoma manifesting as solid nodules for the first time. The 5-year RFS rate in the high-risk group was significantly lower than in the low-risk group (61.3% vs. 94.1%). Our study may aid in optimizing therapeutic strategies and improving survival benefits for those patients.

Increased reliability of CT-imaging signs of bleeding into soft tissue in patients with COVID-19 for planning transarterial embolization.

Spontaneous bleeding into the soft tissues of the abdominal and thoracic wall is described as complication of anticoagulant therapy. Computed tomography (CT) allows to detect the presence of extravasation of the contrast agent into a hematoma, which is indicated as a sign of ongoing bleeding. Other specific CT signs of such coagulopathic bleeding have been described earlier. To evaluate the significance of specific coagulopathic CT signs for predicting the dynamics of spontaneous bleeding into soft tissues in patients with COVID-19. A retrospective study included 60 patients with COVID-19 with spontaneous bleeding into soft tissues and extravasation of a contrast agent on CT. In addition to extravasation, a "hematocrit effect" was detected in 43 patients on CT. Of these, 39 had extravasation in the form of a "signal flare." All patients underwent transarterial catheter angiography (TCA). To assess the prognostic value of CT signs, the results of CT and TCA compared. The absence of extravasation on the TCA more often corresponded to stopped bleeding. Extravasation on TCA found in 27 (45%) patients. The presence of the "hematocrit effect" or the combination of this sign with the phenomenon of a "signal flare" on CT (n = 43) led to more frequent confirmation of extravasation on TCA than in their absence (n = 17): 23.5% vs. 53.4% (p = 0.028). The presence of a fluid level and the phenomenon of a "signal flare" on CT in the structure of spontaneous hematomas of the soft tissues of the abdominal and thoracic wall in COVID-19 patients more often corresponded to ongoing bleeding on the TCA. The absence of coagulopathic CT signs more often corresponded to stopped bleeding.

Quantitative and qualitative liver CT: imaging feature association with histopathologically confirmed hepatic cirrhosis

To assess the diagnostic performance of quantitative and qualitative imaging features of hepatic cirrhosis on CT. A single-center retrospective cohort study was performed on all patients who had undergone non-targeted liver biopsy < 3months following abdominal CT imaging between 2007 and 2020. Histopathology was required as a reference standard for hepatic cirrhosis diagnosis. Two readers independently assessed all CT quantitative and qualitative features, blinded to the clinical history and the reference standard. The diagnostic performance of each imaging feature was assessed using multivariate regression and logistic regression in a recursive feature elimination framework. 98 consecutive patients met inclusion criteria including 26 with histopathologically confirmed hepatic cirrhosis, and 72 without cirrhosis. Liver surface nodularity (p < 0.0001), lobar redistribution (p < 0.0001), and expanded gallbladder fossa (p < 0.0016) were qualitative CT features associated with liver cirrhosis consistent between both reviewers. Liver surface nodularity demonstrated highest sensitivity (73-77%) and specificity (79-82%). Falciform space width was the only quantitative feature associated with cirrhosis, for a single reviewer (p < 0.04). Using a recursive feature elimination framework, liver surface nodularity and falciform space width were the strongest performing features for identifying cirrhosis. No feature combinations strengthened diagnostic performance. Many quantitative and qualitative CT imaging signs of hepatic cirrhosis have either poor accuracy or poor inter-observer agreement. Qualitative imaging features of hepatic cirrhosis on CT performed better than quantitative metrics, with liver surface nodularity the most optimal feature for diagnosing hepatic cirrhosis.

Nomogram based on prognostic nutrition index and Chest CT imaging signs predicts lymph node metastasis in NSCLC patients.

To establish and validate a model capable of predicting lymph node metastasis (LNM) of non-small cell lung cancer (NSCLC) patients. Preoperative clinical and CT imaging data on patients with NSCLC undergoing surgery were retrospectively analyzed. A model was developed using a training cohort of 290 patients. The univariate analysis followed by dichotomous logistic regression was performed to estimate different risk factors of lymph node metastasis, and a nomogram was constructed. Using another testing cohort of 120 patients, the performance of the nomogram was validated using several evaluation methods and indices and evaluated including via the area under the curve (AUC), calibration curve, Hosmer-Lemeshow test and decision curve analysis (DCA). CT-based imaging signs were important independent risk factors for lymph node metastasis in NSCLC patients. The possible risk factors also included four other independent risk factors through dichotomous logistic regression, i.e., age, SIRI, PNI and CEA, which were filtered and included in the nomogram. Nomogram yields AUC values of 0.828 [95% confidence interval (CI): 0.778-0.877] in the training cohort and 0.816 (95% CI: 0.737-0.895) in the validation cohort, respectively. The calibration curves showed high agreement in both the training and validation cohorts. At the threshold probability of 0-0.8, the nomogram increases the net outcomes compared to the treat-none and treat-all lines in the decision curve. The nomogram based on the PNI and CT images signs holds promise as a novel and accurate tool for predicting the LNM in NSCLC patients and guiding intraoperative lymph node dissection.

AN INTELLIGENT CBMIR SYSTEM FOR DETECTION AND LOCALIZATION OF LUNG DISEASES

The diagnosis of lung diseases is a complicated and time-consuming task for radiologists. Often radiologists struggle with accurately diagnosing lung diseases, They use Commonly CT imaging signs (CISs) which common appear in CT lung nodules in the diagnosis of lung diseases. Computer-aided diagnosis systems (CAD) can automatically diagnose and detect these signs by analyzing CT scans, which will reduce radiologists workload. The diagnosis and recognition efficiency and accuracy can be improved by using content-based medical image retrieval (CBMIR). This paper proposes a new intelligent CBMIR method to retrieve CISs helping in diagnosing and recognize lung diseases by using deep Convolutional Neural Network (CNN). Fine-tuned YOLOv4 (You Only Look Once) object detector model are proposed to fast detect and efficiently localize signs in real-time. The proposed CBMIR system can be applied as a useful and accurate medical instrument for diagnostics. The experimental results show an average detection accuracy of CT signs lung diseases as high as 92% and a mean average precision (MAP) of 0.92 is achieved using the proposed technique. Also, it takes only 0.1 milliseconds for the retrieval process. The proposed system presents high improvement as compared to the other system. It achieved better precision of retrieval results and the fastest run of the retrieval time.

An Efficient Content-Based Image Retrieval System for the Diagnosis of Lung Diseases.

The main problem in content-based image retrieval (CBIR) systems is the semantic gap which needs to be reduced for efficient retrieval. The common imaging signs (CISs) which appear in the patient's lung CT scan play a significant role in the identification of cancerous lung nodules and many other lung diseases. In this paper, we propose a new combination of descriptors for the effective retrieval of these imaging signs. First, we construct a feature database by combining local ternary pattern (LTP), local phase quantization (LPQ), and discrete wavelet transform. Next, joint mutual information (JMI)-based feature selection is deployed to reduce the redundancy and to select an optimal feature set for CISs retrieval. To this end, similarity measurement is performed by combining visual and semantic information in equal proportion to construct a balanced graph and the shortest path is computed for learning contextual similarity to obtain final similarity between each query and database image. The proposed system is evaluated on a publicly available database of lung CT imaging signs (LISS), and results are retrieved based on visual feature similarity comparison and graph-based similarity comparison. The proposed system achieves a mean average precision (MAP) of 60% and 0.48 AUC of precision-recall (P-R) graph using only visual features similarity comparison. These results further improve on graph-based similarity measure with a MAP of 70% and 0.58 AUC which shows the superiority of our proposed scheme.

A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases.

The common CT imaging signs of lung diseases (CISLs) which frequently appear in lung CT images are widely used in the diagnosis of lung diseases. Computer-aided diagnosis (CAD) based on the CISLs can improve radiologists' performance in the diagnosis of lung diseases. Since similarity measure is important for CAD, we propose a multi-level method to measure the similarity between the CISLs. The CISLs are characterized in the low-level visual scale, mid-level attribute scale, and high-level semantic scale, for a rich representation. The similarity at multiple levels is calculated and combined in a weighted sum form as the final similarity. The proposed multi-level similarity method is capable of computing the level-specific similarity and optimal cross-level complementary similarity. The effectiveness of the proposed similarity measure method is evaluated on a dataset of 511 lung CT images from clinical patients for CISLs retrieval. It can achieve about 80% precision and take only 3.6ms for the retrieval process. The extensive comparative evaluations on the same datasets are conducted to validate the advantages on retrieval performance of our multi-level similarity measure over the single-level measure and the two-level similarity methods. The proposed method can have wide applications in radiology and decision support. Graphical abstract.

CT appearance of new coronavirus pneumonia in subclinical period and short-term changes

Objective To explore the characteristics and short-term changes of high resolutionCT (HRCT) in subclinical stage of new coronavirus pneumonia (NCP). Methods TheHRCT images of 17 NCP patients in subclinical stage were analyzed retrospectively in Union Hospital of Tongji Medical College, Huazhong University of science and technology and Wuhan JinyintanHospital from January 15 to January 31, 2020. There were 4 males and 13 females, aged from 25.0 to 51.0 (39.8±7.5) years, who were closely contacted with NCP patients. The follow-up CT examination was performed 3 to 6 days after the initial CT examination in all patients. Six patients were treated using anti-virus, anti-inflammation andsymptomatic therapy, while the orther 11 patients were untreated. The CT imaging signs of subclinical and short-term follow-up were analyzed, and the CT image changes of short-term follow-up was summarized. Results Thelesions of 17 NCP patients were mainly located at the lower lobes of both lungs (9 cases at the left lower lobe and 10 cases at the right lower lobe in the subclinical stage, 9 casesat the left lower lobe and 11casesat the right lower lobe in the short-term follow-up). The number of lung segments involved increased from 46 in the subclinical stage to 90 in the short-term follow-up. In the subclinical stage, most of the lesions were multiple (13 cases), while in the short-term follow-up, the number of multiple cases decreased (7 cases), focal (6 cases) and diffuse distribution(4 cases) increased. The lesions were mainly distributed under the pleura (13 cases) or along the bronchovascular bundle (10 cases). In the short-term follow-up, 1 case progressed from subpleural to subpleural and along the bronchovascular bundle. There were 3 main types of lesions, including ground glass nodule, ground glass opacity and crazy-paving pattern. In the subclinical stage and short-term follow-up, ground glass nodules were seen in all the 17 cases. In the short-termfollow-up, ground glass nodules decreased in 4 cases and crazy-paving pattern increased in 4 cases. In 6 patients after treatment, 3 cases were changed from multiple to single ground glass nodule, 3 cases showed multiple ground glass opacity reduced. Therange of lesions in 11 patients without treatment enlarged. Conclusion TheHRCT features of the NCP patients in subcilincal stagehave some charicteristics, such as small ground glass nodule, ground glass opacity along the subpleural or along the bronchovascular bundle, and the great changescan be seen in the short-term follow-up. Key words: Coronaviridae infections; New coronavirus; Pneumonia; Tomography, X-ray computed

Automatic recognition of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNNs.

Ground-glass opacity (GGO) is a common CT imaging sign on high-resolution CT, which means the lesion is more likely to be malignant compared to common solid lung nodules. The automatic recognition of GGO CT imaging signs is of great importance for early diagnosis and possible cure of lung cancers. The present GGO recognition methods employ traditional low-level features and system performance improves slowly. Considering the high-performance of CNN model in computer vision field, we proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling is performed on multi-views and multi-receptive fields, which reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has the ability to obtain the optimal fine-tuning model. Multi-CNN models fusion strategy obtains better performance than any single trained model. We evaluated our method on the GGO nodule samples in publicly available LIDC-IDRI dataset of chest CT scans. The experimental results show that our method yields excellent results with 96.64% sensitivity, 71.43% specificity, and 0.83 F1 score. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images. Graphical abstract We proposed an automatic recognition method of 3D GGO CT imaging signs through the fusion of hybrid resampling and layer-wise fine-tuning CNN models in this paper. Our hybrid resampling reduces the risk of missing small or large GGOs by adopting representative sampling panels and processing GGOs with multiple scales simultaneously. The layer-wise fine-tuning strategy has ability to obtain the optimal fine-tuning model. Our method is a promising approach to apply deep learning method to computer-aided analysis of specific CT imaging signs with insufficient labeled images.

A new method of content based medical image retrieval and its applications to CT imaging sign retrieval

This paper proposes a new method of content based medical image retrieval through considering fused, context-sensitive similarity. Firstly, we fuse the semantic and visual similarities between the query image and each image in the database as their pairwise similarities. Then, we construct a weighted graph whose nodes represent the images and edges measure their pairwise similarities. By using the shortest path algorithm over the weighted graph, we obtain a new similarity measure, context-sensitive similarity measure, between the query image and each database image to complete the retrieval process. Actually, we use the fused pairwise similarity to narrow down the semantic gap for obtaining a more accurate pairwise similarity measure, and spread it on the intrinsic data manifold to achieve the context-sensitive similarity for a better retrieval performance. The proposed method has been evaluated on the retrieval of the Common CT Imaging Signs of Lung Diseases (CISLs) and achieved not only better retrieval results but also the satisfactory computation efficiency.

Learning with distribution of optimized features for recognizing common CT imaging signs of lung diseases

Common CT imaging signs of lung diseases (CISLs) are defined as the imaging signs that frequently appear in lung CT images from patients. CISLs play important roles in the diagnosis of lung diseases. This paper proposes a novel learning method, namely learning with distribution of optimized feature (DOF), to effectively recognize the characteristics of CISLs. We improve the classification performance by learning the optimized features under different distributions. Specifically, we adopt the minimum spanning tree algorithm to capture the relationship between features and discriminant ability of features for selecting the most important features. To overcome the problem of various distributions in one CISL, we propose a hierarchical learning method. First, we use an unsupervised learning method to cluster samples into groups based on their distribution. Second, in each group, we use a supervised learning method to train a model based on their categories of CISLs. Finally, we obtain multiple classification decisions from multiple trained models and use majority voting to achieve the final decision. The proposed approach has been implemented on a set of 511 samples captured from human lung CT images and achieves a classification accuracy of 91.96%. The proposed DOF method is effective and can provide a useful tool for computer-aided diagnosis of lung diseases on CT images.

CT imaging signs of surgically proven bowel trauma

The objective of this study was to determine the incidence and interobserver agreement of individual CT findings as well as the bowel injury prediction score (BIPS) in surgically proven bowel injury after blunt abdominal trauma. This HIPAA-compliant retrospective study was IRB approved and consent was waived. All patients 14years or older who sustained surgically proven bowel injury after blunt abdominal trauma between 1/1/2004 and 6/30/2015 were included. Admission trauma MDCT scans were independently interpreted by two abdominal fellowship-trained radiologists who recorded the following CT findings: intraperitoneal fluid, mesenteric hematoma/fat stranding, bowel wall thickening/hematoma, active intravenous contrast extravasation, free intraperitoneal air, bowel wall discontinuity, and focal bowel hypoenhancement. Subsequently, the electronic medical records of the included patients, admission abdominal physical exam results, admission white blood cell count, and findings at exploratory laparotomy of the included patients were recorded. Thirty-three patients met the inclusion criteria. The incidence and interobserver agreement of the CT findings were as follows: intraperitoneal fluid 93.9%, kappa = 0.784 (good); mesenteric hematoma/fat stranding 84.8%, kappa = 0.718 (good); bowel wall thickening/hematoma 42.4%, kappa = 0.491 (moderate); active IV contrast extravasation 36.3%, kappa = 1.00 (perfect); free intraperitoneal air 21.2%, kappa = 0.904 (very good), bowel wall discontinuity 6.1%, kappa = 1.00 (perfect); and focal bowel hypoenhancement 6.1%, kappa = 0.468 (moderate). An absence of the specified CT findings was encountered in 9.1% with surgically proven bowel injuries (kappa = 1.00, perfect). In our study, 9/16 patients or 56.3% had a bowel injury prediction score (BIPS) of 2 or more as defined by McNutt et al. (J Trauma Acute Care Surg 78(1):105-111, 2014). The presence of intraperitoneal fluid and mesenteric hematoma/fat stranding are the most common CT findings in bowel injuries proven at laparotomy. A small percentage of patients have no abnormal CT findings. This grading system did not prove to be useful in our study likely due to our inherently small patient population; however, the use of BIPS deserves further investigation as it may help in identifying blunt bowel and mesenteric injury patients with often subtle or nonspecific CT findings.

A new classifier fusion method based on historical and on-line classification reliability for recognizing common CT imaging signs of lung diseases

Common CT imaging signs of lung diseases (CISL) play important roles in the diagnosis of lung diseases. This paper proposes a new method of multiple classifier fusion to recognize the CISLs, which is based on the confusion matrices of the classifiers and the classification confidence values outputted by the classifiers. The confusion matrix reflects the historical reliability of decision-making of a classifier, while the difference between the classification confidence values reflects the on-line reliability of its decision-making. The two factors are merged to determine the weights of the classifiers’ classification confidence values. Then the classifiers are fused in a weighted-sum form to make the final decision. We apply the proposed classifier fusion method to combine five types of classifiers for CISL recognition, including support vector machine (SVM), back-propagation neural network (BPNN), Naïve Bayes (NB), k-nearest neighbor (k-NN) and decision tree (DT). In the experiments on lung CT images, our method not only brought stable improvements of recognition performance, compared with single classifiers, but also outperformed two well-known methods of classifier fusion, AdaBoost and Bagging. These results show that the proposed method is effective and promising.

Recognizing common CT imaging signs of lung diseases through a new feature selection method based on Fisher criterion and genetic optimization.

Common CT imaging signs of lung diseases (CISLs) are defined as the imaging signs that frequently appear in lung CT images from patients and play important roles in the diagnosis of lung diseases. This paper proposes a new feature selection method based on FIsher criterion and genetic optimization, called FIG for short, to tackle the CISL recognition problem. In our FIG feature selection method, the Fisher criterion is applied to evaluate feature subsets, based on which a genetic optimization algorithm is developed to find out an optimal feature subset from the candidate features. We use the FIG method to select the features for the CISL recognition from various types of features, including bag-of-visual-words based on the histogram of oriented gradients, the wavelet transform-based features, the local binary pattern, and the CT value histogram. Then, the selected features cooperate with each of five commonly used classifiers including support vector machine (SVM), Bagging (Bag), Naïve Bayes (NB), k -nearest neighbor (k-NN), and AdaBoost (Ada) to classify the regions of interests (ROIs) in lung CT images into the CISL categories. In order to evaluate the proposed feature selection method and CISL recognition approach, we conducted the fivefold cross-validation experiments on a set of 511 ROIs captured from real lung CT images. For all the considered classifiers, our FIG method brought the better recognition performance than not only the full set of original features but also any single type of features. We further compared our FIG method with the feature selection method based on classification accuracy rate and genetic optimization (ARG). The advantages on computation effectiveness and efficiency of FIG over ARG are shown through experiments.

Retroperitoneal neoplasms within the perirenal space in infants and children: Differentiation of renal and non-renal origin in enhanced CT images

Purpose To retrospectively demonstrate the specific CT findings of retroperitoneal neoplasms to diagnosis and differential diagnosis renal and non-renal tumors within the perirenal space in infants and children. Materials and methods We retrospectively reviewed the clinical data and CT images of 42 consecutive patients with surgically and pathologically proven retroperitoneal neoplasms within the perirenal space. The patients were divided into renal tumors group ( n = 16) and non-renal tumors group ( n = 26). The former included nephroblastoma ( n = 15) and renal lymphoma ( n = 1), while the latter included neuroblastoma ( n = 12), retroperitoneal teratoma ( n = 6), adrenal ganglioneuroma ( n = 4), retroperitoneal lymphoma ( n = 2), ectopic pheochromocytoma ( n = 1) and adrenal cortical carcinoma ( n = 1). The clinical information of these patients and the major CT imaging findings which were related to lesion localization in the two groups were compared and statistically analyzed using Pearson Chi-Square Test and Risk Estimate. Results The mean diameter of tumors was 9.82 ± 6.13 cm ( n = 42 range: 2.3–32 cm). The demographic data and chief clinical symptoms between the renal tumor group and the non-renal tumor group showed no statistically significant differences ( P > 0.05). 30.8% (8/26) of non-renal tumor patients presented elevated urinary vanillylmandelic acid (VMA) level, while no patient showed elevated VMA in renal tumor group ( P < 0.05). Some CT imaging signs of the renal tumors including “crescent sign” (odds ratio, OR = 52), “beak sign” (OR = 84), “embedded organ sign” (OR = 84), and “prominent feeding artery sign” (OR = 36) showed significantly higher incidence when compared to the non-renal tumors ( P < 0.001). The sign of “renal displacement and renal axis rotation” (OR = 0.059) was seen in 23 of 26 (88.5%) non-renal tumors, but in only 5 of 16 (31.3%) renal tumors ( P < 0.001). The sign of “extra-renal central plane of tumor” (OR = 0.038) was displayed in 24 of 26 (92.3%) non-renal tumors, but in only 5 of 16 (31.3%) renal tumors ( P < 0.001). The CT findings such as “pseudocapsule” (OR = 38.5), “necrosis and cystic change” (OR = 11.2), “vascularity” (OR = 16.867), “distant metastasis” (OR = 5.96), and “inferior vena cava tumor thrombus” which were thought to be characteristic of renal tumors were observed with significant higher incidence in renal tumors group than in the non-renal tumors group ( P < 0.05); while CT signs of “irregular mass” (OR = 0.045) and “intratumoral calcifications” (OR = 0.065) were observed with lower incidence in renal tumors group than in the non-renal tumors group ( P < 0.05). Conclusion The “crescent sign”, “beak sign”, “embedded kidney sign” and “renal arteries feeding” are the most specific CT signs suggestive of renal tumors and distinguish them from non-renal origin tumors within the perirenal space. Other CT signs, such as “pseudocapsule”, “hypervascular tumors” and “Inferior vena cava tumor thrombus”, when present, tumors of renal origin are strongly suggested. On the other hand, CT signs of “irregular mass”, “intratumoral calcifications”, and associated elevated urinary vanillylmandelic acid strongly suggest the non-renal tumors.

Acute pulmonary embolism: some noticeable unenhanced CT imaging signs

目的 描述能提示急性肺动脉栓塞的CT平扫征象.方法 回顾性分析49例经临床治疗证实的急性肺动脉栓塞病例的螺旋CT影像,发现能提示急性肺动脉栓塞的平扫异常征象.结果 在49例平扫影像中,共有10例出现肺动脉密度改变,其中局限性密度增高6例,局限性密度减低4例.结论 急性肺动脉栓塞的确诊需要行CT增强扫描,但对于不能使用对比剂或因非典型心肺症状而仅作平扫的病例,肺动脉CT平扫的异常密度改变能提示急性肺动脉栓塞的存在。