Computed Tomography Interpretation Research Articles

Pre-Operative Planning of a DCR Surgery Using Virtual Reality

ABSTRACT Purpose To assess a novel Virtual Reality (VR) tool designed to enhance understanding of the nasal anatomy in patients eligible for DCR surgery. Methods Preoperative Computed Tomography (CT) scans of the orbit were obtained and loaded as DICOM (Digital Imaging and Communications in Medicine) files onto the D2P software (3D Systems Inc. Littleton, CO) for tissue segmentation and 3D model preparation. Segmentation was performed on several anatomical structures, including the skull, lacrimal sac, nasal septum, inferior and middle turbinate. The resulting 3D model was visualized using a VR headset. After completing the segmentation procedure, ten cases were evaluated by a panel of six surgeons, including both senior and resident physicians from ENT and oculoplastic specialties. Results The dataset under examination comprised images from 10 preoperative CT scans of the orbits of patients eligible for Endo-DCR. When evaluating the CT using the VR tool, in 73.3% of the cases ENT surgeons were right about the side of pathology, while only 43.3% ophthalmologists were right (chi-square, p = .018). In 72.8% of the cases ENT surgeons were evaluated right that there is a septum deviation, while only in 47.2% of the cases the ophthalmologists were right (chi-square, p = .094). When evaluating the CT using the VR tool, in 60% of the cases consultants were right about the pathology, while 57.7% of the residents were right (chi-square, p = .853). In 81.7% of the cases consultants were evaluated right that there is a septum deviation, while only in 58.3% of the cases the ophthalmologists were right (chi-square, p = .198). Discussion ENT surgeons, as well as consultants, interpreted the CT better than the ophthalmologists and residents. Surprisingly, the VR system did not help them to interpret the CT better. Further, more extensive studies should be done to build a VR system that assists in the correct interpretation of the preoperative CT before DCR surgery as well as during DCR surgery.

Merlin: A Vision Language Foundation Model for 3D Computed Tomography.

Over 85 million computed tomography (CT) scans are performed annually in the US, of which approximately one quarter focus on the abdomen. Given the current shortage of both general and specialized radiologists, there is a large impetus to use artificial intelligence to alleviate the burden of interpreting these complex imaging studies while simultaneously using the images to extract novel physiological insights. Prior state-of-the-art approaches for automated medical image interpretation leverage vision language models (VLMs) that utilize both the image and the corresponding textual radiology reports. However, current medical VLMs are generally limited to 2D images and short reports. To overcome these shortcomings for abdominal CT interpretation, we introduce Merlin - a 3D VLM that leverages both structured electronic health records (EHR) and unstructured radiology reports for pretraining without requiring additional manual annotations. We train Merlin using a high-quality clinical dataset of paired CT scans (6+ million images from 15,331 CTs), EHR diagnosis codes (1.8+ million codes), and radiology reports (6+ million tokens) for training. We comprehensively evaluate Merlin on 6 task types and 752 individual tasks. The non-adapted (off-the-shelf) tasks include zero-shot findings classification (31 findings), phenotype classification (692 phenotypes), and zero-shot cross-modal retrieval (image to findings and image to impressions), while model adapted tasks include 5-year chronic disease prediction (6 diseases), radiology report generation, and 3D semantic segmentation (20 organs). We perform internal validation on a test set of 5,137 CTs, and external validation on 7,000 clinical CTs and on two public CT datasets (VerSe, TotalSegmentator). Beyond these clinically-relevant evaluations, we assess the efficacy of various network architectures and training strategies to depict that Merlin has favorable performance to existing task-specific baselines. We derive data scaling laws to empirically assess training data needs for requisite downstream task performance. Furthermore, unlike conventional VLMs that require hundreds of GPUs for training, we perform all training on a single GPU. This computationally efficient design can help democratize foundation model training, especially for health systems with compute constraints. We plan to release our trained models, code, and dataset, pending manual removal of all protected health information.

Improved differentiation of cavernous malformation and acute intraparenchymal hemorrhage on CT using an AI algorithm

This study aimed to evaluate the utility of an artificial intelligence (AI) algorithm in differentiating between cerebral cavernous malformation (CCM) and acute intraparenchymal hemorrhage (AIH) on brain computed tomography (CT). A retrospective, multireader, randomized study was conducted to validate the performance of an AI algorithm in differentiating AIH from CCM on brain CT. CT images of CM and AIH (< 3 cm) were identified from the database. Six blinded reviewers, including two neuroradiologists, two radiology residents, and two emergency department physicians, evaluated CT images from 288 patients (CCM, n = 173; AIH, n = 115) with and without AI assistance, comparing diagnostic performance. Brain CT interpretation with AI assistance resulted in significantly higher diagnostic accuracy than without (86.92% vs. 79.86%, p < 0.001). Radiology residents and emergency department physicians showed significantly improved accuracy of CT interpretation with AI assistance than without (84.21% vs. 75.35%, 80.73% vs. 72.57%; respectively, p < 0.05). Neuroradiologists showed a trend of higher accuracy with AI assistance in the interpretation but lacked statistical significance (95.83% vs. 91.67%, p = 0.56). The use of an AI algorithm can enhance the differentiation of AIH from CCM in brain CT interpretation, particularly for nonexperts in neuroradiology.

Facial Trauma Affects the Radiological Diagnosis of Nasal Bone Fractures.

Timely and accurate diagnosis of nasal bone fractures (NBFs) is crucial for preserving the cosmetic and functional aspects of the nose. This study aims to identify factors influencing radiographic and computed tomography (CT) diagnosis of NBF in patients with nasal trauma. Two hundred six patients with acute nasal trauma underwent both conventional radiography and facial bone CT. An experienced otorhinolaryngologist independently interpreted images. Results were categorized into "Concordance" or "Discrepancy" groups, with demographic and clinical data compared. The study classified 167 patients into "Concordance" and 39 into "Discrepancy" groups based on radiography and CT interpretations. The "discrepancy group" showed higher rates of previous nasal bone fractures (P=0.044), rhinoplasty history (P=0.044), and concomitant facial bone fractures (P=0.001). Adjusted odds ratios revealed significant associations between discrepancies and a history of nasal bone fracture (OR=5.197, 95% CI 1.165-23.171), rhinoplasty (OR=6.114, 95% CI 1.393-26.847), and concomitant facial bone fractures (OR=3.765, 95% CI 1.663-8.523). This study highlights the impact of facial trauma, including rhinoplasty, on the radiological diagnosis of NBF. Consequently, in the presence of signs of concurrent facial trauma, previous nasal trauma, or rhinoplasty history, a prompt CT scan and comprehensive evaluation are recommended for accurate diagnosis and timely treatment, ultimately improving the patient's prognosis.

Contrastive learning with token projection for Omicron pneumonia identification from few-shot chest CT images.

Deep learning-based methods can promote and save critical time for the diagnosis of pneumonia from computed tomography (CT) images of the chest, where the methods usually rely on large amounts of labeled data to learn good visual representations. However, medical images are difficult to obtain and need to be labeled by professional radiologists. To address this issue, a novel contrastive learning model with token projection, namely CoTP, is proposed for improving the diagnostic quality of few-shot chest CT images. Specifically, (1) we utilize solely unlabeled data for fitting CoTP, along with a small number of labeled samples for fine-tuning, (2) we present a new Omicron dataset and modify the data augmentation strategy, i.e., random Poisson noise perturbation for the CT interpretation task, and (3) token projection is utilized to further improve the quality of the global visual representations. The ResNet50 pre-trained by CoTP attained accuracy (ACC) of 92.35%, sensitivity (SEN) of 92.96%, precision (PRE) of 91.54%, and the area under the receiver-operating characteristics curve (AUC) of 98.90% on the presented Omicron dataset. On the contrary, the ResNet50 without pre-training achieved ACC, SEN, PRE, and AUC of 77.61, 77.90, 76.69, and 85.66%, respectively. Extensive experiments reveal that a model pre-trained by CoTP greatly outperforms that without pre-training. The CoTP can improve the efficacy of diagnosis and reduce the heavy workload of radiologists for screening of Omicron pneumonia.

Stereotactic body radiation therapy for clinically diagnosed early‐stage non‐small cell lung cancer: Importance of accurate CT interpretation by experts

AbstractIntroductionThis study evaluated the clinical outcomes of stereotactic body radiotherapy (SBRT) for both pathologically diagnosed (PD) and clinically diagnosed (CD) early‐stage non‐small cell lung cancer (NSCLC) and explored the significance of accurate expert computed tomography (CT) interpretation.MethodsWe retrospectively analyzed 95 patients with early‐stage NSCLC who received SBRT at our institution. Patients were classified into CD and PD groups. Two chest radiologists retrospectively interpreted the pre‐SBRT CT images to determine the tumor subtype and probability of malignancy (PM). Clinical findings, CT features, and treatment outcomes were compared between the two groups. The survival rate of the CD group was analyzed separately according to the PM grade.ResultsMedian overall survival for the CD and PD groups was 6.0 and 5.4 years (P = 0.57), respectively. Median cause‐specific survival was 10.2 years in the CD group and not reached in the PD group (P = 0.76). In the CD group, lung cancer mortality was lower in the low PM group (25% [1 of 4]) than in the high PM group (47.4% [9 of 19]).ConclusionIt may be desirable to evaluate the PM of the nodule using expert CT interpretation to decide whether SBRT is indicated in CD early‐stage NSCLC.

Effect of modified gastrointestinal decompression under abdominal CT in patients with intestinal obstruction.

We aimed to evaluate the effect of continuous quality improvement on modified gastrointestinal decompression under abdominal computed tomography (CT) in patients with intestinal obstruction. The CT images of 74 patients with intestinal obstruction who underwent gastrointestinal decompression in our hospital from 1 January 2018 to 31 December 2019 were analysed retrospectively (Control group). Factors influencing unsatisfactory decompression effects were analysed, and corresponding improvement measures were formulated and implemented. A total of 77 patients from 1 January 2020 to 31 March 2022 were enrolled prospectively (Study group). The position of the nasogastric tube end, the amount of gastric drainage within 24h and the degree of abdominal distension relief were compared before and after the improvement. After implementation of continuous quality improvement, the proportion of the end of the nasogastric tube reaching the antrum, the amount of gastric fluid drainage within 24h and the degree of abdominal distension relief were better than those before improvement (p<0.001, respectively). The execution rate and accuracy rate of CT interpretations by nurses reached 100% and 82%, respectively. Modified gastrointestinal decompression based on abdominal CT scans can increase the success of gastrointestinal decompression and effectively reduce the discomfort of patients.

Computer-aided diagnosis system versus conventional reading system in low-dose (< 2 mSv) computed tomography: comparative study for patients at risk of lung cancer.

Computer-aided diagnosis in low-dose (≤ 3 mSv) computed tomography (CT) is a potential screening tool for lung nodules, with quality interpretation and less inter-observer variability among readers. Therefore, we aimed to determine the screening potential of CT using a radiation dose that does not exceed 2 mSv. We aimed to compare the diagnostic parameters of low-dose (< 2 mSv) CT interpretation results using a computer-aided diagnosis system for lung cancer screening with those of a conventional reading system used by radiologists. We conducted a comparative study of chest CT images for lung cancer screening at three private institutions. A database of low-dose (< 2 mSv) chest CT images of patients at risk of lung cancer was viewed with the conventional reading system (301 patients and 226 nodules) or computer-aided diagnosis system without any subsequent radiologist review (944 patients and 1,048 nodules). The numbers of detected and solid nodules per patient (both P < 0.0001) were higher using the computer-aided diagnosis system than those using the conventional reading system. The nodule size was reported as the maximum size in any plane in the computer-aided diagnosis system. Higher numbers of patients (102 [11%] versus 20 [7%], P = 0.0345) and nodules (154 [15%] versus 17 [8%], P = 0.0035) were diagnosed with cancer using the computer-aided diagnosis system. The computer-aided diagnosis system facilitates the diagnosis of cancerous nodules, especially solid nodules, in low-dose (< 2 mSv) CT among patients at risk for lung cancer.

Development and validation of a CT algorithm for the identification of nonperforated duodenal bulb ulcer

PurposeTo assess the value of multiplanar computed tomography (CT) in the diagnosis of nonperforated duodenal bulb ulcer (NPDBU). MethodWe retrospectively analyzed data from 135 patients with NPDBU (ulcer group) and 150 patients with a normal duodenal bulb (control group) who underwent contrast-enhanced abdominal CT and were diagnosed via upper endoscopy from January 2018 to February 2022. The clinical and CT features were compared between the two groups. Independent prognostic factors for diagnosing NPDBU were determined using binary logistic regression analysis. An external validation cohort to determine the model’s efficiency comprised 80 patients from another center. ResultsGastrointestinal bleeding was more frequent in patients with NPDBU than in those without (p < 0.001). No significant differences in age and sex were observed between the groups (all p > 0.05). The duodenal bulbar wall was significantly thicker in the ulcer group than in the control group, as determined using CT (p < 0.001). Irregular mucosal surface, layered enhancement, and blurred fat space around the duodenal bulb were more common in the ulcer group than in the control group (all p < 0.001). Binary logistic regression analysis revealed that gastrointestinal bleeding, wall thickness of ≥ 4.85 mm, irregular mucosal surface, and blurred peripheral fat space were the most significant variations associated with NPDBU, with an area under the curve (AUC) of 0.974. The external validation cohort had an AUC of 0.916. ConclusionsCareful multiplanar CT interpretation suggests the underlying presence of NPDBU and allows timely endoscopic verification and appropriate treatment.

Physical Examination Sensitivity for Skull Fracture in Pediatric Patients With Blunt Head Trauma: A Secondary Analysis of the National Emergency X-Radiography Utilization Study II Head Computed Tomography Validation Study.

We evaluated the emergency department (ED) providers' ability to detect skull fractures in pediatric patients presenting with blunt head trauma. This was a secondary analysis of the National Emergency X-Radiography Utilization Study (NEXUS) Head computed tomography (CT) validation study. Demographics and clinical characteristics were analyzed for pediatric patients. Radiologist interpretations of head CT imaging were abstracted and cataloged. Detection of skull fractures was evaluated through provider response to specific clinical decision instrument criteria (NEXUS or Canadian head CT rules) at the time of initial patient evaluation. The presence of skull fracture was determined by formal radiologist interpretation of CT imaging. Between April 2006, and December 2015, 1,018 pediatric patients were enrolled. One hundred twenty-eight (12.5%) children had a notable injury reported on CT head. Skull fracture was present in most (66.4%) children with intracranial injuries. The sensitivity and specificity of provider physical examination to detect skull fractures was 18.5% (95% confidence interval 10.5% to 28.7%) and 96.6% (95.3% to 97.7%), respectively. The most common injuries associated with skull fractures were subarachnoid hemorrhage (27%) and subdural hematoma (22.3%). Skull fracture is common in children with intracranial injury after blunt head trauma. Despite this, providers were found to have poor sensitivity for skull fractures in this population, and these injuries may be missed on initial emergency department assessment.

Sectional Anatomy Quiz-IΧ.

This series lists a pictorial quiz pertaining to identification of normal and abnormal anatomical structures and landmarks at a given level on computed tomography (CT). Readers are expected to identify and appreciate the changes from normal anatomy and variations of a given pathology. The main structures assessed in this quiz are the pons, ventricular system of the brain, and the basal cisterns. Particular emphasis is placed on the presentations of intra-cranial haemorrhages, particularly sub-arachnoid and epidural haemorrhages, and masses around the region of the pons, midbrain and cerebellum. There is also a question pertaining to increased intracranial pressure. Differential diagnoses are also given where necessary to guide clinical practice and further learning. A Points to remember section details key clinical pearls. Furthermore, key resources have been cited as recommendations for further reading. It is anticipated that this series will enhance the understanding of sectional anatomy of the brain to aid in brain CT interpretation.

Thoracic Inlet in Cervical Spine CT of Blunt Trauma Patients: Prevalence of Pathologies and Importance of CT Interpretation.

The thoracic inlet of blunt trauma patients may have pathologies that can be diagnosed on cervical spine computed tomography (CT) but that are not evident on concurrent portable chest radiography (pCXR). This retrospective investigation aimed to identify the prevalence of thoracic inlet pathologies on cervical spine CT and their importance by measuring the diagnostic performance of pCXR and the predictive factors of such abnormalities. This investigation was performed at a level-1 trauma center and included CT and concurrent pCXR of 385 consecutive adult patients (280 men, mean age of 47.6 years) who presented with suspected cervical spine injury. CT and pCXR findings were independently re-reviewed, and CT was considered the reference standard. Traumatic, significant nontraumatic and nonsignificant pathologies were present at 23.4%, 23.6% and 58.2%, respectively. The most common traumatic diagnoses were pneumothorax (12.7%) and pulmonary contusion (10.4%). The most common significant nontraumatic findings were pulmonary nodules (8.1%), micronodules (6.8%) and septal thickening (4.2%). The prevalence of active tuberculosis was 3.4%. The sensitivity and positive predictive value of pCXR was 56.67% and 49.51% in diagnosing traumatic and 8.89% and 50% in significant nontraumatic pathologies. No demographic or pre-admission clinical factors could predict these abnormalities. Several significant pathologies of the thoracic inlet were visualized on trauma cervical spine CT. Since a concurrent pCXR was not sensitive and no demographic or clinical factors could predict these abnormalities, a liberal use of chest CT is suggested, particularly among those experiencing high-energy trauma with significant injuries of the thoracic inlet. If chest CT is not available, a meticulous evaluation of the thoracic inlet in the cervical spine CT of blunt trauma patients is important.

Hematoma Progression Rates on Head Computed Tomography for Fluid Levels versus Mimics in Patients with Primary Intracerebral Hemorrhage

Among stroke patients, primary intracerebral hemorrhage has the highest mortality rate. Expansion of hematoma plays a prognostic role in these patients. Although fluid levels have been shown to predict subsequent hematoma expansion, there are mimics of fluid levels that may confuse interpretation. We hypothesized that patients with true fluid levels on head computed tomography (CT) have higher hematoma progression rates and worse outcomes compared with patients who have fluid level mimics on CT. Adult patients presenting with intracerebral hemorrhage described as a fluid level on initial CT interpretation were included. Medical records were reviewed to extract relevant clinical variables. A CAQ-certified neuroradiologist retrospectively determined whether there was a true fluid level or mimic on CT and then evaluated follow-up CT scans for radiologic progression. We compared radiologic progression, mortality, and anticoagulation status between patients with true fluid levels and fluid level mimics. The study included 12 patients, 8 with true fluid levels and 4 with radiologic mimics. The patients with true fluid levels had a significantly higher likelihood of radiographic progression (P= 0.014). Differences in outcome, use of anticoagulation therapy, and average international normalized ratio were not significant. A fluid level within intraparenchymal hemorrhage on head CT scan is associated with higher likelihood of intracerebral hemorrhage progression. However, this applies only to true fluid levels, with mimics having a lower likelihood of progression. A careful analysis of potential fluid levels is necessary before assigning prognostic implications.

Use of Chinese Visible Human Images to Enhance the Interpretation of CT or MRI Images: Application to Nasopharyngeal Structures Segmentation in the Treatment Planning System

Background: With leading morbidity among malignant tumors in otorhinolaryngology, Nasopharyngeal carcinoma (NPC) is one of the most frequent malignant tumors in China. Objectives: This study aimed to help radiotherapy doctors recognize and segment nasopharyngeal organs at risk of NPC and make a radiotherapy plan. Methods: The authors used B-spline and mutual information to transform, register, and fuse Chinese Visible Human images with the volunteer’s personalized computed tomography (CT) images, and integrated them into the Treatment Planning System (TPS). Consequently, Three-Dimensional Visualization Treatment Planning System (3DV+TPS) was created. To verify it, 3DV+TPS was deployed to identify and segment the nasopharyngeal organs at risk of NPC, and a questionnaire was filled out by radiotherapy doctors. Results: Results showed that 3DV+TPS can finish the registration and fusion of four sets of sectional anatomical images and individual CT images of volunteers in approximately 3 min and 50 sec. Conclusion: The registered and fused images can accurately reflect the position, outline, and adjacent space of the nasopharyngeal structure which is not clear in CT images. Therefore, it is helpful for recognizing and segmenting neural, muscular, and glandular structures. Through automatically registering and fusing color and CT gray images, 3DV+TPS improves the accuracy and efficiency of recognizing nasopharyngeal structures in making radiotherapy plans. It is also useful to improve the teaching quality of tumor radiotherapy for medical students and interns as well.

Reducing intravenous thrombolysis delay in acute ischemic stroke through a quality improvement program in the emergency department

ObjectiveThis study aims to investigate the effectiveness of a quality improvement program for reducing intravenous thrombolysis (IVT) delay in acute ischemic stroke (AIS).Materials and methodsWe implement a quality improvement program consisting of 10 interventions for reducing IVT delay, including the establishment of an acute stroke team, standardized management of stroke teams, popularization of stroke and its treatment, emergency bypass route (BER), the achievement of computed tomography (CT) priority, no-delay CT interpretation, intravenous thrombolysis on the CT table, payment after treatment, whole recording, and incentive policy. We retrospectively analyzed the clinical time and outcome data of AIS patients treated with IVT in pre-intervention (108 patients) and post-intervention groups (598 patients), and further compared the differences between the non-emergency bypass route (NBER) and BER in the post-intervention group.ResultsThe thrombolysis rate increased from ~29% in the pre-intervention group to 48% in the post-intervention group. Compared with the pre-intervention group, the median of door-to-needle time (DNT) was greatly shortened from 95 to 26 min (P < 0.001), door-to-CT time (DCT) was noticeably decreased from 20 to 18 min (P < 0.001), and onset-to-needle time (OTT) significantly declined from 206 to 133 min (P = 0.001). Under the new mode after the intervention, we further analyzed the IVT delay difference between the NBER (518 patients) and BER groups (80 patients) from the post-intervention group. The median values of DNT (18 vs. 27 min, P < 0.001), DCT (10 vs. 19 min, P < 0.001), and OTT (99 vs. 143 min, P < 0.001) showed significant reductions in the BER group. The quality improvement program under the emergency platform successfully controlled the median of DNT to within 26 min.ConclusionsCollectively, the BER mode is a feasible scheme that greatly decreased DNT in AIS patients, and the secret to success was to accomplish as much as possible before the patient arrives at the emergency room.

Liver Imaging Reporting and Data System criteria for the diagnosis of hepatocellular carcinoma in clinical practice: A pictorial minireview.

Hepatocellular carcinoma (HCC) is the sixth most common cancer. The main risk factors associated with HCC development include hepatitis B virus, hepatitis C virus, alcohol consumption, aflatoxin B1, and nonalcoholic fatty liver disease. However, hepatocarcinogenesis is a complex multistep process. Various factors lead to hepatocyte malignant transformation and HCC development. Diagnosis and surveillance of HCC can be made with the use of liver ultrasound (US) every 6 mo. However, the sensitivity of this imaging method to detect HCC in a cirrhotic liver is limited, due to the abnormal liver parenchyma. Computed tomography (CT) and magnetic resonance imaging (MRI) are considered to be most useful tools for at-risk patients or patients with inadequate US. Liver biopsy is still used for diagnosis and prognosis of HCC in specific nodules that cannot be definitely characterized as HCC by imaging. Recently the American College of Radiology designed the Liver Imaging Reporting and Data System (LI-RADS), which is a comprehensive system for standardized interpretation of CT and MRI liver examinations that was first proposed in 2011. In 2018, it was integrated into the American Association for the Study of Liver Diseases guidance statement for HCC. LI-RADS is designed to ensure high sensitivity, precise categorization, and high positive predictive value for the diagnosis of HCC and is applied to “high-risk populations” according to specific criteria. Most importantly LI-RADS criteria achieved international collaboration and consensus among liver experts around the world on the best practices for caring for patients with or at risk for HCC.

Neural network-based method for diagnosis and severity assessment of Graves’ orbitopathy using orbital computed tomography

Computed tomography (CT) has been widely used to diagnose Graves’ orbitopathy, and the utility is gradually increasing. To develop a neural network (NN)-based method for diagnosis and severity assessment of Graves’ orbitopathy (GO) using orbital CT, a specific type of NN optimized for diagnosing GO was developed and trained using 288 orbital CT scans obtained from patients with mild and moderate-to-severe GO and normal controls. The developed NN was compared with three conventional NNs [GoogleNet Inception v1 (GoogLeNet), 50-layer Deep Residual Learning (ResNet-50), and 16-layer Very Deep Convolutional Network from Visual Geometry group (VGG-16)]. The diagnostic performance was also compared with that of three oculoplastic specialists. The developed NN had an area under receiver operating curve (AUC) of 0.979 for diagnosing patients with moderate-to-severe GO. Receiver operating curve (ROC) analysis yielded AUCs of 0.827 for GoogLeNet, 0.611 for ResNet-50, 0.540 for VGG-16, and 0.975 for the oculoplastic specialists for diagnosing moderate-to-severe GO. For the diagnosis of mild GO, the developed NN yielded an AUC of 0.895, which is better than the performances of the other NNs and oculoplastic specialists. This study may contribute to NN-based interpretation of orbital CTs for diagnosing various orbital diseases

Imaging characteristics and CT sensitivity for pyogenic spinal infections

Background/objectiveContrast-enhanced magnetic resonance imaging (MRI) is the preferred imaging modality for diagnosing pyogenic spinal infection (PSI), but it is not always available. Our objective was to describe pyogenic spinal infection imaging characteristics in patients presenting to a community emergency department (ED) and estimate the computed tomography (CT) sensitivity for these infections. MethodsWe examined the MRI reports from a cohort of 88 PSI patients whom we enrolled in a prospective cohort study and report the prevalence of each PSI type (spinal epidural abscess/infection, vertebral osteomyelitis/discitis, septic facet, and paravertebral abscess/infection) according to contemporary nomenclature. In a 14 patient subcohort who underwent both CT and MRI studies, we report the sensitivity for each PSI from a post hoc blinded overread of the CT imaging by a single neuroradiologist. ResultsOf the 88 PSI patients, the median age was 55 years, and 31% were female. The PSI prevalence included: spinal epidural abscess/infection (SEA) in 61(69%), vertebral osteomyelitis/discitis (VO/D) in 54 (61%), septic facet (SF) in 15 (17%), and paravertebral abscess/infection (PVA) in 53 (60%). Of the SEAs, 82% (50/61) were associated with other spinal infections, while 18% (11/61) were isolated SEAs. The overall CT sensitivity in a masked overread was 79% (11/14) for any PSI, 83% (10/12) for any infection outside the spinal canal, and only 18% (2/11) for SEA. ConclusionPatients found to have vertebral osteomyelitis/discitis, septic facet, and paravertebral infections frequently had a SEA coinfection. CT interpretation by a neuroradiologist had moderate sensitivity for infections outside the spinal canal but had low sensitivity for SEA.

Interpretation of CT (Computed Tomography) Scan for Covid- 19 (OMICRON)

COVID-19 is a virus that can cause disease. Phylogenetic analysis Bats have been discovered to have a full genome sequence, according to research done with available entire genome sequences. The COVID-19 virus reservoir has been identified, however the intermediate host(s) has yet to be identified. now. This study was conducted in Marjan Teaching Hospital in Babylon for all patients infected with Covid 19 disease during January of 2022 and their ages were between 30-55, where the diagnosis was made by CT-scan. the reports that I will mention that the new mutation from Corona does not cause severe damage to the lung, and the infection rate is less than 45% in the lung. She also indicated that all patients were exposed to severe diarrhea without losing the sense of smell and taste. From this, we conclude that the new mutations in Covid -19 are Less severe and less severe, and the vaccine reduces a high rate of infection, as most of the vaccinated people had a very weak rate. And here are pictures of the reports of the new mutant from Covid -19 (OMICRON). Keyword: Covid -19, ct-scan, report

Diagnostic Performance of MRI Versus CT in the Evaluation of Intra-articular Osteochondral Fracture in Pediatric Patients With Acute Traumatic Lateral Patellar Dislocation.

Background:Evaluation of intra-articular osteochondral fractures in children with acute traumatic lateral patellar dislocation (LPD) is important for determining treatment options.Purpose:To (1) compare the diagnostic accuracy of computed tomography (CT) and magnetic resonance imaging (MRI) for evaluating intra-articular osteochondral fractures; (2) compare the interpretation of CT and MRI images between radiologists and pediatric orthopaedic surgeons (POS); and (3) investigate any clinical factors influencing the accuracy of CT and MRI evaluations.Study Design:Cohort study (diagnosis); Level of evidence, 2.Methods:We reviewed 35 knees in 35 patients (mean age, 12.2 ± 1.2 years; 12 boys and 23 girls) who were treated arthroscopically for acute traumatic LPD; 71% of the patients had patellar fractures, 54% had femoral fractures, and 60% had free osteochondral fracture fragments. All presurgical MRI and CT images were reviewed by POS who were blinded to both the reports of the radiologists and surgical records. We compared the accuracy of CT and MRI in diagnosing intra-articular osteochondral fractures against the arthroscopic findings and compared the interpretation of the images by the POS (MRI-O, CT-O) with those of the radiologists (MRI-R, CT-R).Results:There was no significant difference in diagnostic accuracy between CT and MRI for overall intra-articular osteochondral fractures by the POS or the radiologists; however, the CT-O images had a higher diagnostic specificity (84.2% vs 69.6%; P < .001) and sensitivity (88.1% vs 70.1%; P < .001) versus the MRI-R images. Regarding free fracture fragments, the CT-R images had a higher diagnostic accuracy than the MRI-R images (73.5% vs 47.1%; P = .026). When backed by clinical data, the MRI-O images had greater diagnostic accuracy (78.7% vs 60.3%; P = .001) and sensitivity (88.1% vs 30.7%; P = .021) but lower specificity compared with the MRI-R images, and the CT-O images had similar diagnostic accuracy but greater sensitivity than the CT-R images (70.1% vs 52.2%; P < .001). The diagnostic accuracy of MRI-O images was lower for children under 12 years versus children 12 years and over (67.5% vs 83.3%; P = .040).Conclusion:Compared with MRI, CT scans had better diagnostic performance in the evaluation of intra-articular osteochondral fractures in pediatric patients with acute traumatic LPD. Clinical data enhanced the diagnostic sensitivity of MRI and CT but decreased the specificity of MRI. MRI evaluations remain challenging for both POS and radiologists.