Thorax computed tomography (CTX) guided ground truth annotation of CHEST radiographs (CXR) for improved classification and detection of COVID-19.

Several data sets have been collected and various artificial intelligence models have been developed for COVID-19 classification and detection from both chest radiography (CXR) and thorax computed tomography (CTX) images. However, the pitfalls and shortcomings of these systems significantly limit their clinical use. In this respect, improving the weaknesses of advanced models can be very effective besides developing new ones. The inability to diagnose ground-glass opacities by conventional CXR has limited the use of this modality in the diagnostic work-up of COVID-19. In our study, we investigated whether we could increase the diagnostic efficiency by collecting a novel CXR data set, which contains pneumonic regions that are not visible to the experts and can only be annotated under CTX guidance. We develop an ensemble methodology of well-established deep CXR models for this new data set and develop a machine learning-based non-maximum suppression strategy to boost the performance for challenging CXR images. CTX and CXR images of 379 patients who applied to our hospital with suspected COVID-19 were evaluated with consensus by seven radiologists. Among these, CXR images of 161 patients who also have had a CTX examination on the same day or until the day before or after and whose CTX findings are compatible with COVID-19 pneumonia, are selected for annotating. CTX images are arranged in the main section passing through the anterior, middle, and posterior according to the sagittal plane with the reformed maximum intensity projection (MIP) method in the coronal plane. Based on the analysis of coronal MIP reconstructed CTX images, the regions corresponding to the pneumonia foci are annotated manually in CXR images. Radiologically classified posterior to anterior (PA) CXR of 218 patients with negative thorax CTX imaging were classified as COVID-19 pneumonia negative group. Accordingly, we have collected a new data set using anonymized CXR (JPEG) and CT (DICOM) images, where the PA CXRs contain pneumonic regions that are hidden or not easily recognized and annotated under CTX guidance. The reference finding was the presence of pneumonic infiltration consistent with COVID-19 on chest CTX examination. COVID-Net, a specially designed convolutional neural network, was used to detect cases of COVID-19 among CXRs. Diagnostic performances were evaluated by ROC analysis by applying six COVID-Net variants (COVIDNet-CXR3-A, -B, -C/COVIDNet-CXR4-A, -B, -C) to the defined data set and combining these models in various ways via ensemble strategies. Finally, a convex optimization strategy is carried out to find the outperforming weighted ensemble of individual models. The mean age of 161 patients with pneumonia was 49.31 ± 15.12, and the median age was 48 years. The mean age of 218 patients without signs of pneumonia in thorax CTX examination was 40.04 ± 14.46, and the median was 38. When working with different combinations of COVID-Net's six variants, the area under the curve (AUC) using the ensemble COVID-Net CXR 4A-4B-3C was .78, sensitivity 67%, specificity 95%; COVID-Net CXR 4a-3b-3c was .79, sensitivity 69% and specificity 94%. When diverse and complementary COVID-Net models are used together through an ensemble, it has been determined that the AUC values are close to other studies, and the specificity is significantly higher than other studies in the literature.

State-of-the-art Prostate Imaging.

Prostate cancer is one of the most common cancers in men. In addition to methods such as prostate-specific antigen test, digital rectal examination, and transrectal ultrasonography, magnetic resonance imaging has an important role for accurate and reproducible diagnosis. However, guidance in targeted biopsies and recent use in determining localization for treatment increase its importance. Due to technical difficulties, patient tolerance, and differences in interpretation, the prostate imaging reporting and data system recommends preparations for the patient and magnetic resonance imaging techniques. However, techniques continue to be developed to improve the diagnosis rate and image quality. In our article, patient preparation before imaging and techniques were tried to be discussed in detail. In addition, current approaches in biparametric magnetic resonance imaging and radiomics and new techniques such as T1 and T2 mapping will be mentioned.

Radiological Findings in SARS-CoV-2 Viral Pneumonia Compared to Other Viral Pneumonias: A Single-Centre Study.

Background: Thorax computed tomography (CT) imaging is widely used as a diagnostic method in the diagnosis of coronavirus disease 2019 (COVID-19)-related pneumonia. Radiological differential diagnosis and isolation of other viral agents causing pneumonia in patients have gained importance, particularly during the pandemic. Aims: We aimed to investigate whether there is a difference between CT images from patients with COVID-19-associated pneumonia compared to CT images of patients with pneumonia due to other viral agents and which finding may be more effective in diagnosis. Study Design. The study included 249 adult patients with pneumonia identified by thorax CT examination and with a positive COVID-19 RT-PCR test compared to 94 patients diagnosed with non-COVID-19 pneumonia (viral PCR positive but no bacterial or fungal agents detected in other cultures) between 2015 and 2019. CT images were retrospectively analyzed using the PACS system. CT findings were evaluated by two radiologists with 5 and 20 years of experience, in a blinded fashion, and the outcome was decided by consensus. Methods: Demographic data (age, gender, and known chronic disease) and CT imaging findings (percentage of involvement, number of lesions, distribution preference, dominant pattern, ground-glass opacity distribution pattern, nodule, tree in bud sign, interstitial changes, crazy paving sign, reversed halo sign, vacuolar sign, halo sign, vascular enlargement, linear opacities, traction bronchiectasis, peribronchial wall thickness, air trapping, pleural retraction, pleural effusion, pericardial effusion, cavitation, mediastinal/hilar lymphadenopathy, dominant lesion size, consolidation, subpleural curvilinear opacities, air bronchogram, and pleural thickening) of the patients were evaluated. CT findings were also evaluated with the RSNA consensus guideline and the CORADS scoring system. Data were divided into two main groups-non-COVID-19 and COVID-19 pneumonia-and compared statistically with chi-squared tests and multiple regression analysis of independent variables. Results: RSNA and CORADS classifications of CT scan images were able to successfully differentiate between positive and negative COVID-19 pneumonia patients. Statistically significant differences were found between the two patient groups in various categories including the percentage of involvement, number of lesions, distribution preference, dominant pattern, nodule, tree in bud, interstitial changes, crazy paving, reverse halo vascular enlargement, peribronchial wall thickness, air trapping, pleural retraction, pleural/pericardial effusion, cavitation, and mediastinal/hilar lymphadenopathy (p < 0.01). Multiple linear regression analysis of independent variables found a significant effect in reverse halo sign (ß = 0.097, p < 0.05) and pleural effusion (ß = 10.631, p < 0.05) on COVID-19 pneumonia patients. Conclusion: The presence of reverse halo and absence of pleural effusion was found to be characteristic of COVID-19 pneumonia and therefore a reliable diagnostic tool to differentiate it from non-COVID-19 pneumonia.

Correlation of laboratory parameters and Chest CT findings in young adults with COVID-19 and comparison of imaging findings with children.

PURPOSE: We aimed to compare COVID-19 imaging findings of young adults (19-35 years of age) with those of children (0-18 years) and to correlate imaging findings of young adults with their laboratory tests. MATERIALS AND METHODS: This retrospective study included Real Time-Polymerase Chain Reaction (RT-PCR) confirmed 130 young adults (mean age: 28.39 ± 4.77; 65 male, 65 female) and 36 children (mean age: 12.41 ± 4.51; 17 male, 19 female), between March and June 2020. COVID-19 related imaging findings on chest CT were examined in young adults and compared with children by the Mann-Whitney U, and Chi-square or Fisher's exact test. Laboratory examinations of young adults were assessed in terms of correlation with radiological findings by the Spearman's correlation analysis. RESULTS: Bilateral multiple distributions (p = 0.014), subpleural involvement, and pleural thickening (p = 0.004), GGOs with internal consolidations were more frequent in adults (p = 0.009). Infiltrations were significantly larger than 20 mm in young adults (p = 0.011). The rates of feeding vessel sign, vascular enlargement, and halo sign were significantly higher in young adults (p < 0.003). Highly significant positive correlations were found between radiological and biochemical parameters. CONCLUSION: Distribution, size, and pattern of COVID-19 related imaging findings differed in children and young adults. Radiological findings were correlated with biochemical parameters but not with blood count results of young adults.

Covid-19: Correlation of Early Chest Computed Tomography Findings With the Course of Disease.

OBJECTIVE: To investigate the role of chest computed tomography (CT) examinations acquired early after initial onset of symptoms in predicting disease course in coronavirus disease 2019. METHODS: Two hundred sixty-two patients were categorized according to intensive care unit (ICU) admission, survival, length of hospital stay, and reverse transcriptase-polymerase chain reaction positivity. Mean time interval between the onset of symptoms and CT scan was 5.2 ± 2.3 days. Groups were compared using Student t test, Mann-Whitney U, and Fisher exact tests. RESULTS: In the ICU (+) and died groups, crazy paving (64% and 57.1%), bronchus distortion (68% and 66.7%), bronchiectasis-bronchiolectasis (80% and 76.2%), air trapping (52% and 52.4%) and mediastinal-hilar lymph node enlargement (52% and 52.4%) were significantly more encountered (P < 0,05). These findings were correlated with longer hospital stays (P < 0.05). There were no differences between reverse transcriptase-polymerase chain reaction-positive and -negative patients except bronchiectasis-bronchiolectasis. CONCLUSION: Computed tomography examinations performed early after the onset of symptoms may help in predicting disease course and planning of resources, such as ICU beds.

Frequency of abnormal pulmonary computed tomography findings in asylum seeking refugees in Turkey.

Background: Lungs are particularly vulnerable to both acute infections, including TB, and chronic diseases such as chronic obstructive pulmonary disease, as well as to malignancies, all of which require particular attention during war times in which health conditions are far from optimal. Methods: This retrospective cross-sectional study included 1149 refugees that underwent thoracic computed tomography (CT) for respiratory symptoms between March 2013 and February 2015 in Turkey. Results: At least one positive CT finding was seen in 231 (20.1%) of the patients. The most common findings were chronic pulmonary changes (n=197, 17.2%), followed by findings suggestive of infections (n=39, 3.4%), and mass/nodular lesions (n=16, 1.4%). The rates of the lesions suggestive of active TB and malignancy were 1.0% (n=11) and 0.7% (n=8), respectively. Age 55-64 years was an independent significant predictor for any CT lesion, chronic changes, mass lesions, and lesions suggestive of malignancy. Age>65 years was predictive of any CT lesion and chronic changes. Conclusions: The findings of this study indicate the need for implementation of cost-effective screening strategies in refugees, particularly during war times. Screening for TB would improve disease control among both refugees and the host populations. Middle aged and older individuals, in particular, would benefit from more proactive screening tools and strategies for the early diagnosis of pulmonary malignancies and chronic lung diseases.

Tissue Resonance Interaction Method (TRIMprob) has the potential to be used alongside the recognized tests in the screening protocols for prostate cancer.

The objective of this study was to evaluate the accuracy of the magnetic induction technique with a nonlinear tunable oscillator (the Tissue Resonance Interaction Method [TRIMprob]) in the diagnosis of prostate cancer (CaP). Overall, 148 men were split into two groups (patients at risk of CaP [Group 1] and controls [Group 2]) and evaluated with the TRIMprob. Group 1 consisted of 100 patients (mean age: 63.8 +/- 7.2 years) with elevated prostate-specific antigen (>4 ng/mL) levels and/or abnormal digital rectal examination. Eleven patients (Group 2a, mean age: 59.5 +/- 7.3) with previously biopsy-proven CaP served as positive controls. In addition, 37 voluntary men (Group 2b, mean age: 39.8 +/- 10.4) with normal prostate-specific antigen and digital rectal examination without lower urinary tract symptoms served as negative controls. Non-linear resonance was analyzed at 465 MHz and a cut-off value of 40 units was detected as the resonance value for the best threshold to distinguish benign conditions from CaP after transrectal ultrasonography-guided biopsy with a standard 10-12 core technique in Group 1. Mean resonance values (+/-standard deviation) with the TRIMprob examination for patients in Groups 1 and 2b were 36.72 +/- 22.35 and 73.64 +/- 10.06, respectively, whereas for patients in Group 2a, it was 13.73 +/- 12.12 (P < 0.01). Sensitivity, specificity, positive and negative predictive values of the TRIMprob using the study cohort of Group 1 were found as 76%, 61.3%, 39.6% and 88.5%, respectively. Despite some technical limitations, the non-invasive TRIMprob examination may have a role in screening protocols for CaP.

[The diagnostic efficiency of multislice CT virtual bronchoscopy in detecting endobronchial tumors]. / Endobronsiyal tümörlerde çok kesitli BT sanal bronkoskopinin tanisal etkinligi.

In this study, the diagnostic efficiency of virtual bronchoscopy, which is a new and helpful method to conventional fiberoptic bronchoscopy, has been investigated for endobronchial lung tumors and its clinical applications are discussed. 36 patients with clinically suspected lung cancer (28 males, 8 females, mean age 61; range from 39 to 74) underwent multislice computed tomography (MSCT) virtual bronchoscopy and then conventional bronchoscopy on the same day. For all patients, investigators were uninformed about results of conventional bronchoscopy. Sensitivity, specificity, positive and negative predictive values of virtual bronchoscopy were calculated using conventional bronchoscopy results as standard reference values. In 12 patients, conventional bronchoscopy did not show pathologic findings. In 24 cases pathologic findings were detected; mucosal infiltration was observed in three cases, vegetating lesions were detected in 21 cases. Review of these 21 cases demonstrated preocclusive stenosis in five and various degrees of luminal stenosis in 16 cases. All 21 tumoral lesions observed with conventional bronchoscopy were also detected with virtual bronchoscopy. Retrospective evaluation of six lesions visualized with virtual bronchoscopy but not detected with conventional bronchoscopy showed that they consisted of highly viscous mucous secretion. No abnormalities were detected on both conventional and virtual bronchoscopy in six patients. Three mucosal infiltrations observed on conventional bronchoscopy were not visualised on virtual bronchoscopy. The sensitivity of MSCT virtual bronchoscopy was 88% and specificity was 50% which is concordant with the literature. Positive predictive value, negative predictive value and accuracy was found 78%, 66% and 75%, respectively.

Cardiac hydatid disease: CT and MRI findings.

OBJECTIVE: The purpose of this article is to review the CT and MRI findings of cardiac hydatid disease. CONCLUSIONS: CT and MRI are helpful for localizing and defining the morphologic features of hydatid cysts. Specific signs include calcification of the cyst wall, presence of daughter cysts, and membrane detachment. CT best shows wall calcification, whereas MRI depicts the exact anatomic location and nature of the internal and external structures.

Effect of using endorectal coil in preoperative staging of rectal carcinomas by pelvic MR imaging.

PURPOSE: To assess the accuracy of magnetic resonance imaging with pelvic phased-array and endorectal coils prospectively, and evaluate if endorectal coil provides any additional information to high resolution pelvic MR imaging in rectal carcinoma staging. MATERIALS AND METHODS: Preoperative MRI of 25 patients with rectal carcinoma was performed with pelvic phased-array coil alone, and with both phased-array coil and endorectal coil placed. Staging was made by evaluating images obtained by using both coils prospectively, and correlated with histopathologic staging. The images were then assessed separately, and compared to each other retrospectively. RESULTS: Two and 3 of the 5 histopathologically proved T1 tumors were staged correctly on MRI with pelvic phased-array coil alone and after the endorectal coil placement, respectively. Histopathologically identified five T2 tumors were staged correctly as T2 in 4 of the cases, 1 was understaged and 10 of 14 patients who had T3 tumor were staged as T3, 4 of them were understaged as T2 on both techniques. Specificity, sensitivity and accuracy rates for staging of T3 tumors were found as 71%, 100% and 84%, respectively, for each technique. Sensitivity and positive predictive value of N staging were both 88% on both techniques. CONCLUSION: Pelvic MR imaging after the placement of endorectal coil in addition to the phase-array coil was not superior to the imaging with phased-array coil alone in T staging of rectal carcinomas and the latter achieved better visualization of the lymph nodes by means of larger field of view.

Dynamic contrast enhancement patterns of solitary pulmonary nodules on 3D gradient-recalled echo MRI.

OBJECTIVE: The purpose of this study was to determine whether contrast enhancement features on 3D volumetric gradient-recalled echoMR images allow differentiation of benign from malignant solitary pulmonary nodules. MATERIALS AND METHODS: Forty patients with solitary pulmonary nodules (range of greatest diameter, 7-40 mm) detected on CT underwent unenhanced MRI and contrast-enhanced MRI performed in 10 consecutive dynamic 3D volumetric gradient-recalled echo sequences every 30 seconds. Contrast enhancement patterns (homogeneous, heterogeneous, rim, peripheral, and central) of the lesions were visually evaluated, and time-intensity curves of the lesions were drawn. RESULTS: Twenty patients had benign lesions (nine, tuberculoma; one, aspergilloma; nine, round atelectasis; one, postinflammatory nodule). The other 20 patients had malignant lesions (18, primary lung cancer; two, metastasis). At visual analysis, all 20 malignant lesions displayed peripheral enhancement with progressive heterogeneous fill-in on the late images. All nine tuberculomas and the aspergilloma had rim enhancement, and all nine round atelectasis lesions and the postinflammatory nodule had early intense homogeneous enhancement. Regarding the time-intensity curves, all malignant lesions except one lung cancer lesion had early peak enhancement with rapid washout. All benign lesions displayed early increasing enhancement with an early plateau in the second minute after contrast administration (nine tuberculomas and one aspergilloma) or a late plateau in the fourth minute (nine round atelectasis lesions and one postinflammatory nodule). CONCLUSION: Rim contrast enhancement is highly valuable in the diagnosis of tuberculoma. Time-intensity curve types can be taken into consideration for noninvasive differentiation of lung cancer, tuberculoma, and round atelectasis.

Frequency of sternal variations and anomalies evaluated by MDCT.

OBJECTIVE: Our objective was to reveal the frequency and MDCT appearances of sternal variations and anomalies in subjects without sternal deformities. SUBJECTS AND METHODS: One thousand consecutive patients who underwent thoracic MDCT examination were enrolled in the study. All MDCT data, including multiplanar and curved-planar reconstructed images, were evaluated for detection of sternal variations and anomalies. Various kinds of sternal variations and anomalies, such as suprasternal bones and tubercles, manubriosternal and sternoxiphoidal fusions, sternal clefts and foramina, and sternal sclerotic bands were documented. RESULTS: In 1,000 subjects, the frequencies of main sternal variations and anomalies were as follows: suprasternal bone in 4.1%, suprasternal tubercle in 4%, complete manubriosternal fusion in 19.6%, complete sternoxiphoidal fusion in 30.3%, sternal foramen in 4.5%, and sternal sclerotic band in 37.1%. Xiphoidal foramen was seen in 27.4%, and the most common type was single foramen. Xiphoid process mostly ended as a single process (71%). Double-ended xiphoid process was also frequent (27.2%). Pseudocleft and pseudoforamen at the sternoxiphoidal junction were detected in 3.3% and in 3.6% of subjects, respectively. CONCLUSION: MDCT exhibited various sternal variations and anomalies. Sternal foramen is a frequent minor anomaly and generally associated with sternal sclerotic bands. Early manubriosternal and sternoxiphoidal fusions can be seen in early adulthood without osteodegeneration. Double-ended xiphoid process and single xiphoidal foramen are frequent sternal variations. Awareness of MDCT appearances of sternal variations and anomalies provides a better differential diagnosis with pathologic conditions.

A rare cause of delayed contrast enhancement on cardiac magnetic resonance imaging: infective endocarditis.

Although there have been a few reports about the magnetic resonance (MR) imaging features of infective endocarditis (IE), delayed contrast enhancement attributable to fibrosis has not been previously described. The case of a 4-year-old girl who was diagnosed with IE based on positive blood culture results and echocardiographic findings is presented. At cardiac MR imaging, late phase contrast-enhanced images revealed a significant enhancement suggesting fibrosis secondary to IE.

Multiple pulmonary metastases from intracranial meningioma: MR imaging findings (case report).

Extracranial metastases from meningioma are very rare and among those the lungs are the most common metastatic site. In the literature, pulmonary metastases of meningiomas have been emphasized on their rarity, non-specific imaging findings, and cytologic features. Some definitive MR imaging features of intracranial meningiomas have been described. However, MR imaging findings of the lung metastases of meningiomas have not been investigated with regard to these diagnostic imaging features. In this report, similarities between MR imaging features of primary intracranial meningioma and its rare lung metastases are presented.

Contrast-enhanced 3D MR voiding urethrography: preliminary results.

Contrast-enhanced 3D MR voiding urethrography (CE 3D MRVU) was performed on 5 healthy volunteers and 18 patients with urethral disease. After intravenous injection of 0.3 ml/kg gadolinium, the images of the three consecutive acquisitions of the 3D MRVU technique were obtained during voiding. The raw data were reconstructed on all patients for visual analysis. The image quality of the volunteers was technically sufficient to demonstrate normal urethral anatomy. Contrast-enhanced 3D MR voiding urethrography of the urethral strictures was compared with conventional retrograde urethrography (n = 10) and urethroscopy (n = 12). The urethral pathologies including strictures and other obstructive causes of impaired urethral flow were correctly identified on CE 3D MRVU.

[Diagnostic efficiency of multislice computed tomography colonography in the detection of colorectal tumors: comparison with conventional colonography]. / Kolorektal tümörlerin tanisinda çok-kesitli BT kolonografinin konvansiyonel kolonoskopi ile karsilastirilmasi.

PURPOSE: To evaluate the diagnostic efficiency of multislice CT colonography in the detection of colorectal tumors by comparing it with conventional colonography in patients with high risk of colorectal cancer. MATERIALS AND METHODS: Thirty-seven patients who had undergone conventional colonoscopy because of a suspicion of colorectal cancer were scanned with a four-detector multislice CT scanner with 4 x 1 mm detector collimation, 120 kV, 0.5 sec gantry rotation and 120 mAs scan parameters. Multiplanar reformatted images, virtual colonography and virtual colonoscopy images were compared with conventional colonoscopy. With conventional colonoscopy taken as the reference standard, the results were calculated with 95% confidence interval technique. RESULTS: Seventeen of the 23 polyps detected in conventional colonoscopy were identified correctly with multislice CT. Nine of 11 lesions with a diameter of 10 mm or greater (81%), three of four lesions with a diameter of 6-9 mm (75%), and five of eight lesions with a diameter of 1-5 mm (62%) were correctly identified with multislice CT. CONCLUSION: Multislice CT colonography is a good alternative to other colorectal screening tests because it has high sensitivity for polyps 10 mm or larger in diameter, is relatively safe and minimally invasive.

Analysis of the thymus in 151 healthy infants from 0 to 2 years of age.

OBJECTIVE: A prospective sonographic study of the normal thymus was performed to determine the size changes with age and to compare the results according to some clinical conditions, such as sex, breast versus formula feeding, and term or preterm status. METHODS: One hundred fifty-one healthy infants underwent thymic sonography. Maximal transverse and longitudinal dimensions and anteroposterior dimensions of the right and left lobes were measured, and thymic indices were calculated. Mean values of thymic measurements for each group (sex, age, breast or formula feeding, and term or preterm status) were determined. The results were statistically evaluated. RESULTS: Thymic dimensions showed the maximal values at about 4 to 6 months and gradually decreased after 6 to 8 months. No significant differences were found between mean values of thymic dimensions according to the sex and formula- versus breast-fed groups. As expected, the term group had greater thymic size values than the preterm group, probably because of positive correlations between thymus size, birth weight, and height. CONCLUSIONS: The thymus is clearly and easily visualized on sonography in the 0- to 2-year age period. This may be useful for evaluating qualitative and quantitative properties of the thymus and determining size changes according to age in various clinical conditions.

Multidetector row CT of the kidneys.

In this article, the value of multiple detector-row computed tomography (MDCT) in renal applications is discussed, with emphasis on clinical uses. The superiority of application techniques of MDCT renders it one of the most distinguished modality in detection of congenital anomalies, tumors, transplants, trauma, and arterial diseases of the kidney.