The aim of our study was to establish and compare the diagnostic accuracy and clinical applicability of published chest CT severity scoring systems used for COVID-19 pneumonia assessment and to ...propose the most efficient CT scoring system with the highest diagnostic performance and the most accurate prediction of disease severity. This retrospective study included 218 patients with PCR-confirmed SARS-CoV-2 infection and chest CT. Two radiologists blindly evaluated CT scans and calculated nine different CT severity scores (CT SSs). The diagnostic validity of CT SSs was tested by ROC analysis. Interobserver agreement was excellent (intraclass correlation coefficient: 0.982-0.995). The predominance of either consolidations or a combination of consolidations and ground-glass opacities (GGOs) was a predictor of more severe disease (both
< 0.005), while GGO prevalence alone was not. Correlation between all CT SSs was high, ranging from 0.848 to 0.971. CT SS 30 had the highest diagnostic accuracy (AUC = 0.805) in discriminating mild from severe COVID-19 disease compared to all the other proposed scoring systems (AUC range 0.755-0.788). In conclusion, CT SS 30 achieved the highest diagnostic accuracy in predicting the severity of COVID-19 disease while maintaining simplicity, reproducibility, and applicability in complex clinical settings.
Highlights • We examine the possibility of semi-automated diagnoses of ACL injury from knee MRI volumes • ACL conditions under consideration were: normal, partially injured and completely ruptured • ...We explore two feature-extraction techniques with two machine-learning models • Good generalisation properties were obtained for a linear-kernel SVM model learned from HOG descriptors • Experimental results on a large knee MRI-volume sample suggest possible clinical use in CAD
A case of 16-year-old female with secondary psoas abscess as the complication of the Crohn’s disease was analysed. Her pre-hospital, long lasting, non-specific symptoms led to ultrasound (US) and ...radiologic imaging confirming the diagnosis. The antibiotic treatment was insufficient and worsening of the patient’s condition required surgical treatment including descendent colectomy, abscess drainage and negative pressure wound therapy (NPWT). In spite of numerous complications the condition of the child gradually improved and she was discharged from the hospital on the 71st postoperative day. Two years after the colectomy, the occlusion of her colostomy was performed.
The aim of our study was to investigate iodine density (ID) and fat fraction (FF) on dual-energy computed tomography (DECT) in patients with acute pancreatitis (AP). This retrospective study included ...72 patients with clinically confirmed AP and 62 control subjects with DECT of the abdomen. Two radiologists assessed necrosis and measured attenuation values, ID, and FF in three pancreatic segments. We used receiver operating characteristic (ROC) analysis to determine the optimal threshold for ID for the differentiation between AP groups. The ID was significantly higher in interstitial edematous AP compared to necrotizing AP and the control group (both
< 0.05). The ROC curve analysis revealed the thresholds of ID for detecting pancreatic necrosis ≤ 2.2, ≤2.3, and ≤2.4 mg/mL (AUC between 0.880 and 0.893,
> 0.05) for the head, body, and tail, respectively. The FF was significantly higher for pancreatitis groups when compared with the control group in the head and body segments (both
< 0.001). In the tail, the difference was significant in necrotizing AP (
= 0.028). The ID values were independent of attenuation values correlated with the FF values in pancreatic tissue. Iodine density values allow for differentiation between morphologic types of AP.
Studies show insufficient sensitivity of virtual non-contrast (VNC) reconstructions for stone detection in dual-energy CT urography (DE-CTU). The aim of this study was to investigate if ...side-by-side-evaluation of both VNC and post-contrast images could increase the sensitivity of single-phase split bolus DE-CTU.
Consecutive patients with haematuria who underwent split bolus DE-CTU on the same dual-source DE-CT scanner were retrospectively enrolled in the study. Intravenous furosemide and oral hydration were employed. Two readers, independently and then jointly in two separate sessions, recorded the location and the longest axial stone diameter on three randomised sets of images: separate VNC and post-contrast images, and side-by-side-reconstructions. True non-contrast (TNC) images served as the standard of reference.
A total of 83 urinary stones were detected on TNC images. Independent reader side-by-side-evaluation of VNC and post-contrast images yielded higher stone detection sensitivity (76 and 84%, respectively) compared to evaluation of only VNC (71 and 81%, respectively) or post-contrast images (64 and 80%, respectively). The sensitivity of joint reader evaluation of side-by-side-images reached almost 86% and was not significantly different from TNC images (
= 0.77). All stones larger than 3 mm were correctly detected by side-by-side-evaluation. Dose reduction of 55% could be achieved by omitting TNC scans.
Side-by-side-VNC and post-contrast image evaluation enable detection of clinically significant urolithiasis on single-phase split bolus DE-CTU with significant dose reduction.
This study shows that single-phase DE-CTU is feasible if VNC imaging is simultaneously utilised with post-contrast images.
Narrative texts in electronic health records can be efficiently utilized for building decision support systems in the clinic, only if they are correctly interpreted automatically in accordance with a ...specified standard. This paper tackles the problem of developing an automated method of labeling free-form radiology reports, as a precursor for building query-capable report databases in hospitals. The analyzed dataset consists of 1295 radiology reports concerning the condition of a knee, retrospectively gathered at the Clinical Hospital Centre Rijeka, Croatia. Reports were manually labeled with one or more labels from a set of 10 most commonly occurring clinical conditions. After primary preprocessing of the texts, two sets of text classification methods were compared: (1) traditional classification models-Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), and Random Forests (RF)-coupled with Bag-of-Words (BoW) features (i.e., symbolic text representation) and (2) Convolutional Neural Network (CNN) coupled with dense word vectors (i.e., word embeddings as a semantic text representation) as input features. We resorted to nested 10-fold cross-validation to evaluate the performance of competing methods using accuracy, precision, recall, and F 1 score. The CNN with semantic word representations as input yielded the overall best performance, having a micro-averaged F 1 score of 86 . 7 % . The CNN classifier yielded particularly encouraging results for the most represented conditions: degenerative disease ( 95 . 9 % ), arthrosis ( 93 . 3 % ), and injury ( 89 . 2 % ). As a data-hungry deep learning model, the CNN, however, performed notably worse than the competing models on underrepresented classes with fewer training instances such as multicausal disease or metabolic disease. LR, RF, and SVM performed comparably well, with the obtained micro-averaged F 1 scores of 84 . 6 % , 82 . 2 % , and 82 . 1 % , respectively.
Sažetak. Rak debelog crijeva jedan je od najčešćih zloćudnih tumora u zapadnim zemljama. Ishod liječenja bolesnika s ovom bolešću posljednjih se godina znatno poboljšao zbog napretka u dijagnostici ...(patohistologija, radiologija, nuklearna medicina), kirurškom i onkološkom liječenju (kemoterapija, imunoterapija, radioterapija) te provođenju probira. Dodatan je napredak postignut u definiranju prognostičkih i prediktivnih čimbenika raka debelog crijeva. Neobično je važno naglasiti multidisciplinarni pristup bolesnicima s rakom debelog crijeva te donošenje odluke o optimalnom cilju i strategiji liječenja na temelju dokaza.
Computerized tomography (CT) is the most accurate method for evaluating pelvic calcifications, which are of utmost importance for planning kidney transplantation (KT). The aim of our study was to ...evaluate the incidence and distribution of iliac artery calcifications and correlate the novel pelvic calcification score (PCS) with cardiovascular risk factors and graft and overall survival in KT patients.
We retrospectively included 118 KT patients operated at our institution with pretransplant pelvic CT. Calcification morphology, circumference and length of both common and external iliac arteries were independently scored by two uroradiologists. PCS was calculated as the total score sum of all three calcification features in all vessels. PCS correlation with graft and patient survival was performed.
Calcification in at least one vascular segment was found in 79% of patients. PCS was significantly higher in male patients (
= 0.006), patients over 55 years (
< 0.001), and patients on haemodialysis (
= 0.016). Patients with a PCS >3 had significantly shorter graft and overall survival rates (
= 0.041 and
= 0.039, respectively).
The extent of iliac artery calcification in KT recipients quantified by PCS on pretransplant CT correlates with graft and overall patient survival. A PCS over three was associated with worse clinical outcomes and could become a possible prognostic factor.
Our novel PCS is a robust method for quantifying iliac artery calcification burden. Since higher a PCS correlates with worse patient and graft survival, PCS has the potential to become a prognostic factor in kidney transplant patients.
Background
Virtual monoenergetic (VM) dual-energy computed tomography (DE-CT) enables grey-to-white matter contrast-to-noise ratio optimization, potentially increasing ischaemic brain oedema ...visibility. The aim of this study was to compare the diagnostic accuracy of VM and standard DE-CT reconstructions for early stroke detection.
Methods
Consecutive patients with non-contrast DE-CT of the brain scanned within 12 h of stroke symptom onset were prospectively included in the study. Patients with other significant brain pathology were excluded. Two radiologists jointly evaluated standard and VM reconstructions (from 40 to 190 keV at increments of 10 keV) for early stroke signs on a four-point Likert scale: (a) stroke definitely present, (b) stroke probably present, (c) probably no stroke, and (d) definitely no stroke. Follow-up imaging and clinical data served as the standard of reference. Diagnostic accuracy was evaluated by receiver operating characteristic analysis.
Results
Stroke incidence among 184 patients was 76%. In 64 patients follow-up imaging served as the standard of reference: ischemic brain oedema detection was significantly more accurate on VM reconstructions at 80 keV compared with standard DE-CT reconstructions (area under the curve (AUC) = 0.821 vs. AUC = 0.672, p = 0.002). The difference was most prominent within the first 3 h after symptom onset (at 11%, AUC = 0.819 vs. AUC = 0.709, p = 0.17) and in patients with National Institutes of Health Stroke Scale above 16 (at 37.5%, AUC = 1 vs. AUC = 0.625, p = 0.14).
Conclusion
VM DE-CT reconstructions at 80 keV appear to be the optimal non-contrast CT technique for diagnosing early ischaemic stroke, particularly within the first 3 h after symptom onset and in severely ill patients.