Staging of Endometrial Cancer Using Fusion T2-Weighted Images with Diffusion-Weighted Images: A Way to Avoid Gadolinium?

Endometrial cancer is the eighth most common cancer worldwide, and its prognosis depends on various factors, with myometrial invasion having a major impact on prognosis. Optimizing MRI protocols is essential, and it would be useful to improve the diagnostic accuracy without the need for other sequences. We conducted a retrospective, single-center study, which included a total of 87 patients with surgically confirmed primary endometrial cancer, and who had undergone a pre-operative pelvic MRI. All exams were read by an experienced radiologist dedicated to urogenital radiology, and the depth of myometrial invasion was evaluated using T2-Weighted Images (T2WI) and fused T2WI with Diffusion-Weighted Images (DWI). Both results were compared to histopathological evaluations. When comparing both sets of imaging (T2WI and fused T2WI-DWI images) in diagnosing myometrial invasion, the fused images had better accuracy, and this difference was statistically significant (p < 0.001). T2WI analysis correctly diagnosed 82.1% (70.6–88.7) of cases, compared to 92.1% correctly diagnosed cases with fused images (79.5–97.2). The addition of fused images to a standard MRI protocol improves the diagnostic accuracy of myometrial invasion depth, encouraging its use, since it does not require more acquisition time.

Limb Ischemia Associated With Covid-19 and Its Treatment With Above-Knee Amputation

An 84-year-old male patient with no known comorbidity was admitted to the emergency department with complaints of dyspnea and respiratory distress. The patient was referred to the COVID outpatient clinic, laboratory and radiology tests were performed. Thoracic CT scan of the patient showed large peripheral patchy ground glass densities observed in the lower lobes of both lungs. CT imaging findings were evaluated by an experienced radiologist and reported as COVID-19 pneumonia. The patient, who was self-isolated at home for 5 days, presented to the emergency department again on the fifth day with complaints of respiratory distress, fever, bruising with cough, and loss of peripheral pulse in the left lower extremity. Necessary tests were performed on the patient. An above-knee amputation was performed when a diagnosis of limb ischemic necrosis was made and no revascularization attempt was considered by the CVS department. This case study describes the coexistence of sudden lower extremity thrombosis and Covid-19 in our case without a known chronic disease.

Structured reporting in radiologic education – Potential of different PI-RADS versions in prostate MRI controlled by in-bore MR-guided biopsies

Objectives: To evaluate the efficiency of structured reporting in radiologic education – based on the example of different PI-RADS score versions for multiparametric MRI (mpMRI) of the prostate. Methods: MpMRI of 688 prostate lesions in 180 patients were retrospectively reviewed by an experienced radiologist and by a student using PI-RADS V1 and V2. Data sets were reviewed for changes according to PI-RADS V2.1. The results were correlated with results obtained by MR-guided biopsy. Diagnostic potency was evaluated by ROC analysis. Sensitivity, specificity and correct-graded samples were evaluated for different cutpoints. The agreement between radiologist and student was determined for the aggregation of the PI-RADS score in three categories. The student’s time needed for evaluation was measured. Results: The area under curve of the ROC analysis was 0.782/0.788 (V1/V2) for the student and 0.841/0.833 (V1/V2) for the radiologist. The agreement between student and radiologist showed a Cohen‘s weighted κ coefficient of 0.495 for V1 and 0.518 for V2. Median student’s time needed for score assessment was 4:34 min for PI-RADSv1 and 2:00 min for PI-RADSv2 (p < 0.001). Re-evaluation for V2.1 changed the category in 1.4% of all ratings. Conclusion: The capacity of prostate cancer detection using PI-RADS V1 and V2 is dependent on the reader‘s experience. The results from the two observers indicate that structured reporting using PI-RADS and, controlled by histopathology, can be a valuable and quantifiable tool in students‘ or residents’ education. Herein, V2 was superior to V1 in terms of inter-observer agreement and time efficacy. Advances in knowledge: Structured reporting can be a valuable and quantifiable tool in radiologic education. Structured reporting using PI-RADS can be used by a student with good performance. PI-RADS V2 is superior to V1 in terms of inter-observer agreement and time efficacy.

Outcome of Tuberculosis Case Surveillance at Kano Central Correctional Center, North-west Nigeria: A Need for Routine Active Case Findings for TB in Nigerian Correctional Centers

Aim: To demonstrate the need for routine active TB case finding in Nigerian correctional centers through a TB case surveillance intervention at the largest correctional centre in the most populous state in Nigeria by KNCV Tuberculosis Foundation Nigeria. Study Design: It was a retrospective review of public health intervention data derived from the mass TB screening of Kano central correctional centre inmates in Kano state, Nigeria. Methodology: A digital X-ray with artificial intelligence (AI) was used for mass TB screening of 1,967 consenting inmates at the Kano central correctional centre in Kano state, Nigeria, from 21st September to 2nd October 2020. Participants with CAD4TB score ≥ 60 had a GeneXpert assessment of their sputa for TB diagnosis. Where sputum production was not possible, or GeneXpert result was negative, expert clinical evaluation of the presumptive radiogram was carried out by experienced radiologist. Data from the project were extracted and analysed for this report. Proportions and means were compared with Fisher Exact test and Student t-test, respectively. A p-value of < 0.05 was considered statistically significant. Results: Overall, 1,967 inmates were screened for TB and 92 (4.7%) presumptive were identified - males (4.8%, 91/92), females (1.9%, 1/92). Out of the 92 presumptive, 21 males were diagnosed as TB cases giving a TB prevalence of 1.1% among the inmates and 22.8% among presumptive. One of the TB cases had multi-drug resistant TB. The number needed to screen (NNS) was 94. All TB cases were enrolled in treatment. Conclusion: The prevalence of TB at the Kano central correctional centre during the mass TB screening project was high. The National Tuberculosis Control Programme of Nigeria should accelerate the planned paradigm shift from passive to active case-finding for TB in Nigerian correctional centers.

AutoProstate: Towards Automated Reporting of Prostate MRI for Prostate Cancer Assessment Using Deep Learning

Multiparametric magnetic resonance imaging (mpMRI) of the prostate is used by radiologists to identify, score, and stage abnormalities that may correspond to clinically significant prostate cancer (CSPCa). Automatic assessment of prostate mpMRI using artificial intelligence algorithms may facilitate a reduction in missed cancers and unnecessary biopsies, an increase in inter-observer agreement between radiologists, and an improvement in reporting quality. In this work, we introduce AutoProstate, a deep learning-powered framework for automatic MRI-based prostate cancer assessment. AutoProstate comprises of three modules: Zone-Segmenter, CSPCa-Segmenter, and Report-Generator. Zone-Segmenter segments the prostatic zones on T2-weighted imaging, CSPCa-Segmenter detects and segments CSPCa lesions using biparametric MRI, and Report-Generator generates an automatic web-based report containing four sections: Patient Details, Prostate Size and PSA Density, Clinically Significant Lesion Candidates, and Findings Summary. In our experiment, AutoProstate was trained using the publicly available PROSTATEx dataset, and externally validated using the PICTURE dataset. Moreover, the performance of AutoProstate was compared to the performance of an experienced radiologist who prospectively read PICTURE dataset cases. In comparison to the radiologist, AutoProstate showed statistically significant improvements in prostate volume and prostate-specific antigen density estimation. Furthermore, AutoProstate matched the CSPCa lesion detection sensitivity of the radiologist, which is paramount, but produced more false positive detections.

Rib fracture detection system based on deep learning

Rib fracture detection is time-consuming and demanding work for radiologists. This study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately. A total of 1707 patients were included in this study from a single center. We developed a novel rib fracture detection system on chest CT using a three-step algorithm. According to the examination time, 1507, 100 and 100 patients were allocated to the training set, the validation set and the testing set, respectively. Free Response ROC analysis was performed to evaluate the sensitivity and false positivity of the deep learning algorithm. Precision, recall, F1-score, negative predictive value (NPV) and detection and diagnosis were selected as evaluation metrics to compare the diagnostic efficiency of this system with radiologists. The radiologist-only study was used as a benchmark and the radiologist-model collaboration study was evaluated to assess the model’s clinical applicability. A total of 50,170,399 blocks (fracture blocks, 91,574; normal blocks, 50,078,825) were labelled for training. The F1-score of the Rib Fracture Detection System was 0.890 and the precision, recall and NPV values were 0.869, 0.913 and 0.969, respectively. By interacting with this detection system, the F1-score of the junior and the experienced radiologists had improved from 0.796 to 0.925 and 0.889 to 0.970, respectively; the recall scores had increased from 0.693 to 0.920 and 0.853 to 0.972, respectively. On average, the diagnosis time of radiologist assisted with this detection system was reduced by 65.3 s. The constructed Rib Fracture Detection System has a comparable performance with the experienced radiologist and is readily available to automatically detect rib fracture in the clinical setting with high efficacy, which could reduce diagnosis time and radiologists’ workload in the clinical practice.

Diagnostic accuracy and validity of the O-RADS MRI score based on a simplified MRI protocol: a single tertiary center retrospective study

Background Adnexal masses (AM) are a common gynecological problem. It is important to use a reliable imaging method in the differentiation of benign and malignant AMs. Purpose To assess the accuracy and validity of the O-RADS magnetic resonance imaging (MRI) score for characterizing AM using a simplified MRI protocol. Material and Methods The study population comprised 332 women who underwent MRI due to the detection of indeterminate AM on ultrasonography between January 2018 and June 2020. An experienced radiologist calculated the O-RADS MRI score into five categories, using an MRI protocol with a simplified dynamic study. Sensitivity, specificity, positive and negative predictive values, and area under the curve (AUC) were calculated (cutoff for malignancy, score ≥ 4). The reference standard was histopathologic diagnosis or imaging findings during >24 months of follow-up. Results Of 237 AMs, 28 (11.9%) were malignant. The malignancy rates of AMs with scores of 1, 2, 3, 4, and 5 were 0% (0/12), 0% (0/111), 1.2% (1/77), 50% (10/20), and 100% (17/17), respectively. The O-RADS MRI score showed 96.3% sensitivity, 95.2% specificity, and 95.3% accuracy in malignancy prediction. The AUC for the differentiation of benign and malignant masses were 0.983. False positivity rate was high in cases with an O-RADS MRI score of 4 (50%). Conclusion The O-RADS MRI score, based on a simplified MRI protocol, has high accuracy and validity in distinguishing benign from malignant sonographically indeterminate AMs. Its use in clinical practice can classify the malignancy risks of masses and prevent unnecessary surgery in benign lesions.

Accuracy and Reproducibility of a Software Prototype for Semi-Automated Computer-Aided Volumetry of the solid and subsolid Components of part-solid Pulmonary Nodules

Purpose To test the accuracy and reproducibility of a software prototype for semi-automated computer-aided volumetry (CAV) of part-solid pulmonary nodules (PSN) with separate segmentation of the solid part. Materials and Methods 66 PSNs were retrospectively identified in 34 thin-slice unenhanced chest CTs of 19 patients. CAV was performed by two medical students. Manual volumetry (MV) was carried out by two radiology residents. The reference standard was determined by an experienced radiologist in consensus with one of the residents. Visual assessment of CAV accuracy was performed. Measurement variability between CAV/MV and the reference standard as a measure of accuracy, CAV inter- and intra-rater variability as well as CAV intrascan variability between two recontruction kernels was determined via the Bland-Altman method and intraclass correlation coefficients (ICC). Results Subjectively assessed accuracy of CAV/MV was 77 %/79 %–80 % for the solid part and 67 %/73 %–76 % for the entire nodule. Measurement variability between CAV and the reference standard ranged from –151–117 % for the solid part and –106–54 % for the entire nodule. Interrater variability was –16–16 % for the solid part (ICC 0.998) and –102–65 % for the entire nodule (ICC 0.880). Intra-rater variability was –70–49 % for the solid part (ICC 0.992) and –111–31 % for the entire nodule (ICC 0.929). Intrascan variability between the smooth and the sharp reconstruction kernel was –45–39 % for the solid part and –21–46 % for the entire nodule. Conclusion Although the software prototype delivered satisfactory results when segmentation is evaluated subjectively, quantitative statistical analysis revealed room for improvement especially regarding the segmentation accuracy of the solid part and the reproducibility of measurements of the nodule’s subsolid margins. Key points:

Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks

Researchers address the generalization problem of deep image processing networks mainly through extensive use of data augmentation techniques such as random flips, rotations, and deformations. A data augmentation technique called mixup, which constructs virtual training samples from convex combinations of inputs, was recently proposed for deep classification networks. The algorithm contributed to increased performance on classification in a variety of datasets, but so far has not been evaluated for image segmentation tasks. In this paper, we tested whether the mixup algorithm can improve the generalization performance of deep segmentation networks for medical image data. We trained a standard U-net architecture to segment the prostate in 100 T2-weighted 3D magnetic resonance images from prostate cancer patients, and compared the results with and without mixup in terms of Dice similarity coefficient and mean surface distance from a reference segmentation made by an experienced radiologist. Our results suggest that mixup offers a statistically significant boost in performance compared to non-mixup training, leading to up to 1.9% increase in Dice and a 10.9% decrease in surface distance. The mixup algorithm may thus offer an important aid for medical image segmentation applications, which are typically limited by severe data scarcity.

Diagnostic performance of radiologists with different levels of experience in the interpretation of MRI of the placenta accreta spectrum disorder

Objectives: There have been no investigations on the association between previous abdominopelvic MRI experience without placental MRI experience and diagnostic accuracy of placenta accreta spectrum (PAS). To evaluate the diagnostic performance of radiologists with different experience levels in interpreting PAS-related MRI findings. Methods: This retrospective study included 60 women who underwent MRI for placental assessment between 2016 and 2020. MR images were reviewed by four radiologists who were blinded to the clinical outcomes and had different experience levels in interpreting PAS-related MRI findings. The radiologists’ diagnostic performance was evaluated according to the pathologic and surgical outcomes. Simple κ statistics were calculated to determine agreement among the radiologists. Results: Of 60 women, 46 were diagnosed with PAS. The maternal age mean ± SD was 33.0 years ± 5.0 for the PAS absent group and 36.0 ± 4.3 for the PAS present group (p = 0.013). Overall, the most experienced radiologist had the highest sensitivity (100%, 95% confidence interval (CI): 92.3–100%) and NPV (100%, 95% CI: 63.1–100%) in PAS diagnoses. However, the PPV and specificity were independent of experience. The most experienced radiologist had the highest diagnostic accuracy in PAS (90%, 95% CI: 79.5–96.2%) and placenta percreta (95%, 95% CI: 86.1–99.0%). There was a strong association between definitive PAS diagnoses and the highest experience level. The κ values for the interobserver agreement regarding PAS diagnoses were 0.67 for the most experienced radiologist (p < 0.001) and 0.38, 0.40, and 0.43 for the other radiologists (p = 0.001) and regarding placenta percreta diagnoses were 0.87 for the senior radiologist (p < 0.001) and 0.63, 0.57, and 0.62 for the other radiologists (p < 0.001). Conclusion: Previous experience in interpreting PAS-related MRI findings plays a significant role in accurately interpreting such imaging findings. Previous abdominopelvic MRI experience without specific placental MRI experience did not improve diagnostic performance. Advances in knowledge: We believe that our study makes a significant contribution to the literature and that this paper will be of interest to the readership of your journal because to the best of our knowledge, this study is the first in which the correlation between previous experience in abdominopelvic MRI with no specific experience in PAS-related MRI and diagnostic accuracy of radiologists has been explored. Our results could aid in setting up specialized multidisciplinary teams to assist women with PAS disorders.