The feasibility of half-dose contrast-enhanced scanning of brain tumours at 5.0 T: a preliminary study.

PURPOSE: This study investigated and compared the effects of Gd enhancement on brain tumours with a half-dose of contrast medium at 5.0 T and with a full dose at 3.0 T. METHODS: Twelve subjects diagnosed with brain tumours were included in this study and underwent MRI after contrast agent injection at 3.0 T (full dose) or 5.0 T (half dose) with a 3D T1-weighted gradient echo sequence. The postcontrast images were compared by two independent neuroradiologists in terms of the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and subjective image quality score on a ten-point Likert scale. Quantitative indices and subjective quality ratings were compared with paired Student's t tests, and interreader agreement was assessed with the intraclass correlation coefficient (ICC). RESULTS: A total of 16 enhanced tumour lesions were detected. The SNR was significantly greater at 5.0 T than at 3.0 T in grey matter, white matter and enhanced lesions (p < 0.001). The CNR was also significantly greater at 5.0 T than at 3.0 T for grey matter/tumour lesions, white matter/tumour lesions, and grey matter/white matter (p < 0.001). Subjective evaluation revealed that the internal structure and outline of the tumour lesions were more clearly displayed with a half-dose at 5.0 T (Likert scale 8.1 ± 0.3 at 3.0 T, 8.9 ± 0.3 at 5.0 T, p < 0.001), and the effects of enhancement in the lesions were comparable to those with a full dose at 3.0 T (7.8 ± 0.3 at 3.0 T, 8.7 ± 0.4 at 5.0 T, p < 0.001). All subjective scores were good to excellent at both 5.0 T and 3.0 T. CONCLUSION: Both quantitative and subjective evaluation parameters suggested that half-dose enhanced scanning via 5.0 T MRI might be feasible for meeting clinical diagnostic requirements, as the image quality remains optimal. Enhanced scanning at 5.0 T with a half-dose of contrast agents might benefit patients with conditions that require less intravenous contrast agent, such as renal dysfunction.

Screening mammography performance according to breast density: a comparison between radiologists versus standalone intelligence detection.

BACKGROUND: Artificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women. METHODS: We retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI's performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A-D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories. RESULTS: Mean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7-77.3] vs. 67.1% [95% CI, 58.8-74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9-93.2] vs. 77.6% [95% CI, 61.7-77.9]), PPV (1.5% [95% CI, 1.2-1.9] vs. 0.5% [95% CI, 0.4-0.6]), recall rate (7.1% [95% CI, 6.9-7.2] vs. 22.5% [95% CI, 22.2-22.7]), and AUC values (0.8 [95% CI, 0.76-0.84] vs. 0.74 [95% CI, 0.7-0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category. CONCLUSIONS: AI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

High sensitivity methods for automated rib fracture detection in pediatric radiographs.

Rib fractures are highly predictive of non-accidental trauma in children under 3 years old. Rib fracture detection in pediatric radiographs is challenging because fractures can be obliquely oriented to the imaging detector, obfuscated by other structures, incomplete, and non-displaced. Prior studies have shown up to two-thirds of rib fractures may be missed during initial interpretation. In this paper, we implemented methods for improving the sensitivity (i.e. recall) performance for detecting and localizing rib fractures in pediatric chest radiographs to help augment performance of radiology interpretation. These methods adapted two convolutional neural network (CNN) architectures, RetinaNet and YOLOv5, and our previously proposed decision scheme, "avalanche decision", that dynamically reduces the acceptance threshold for proposed regions in each image. Additionally, we present contributions of using multiple image pre-processing and model ensembling techniques. Using a custom dataset of 1109 pediatric chest radiographs manually labeled by seven pediatric radiologists, we performed 10-fold cross-validation and reported detection performance using several metrics, including F2 score which summarizes precision and recall for high-sensitivity tasks. Our best performing model used three ensembled YOLOv5 models with varied input processing and an avalanche decision scheme, achieving an F2 score of 0.725 ± 0.012. Expert inter-reader performance yielded an F2 score of 0.732. Results demonstrate that our combination of sensitivity-driving methods provides object detector performance approaching the capabilities of expert human readers, suggesting that these methods may provide a viable approach to identify all rib fractures.

Women in Radiology: A perspective from Spain.

INTRODUCTION: There are gender inequalities in all fields, including radiology. Although the situation is improving, the presence of radiologists in leadership positions continues to be a minority. The objective of this article is to analyse the situation of women in the spanish radiology, comparing it with Europe and the United States. MATERIALS AND METHODS: We selected the years 2000-2022 as reference period to make a comparison with feminization data throughout history. In addition, relevant specific data from the just begun 2023 were also included. The variables in which we investigated feminization were the following: medical students, medical graduates, radiology residents and specialists, section chiefs, department chairs, radiology residency programme directors, radiology university professors, presidents of the main radiological entities and societies in Spain, Europe and the United States, recipients of the main awards given by these radiological societies and chief editors of their journals. In order to perform this analysis we conducted an in-depth bibliographic research, we contacted the radiological societies of Spain, Europe and the USA and we carried out a survey in the main Spanish radiology departments. RESULTS: The female presence in radiology decreases as we rise to leadership positions, a situation that is patent in Spain, Europe and the US, comparison that will be analysed in depth throughout the article. In Spanish hospitals in 2021 there were 58.1% female radiology residents, 55% female radiologists, 42.9% female section chiefs and 24.4% female department chairs. In SERAM's history there have been 10% female presidents, 22% female gold medallists and 5% female editors-in-chief. If we analyse data from 2000 to 2023, female presidents reach 32% and female gold medallists 31%. CONCLUSIONS: Although gender inequality is declining, in radiology women continue to be underrepresented in leadership positions. Work must be done in order to build a diverse and inclusive profession that reflects demographic reality.

Potential of GPT-4 for Detecting Errors in Radiology Reports: Implications for Reporting Accuracy.

Background Errors in radiology reports may occur because of resident-to-attending discrepancies, speech recognition inaccuracies, and large workload. Large language models, such as GPT-4 (ChatGPT; OpenAI), may assist in generating reports. Purpose To assess effectiveness of GPT-4 in identifying common errors in radiology reports, focusing on performance, time, and cost-efficiency. Materials and Methods In this retrospective study, 200 radiology reports (radiography and cross-sectional imaging [CT and MRI]) were compiled between June 2023 and December 2023 at one institution. There were 150 errors from five common error categories (omission, insertion, spelling, side confusion, and other) intentionally inserted into 100 of the reports and used as the reference standard. Six radiologists (two senior radiologists, two attending physicians, and two residents) and GPT-4 were tasked with detecting these errors. Overall error detection performance, error detection in the five error categories, and reading time were assessed using Wald χ2 tests and paired-sample t tests. Results GPT-4 (detection rate, 82.7%;124 of 150; 95% CI: 75.8, 87.9) matched the average detection performance of radiologists independent of their experience (senior radiologists, 89.3% [134 of 150; 95% CI: 83.4, 93.3]; attending physicians, 80.0% [120 of 150; 95% CI: 72.9, 85.6]; residents, 80.0% [120 of 150; 95% CI: 72.9, 85.6]; P value range, .522-.99). One senior radiologist outperformed GPT-4 (detection rate, 94.7%; 142 of 150; 95% CI: 89.8, 97.3; P = .006). GPT-4 required less processing time per radiology report than the fastest human reader in the study (mean reading time, 3.5 seconds ± 0.5 [SD] vs 25.1 seconds ± 20.1, respectively; P < .001; Cohen d = -1.08). The use of GPT-4 resulted in lower mean correction cost per report than the most cost-efficient radiologist ($0.03 ± 0.01 vs $0.42 ± 0.41; P < .001; Cohen d = -1.12). Conclusion The radiology report error detection rate of GPT-4 was comparable with that of radiologists, potentially reducing work hours and cost. © RSNA, 2024 See also the editorial by Forman in this issue.

RASopathies for Radiologists.

RASopathies are a heterogeneous group of genetic syndromes caused by germline mutations in a group of genes that encode components or regulators of the Ras/mitogen-activated protein kinase (MAPK) signaling pathway. RASopathies include neurofibromatosis type 1, Legius syndrome, Noonan syndrome, Costello syndrome, cardiofaciocutaneous syndrome, central conducting lymphatic anomaly, and capillary malformation-arteriovenous malformation syndrome. These disorders are grouped together as RASopathies based on our current understanding of the Ras/MAPK pathway. Abnormal activation of the Ras/MAPK pathway plays a major role in development of RASopathies. The individual disorders of RASopathies are rare, but collectively they are the most common genetic condition (one in 1000 newborns). Activation or dysregulation of the common Ras/MAPK pathway gives rise to overlapping clinical features of RASopathies, involving the cardiovascular, lymphatic, musculoskeletal, cutaneous, and central nervous systems. At the same time, there is much phenotypic variability in this group of disorders. Benign and malignant tumors are associated with certain disorders. Recently, many institutions have established multidisciplinary RASopathy clinics to address unique therapeutic challenges for patients with RASopathies. Medications developed for Ras/MAPK pathway-related cancer treatment may also control the clinical symptoms due to an abnormal Ras/MAPK pathway in RASopathies. Therefore, radiologists need to be aware of the concept of RASopathies to participate in multidisciplinary care. As with the clinical manifestations, imaging features of RASopathies are overlapping and at the same time diverse. As an introduction to the concept of RASopathies, the authors present major representative RASopathies, with emphasis on their imaging similarities and differences. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Multiple and hereditary renal tumors: a review for radiologists.

80% of renal carcinomas (RC) are diagnosed incidentally by imaging. 2-4% of "sporadic" multifocality and 5-8% of hereditary syndromes are accepted, probably with underestimation. Multifocality, young age, familiar history, syndromic data, and certain histologies lead to suspicion of hereditary syndrome. Each tumor must be studied individually, with a multidisciplinary evaluation of the patient. Nephron-sparing therapeutic strategies and a radioprotective diagnostic approach are recommended. Relevant data for the radiologist in major RC hereditary syndromes are presented: von-Hippel-Lindau, Chromosome-3 translocation, BRCA-associated protein-1 mutation, RC associated with succinate dehydrogenase deficiency, PTEN, hereditary papillary RC, Papillary thyroid cancer- Papillary RC, Hereditary leiomyomatosis and RC, Birt-Hogg-Dubé, Tuberous sclerosis complex, Lynch, Xp11.2 translocation/TFE3 fusion, Sickle cell trait, DICER1 mutation, Hereditary hyperparathyroidism and jaw tumor, as well as the main syndromes of Wilms tumor predisposition. The concept of "non-hereditary" familial RC and other malignant and benign entities that can present as multiple renal lesions are discussed.

Society of Radiologists in Ultrasound Consensus on Routine Pelvic US for Endometriosis.

Endometriosis is a prevalent and potentially debilitating condition that mostly affects individuals of reproductive age, and often has a substantial diagnostic delay. US is usually the first-line imaging modality used when patients report chronic pelvic pain or have issues of infertility, both common symptoms of endometriosis. Other than the visualization of an endometrioma, sonologists frequently do not appreciate endometriosis on routine transvaginal US images. Given a substantial body of literature describing techniques to depict endometriosis at US, the Society of Radiologists in Ultrasound convened a multidisciplinary panel of experts to make recommendations aimed at improving the screening process for endometriosis. The panel was composed of experts in the imaging and management of endometriosis, including radiologists, sonographers, gynecologists, reproductive endocrinologists, and minimally invasive gynecologic surgeons. A comprehensive literature review combined with a modified Delphi technique achieved a consensus. This statement defines the targeted screening population, describes techniques for augmenting pelvic US, establishes direct and indirect observations for endometriosis at US, creates an observational grading and reporting system, and makes recommendations for additional imaging and patient management. The panel recommends transvaginal US of the posterior compartment, observation of the relative positioning of the uterus and ovaries, and the uterine sliding sign maneuver to improve the detection of endometriosis. These additional techniques can be performed in 5 minutes or less and could ultimately decrease the delay of an endometriosis diagnosis in at-risk patients.

Chronic Nonspinal Osteomyelitis in Adults: Consensus Recommendations on Percutaneous Bone Biopsies from the Society of Academic Bone Radiologists.

The diagnosis and management of chronic nonspinal osteomyelitis can be challenging, and guidelines regarding the appropriateness of performing percutaneous image-guided biopsies to acquire bone samples for microbiological analysis remain limited. An expert panel convened by the Society of Academic Bone Radiologists developed and endorsed consensus statements on the various indications for percutaneous image-guided biopsies to standardize care and eliminate inconsistencies across institutions. The issued statements pertain to several commonly encountered clinical presentations of chronic osteomyelitis and were supported by a literature review. For most patients, MRI can help guide management and effectively rule out osteomyelitis when performed soon after presentation. Additionally, in the appropriate clinical setting, open wounds such as sinus tracts and ulcers, as well as joint fluid aspirates, can be used for microbiological culture to determine the causative microorganism. If MRI findings are positive, surgery is not needed, and alternative sites for microbiological culture are not available, then percutaneous image-guided biopsies can be performed. The expert panel recommends that antibiotics be avoided or discontinued for an optimal period of 2 weeks prior to a biopsy whenever possible. Patients with extensive necrotic decubitus ulcers or other surgical emergencies should not undergo percutaneous image-guided biopsies but rather should be admitted for surgical debridement and intraoperative cultures. Multidisciplinary discussion and approach are crucial to ensure optimal diagnosis and care of patients diagnosed with chronic osteomyelitis.

How does deep learning/machine learning perform in comparison to radiologists in distinguishing glioblastomas (or grade IV astrocytomas) from primary CNS lymphomas?: a meta-analysis and systematic review.

BACKGROUND: Several studies have been published comparing deep learning (DL)/machine learning (ML) to radiologists in differentiating PCNSLs from GBMs with equivocal results. We aimed to perform this meta-analysis to evaluate the diagnostic accuracy of ML/DL versus radiologists in classifying PCNSL versus GBM using MRI. METHODOLOGY: The study was performed in accordance with PRISMA guidelines. Data was extracted and interpreted by two researchers with 12 and 23 years' experience, respectively, and QUADAS-2 tool was used for quality and risk-bias assessment. We constructed contingency tables to derive sensitivity, specificity accuracy, summary receiver operating characteristic (SROC) curve, and the area under the curve (AUC). RESULTS: Our search identified 11 studies, of which 8 satisfied our inclusion criteria and restricted the analysis in each study to reporting the model showing highest accuracy, with a total sample size of 1159 patients. The random effects model showed a pooled sensitivity of 0.89 [95% CI:0.84-0.92] for ML and 0.82 [95% CI:0.76-0.87] for radiologists. Pooled specificity was 0.88 [95% CI: 0.84-0.91] for ML and 0.90 [95% CI: 0.81-0.95] for radiologists. Pooled accuracy was 0.88 [95% CI: 0.86-0.90] for ML and 0.86 [95% CI: 0.78-0.91] for radiologists. Pooled AUC of ML was 0.94 [95% CI:0.92-0.96]and for radiologists, it was 0.90 [95% CI: 0.84-0.93]. CONCLUSIONS: MRI-based ML/DL techniques can complement radiologists to improve the accuracy of classifying GBMs from PCNSL, possibly reduce the need for a biopsy, and avoid any unwanted neurosurgical resection of a PCNSL.

Service Improvements and Workload Increases: Royal College of Radiologists (RCR) Re-Audit of Curative Intent Radiotherapy for Non-Small Cell Lung Cancer (NSCLC).

AIMS: The Royal College of Radiologists (RCR) audit of radical radiotherapy (RR) for patients with non-small cell lung cancer (NSCLC) in 2013 concluded that there was under-treatment compared to international comparators and marked variability between cancer networks. Elderly patients were less likely to receive guideline recommended treatments. Access to technological developments was low. Various national and local interventions have since taken place. This study aims to re-assess national practice. MATERIALS AND METHODS: Radiotherapy departments completed one questionnaire for each patient started on RR for 4 weeks in January 2023. RESULTS: Ninety-three percent of centres returned data on 295 patients. RR has increased 70% since 2013 but patients on average wait 20% longer to start treatment (p = 0.02). Staging investigations were often outside a desirable timeframe (79% of PET/CT scans). Advanced planning techniques are used more frequently: 4-dimensional planning increased from 33% to 90% (P < 0.001), cone beam imaging from 67% to 97% (p < 0.001) and colleague led peer review increased from 41% to 73% (P < 0.001). CONCLUSION: There have been significant improvements in care. There has been a considerable increase in clinical oncology workload with evidence of stress on the system that requires additional resourcing.

Streaming Success: Harnessing Social Media for Dynamic Radiology Education.

Social media are increasingly used as tools in radiologists education. This article describes features that aid with the selection of SM platforms, and how to emulate educator roles in the digital world. In addition, we summarize best practices regarding curating and delivering stellar content, building a SM brand, and rules of professionalism when using SM in radiology education.

Workflow interruptions in an era of instant messaging: A detailed analysis.

INTRODUCTION: The complex practice environment and responsibilities incumbent on diagnostic radiologists creates a workflow susceptible to disruption. While interruptions have been shown to contribute to medical errors in the healthcare delivery environment, the exact impact on highly subspecialized services such as diagnostic radiology is less certain. One potential source of workflow disruption is the use of a departmental instant messaging system (Webex), to facilitate communications between radiology faculty, residents, fellows, and technologists. A retrospective review was conducted to quantify the frequency of interruption experienced by our neuroradiology fellows. MATERIALS AND METHODS: Data logs were gathered comprising all instant messages sent and received within the designated group chats from July 5-December 31, 2021, during weekday shifts staffed by neuroradiology fellows. Interruptions per shift were calculated based on month, week, and day of the week. RESULTS: 14,424 messages were sent across 289 total shifts. The 6 fellows assigned to the main neuroradiology reading room sent 3258 messages and received 10,260 messages from technologists and other staff. There was an average of 50 interruptions per shift when examined by month (range 48-53), and 52 interruptions per shift when examined by day of the week (range 40-60). CONCLUSION: Neuroradiology fellows experience frequent interruptions from the departmental instant messaging system. These disruptions, when considered in conjunction with other non-interpretative tasks, may have negative implications for workflow efficiency, requiring iterative process improvements when incorporating new technology into the practice environment of diagnostic radiology.

Development of automatic generation system for lung nodule finding descriptions.

Worldwide, lung cancer is the leading cause of cancer-related deaths. To manage lung nodules, radiologists observe computed tomography images, review various imaging findings, and record these in radiology reports. The report contents should be of high quality and uniform regardless of the radiologist. Here, we propose an artificial intelligence system that automatically generates descriptions related to lung nodules in computed tomography images. Our system consists of an image recognition method for extracting contents-namely, bronchopulmonary segments and nodule characteristics from images-and a natural language processing method to generate fluent descriptions. To verify our system's clinical usefulness, we conducted an experiment in which two radiologists created nodule descriptions of findings using our system. Through our system, the similarity of the described contents between the two radiologists (p = 0.001) and the comprehensiveness of the contents (p = 0.025) improved, while the accuracy did not significantly deteriorate (p = 0.484).