BACKGROUND: Pancreatic cystic lesions (PCLs) are frequent and underreported incidental findings on computed tomography (CT) scans and can evolve to pancreatic cancer-the most lethal cancer, with less than 5 months of life expectancy.
OBJECTIVE: The aim of this study was to develop and validate an artificial deep neural network (attention gate U-Net, also named \"AGNet\") for automated detection of PCLs. This kind of technology can help radiologists to cope with an increasing demand of cross-sectional imaging tests and increase the number of PCLs incidentally detected, thus increasing the early detection of pancreatic cancer.
METHODS: We adapted and evaluated an algorithm based on an attention gate U-Net architecture for automated detection of PCL on CTs. A total of 335 abdominal CTs with PCLs and control cases were manually segmented in 3D by 2 radiologists with over 10 years of experience in consensus with a board-certified radiologist specialized in abdominal radiology. This information was used to train a neural network for segmentation followed by a postprocessing pipeline that filtered the results of the network and applied some physical constraints, such as the expected position of the pancreas, to minimize the number of false positives.
RESULTS: Of 335 studies included in this study, 297 had a PCL, including serous cystadenoma, intraductal pseudopapillary mucinous neoplasia, mucinous cystic neoplasm, and pseudocysts . The Shannon Index of the chosen data set was 0.991 with an evenness of 0.902. The mean sensitivity obtained in the detection of these lesions was 93.1% (SD 0.1%), and the specificity was 81.8% (SD 0.1%).
CONCLUSIONS: This study shows a good performance of an automated artificial deep neural network in the detection of PCL on both noncontrast- and contrast-enhanced abdominal CT scans.

OBJECTIVE: To noninvasively detect prostate cancer and predict the Gleason grade using single-modality T2-weighted imaging with a deep-learning approach.
METHODS: Patients with prostate cancer, confirmed by histopathology, who underwent magnetic resonance imaging examinations at our hospital during September 2015-June 2022 were retrospectively included in an internal dataset. An external dataset from another medical center and a public challenge dataset were used for external validation. A deep-learning approach was designed for prostate cancer detection and Gleason grade prediction. The area under the curve (AUC) was calculated to compare the model performance.
RESULTS: For prostate cancer detection, the internal datasets comprised data from 195 healthy individuals (age: 57.27 ± 14.45 years) and 302 patients (age: 72.20 ± 8.34 years) diagnosed with prostate cancer. The AUC of our model for prostate cancer detection in the validation set (n = 96, 19.7%) was 0.918. For Gleason grade prediction, datasets comprising data from 283 of 302 patients with prostate cancer were used, with 227 (age: 72.06 ± 7.98 years) and 56 (age: 72.78 ± 9.49 years) patients being used for training and testing, respectively. The external and public challenge datasets comprised data from 48 (age: 72.19 ± 7.81 years) and 91 patients (unavailable information on age), respectively. The AUC of our model for Gleason grade prediction in the training set (n = 227) was 0.902, whereas those of the validation (n = 56), external validation (n = 48), and public challenge validation sets (n = 91) were 0.854, 0.776, and 0.838, respectively.
CONCLUSIONS: Through multicenter dataset validation, our proposed deep-learning method could detect prostate cancer and predict the Gleason grade better than human experts.
UNASSIGNED: Precise prostate cancer detection and Gleason grade prediction have great significance for clinical treatment and decision making.
CONCLUSIONS: Prostate segmentation is easier to annotate than prostate cancer lesions for radiologists. Our deep-learning method detected prostate cancer and predicted the Gleason grade, outperforming human experts. Non-invasive Gleason grade prediction can reduce the number of unnecessary biopsies.

UNASSIGNED: Imaging is indispensable to the diagnostic and treatment process. By facilitating access to rapid timely image interpretation, teleradiology plays a prominent role in improving access, quality of critical care, and management of the patients in intensive care units (ICU). The aim of the study is to investigate the role of teleradiology in ICU patient care and management.
UNASSIGNED: In our study, a total of 22,081 studies of a cohort of 14,900 patients which had been transmitted from intensive care units of 80 hospitals located across the United States of America through a teleradiology reporting workflow, were interpreted by the American Board Certified Radiologists empanelled by a teleradiology service provider, located in India.
UNASSIGNED: Among all modalities, the highest percentage of studies performed were computed tomography scan (47%) followed by radiographs (37.22%). Out of 22,081 cases under the study, 16,582 cases were reported during nighttime with a mean turnaround time (TAT) of 46.66 minutes 95% CI (46.27-47.04) while 5,499 cases were reported during daytime with a mean TAT of 44.66 minutes 95% CI (45.40-43.92).
UNASSIGNED: Setting up teleradiology service connectivity with a teleradiology service provider located in India, providing high-quality diagnostic interpretations and lower turnaround time with the ICUs in the US hospitals reduces the interval to intervention time and leads to efficient patient care management. Moreover, it also provides time advantage for US hospitals when on-site radiologists at night are unable to provide immediate coverage.
UNASSIGNED: The ICU teleradiology service model designed in the study would greatly help overcome the shortfall of radiologists in the hospitals, provide better patient management and care by quality reporting in short turnaround time, not only during daytime but also in the night hours or on holidays when on-site radiologists are unable to provide immediate coverage.
UNASSIGNED: Rao P, Mathur N, Kalyanpur A. Utilization of Teleradiology by Intensive Care Units: A Cohort Study. Indian J Crit Care Med 2024;28(1):20-25.

OBJECTIVE: The aim of this study was to investigate associations between workforce and workload among radiologists in Taiwan.
METHODS: Data for the period 2000-2020 describing the demand for imaging services and radiologists have been obtained from databases and statistical reports of the Ministry of Health and Welfare. The future demand for radiologists was based on Taiwanese people aged 40 and over.
RESULTS: The workforce of Taiwan\'s radiologists has increased by 6 % annually over the past 20 years (from 450 to 993), performing 2125, 3202 and 3620 monthly examinations (mainly conventional radiography and CT) in medical centers, regional hospitals and district hospitals. Between 2000 and 2020, the use of CT and MRI increased by more than 3.5 times. Demand for interventional radiology also increased by 1.77 times, 2.25 times, and 5 times, respectively. To maintain this volume of services in 2040, at least 1168 radiologists are needed, about 1.18 times more in 2020.
CONCLUSIONS: Taiwan has 2.4 to 2.9 times fewer radiologists than the United States and 3 times fewer than Europe, while the annual workload is approximately 2 to 3.4 times greater than that of the United States and 1.4 to 2.5 times greater than that of the United Kingdom. This report may serve as a reference for policy makers who address the challenges of the growing workload among radiologists in countries of similar situations.

Chondral lesions (CL) in the ankle following acute fractures are frequently overlooked immediately after the injury or diagnosed at a later stage, leading to persistent symptoms despite successful surgery. The literature presents a wide range of discrepancies in the reported incidence of CLs in acute ankle fractures. The objective of this prospective study is to provide a precise assessment of the occurrence of chondral lesions (CLs) in acute ankle fractures through MRI scans conducted immediately after the trauma and prior to scheduled surgery. Furthermore, the study aims to highlight the disparities in the interpretation of these MRI scans, particularly concerning the size and extent of chondral damage, between radiologists and orthopedic surgeons. Over the period of three years, all patients presenting with an unstable ankle fracture that underwent operative treatment were consecutively included in this single-center prospective study. Preoperative MRIs were obtained for all included patients within 10 days of the trauma and were evaluated by a trauma surgeon and a radiologist specialized in musculoskeletal MRI blinded to each other\'s results. The location of the lesions was documented, as well as their size and ICRS classification. Correlations and kappa coefficients as well as the p-values were calculated. A total of 65 patients were included, with a mean age of 41 years. The evaluation of the orthopedic surgeon showed CLs in 52.3% of patients. CLs occurred mainly on the tibial articular surface (70.6%). Most talar lesions were located laterally (11.2%). The observed CLs were mainly ICRS grade 4. According to the radiologist, 69.2% of the patients presented with CLs. The most common location was the talar dome (48.9%), especially laterally. Most detected CLs were graded ICRS 3a. The correlation between the two observers was weak/fair regarding the detection and classification of CLs and moderate regarding the size of the detected CLs. To enhance the planning of surgical treatment for ankle chondral lesions (CLs), it may be beneficial to conduct an interdisciplinary preoperative assessment of the performed scans. This collaborative approach can optimize the evaluation of ankle CLs and improve overall treatment strategies.

OBJECTIVE: To evaluate the diagnostic performance of a commercial artificial intelligence (AI)-assisted ultrasonography (US) for thyroid nodules and to validate its value in real-world medical practice.
METHODS: From March 2021 to July 2021, 236 consecutive patients with 312 suspicious thyroid nodules were prospectively enrolled in this study. One experienced radiologist performed US examinations with a real-time AI system (S-Detect). US images and AI reports of the nodules were recorded. Nine residents and three senior radiologists were invited to make a \"benign\" or \"malignant\" diagnosis based on recorded US images without knowing the AI reports. After referring to AI reports, the diagnosis was made again. The diagnostic performance of AI, residents, and senior radiologists with and without AI reports were analyzed.
RESULTS: The sensitivity, accuracy, and AUC of the AI system were 0.95, 0.84, and 0.753, respectively, and were not statistically different from those of the experienced radiologists, but were superior to those of the residents (all p < 0.01). The AI-assisted resident strategy significantly improved the accuracy and sensitivity for nodules ≤ 1.5 cm (all p < 0.01), while reducing the unnecessary biopsy rate by up to 27.7% for nodules > 1.5 cm (p = 0.034).
CONCLUSIONS: The AI system achieved performance, for cancer diagnosis, comparable to that of an average senior thyroid radiologist. The AI-assisted strategy can significantly improve the overall diagnostic performance for less-experienced radiologists, while increasing the discovery of thyroid cancer ≤ 1.5 cm and reducing unnecessary biopsies for nodules > 1.5 cm in real-world medical practice.
CONCLUSIONS: • The AI system reached a senior radiologist-like level in the evaluation of thyroid cancer and could significantly improve the overall diagnostic performance of residents. • The AI-assisted strategy significantly improved ≤ 1.5 cm thyroid cancer screening AUC, accuracy, and sensitivity of the residents, leading to an increased detection of thyroid cancer while maintaining a comparable specificity to that of radiologists alone. • The AI-assisted strategy significantly reduced the unnecessary biopsy rate for thyroid nodules > 1.5 cm by the residents, while maintaining a comparable sensitivity to that of radiologists alone.

UNASSIGNED: Posterior cerebral ischemic stroke and its underlying causes can be easily misdiagnosed in routine practice. Therefore, more than a third of positive cases can be easily missed during routine CT image reporting unless expert neuroimaging radiologists carefully report it.
UNASSIGNED: To assess the inter-rater agreement level between senior residents and general radiologists and a specialized expert neuroradiologist when detecting and diagnosing posterior cerebral circulation calcification.
UNASSIGNED: This was a cross-sectional observational study. A total of fifteen senior radiology residents (SRRs) and fifteen general radiologists (GRs) at four different hospitals in Riyadh, Saudi Arabia, were included in the study. A total of four CT-scanned brain cases with the presence of posterior circulation calcification (PCC) with different degrees of severity and one brain case with negative PCC were selected. These cases were predefined by expert neuroradiologists at our center. The cases were uploaded into the picture archiving and communication systems (PACS) at four different centers as outsider cases. These cases were then randomly assigned to the participating SRRs and GRs for reporting. All radiologists were blinded to the findings of the cases. Inter-observer agreement was assessed using the weighted kappa coefficient of agreement (k) between the two groups.
UNASSIGNED: The cerebral calcification misdiagnosis rate for the SRRs and GRs was > 93% for most of the positive cases. There was 1) poor inter-observer agreement between the SRRs and GRs for the detection of severe posterior cerebral calcification(PCC) in a negative stroke case (agreement for misdiagnosis, k = 0.93; correct diagnosis, k = 0.00), 2) poor inter-observer agreement for mild PCC in a negative stroke case (agreement for misdiagnosis, k = 0.93; correct diagnosis, k = 0.00), 3) moderate PCC in a positive posterior stroke case (agreement for misdiagnosis, k = 0.92; correct diagnosis, k = 0.00), and 4) poor interobserver agreement for severe PCC in a positive posterior cerebral stroke case (agreement for misdiagnosis, k = 0.846; correct diagnosis, k = 0.00). There was excellent agreement between the SRRs and GRs when reporting negative cases of PCC and stroke.
UNASSIGNED: Our study concluded that most of the SRRs and GRs missed the diagnosis of posterior cerebral calcification in the presented cases.

Early detection of lung nodules is essential for preventing lung cancer. However, the number of radiologists who can diagnose lung nodules is limited, and considerable effort and time are required. To address this problem, researchers are investigating the automation of deep-learning-based lung nodule detection. However, deep learning requires large amounts of data, which can be difficult to collect. Therefore, data collection should be optimized to facilitate experiments at the beginning of lung nodule detection studies. We collected chest computed tomography scans from 515 patients with lung nodules from three hospitals and high-quality lung nodule annotations reviewed by radiologists. We conducted several experiments using the collected datasets and publicly available data from LUNA16. The object detection model, YOLOX was used in the lung nodule detection experiment. Similar or better performance was obtained when training the model with the collected data rather than LUNA16 with large amounts of data. We also show that weight transfer learning from pre-trained open data is very useful when it is difficult to collect large amounts of data. Good performance can otherwise be expected when reaching more than 100 patients. This study offers valuable insights for guiding data collection in lung nodules studies in the future.

A cross-sectional inter-examiner agreement and reliability study on fresh frozen cadaver shoulders.
Musculoskeletal ultrasound (MSU) is frequently used by physical therapists and radiologists to improve specific diagnosis in rotator cuff related pathology. The evaluation of the rotator cable seems to be important as stabilizing structure when cuff tears occur.
To evaluate the inter-examiner agreement and reliability of MSU of the shoulder to detect rotator cuff-pathology and the involvement of the rotator cable in comparison to \"dissection\".
Physical therapists, a radiologist and an orthopedic surgeon (dissection) investigated 40 fresh frozen cadaver shoulders in order to detect shoulder pathology including rotator cable involvement. Examiners were blinded to each other\'s findings.
We found a strong and significant agreement between the raters: PTs, the radiologist and the dissector in this cadaver study for all rotator cuff, the long head of the biceps pathologies and in detecting abnormalities of the rotator cable. The kappa value was substantial to (almost) perfect agreement for all diagnostic outcome categories.
This study shows that among a limited group of physical therapists, one radiologist and a dissector a strong level of agreement with kappa values from substantial to (almost) perfect in finding subacromial pathology.

BACKGROUND: Burnout amongst radiologists is common in many different institutions and is increasing day by day. To battle burnout, we have to address the root causes already recognized in published literature. Therefore, it is crucial to examine and discern important publications.
OBJECTIVE: To provide evidence-based data and trends related to burnout in radiologists so that researchers can work on it further and develop preventive strategies to overcome this problem.
METHODS: Bibliometric analysis conducted by two independent reviewers separately used Scopus Library for data extraction by using medical subject heading and International Classification of Diseases keywords. Forty-nine articles were selected for analysis after an extensive scrutiny. Statistical Package for the Social Sciences version 20 was used for analysis. Pearson correlation coefficient, Kruskal Wallis test, and Mann-Whitney U test were applied.
RESULTS: The most productive period with regards to the number of publications was between 2017 and 2019. A total of 160 authors contributed to the topic burnout among radiologists, with an average of 3.26 authors per paper. About 41.68% of the authors were female, whilst 35% of them were first authors. The co-citation analysis by author involved 188 cited authors, 13 of whom were cited at least 70 times. Only six out of forty-nine studies were funded by various government institutions and non-governmental organizations.
CONCLUSIONS: Current analysis casts a spotlight on important trends being witnessed in regard to the mental health of radiologists, including lack of funding for mental health research, narrowing of female vs male citation gap, as well as authorship and citation trends.