Unveiling the potential of strain elastography in perihilar cholangiocarcinoma biopsies.

PURPOSE: This study was conducted to investigate the effectiveness of strain elastography in guiding precise and sufficient tissue sampling for perihilar cholangiocarcinoma (CCA) biopsies. METHODS: Our retrospective analysis included 23 liver biopsies conducted between March 2019 and July 2022 for suspected perihilar CCA. An experienced radiologist performed the biopsies via an ultrasound machine with elastography configuration. Tissue stiffness color maps were used for guiding when the biopsies were performed. Strain index value calculations were made by radiologists on recorded images. RESULTS: Patient demographics revealed a mean age of 65.17 ± 9.25 years, with a gender distribution of six females and 17 males. Gray-scale examinations unveiled diverse echogenic characteristics in liver lesions. Elastography-guided biopsies demonstrated no need for repeats, while gray-scale biopsies necessitated re-biopsy in four patients, resulting in cholangiocarcinoma diagnosis (P = 0.037). Strain index values showcased strong inter- and intra-observer agreements (P < 0.001). Notably, no post-biopsy complications emerged in either study group. CONCLUSION: The diagnostic advantage of elastography, particularly in enhancing accuracy in challenging isoechoic lesions, was demonstrated, although the substantial overlap between strain index values of benign and malignant liver masses limits clinical usefulness of this technique.

Elevating healthcare through artificial intelligence: analyzing the abdominal emergencies data set (TR_ABDOMEN_RAD_EMERGENCY) at TEKNOFEST-2022.

OBJECTIVES: The artificial intelligence competition in healthcare at TEKNOFEST-2022 provided a platform to address the complex multi-class classification challenge of abdominal emergencies using computer vision techniques. This manuscript aimed to comprehensively present the methodologies for data preparation, annotation procedures, and rigorous evaluation metrics. Moreover, it was conducted to introduce a meticulously curated abdominal emergencies data set to the researchers. METHODS: The data set underwent a comprehensive central screening procedure employing diverse algorithms extracted from the e-Nabiz (Pulse) and National Teleradiology System of the Republic of Türkiye, Ministry of Health. Full anonymization of the data set was conducted. Subsequently, the data set was annotated by a group of ten experienced radiologists. The evaluation process was executed by calculating F1 scores, which were derived from the intersection over union values between the predicted bounding boxes and the corresponding ground truth (GT) bounding boxes. The establishment of baseline performance metrics involved computing the average of the highest five F1 scores. RESULTS: Observations indicated a progressive decline in F1 scores as the threshold value increased. Furthermore, it could be deduced that class 6 (abdominal aortic aneurysm/dissection) was relatively straightforward to detect compared to other classes, with class 5 (acute diverticulitis) presenting the most formidable challenge. It is noteworthy, however, that if all achieved outcomes for all classes were considered with a threshold of 0.5, the data set's complexity and associated challenges became pronounced. CONCLUSION: This data set's significance lies in its pioneering provision of labels and GT-boxes for six classes, fostering opportunities for researchers. CLINICAL RELEVANCE STATEMENT: The prompt identification and timely intervention in cases of emergent medical conditions hold paramount significance. The handling of patients' care can be augmented, while the potential for errors is minimized, particularly amidst high caseload scenarios, through the application of AI. KEY POINTS: • The data set used in artificial intelligence competition in healthcare (TEKNOFEST-2022) provides a 6-class data set of abdominal CT images consisting of a great variety of abdominal emergencies. • This data set is compiled from the National Teleradiology System data repository of emergency radiology departments of 459 hospitals. • Radiological data on abdominal emergencies is scarce in literature and this annotated competition data set can be a valuable resource for further studies and new AI models.

Artificial Intelligence in Healthcare Competition (TEKNOFEST-2021): Stroke Data Set.

OBJECTIVE: The artificial intelligence competition in healthcare was organized for the first time at the annual aviation, space, and technology festival (TEKNOFEST), Istanbul/Türkiye, in September 2021. In this article, the data set preparation and competition processes were explained in detail; the anonymized and annotated data set is also provided via official website for further research. MATERIALS AND METHODS: Data set recorded over the period covering 2019 and 2020 were centrally screened from the e-Pulse and Teleradiology System of the Republic of Türkiye, Ministry of Health using various codes and filtering criteria. The data set was anonymized. The data set was prepared, pooled, curated, and annotated by 7 radiologists. The training data set was shared with the teams via a dedicated file transfer protocol server, which could be accessed using private usernames and passwords given to the teams under a nondisclosure agreement signed by the representative of each team. RESULTS: The competition consisted of 2 stages. In the first stage, teams were given 192 digital imaging and communications in medicine images that belong to 1 of 3 possible categories namely, hemorrhage, ischemic, or non-stroke. Teams were asked to classify each image as either stroke present or absent. In the second stage of the competition, qualifying 36 teams were given 97 digital imaging and communications in medicine images that contained hemorrhage, ischemia, or both lesions. Among the employed methods, Unet and DeepLabv3 were the most frequently observed ones. CONCLUSION: Artificial intelligence competitions in healthcare offer good opportunities to collect data reflecting various cases and problems. Especially, annotated data set by domain experts is more valuable.

Deep Learning-Based Brain Hemorrhage Detection in CT Reports.

Radiology reports can potentially be used to detect critical cases that need immediate attention from physicians. We focus on detecting Brain Hemorrhage from Computed Tomography (CT) reports. We train a deep learning classifier and observe the effect of using different pre-trained word representations along with domain-specific fine-tuning. We have several contributions. Firstly, we report the results of a large-scale classification model for brain hemorrhage detection from Turkish radiology reports. Second, we show the effect of fine-tuning pre-trained language models using domain-specific data on the performance. We conclude that deep learning models can be used for detecting brain Hemorrhage with reasonable accuracy and fine-tuning language models using domain-specific data to improve classification performance.

A comparison between the CS-TOF and the CTA/DSA for WEB device management.

PURPOSE: There is no study on the role of three-dimensional compressed sensing time of flight MR angiography (3D-CS-TOF) in the management of the WEB device. We evaluated the efficacy of 3-tesla 3D-CS-TOF for the management and follow-up of the WEB device implantations. MATERIALS AND METHODS: Seventy-three aneurysms of 69 patients treated with the WEB device were retrospectively examined. Morphological parameters and embolization results of the aneurysms were assessed and compared on 3D-CS-TOF, CTA, and DSA images. RESULTS: Occluded, neck remnant, and recurrent aneurysms were observed in 61 (83.6%), 7 (9.6%), and 5 (6.8%) aneurysms, respectively. Inter- and intra-reader agreement values related to aneurysm size measurements were perfect. Aneurysms size, age, and proximal vessel tortuosity were negatively correlated with the visibility of the aneurysms and parent vessels on 3D-CS-TOF images (p = 0.043; p = 0.032; p < 0.001, respectively). Subarachnoid hemorrhage and age are associated with 3D-CS-TOF artifacts (p = 0.031; p = 0.005, respectively). 3D-CS-TOF findings are in perfect agreement with DSA or CT angiography (CTA) results (p < 0.001). CONCLUSION: According to our results, 3D-CS-TOF can be an easy, fast, and reliable alternative for the management or follow-up of WEB assisted embolization.

Feasibility of 3D T1W sequences in contrast-material enhanced MR cisternography at 3T.

BACKGROUND: We investigated the diagnostic values and artifact severities of 3D-T1W sequences in the diagnosis of cerebrospinal fluid (CSF) leakage. METHODS: We retrospectively reviewed 3-tesla contrast-material enhanced MR cisternography exams of 22 patients with suspected CSF leakage in 4 years. The presence of the artifacts on 3D-T1W data was evaluated using a 4-point scale (0: none; 1: minimal; 2: moderate; 3: prominent). Agreements between CSF leakage results of the 3D-T1W sequences and consensus decisions were evaluated via kappa values. Artifact scores were analyzed by Fisher's exact test. RESULTS: The most compatible techniques with the consensus diagnoses were fat-saturated 3D-T1W-SPACE and 3D-T1W-VIBE sequences. The most artifact containing the 3D-T1W sequence was 3D-MPRAGE. DISCUSSION: 3D-SPACE and 3D-VIBE are more successful in evaluating CSF leakages compared to 3D-MPRAGE. 3D-SPACE has lower artifact scores compared to 3D-VIBE and 3D-MPRAGE sequences.

An international survey on AI in radiology in 1041 radiologists and radiology residents part 2: expectations, hurdles to implementation, and education.

OBJECTIVES: Currently, hurdles to implementation of artificial intelligence (AI) in radiology are a much-debated topic but have not been investigated in the community at large. Also, controversy exists if and to what extent AI should be incorporated into radiology residency programs. METHODS: Between April and July 2019, an international survey took place on AI regarding its impact on the profession and training. The survey was accessible for radiologists and residents and distributed through several radiological societies. Relationships of independent variables with opinions, hurdles, and education were assessed using multivariable logistic regression. RESULTS: The survey was completed by 1041 respondents from 54 countries. A majority (n = 855, 82%) expects that AI will cause a change to the radiology field within 10 years. Most frequently, expected roles of AI in clinical practice were second reader (n = 829, 78%) and work-flow optimization (n = 802, 77%). Ethical and legal issues (n = 630, 62%) and lack of knowledge (n = 584, 57%) were mentioned most often as hurdles to implementation. Expert respondents added lack of labelled images and generalizability issues. A majority (n = 819, 79%) indicated that AI should be incorporated in residency programs, while less support for imaging informatics and AI as a subspecialty was found (n = 241, 23%). CONCLUSIONS: Broad community demand exists for incorporation of AI into residency programs. Based on the results of the current study, integration of AI education seems advisable for radiology residents, including issues related to data management, ethics, and legislation. KEY POINTS: • There is broad demand from the radiological community to incorporate AI into residency programs, but there is less support to recognize imaging informatics as a radiological subspecialty. • Ethical and legal issues and lack of knowledge are recognized as major bottlenecks for AI implementation by the radiological community, while the shortage in labeled data and IT-infrastructure issues are less often recognized as hurdles. • Integrating AI education in radiology curricula including technical aspects of data management, risk of bias, and ethical and legal issues may aid successful integration of AI into diagnostic radiology.

An international survey on AI in radiology in 1,041 radiologists and radiology residents part 1: fear of replacement, knowledge, and attitude.

OBJECTIVES: Radiologists' perception is likely to influence the adoption of artificial intelligence (AI) into clinical practice. We investigated knowledge and attitude towards AI by radiologists and residents in Europe and beyond. METHODS: Between April and July 2019, a survey on fear of replacement, knowledge, and attitude towards AI was accessible to radiologists and residents. The survey was distributed through several radiological societies, author networks, and social media. Independent predictors of fear of replacement and a positive attitude towards AI were assessed using multivariable logistic regression. RESULTS: The survey was completed by 1,041 respondents from 54 mostly European countries. Most respondents were male (n = 670, 65%), median age was 38 (24-74) years, n = 142 (35%) residents, and n = 471 (45%) worked in an academic center. Basic AI-specific knowledge was associated with fear (adjusted OR 1.56, 95% CI 1.10-2.21, p = 0.01), while intermediate AI-specific knowledge (adjusted OR 0.40, 95% CI 0.20-0.80, p = 0.01) or advanced AI-specific knowledge (adjusted OR 0.43, 95% CI 0.21-0.90, p = 0.03) was inversely associated with fear. A positive attitude towards AI was observed in 48% (n = 501) and was associated with only having heard of AI, intermediate (adjusted OR 11.65, 95% CI 4.25-31.92, p < 0.001), or advanced AI-specific knowledge (adjusted OR 17.65, 95% CI 6.16-50.54, p < 0.001). CONCLUSIONS: Limited AI-specific knowledge levels among radiology residents and radiologists are associated with fear, while intermediate to advanced AI-specific knowledge levels are associated with a positive attitude towards AI. Additional training may therefore improve clinical adoption. KEY POINTS: • Forty-eight percent of radiologists and residents have an open and proactive attitude towards artificial intelligence (AI), while 38% fear of replacement by AI. • Intermediate and advanced AI-specific knowledge levels may enhance adoption of AI in clinical practice, while rudimentary knowledge levels appear to be inhibitive. • AI should be incorporated in radiology training curricula to help facilitate its clinical adoption.

The Greulich-Pyle and Gilsanz-Ratib atlas method versus automated estimation tool for bone age: a multi-observer agreement study.

PURPOSE: To evaluate the agreement between observers using Greulich-Pyle (GP) and Gilsanz-Ratib (GR) methods, between four specialities (radiology, pediatrics, pediatric endocrinology and pediatric radiology) and between observers and automated tool in the bone age estimation. MATERIALS AND METHODS: A total of 99 observers participated in this questionnaire-based study. BoneXpert was used for the automated tool. Experienced, senior, and junior observers were defined by their experience, and the bone age determined by experienced observers was regarded as the ground truth. Agreement between observers was evaluated using the coefficient of variance (CV) and intraclass correlation coefficient (ICC), and they were reevaluated after adding BoneXpert to the observers. Agreement of BoneXpert, the senior, and the junior observers was also evaluated using the root-mean-square-error (RMSE) values and Blant Altman method by comparing with the ground truth. RESULTS: The CV ranged from 4.98% to 22.08%. The ICC were 0.980 for GP, 0.980 for GP and BoneXpert, 0.973 for GR, and 0.976 for GR and BoneXpert, and the ICC between four specialities ranged form 0.963 to 0.990. BoneXpert tool had the lowest RMSE values (0.504 years for GP atlas). CONCLUSION: Automated bone age estimation showed comparable results with GP and GR methods and its utilization may decrease inter-observer variability.

Evaluation of pancreatic steatosis prevalence and anthropometric measurements using non-contrast computed tomography.

BACKGROUND/AIMS: Pancreatic steatosis (PS) is a subject of current interest and its prevalence has been reported to range from 16.1% to 30.7% using various radiological methods. This study aimed to evaluate PS prevalence with non-contrast computed tomography (CT). MATERIALS AND METHODS: The non-contrast CT scans taken in 2016 and 2017 in our hospital were retrospectively screened. A total of 637 cases (320 males, 317 females) were included in the study. CT number measurements were performed from three anatomic regions of the pancreas using regions of interest (ROI) of approximately 1 cm2. The cases with a <0.7 ratio of the pancreatic over splenic CT number were accepted as quantitatively steatosis-positive. Anthropometric evaluations were undertaken by determining various parameters defined on CT. RESULTS: PS was determined visually in 30.6% of the males and 29% of the females, and quantitatively in 32.8% and 30.6%, respectively. A positive agreement was determined between the quantitative and visual evaluations of steatosis (Cohen's kappa coefficient=0.587, p<0.001). Although PS was seen to be mostly diffuse, the tail region of the pancreas was determined to be the area with most steatosis. CONCLUSION: PS is usually overlooked in radiology practice but it has a clinical presentation with non-insignificant prevalence. Current radiological methods are adequate in the evaluation of PS. The determination of the cut-off values for various criteria on non-contrast CT can provide more objective evaluations.

Statistical shape analysis of hand and wrist in paediatric population on radiographs

Background/aim: The goal of this study was to compare differences in hand and wrist shapes and to evaluate these according to growth and allometry in children on radiographs related to bone age. Materials and methods: The study included 263 males and 189 females. A total of 452 left hand and wrist radiographs were retrospectively collected. Standard anatomical landmarks marked on radiographs. Results: There were seen to be significant differences in comparisons of hand and wrist shapes according to sex (P = 0.009). The most suitable model in the growth models was seen as the Gompertz growth model for both females and males (model P < 0.001). For the relationship between shape and size to evaluate allometry, significant models were obtained in females (model P = 0.017, MSE = 0.0002) and in males (model P < 0.001, MSE = 0.0002). In our study, the difference between the sexes was found mostly in the radiocarpal region. It was observed that the deformation of the carpal bones started in the distal row carpal bones. Conclusion: Significant differences were found in hand and wrist shapes according to sex. Models for growth and allometry of hand and wrist shapes were found to be significant in children.

Evaluation of Hepatic Steatosis with CT and Correlation with Anthropometric Measurements.

OBJECTIVE: The aim of the study was to evaluate hepatic steatosis in an asymptomatic group of patients with unenhanced abdominal computed tomography (CT) and to compare the results with anthropometric measurements. METHODS: The study included 617 patients aged 18-93 years, who underwent unenhanced abdominopelvic CT between January 2016 and December 2017. Three imaging criteria were used in the assessment of hepatic steatosis on CT: mean region of interest (ROI) value of measured liver lobe (40 HU ≥), mean ROI value of measured liver lobe / measured spleen mean ROI value (1 ≥), mean ROI value of measured liver lobe - mean ROI value of spleen (10 HU≥). The liver fat was quantitatively assessed both visually and using multidetector CT grading. The anthropometric measurements used were the size of the liver and spleen, abdominal anterior-posterior diameter, abdominal transverse diameter, abdominal circumference, subcutaneous adipose tissue area, and anterior, posterior, and posterolateral subcutaneous adipose tissue thickness. RESULTS: The prevalence of hepatic steatosis was 29.3% according to the visual evaluation, 29.8% according to the quantitative evaluation, 67.1% according to at least one criterion and 23.3% according to at least two criteria. A positive correlation was determined between hepatic steatosis and anthropometric measurements. Differences between the genders were observed in both hepatic steatosis and anthropometric measurements. CONCLUSION: By setting more objective criteria for evaluation, with the possibility of quantitative analysis in particular, non-contrast CT will have a more important role in assessing liver fat in the future.

Is ischemia associated with the formation of White matter lesions in migraine?

OBJECTIVE: White matter lesions (WMLs) are more common in migraine patients than in the normal population. Ischemia/hypoxia and oxidative stress are considered to play a role in WMLs formation. This study aimed to investigate ischemia-modified albumin (IMA), ferroxidase and thiol/disulfide homeostasis in migraineurs with and without WMLs. PATIENTS AND METHODS: Sixty-two migraineurs with WML, 59 migraineurs without WML and 61 controls were included in the study. All participants underwent brain MRI. WMLs was evaluated according to the Fazekas scale. IMA, ferroxidase, total thiol, native thiol and disulfide measurements were carried out in all participants. RESULTS: The IMA levels were higher in the migraine groups compared to the control group (p < 0.001) and in the WML group compared to non-WML (p < 0.001). The total and native thiol levels were higher in the non-WML group compared to the control and WML groups (p < 0.001 for both). The disulfide levels were similar between the control and non-WML groups, but they were significantly lower in the WML group compared to the control and non-WML groups. There was no significant difference between the groups in terms of the ferroxidase levels (p = 0.092). The thiol/disulfide, IMA and ferroxidase levels were not significantly correlated with the frequency and duration of attacks, severity of pain and disability due to migraine. CONCLUSION: Increased serum IMA levels in migraineurs point to the role of ischemia/hypoxia, and increased total thiol and decreased disulfide levels indicate an oxidant/antioxidant imbalance in migraine. Ischemia/hypoxia may play a role in WMLs formation in migraine.

Computed Tomography Measurements of Hepatic Steatosis in Cholelitihiasis and Cholecystectomy Cases Using Unenhanced Images.

INTRODUCTION: Computed tomography (CT) measurements of hepatic steatosis can be performed using unenhanced CT images. The purpose of this study was to assess the occurrence of hepatic steatosis using unenhanced CT images for patients undergoing cholecystectomy or having cholelithiasis. METHODS: A total of 143 unenhanced CT cases from a single centre were retrospectively examined. The CT number of liver, ratio of CT number of liver to spleen, and CT number of liver minus CT number of spleen were measured in three groups: (1) patients undergoing cholecystectomy, (2) patients having cholelithiasis, and (3) control group. Abdominal circumference, anterior subcutaneous fat tissue thickness, and body mass index were obtained. RESULTS: Mean CT number of liver was significantly different between the group of patients with cholecystectomy and cholelithiasis and the control group (P < .001) and also between cases of cholecystectomy and cholelithiasis (P = .041), with the lowest CT number of liver in the cholecystectomy group. The mean CT number of liver minus CT number of spleen and mean CT number (liver/spleen) ratios, evaluated separately for both lobes, were not different comparing the cholelithiasis and cholecystectomy groups. The mean CT number of liver minus CT number of spleen and mean CT number (liver/spleen) ratios differed significantly between the control group and both patient groups (P < .001). Positive correlations were identified between abdominal circumference, subcutaneous fat depth, body mass index, and liver size and hepatic steatosis. CONCLUSION: There was an increased occurrence of hepatic steatosis in patients who have undergone a cholecystectomy compared with patients treated for cholelithiasis and the control group.

Evaluation of major complications associated with percutaneous CT-guided biopsy of lung nodules below 3 cm

Background/aim: The aim of this study was to evaluate retrospectively the incidence and risk factors for the serious complications of pneumothorax and/or parenchymal haemorrhage occurring after computed tomography (CT) guided transthoracic biopsy. Materials and methods: The relation between the incidence of pneumothorax and parenchymal haemorrhage due to biopsy, age, sex, lesion localization, lesion size, duration of the procedure, depth of lesion, number of pleural insertions of the biopsy needle and pathology results were statistically evaluated. Results: Between 2016 and 2017, 309 cases with lesions below 3 cm in diameter of a total of 768 (40.2%) CT-guided chest biopsy patients were selected for retrospective review. The rate of pneumothorax and parenchymal haemorrhage was 18.1% (59/309) and 51% (158/309), respectively post biopsy. The number of needle pleural insertions was correlated with the development of pneumothorax (P = 0.002). At regression analysis, for parenchymal haemorrhage, lesion depth (P < 0.001) and total procedure time (p=0.036) were determined as the most important independent risk factors. Conclusion: Pneumothorax and parenchymal haemorrhage are common complications after CT-guided percutaneous biopsy. The minimum number of needle-pleural insertions, the optimal access route to the lesion and as quick as possible biopsy procedure should be selected to reduce the risk of pneumothorax and parenchymal haemorrhage.

The efficacy of the 3-dimensional vibe-caipirinha-dixon technique in the evaluation of pancreatic steatosis

Background/aim: CAIPIRINHA is a new technique in abdominal imaging. Pancreatic steatosis (PS) is a subject of increasing scientific interest. The aim of this study was to investigate the efficacy of the isotropic 3D-VIBE- CAIPIRINHA -DIXON technique on a new generation 3-tesla MR unit in the evaluation of PS. Materials and methods: In this retrospective study, the imaging findings of 49 patients with PS and 41 control subjects were examined. The pancreas-to-spleen ratio (PSR), pancreas-to-muscle ratio (PMR), and pancreatic signal intensity index (PSII) were defined as 3 new parameters and these indexes were calculated from the in-phase/out of phase 3D-VIBE- CAIPIRINHA-DIXON images. Results: The PSR, PMR, and PSII values were significantly different between the patient and control groups (P = 0.001, P = 0.009, P < 0.001, respectively). Statistically significant differences were observed between patient and control groups for ROI measurements of fatty areas on these sequences/images: subtraction (in-out) (P < 0.001), T2W HASTE (P < 0.001), DIXON-fat (P < 0.001), fat-suppressed T1W (P = 0.002), and subtraction (out-in) (P = 0.010). Conclusion: Evaluation of PS with the 3D-VIBE-CAIPIRINHA-DIXON technique can be made rapidly and effectively.

Investigation of the Relationship between Fatty Pancreas and Cholecystectomy Using Noncontrast Computed Tomography.

INTRODUCTION: Fatty pancreas, which can be evaluated with radiological methods, is a frequently overlooked finding. The aim of this study was to use noncontrast computed tomography (CT) to evaluate whether there was a relationship between fatty pancreas and cholecystectomy, similar to the relationship between fatty liver and cholecystectomy, which has been previously shown in literature. METHODS: The study included 46 cases who underwent cholecystectomy and 74 age- and gender-matched control subjects. All the cases were scanned with noncontrast CT. Regions of interest were defined in the liver and pancreas, and density measurements were taken from four anatomic regions in the liver and three anatomic regions in the pancreas by two experienced radiologists in the same session with consensus. Cases in which the pancreas density was evaluated as <0.7 of the spleen density were accepted as quantitatively steatosis positive. In addition, visual evaluations were made, and anthropometric measurements were taken. RESULTS: Density and ratio values measured at the level of the pancreas body were determined to be statistically significantly lower in the cholecystectomy group than in the control group (P = .045 and P = .025, respectively). In the visual evaluation of fatty pancreas, the frequency 27 of 46 (50.7%) in the cholecystectomy group was statistically significantly higher than that of the control group at 27 of 74 (36.5%) (P = .017). Although the quantitative assessment showed that pancreatic steatosis frequency was higher in the cholecystectomy group, there was no statistically significant difference between the groups (P = .543). CONCLUSION: Using CT in the present study, higher rates of fatty liver and fatty pancreas were determined in cholecystectomy cases than in the normal population. Longitudinal studies of an extensive population will be able to better evaluate the relationship between cholecystectomy and fatty pancreas.