-
Journal of Imaging Informatics in... Jul 2024This study aims to evaluate an AI model designed to automatically classify skull fractures and visualize segmentation on emergent CT scans. The model's goal is to boost...
This study aims to evaluate an AI model designed to automatically classify skull fractures and visualize segmentation on emergent CT scans. The model's goal is to boost diagnostic accuracy, alleviate radiologists' workload, and hasten diagnosis, thereby enhancing patient outcomes. Unique to this research, both pediatric and post-operative patients were not excluded, and diagnostic durations were analyzed. Our testing dataset for the observer studies involved 671 patients, with a mean age of 58.88 years and fairly balanced gender representation. Model 1 of our AI algorithm, trained with 1499 fracture-positive cases, showed a sensitivity of 0.94 and specificity of 0.87, with a DICE score of 0.65. Implementing post-processing rules (specifically Rule B) improved the model's performance, resulting in a sensitivity of 0.94, specificity of 0.99, and a DICE score of 0.63. AI-assisted diagnosis resulted in significantly enhanced performance for all participants, with sensitivity almost doubling for junior radiology residents and other specialists. Additionally, diagnostic durations were significantly reduced (p < 0.01) with AI assistance across all participant categories. Our skull fracture detection model, employing a segmentation approach, demonstrated high performance, enhancing diagnostic accuracy and efficiency for radiologists and clinical physicians. This underlines the potential of AI integration in medical imaging analysis to improve patient care.
PubMed: 38954293
DOI: 10.1007/s10278-024-01156-0 -
Japanese Journal of Radiology Jul 2024Large language models (LLMs) are rapidly advancing and demonstrating high performance in understanding textual information, suggesting potential applications in...
PURPOSE
Large language models (LLMs) are rapidly advancing and demonstrating high performance in understanding textual information, suggesting potential applications in interpreting patient histories and documented imaging findings. As LLMs continue to improve, their diagnostic abilities are expected to be enhanced further. However, there is a lack of comprehensive comparisons between LLMs from different manufacturers. In this study, we aimed to test the diagnostic performance of the three latest major LLMs (GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro) using Radiology Diagnosis Please Cases, a monthly diagnostic quiz series for radiology experts.
MATERIALS AND METHODS
Clinical history and imaging findings, provided textually by the case submitters, were extracted from 324 quiz questions originating from Radiology Diagnosis Please cases published between 1998 and 2023. The top three differential diagnoses were generated by GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro, using their respective application programming interfaces. A comparative analysis of diagnostic performance among these three LLMs was conducted using Cochrane's Q and post hoc McNemar's tests.
RESULTS
The respective diagnostic accuracies of GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro for primary diagnosis were 41.0%, 54.0%, and 33.9%, which further improved to 49.4%, 62.0%, and 41.0%, when considering the accuracy of any of the top three differential diagnoses. Significant differences in the diagnostic performance were observed among all pairs of models.
CONCLUSION
Claude 3 Opus outperformed GPT-4o and Gemini 1.5 Pro in solving radiology quiz cases. These models appear capable of assisting radiologists when supplied with accurate evaluations and worded descriptions of imaging findings.
PubMed: 38954192
DOI: 10.1007/s11604-024-01619-y -
Annals of Surgical Oncology Jul 2024With nodal surveillance increasingly used for sentinel lymph node-positive (SLN+) melanoma following the Second Multicenter Selective Lymphadenectomy Trial (MSLT-II),...
BACKGROUND
With nodal surveillance increasingly used for sentinel lymph node-positive (SLN+) melanoma following the Second Multicenter Selective Lymphadenectomy Trial (MSLT-II), high-quality nodal ultrasonography (U/S) has become a critical need. Previous work has demonstrated low utilization of MSLT-II U/S criteria to define abnormal lymph nodes requiring intervention or biopsy. To address this gap, an evidence-based synoptic template was designed and implemented in this single-center study.
METHODS
Sentinel lymph node-positive patients undergoing nodal surveillance at a tertiary cancer center from July 2017 to June 2023 were identified retrospectively. Ultrasound reporting language was analyzed for MSLT-II criteria reported and clinically actionable recommendations (e.g., normal, abnormal with recommendation for biopsy). Following a multidisciplinary design process, the synoptic template was implemented in January 2023. Postimplementation outcomes were evaluated by using U/S reports and provider surveys.
RESULTS
A total of 337 U/S studies were performed on 94 SLN+ patients, with a median of 3 U/S per patient (range 1-12). Among 42 synoptic-eligible U/S performed postimplementation, 32 U/S (76.0%) were reported synoptically. Significant increases were seen in the number of MSLT-II criteria reported (Pre 0.5 ± 0.8 vs. Post 2.5 ± 1.0, p < 0.001), and clinically actionable recommendations for abnormal findings (Pre 64.0% vs. Post 93.0%, p = 0.04). Nearly all surgeon and radiologist survey respondents were "very" or "completely" satisfied with the clinical utility of the synoptic template (90.0%).
CONCLUSIONS
Following implementation of a synoptic template, U/S reports were significantly more likely to document MSLT-II criteria and provide an actionable recommendation, increasing usefulness to providers. Efforts to disseminate this synoptic template to other centers are ongoing.
PubMed: 38954095
DOI: 10.1245/s10434-024-15630-0 -
Abdominal Radiology (New York) Jul 2024To evaluate the diagnostic performance of bowel wall enhancement for diagnosing concomitant bowel ischemia in patients with parietal pneumatosis (PI) diagnosed at...
PURPOSE
To evaluate the diagnostic performance of bowel wall enhancement for diagnosing concomitant bowel ischemia in patients with parietal pneumatosis (PI) diagnosed at abdominal CT.
MATERIALS AND METHODS
From January 1, 2012 to December 31, 2021, 226 consecutive patients who presented with PI on abdominal CT from any bowel segment were included. Variables at the time of the CT were retrospectively extracted from medical charts. CT examinations were blindly analyzed by two independent radiologists. The third reader classified all disagreement of bowel enhancement in three categories: (1) normal bowel enhancement; (2) doubtful bowel wall enhancement; (3) absent bowel wall enhancement. Multivariable logistic regression analysis was performed. Concomitant bowel ischemia was defined as requirement of bowel resection specifically due to ischemic lesion in operated patients and death from bowel ischemia in non-operated patients.
RESULTS
Overall, 78/226 (35%) patients had PI associated with concomitant bowel ischemia. At multivariate analysis, Only absence or doubtful bowel wall enhancement was associated with concomitant bowel ischemia (OR = 167.73 95%CI [23.39-4349.81], P < 0,001) and acute mesenteric ischemia associated with PP (OR = 67.94; 95%CI [5.18-3262.36], P < 0.009). Among the 82 patients who underwent a laparotomy for suspected bowel ischemia, rate of non-therapeutic laparotomy increased from 15/59 (25%), 2/6 (50%) and 16/17 (94%) when bowel wall enhancement was absent, doubtful and normal respectively.
CONCLUSION
Absence of enhancement of the bowel wall is the primary feature associated with concomitant bowel ischemia. It should be carefully assessed when PI is detected to avoid non-therapeutic laparotomy.
PubMed: 38954000
DOI: 10.1007/s00261-024-04450-1 -
Diagnostic and Interventional Radiology... Jul 2024Teleconferencing can facilitate a multidisciplinary approach to teaching radiology to medical students. This study aimed to determine whether an online learning approach...
Teleconferencing can facilitate a multidisciplinary approach to teaching radiology to medical students. This study aimed to determine whether an online learning approach enables students to appreciate the interrelated roles of radiology and other specialties during the management of different medical cases. Turkish medical students attended five 60-90-minute online lectures delivered by radiologists and other specialists from the United States and Canada through Zoom meetings between November 2020 and January 2021. Student ambassadors from their respective Turkish medical schools recruited their classmates with guidance from the course director. Students took a pretest and posttest to assess the knowledge imparted from each session and a final course survey to assess their confidence in radiology and the value of the course. A paired t-test was used to assess pretest and posttest score differences. A 4-point Likert-type scale was used to assess confidence rating differences before and after attending the course sessions. A total of 1,458 Turkish medical students registered for the course. An average of 437 completed both pre- and posttests when accounting for all five sessions. Posttest scores were significantly higher than pretest scores for each session ( < 0.001). A total of 546 medical students completed the final course survey evaluation. Students' rating of their confidence in their radiology knowledge increased after taking the course ( < 0.001). Students who took our course gained an appreciation for the interrelated roles of different specialties in approaching medical diagnoses and interpreting radiological findings. These students also reported an increased confidence in radiology topics and rated the course highly relevant and insightful. Overall, our findings indicated that multidisciplinary online education can be feasibly implemented for medical students by video teleconferencing.
PubMed: 38953312
DOI: 10.4274/dir.2024.242828 -
Nigerian Medical Journal : Journal of... 2023Oligohydramnios is defined as amniotic fluid index (AFI) less than or equal to 5cm. A borderline AFI has been defined as an AFI of 5.1cm to 8cm. The incidence of...
Comparison of the Effect of Injection Enoxaparin Versus Conventional Treatment on Amniotic Fluid Index in Borderline Oligohydramnios in Third Trimester of Pregnancy: A Randomized Control Trial in a Tertiary Care Hospital.
BACKGROUND
Oligohydramnios is defined as amniotic fluid index (AFI) less than or equal to 5cm. A borderline AFI has been defined as an AFI of 5.1cm to 8cm. The incidence of borderline AFI compared with a normal AFI (8.1cm to 18cm) is 6% to 44% in different studies. A decrease in amniotic fluid leads to serious complications for the mother and fetus. The study objective was to evaluate if an injection of Enoxaparin improves the amount of liquor in oligohydramnios in the third trimester of pregnancy.
METHODOLOGY
A randomized controlled trial was conducted at a tertiary care obstetric center, involving a total of 130 participants. Inclusion criteria include participant in 3 trimester of pregnancy, singleton pregnancy, intact amniotic membranes, and no known medical disorder. Patients with multiple pregnancies, ruptured amniotic membranes, anomalous fetuses, and known medical disorders were excluded. These participants were divided into two groups, each consisting of 65 participants. Group A received conventional treatment (intravenous fluid, tablet Aspirin, and rest in lateral position), while Group B received an injection of enoxaparin in addition to conventional treatment. AFI measurements were performed in the radiology department by radiologists using standard 4 quadrant measurements, twice weekly after the initiation of the treatment. The weight of the baby noted at birth and admission to neonatal intensive care was noted to assess the health of the neonate. Data was analyzed on SPSS (statistical package for social sciences) version 23.
RESULTS
In group A, the AFI increased after treatment in 47(72.3%) patients, remained static in 6(9.2%) patients, and decreased in 12(18.4%) patients. Whereas in group B, AFI increased in 31(68.8%) patients and decreased in 14(31.3%) patients, p= 0.334.
CONCLUSION
The findings in the current study did not demonstrate any significant effect of the use of injection enoxaparin in improving borderline oligohydramnios. Further research is needed to apply this research to the general population.
PubMed: 38952876
DOI: 10.60787/NMJ-64-4-319 -
Frontiers in Public Health 2024Occupational stress and job satisfaction significantly impact the well-being and performance of healthcare professionals, including radiologists. Understanding the...
BACKGROUND
Occupational stress and job satisfaction significantly impact the well-being and performance of healthcare professionals, including radiologists. Understanding the complex interplay between these factors through network analysis can provide valuable insights into intervention strategies to enhance workplace satisfaction and productivity.
METHOD
In this study, a convenience sampling method was used to recruit 312 radiologists for participation. Data on socio-demographic characteristics, job satisfaction measured by the Minnesota job satisfaction questionnaire revised short version (MJSQ-RSV), and occupational stress assessed using the occupational stress scale. Network analysis was employed to analyze the data in this study.
RESULTS
The network analysis revealed intricate patterns of associations between occupational stress and job satisfaction symptoms among radiologists. Organizational management and occupational interests emerged as crucial nodes in the network, indicating strong relationships within these domains. Additionally, intrinsic satisfaction was identified as a central symptom with high connectivity in the network structure. The stability analysis demonstrated robustness in the network edges and centrality metrics, supporting the reliability of the findings.
CONCLUSION
This study sheds light on the complex relationships between occupational stress and job satisfaction in radiologists, offering valuable insights for targeted interventions and support strategies to promote well-being and job satisfaction in healthcare settings.
Topics: Humans; Job Satisfaction; Female; Male; Adult; Surveys and Questionnaires; Occupational Stress; Middle Aged; Radiologists; Workplace
PubMed: 38952733
DOI: 10.3389/fpubh.2024.1411688 -
Cureus Jun 2024Introduction Disparities in access to breast cancer screening led to the creation of the Linda Fenner 3D Mobile Mammography Center (LFMMC), successfully increasing...
Introduction Disparities in access to breast cancer screening led to the creation of the Linda Fenner 3D Mobile Mammography Center (LFMMC), successfully increasing screening for uninsured women in Miami-Dade. However, a higher-than-expected rate of inconclusive mammograms (Breast Imaging-Reporting and Data System (BI-RADS) 0) was found, which could lead to unnecessary procedures, stress, costs, and radiation. Methods In this retrospective cross-sectional study, we analyzed data from 3,044 uninsured women aged over 40 (younger if positive family history of breast cancer) from Miami-Dade without breast symptoms or breast cancer history. Women's demographic characteristics, primary language spoken, body mass index (BMI), use of hormone replacement therapy and birth control, history of benign biopsy, breast surgery, family breast cancer, and menopausal status were assessed as potential risk factors for an inconclusive (BI-RADS 0) screening mammogram result. Multivariable logistic regression analyses were used to evaluate associations. Results The average age of women was 51 years (SD = 9); 59% were White, and 30% were African American. The overall frequency of BI-RADS 0 was 35%. Higher odds of BI-RADS 0 were found for women who were younger, single, premenopausal, and with benign biopsy history. Conversely, obesity and breast implant history decreased the odds of BI-RADS 0. Conclusion We found a high frequency of BI-RADS 0 in the LFMMC sample. Potential reasons include a higher risk for breast cancer or a younger sample of women screened. Future research should explore radiologists' reasoning for assigning BI-RADS 0 results and testing alternative screening strategies for younger women.
PubMed: 38952599
DOI: 10.7759/cureus.61495 -
Scientific Reports Jul 2024Spinal magnetic resonance (MR) scans are a vital tool for diagnosing the cause of back pain for many diseases and conditions. However, interpreting clinically useful...
Spinal magnetic resonance (MR) scans are a vital tool for diagnosing the cause of back pain for many diseases and conditions. However, interpreting clinically useful information from these scans can be challenging, time-consuming and hard to reproduce across different radiologists. In this paper, we alleviate these problems by introducing a multi-stage automated pipeline for analysing spinal MR scans. This pipeline first detects and labels vertebral bodies across several commonly used sequences (e.g. T1w, T2w and STIR) and fields of view (e.g. lumbar, cervical, whole spine). Using these detections it then performs automated diagnosis for several spinal disorders, including intervertebral disc degenerative changes in T1w and T2w lumbar scans, and spinal metastases, cord compression and vertebral fractures. To achieve this, we propose a new method of vertebrae detection and labelling, using vector fields to group together detected vertebral landmarks and a language-modelling inspired beam search to determine the corresponding levels of the detections. We also employ a new transformer-based architecture to perform radiological grading which incorporates context from multiple vertebrae and sequences, as a real radiologist would. The performance of each stage of the pipeline is tested in isolation on several clinical datasets, each consisting of 66 to 421 scans. The outputs are compared to manual annotations of expert radiologists, demonstrating accurate vertebrae detection across a range of scan parameters. Similarly, the model's grading predictions for various types of disc degeneration and detection of spinal metastases closely match those of an expert radiologist. To aid future research, our code and trained models are made publicly available.
Topics: Humans; Magnetic Resonance Imaging; Spinal Diseases; Spine; Intervertebral Disc Degeneration; Image Processing, Computer-Assisted; Image Interpretation, Computer-Assisted
PubMed: 38951574
DOI: 10.1038/s41598-024-64580-w -
Cardiovascular and Interventional... Jul 2024Imaging plays an important role in the identification and assessment of clinically suspected venous pathology. The purpose of this article is to review the spectrum of... (Review)
Review
Imaging plays an important role in the identification and assessment of clinically suspected venous pathology. The purpose of this article is to review the spectrum of image-based diagnostic tools used in the investigation of suspected deep vein disease, both obstructive (deep vein thrombosis and post-thrombotic vein changes) as well as insufficiency (e.g., compression syndromes and pelvic venous insufficiency). Additionally, specific imaging modalities are used for the treatment and during clinical follow-up. The use of duplex ultrasound, magnetic resonance venography, computed tomography venography and intravascular ultrasound as well as conventional venography will be discussed in this pictorial review.
PubMed: 38951251
DOI: 10.1007/s00270-024-03785-y