Value of chemical shift imaging in the evaluation of neural foramen stenosis.

Background: Chemical shift Magnetic Resonance Imaging (MRI) is often routinely acquired to assess a spectrum of spinal lesions due to its ability versatility to obtain rapid sequences at the expense of spatial resolution images. It is one of the quickest sequences to acquire at the expense of spatial resolution. Objective: In this study we assess the diagnostic efficacy of Chemical shift Magnetic Resonance Imaging (MRI) in the evaluation of Neural Foraminal stenosis. Materials and methods: Conventional T2, T1 and STIR sagittal and axial images as well as 'in' and 'out' phase chemical shift sagittal MRI sequences of 25 consecutive patients presenting with back pain and radiculopathy were reviewed. The degree of neural stenosis in the lumbar spine foramina on both sides was graded using the Lee classification on T2 and 'in' and 'out' phase MRI sequences by two independent MSK radiologists. Statistical analysis was performed using paired T-Test and Cohen's weighted kappa test was applied as a measure of agreement between the two observed raters. Results: A total of 250 lumbar neural foramina were assessed. There was substantial agreement (Cohen's weighted kappa) for both raters between 'in' and 'out' phase chemical shift sagittal MRI sequences (rater 1 = 0.699, rater 2 = 0.718), as well as good agreement between raters for both 'in' and 'out' phase chemical shift sagittal MRI sequences (in phase = 0.656, 'out' phase = 0.576). However, when compared to the gold standard rating on a T2 based sequence, ratings on in' and 'out' phase MRI sequences overestimated the degree of stenosis. When comparing 'in' and 'out' ratings to the T2 ratings, agreement was poor with kappa ranging from 0.132 to 0.202. Conclusion: Though both 'in' and 'out' phase chemical shift sagittal MRI sequences can be used to analyse neural foraminal stenosis, given its propensity to over-estimate the degree of stenosis in comparison to the T2 based images, assessment of the condition on these complementary limited sequences technique should be avoided/should be undertaken with caution.

Exploring the potential of ChatGPT in the peer review process: An observational study.

BACKGROUND: Peer review is the established method for evaluating the quality and validity of research manuscripts in scholarly publishing. However, scientific peer review faces challenges as the volume of submitted research has steadily increased in recent years. Time constraints and peer review quality assurance can place burdens on reviewers, potentially discouraging their participation. Some artificial intelligence (AI) tools might assist in relieving these pressures. This study explores the efficiency and effectiveness of one of the artificial intelligence (AI) chatbots, ChatGPT (Generative Pre-trained Transformer), in the peer review process. METHODS: Twenty-one peer-reviewed research articles were anonymised to ensure unbiased evaluation. Each article was reviewed by two humans and by versions 3.5 and 4.0 of ChatGPT. The AI was instructed to provide three positive and three negative comments on the articles and recommend whether they should be accepted or rejected. The human and AI results were compared using a 5-point Likert scale to determine the level of agreement. The correlation between ChatGPT responses and the acceptance or rejection of the papers was also examined. RESULTS: Subjective review similarity between human reviewers and ChatGPT showed a mean score of 3.6/5 for ChatGPT 3.5 and 3.76/5 for ChatGPT 4.0. The correlation between human and AI review scores was statistically significant for ChatGPT 3.5, but not for ChatGPT 4.0. CONCLUSION: ChatGPT can complement human scientific peer review, enhancing efficiency and promptness in the editorial process. However, a fully automated AI review process is currently not advisable, and ChatGPT's role should be regarded as highly constrained for the present and near future.

Could ChatGPT Pass the UK Radiology Fellowship Examinations?

RATIONALE AND OBJECTIVES: Chat Generative Pre-trained Transformer (ChatGPT) is an artificial intelligence (AI) tool which utilises machine learning to generate original text resembling human language. AI models have recently demonstrated remarkable ability at analysing and solving problems, including passing professional examinations. We investigate the performance of ChatGPT on some of the UK radiology fellowship equivalent examination questions. METHODS: ChatGPT was asked to answer questions from question banks resembling the Fellowship of the Royal College of Radiologists (FRCR) examination. The entire physics part 1 question bank (203 5-part true/false questions) was answered by the GPT-4 model and answers recorded. 240 single best answer questions (SBAs) (representing the true length of the FRCR 2A examination) were answered by both GPT-3.5 and GPT-4 models. RESULTS: ChatGPT 4 answered 74.8% of part 1 true/false statements correctly. The spring 2023 passing mark of the part 1 examination was 75.5% and ChatGPT thus narrowly failed. In the 2A examination, ChatGPT 3.5 answered 50.8% SBAs correctly, while GPT-4 answered 74.2% correctly. The winter 2022 2A pass mark was 63.3% and thus GPT-4 clearly passed. CONCLUSION: AI models such as ChatGPT are able to answer the majority of questions in an FRCR style examination. It is reasonable to assume that further developments in AI will be more likely to succeed in comprehending and solving questions related to medicine, specifically clinical radiology. ADVANCES IN KNOWLEDGE: Our findings outline the unprecedented capabilities of AI, adding to the current relatively small body of literature on the subject, which in turn can play a role medical training, evaluation and practice. This can undoubtedly have implications for radiology.

Validation of the supinator fat pad sign in radial head and neck fractures.

OBJECTIVE: To assess the displacement of the supinator fat pad in radial head and neck fractures and to validate its significance. MATERIAL AND METHODS: One hundred two adult patients from the Royal Orthopaedic Hospital, Birmingham, United Kingdom and Sultan Qaboos University Hospital, Muscat, Oman with confirmed radial head and/or neck fractures were included. Fractures were classified using the Mason-Johnston classification. The displacement of the supinator fat pad from the radius was measured on anterior-posterior (AP) and lateral radiographs and correlated to fracture classification. RESULTS: The supinator fat pad was on average displaced by 10.6 mm and 13.8 mm from the radius on AP and lateral radiographs, respectively. The displacement of the fat pad progressively increased between non-displaced (Mason I) and severely comminuted (Mason III) fractures on both the AP (10.25 to 14.25 mm) and lateral (12.70 to 16.00 mm) projections. The progression of displacement on AP (p = 0.016) and on lateral (p = 0.007) projections was statistically significant. Fracture dislocation was not associated with increased fat pad displacement. CONCLUSION: The supinator fat pad sign is a useful adjunct in the assessment of radial head and neck fractures.

Primary Benign Neoplasms of the Spine.

Benign tumours comprise the majority of primary vertebral tumours, and these are often found incidentally on imaging. Nonetheless, accurate diagnosis of these benign lesions is crucial, in order to avoid misdiagnosis as more ominous malignant lesions or infection. Furthermore, some of these tumours, despite their benign nature, can have localised effects on the spine including neural compromise, or can be locally aggressive, thus necessitating active management. Haemangiomas and osteomas (enostosis) are the commonest benign tumours encountered. Others include osteoid osteoma, osteoblastoma, fibrous dysplasia, osteochondroma, chondroblastoma, haemangioma, simple bone cysts, aneurysmal bone cysts, giant cell tumours, eosinophilic granuloma and notochordal rests. The majority of lesions are asymptomatic; however, locally aggressive lesions (such as aneurysmal bone cysts or giant cell tumours) can present with nonspecific symptoms, such as back pain, neurological deficits and spinal instability, which may be indistinguishable from more commonly encountered mechanical back pain or malignant lesions including metastases. Hence, imaging, including radiography, computed tomography (CT) and magnetic resonance imaging (MRI), plays a critical role in diagnosis. Generally, most incidental or asymptomatic regions are conservatively managed or may not require any follow-up, while symptomatic or locally aggressive lesions warrant active interventions, which include surgical resection or percutaneous treatment techniques. Due to advances in interventional radiology techniques in recent years, percutaneous minimally invasive techniques such as radiofrequency ablation, sclerotherapy and cryoablation have played an increasing role in the management of these tumours with favourable outcomes. The different types of primary benign vertebral tumours will be discussed in this article with an emphasis on pertinent imaging features.

Performance of ChatGPT on dermatology Specialty Certificate Examination multiple choice questions.

ChatGPT is a large language model trained on increasingly large datasets by OpenAI to perform language-based tasks. It is capable of answering multiple-choice questions, such as those posed by the dermatology SCE examination. We asked two iterations of ChatGPT: ChatGPT-3.5 and ChatGPT-4 84 multiple-choice sample questions from the sample dermatology SCE question bank. ChatGPT-3.5 achieved an overall score of 63.1%, and ChatGPT-4 scored 90.5% (a significant improvement in performance (p<0.001)). The typical pass mark for the dermatology SCE is 70-72%. ChatGPT-4 is therefore capable of answering clinical questions and achieving a passing grade in these sample questions. There are many possible educational and clinical implications for increasingly advanced artificial intelligence (AI) and its use in medicine, including in the diagnosis of dermatological conditions. Such advances should be embraced provided that patient safety is a core tenet, and the limitations of AI in the nuances of complex clinical cases are recognised.

Primary Osseous Malignancies of the Spine.

Malignant primary vertebral tumours comprise an uncommon group of primary bone malignancies that can pose a diagnostic and therapeutic challenge. The most frequently encountered malignant primary vertebral tumours include chordoma, chondrosarcoma, Ewing sarcoma and osteosarcoma. These tumours often present with nonspecific symptoms, such as back pain, neurologic deficits and spinal instability, which can be confused for the more commonly encountered mechanical back pain and may delay their diagnosis and treatment. Imaging, including radiography, computed tomography (CT) and magnetic resonance imaging (MRI) is crucial for diagnosis, staging, treatment planning and follow-up. Surgical resection remains the mainstay of treatment for malignant primary vertebral tumours, but adjuvant radiotherapy and chemotherapy may be necessary for achieving complete tumour control depending on the type of tumour. In recent years, advances in imaging techniques and surgical approaches, such as en-bloc resection and spinal reconstruction, have improved the outcomes for patients with malignant primary vertebral tumours. However, the management can be complex due to the anatomy involved and the high morbidity and mortality associated with surgery. The different types of malignant primary vertebral lesions will be discussed in this article with an emphasis on the imaging features.

The (extended) achondroplasia foramen magnum score has good observer reliability.

BACKGROUND: Achondroplasia is the most common skeletal dysplasia. A significant complication is foramen magnum stenosis. When severe, compression of the spinal cord may result in sleep apnea, sudden respiratory arrest and death. To avoid complications, surgical decompression of the craniocervical junction is offered in at-risk cases. However, practice varies among centres. To standardize magnetic resonance (MR) reporting, the achondroplasia foramen magnum score was recently developed. The reliability of the score has not been assessed. OBJECTIVE: To assess the interobserver reliability of the achondroplasia foramen magnum score. MATERIALS AND METHODS: Base of skull imaging of children with achondroplasia under the care of Sheffield Children's Hospital was retrospectively and independently reviewed by four observers using the achondroplasia foramen magnum score. Two-way random-effects intraclass coefficient (ICC) was used to assess inter- and intra-observer reliability. RESULTS: Forty-nine eligible cases and five controls were included. Of these, 10 were scored normal, 17 had a median score of 1 (mild narrowing), 11 had a median score of 2 (effacement of cerebral spinal fluid), 10 had a score of 3 (compression of cord) and 6 had a median score of 4 (cord myelopathic change). Interobserver ICC was 0.72 (95% confidence interval = 0.62-0.81). Intra-observer ICC ranged from 0.60 to 0.86. Reasons for reader disagreement included flow void artefact, subtle T2 cord signal and myelopathic T2 cord change disproportionate to canal narrowing. CONCLUSION: The achondroplasia foramen magnum score has good interobserver reliability. Imaging features leading to interobserver disagreement have been identified. Further research is required to prospectively validate the score against clinical outcomes.