Magnetic Resonance Imaging Reports Research Articles

Correlation between magnetic resonance imaging and arthroscopic findings in superior labral from anterior to posterior injuries of shoulder joint

Background: The aim of our study was to identify the accuracy of the magnetic resonance imaging (MRI) in detecting superior labral from anterior to posterior (SLAP) lesions when compared to arthroscopic findings, considering arthroscopy as the gold standard. Methods: This is a retrospective study conducted between January 2015 to July 2021 that focuses on SLAP lesions to evaluate the accuracy of its magnetic resonance imaging (MRI) reporting. All patients who had shoulder arthroscopy were included, and their intra-operative pathology was recorded and compared to their pre-operative MRI reports. Accuracy was assessed by calculating the sensitivity and specificity of MRI in comparison to the standard shoulder arthroscopy. Results: 60 patients were included in the study. In diagnosing SLAP lesions this study showed that MRI was 54% sensitivity, 67% specificity with 79% positive predictive value and 39% negative predictive value. Accuracy was found to be 55%. Conclusions: In this study, the MRI did not detect SLAP lesions at a rate as high as arthroscopy, which is considered the gold standard. When performing arthroscopy, it is important to be diligent in detecting actual SLAP lesions that may not have been identified by traditional MRI scans.

GPT-Driven Radiology Report Generation with Fine-Tuned Llama 3.

The integration of deep learning into radiology has the potential to enhance diagnostic processes, yet its acceptance in clinical practice remains limited due to various challenges. This study aimed to develop and evaluate a fine-tuned large language model (LLM), based on Llama 3-8B, to automate the generation of accurate and concise conclusions in magnetic resonance imaging (MRI) and computed tomography (CT) radiology reports, thereby assisting radiologists and improving reporting efficiency. A dataset comprising 15,000 radiology reports was collected from the University of Medicine and Pharmacy of Craiova's Imaging Center, covering a diverse range of MRI and CT examinations made by four experienced radiologists. The Llama 3-8B model was fine-tuned using transfer-learning techniques, incorporating parameter quantization to 4-bit precision and low-rank adaptation (LoRA) with a rank of 16 to optimize computational efficiency on consumer-grade GPUs. The model was trained over five epochs using an NVIDIA RTX 3090 GPU, with intermediary checkpoints saved for monitoring. Performance was evaluated quantitatively using Bidirectional Encoder Representations from Transformers Score (BERTScore), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), Bilingual Evaluation Understudy (BLEU), and Metric for Evaluation of Translation with Explicit Ordering (METEOR) metrics on a held-out test set. Additionally, a qualitative assessment was conducted, involving 13 independent radiologists who participated in a Turing-like test and provided ratings for the AI-generated conclusions. The fine-tuned model demonstrated strong quantitative performance, achieving a BERTScore F1 of 0.8054, a ROUGE-1 F1 of 0.4998, a ROUGE-L F1 of 0.4628, and a METEOR score of 0.4282. In the human evaluation, the artificial intelligence (AI)-generated conclusions were preferred over human-written ones in approximately 21.8% of cases, indicating that the model's outputs were competitive with those of experienced radiologists. The average rating of the AI-generated conclusions was 3.65 out of 5, reflecting a generally favorable assessment. Notably, the model maintained its consistency across various types of reports and demonstrated the ability to generalize to unseen data. The fine-tuned Llama 3-8B model effectively generates accurate and coherent conclusions for MRI and CT radiology reports. By automating the conclusion-writing process, this approach can assist radiologists in reducing their workload and enhancing report consistency, potentially addressing some barriers to the adoption of deep learning in clinical practice. The positive evaluations from independent radiologists underscore the model's potential utility. While the model demonstrated strong performance, limitations such as dataset bias, limited sample diversity, a lack of clinical judgment, and the need for large computational resources require further refinement and real-world validation. Future work should explore the integration of such models into clinical workflows, address ethical and legal considerations, and extend this approach to generate complete radiology reports.

Diagnostic Capability of Ultrasonography in Evaluating Peripheral Nerve Injuries of the Brachial Plexus.

The purpose of this study is to determine the diagnostic capability of ultrasonography (US) in patients with suspected brachial plexus injury (BPI) to the terminal nerves by comparing physical examination (PE) findings with US, electromyography (EMG), and magnetic resonance imaging (MRI) reports. All patients at a single institution who underwent US for peripheral nerve injury of the brachial plexus and terminal nerves resulting in sensory-motor deficits from October 1, 2017 to October 31, 2023 were identified. A retrospective chart review was performed. Each PE, US, EMG, and MRI reports were given an overall rating: "normal" or "abnormal." Terminal nerves (musculocutaneous, axillary, radial, ulnar, medial) were individually assessed as "normal" or "abnormal." The interobserver agreement between reports was calculated using Cohen kappa. Specificity and sensitivity analyses were performed to determine diagnostic accuracy and were reported with 95% confidence intervals (CI). A total of 120 patients were included. Most injuries were traumatic in nature (78.8%) and were low-energy (53.8%). When each imaging modality was compared with the PE findings, EMG had the highest interobserver agreement (Cohen kappa = 0.18), followed by US (Cohen kappa = 0.10), and last MRI (Cohen kappa = 0.07). The US had the highest sensitivity (0.92, CI = 0.85, 0.96) among the 3 imaging modalities (Table 2). On US, the ulnar nerve was most commonly abnormal (n = 84, 70.0%). Ultrasonography serves as a useful adjunct in the workup of patients with suspected peripheral BPI and is reliable in localizing the pathology of injured terminal nerves in the brachial plexus.

Comparison of the Effectiveness of Computed Tomography and Magnetic Resonance Imaging Techniques in Patient Groups Aged under and over 65 Years and Diagnosed with Ischemic Stroke in the Emergency Department

Objectives: Stroke is a condition with high morbidity and mortality. This study aims to investigate whether the effectiveness of Computed Tomography (CT) and diffusion-weighted Magnetic Resonance Imaging (MRI), the techniques that have a significant place in the diagnosis of ischemic stroke, the most common form of stroke, are affected by the physiological changes of advanced age. Methods: A total of 436 patients were included in the study. The study population was divided into two groups depending on age: those above 65 and those under 65. Medical files, both the emergency department and clinical ward files, of the patients who were admitted to the emergency department in nine months and admitted to the neurology clinic with the diagnosis of ischemic stroke were retrospectively analyzed. The time from admission to imaging was determined depending on patient files and the Hospital Management Information System (HBYS). The CT and MRI reports interpreted by radiologists were also reviewed. While recording the data, the presence of a lesion, its direction, and localization were also noted. Results: CT positivity was 21.3%, and the positivity of diffusion-weighted imaging was 82.1% in the study population. The time was shorter in the group of patients with positive CT results than in the group with negative CT results. In subjects under 65, the time between onset and imaging was shorter in the group with positive CT results than in the group with negative CT results. In subjects over 65, the time with positive CT results was not different from the group with negative CT results. It was determined that the mean time was shorter in the group with positive MRI results than in the group with negative results. In both the groups under the age of 65 and over the age of 65, the time interval was shorter in the patients with positive MRI results compared to those with negative MRI results. Conclusions: Regardless of the positivity or negativity of CT and MRI results, the mean time from symptom onset to imaging was shorter in the group under 65 years of age compared to the group over 65 years. Aging prolongs the time to admission and the neuroradiological response of geriatric patients.

Accuracy of Intra-Axial Brain Tumor Characterization in the Emergency MRI Reports: A Retrospective Human Performance Benchmarking Pilot Study.

Demand for emergency neuroimaging is increasing. Even magnetic resonance imaging (MRI) is often performed outside office hours, sometimes revealing more uncommon entities like brain tumors. The scientific literature studying artificial intelligence (AI) methods for classifying brain tumors on imaging is growing, but knowledge about the radiologist's performance on this task is surprisingly scarce. Our study aimed to tentatively fill this knowledge gap. We hypothesized that the radiologist could classify intra-axial brain tumors at the emergency department with clinically acceptable accuracy. We retrospectively examined emergency brain MRI reports from 2013 to 2021, the inclusion criteria being (1) emergency brain MRI, (2) no previously known intra-axial brain tumor, and (3) suspicion of an intra-axial brain tumor on emergency MRI report. The tumor type suggestion and the final clinical diagnosis were pooled into groups: (1) glial tumors, (2) metastasis, (3) lymphoma, and (4) other tumors. The final study sample included 150 patients, of which 108 had histopathological tumor type confirmation. Among the patients with histopathological tumor type confirmation, the accuracy of the MRI reports in classifying the tumor type was 0.86 for gliomas against other tumor types, 0.89 for metastases, and 0.99 for lymphomas. We found the result encouraging, given the prolific need for emergency imaging.

Decoding Radiology Reports: Artificial Intelligence-Large Language Models Can Improve the Readability of Hand and Wrist Orthopedic Radiology Reports.

The purpose of this study was to assess the effectiveness of an Artificial Intelligence-Large Language Model (AI-LLM) at improving the readability of hand and wrist radiology reports. The radiology reports of 100 hand and/or wrist radiographs, 100 hand and/or wrist computed tomography (CT) scans, and 100 hand and/or wrist magnetic resonance imaging (MRI) scans were extracted. The following prompt command was inserted into the AI-LLM: "Explain this radiology report to a patient in layman's terms in the second person: [Report Text]." The report length, Flesch reading ease score (FRES), and Flesch-Kincaid reading level (FKRL) were calculated for the original radiology report and the AI-LLM-generated report. The accuracy of the AI-LLM report was assessed via a 5-point Likert scale. Any "hallucination" produced by the AI-LLM-generated report was recorded. There was a statistically significant improvement in mean FRES scores and FKRL scores in the AI-LLM-generated radiograph report, CT report, and MRI report. For all AI-LLM-generated reports, the mean reading level improved to below an eighth-grade reading level. The mean Likert score for the AI-LLM-generated radiograph report, CT report, and MRI report was 4.1 ± 0.6, 3.9 ± 0.6, and 3.9 ± 0.7, respectively. The hallucination rate in the AI-LLM-generated radiograph report, CT report, and MRI report was 3%, 6%, and 6%, respectively. This study demonstrates that AI-LLM effectively improves the readability of hand and wrist radiology reports, underscoring the potential application of AI-LLM as a promising and innovative patient-centric strategy to improve patient comprehension of their imaging reports.Level of Evidence: IV.

A Critical Examination of Academic Hospital Practices-Paving the Way for Standardized Structured Reports in Neuroimaging.

Background/Objectives: Imaging studies are often an integral part of patient evaluation and serve as the primary means of communication between radiologists and referring physicians. This study aimed to evaluate brain Magnetic Resonance Imaging (MRI) reports and to determine whether these reports follow a standardized or narrative format. Methods: A series of 466 anonymized MRI reports from an academic hospital were downloaded from the Picture Archiving and Communication System (PACS) in portable document format (pdf) for the period between August 2017 and March 2018. Two hundred brain MRI reports, written by four radiologists, were compared to a structured report template from the Radiology Society of North America (RSNA) and were included, whereas MR-modified techniques, such as MRI orbits and MR venography reports, were excluded (n = 266). All statistical analyses were conducted using Statistical Package for the Social Sciences (SPSS) statistical software (version 16.4.1, MedCalc Software). Results: None of the included studies used the RSNA template for structured reports (SRs). The highest number of brain-reported pathologies was for vascular disease (24%), while the lowest was for infections (3.5%) and motor dysfunction (5.5%). Radiologists specified the Technique (n = 170, 85%), Clinical Information (n = 187, 93.5%), and Impression (n = 197, 98.5%) in almost all reports. However, information in the Findings section was often missing. As hypothesized, radiologists with less experience showed a greater commitment to reporting additional elements than those with more experience. Conclusions: The SR template for medical imaging has been accessible online for over a decade. However, many hospitals and radiologists still use the free-text style for reporting. Our study was conducted in an academic hospital with a fellowship program, and we found that structured reporting had not yet been implemented. As the health system transitions towards teleservices and teleradiology, more efforts need to be put into advocating standardized reporting in medical imaging.

Exploring the potential of water channels for developing genetically encoded reporters and biosensors for diffusion-weighted MRI

Genetically encoded reporters for magnetic resonance imaging (MRI) offer a valuable technology for making molecular-scale measurements of biological processes within living organisms with high anatomical resolution and whole-organ coverage without relying on ionizing radiation. However, most MRI reporters rely on synthetic contrast agents, typically paramagnetic metals and metal complexes, which often need to be supplemented exogenously to create optimal contrast. To eliminate the need for synthetic contrast agents, we previously introduced aquaporin-1, a mammalian water channel, as a new reporter gene for the fully autonomous detection of genetically labeled cells using diffusion-weighted MRI. In this study, we aimed to expand the toolbox of diffusion-based genetic reporters by modulating aquaporin membrane trafficking and harnessing the evolutionary diversity of water channels across species. We identified a number of new water channels that functioned as diffusion-weighted reporter genes. In addition, we show that loss-of-function variants of yeast and human aquaporins can be leveraged to design first-in-class diffusion-based sensors for detecting the activity of a model protease within living cells.

Poster 244: Magnetic Resonance Imaging versus Diagnostic Arthroscopy to Identify Intraarticular Pathology Associated with Patellar Instability: A High Rate of Discordant Findings Altering Surgical Treatment

Objectives: While uncommon, acute traumatic patellar dislocations can lead to recurrent symptoms of patellar instability in 15% to 45% of patients. Patellar stability is an interplay of bony and soft tissue restraints as well as anatomic factors, however, a mainstay of treatment remains reconstruction of the medial patellofemoral ligament (MPFL). Instability events can lead to intra-articular derangements of the knee, both in the acute and chronic patellar instability setting. These findings may not always be appropriately identified on magnetic resonance imaging (MRI). The incidence of these “surprise” injuries have not been previously reported. The purpose of this study is to determine the rates of coexisting intra-articular pathology in patients with patellar instability requiring MPFL reconstruction and elucidate any discordance between preoperative MRI findings and diagnostic arthroscopy findings. Methods: All patients undergoing MPFL reconstruction at a single institution between 2010 and 2023 were identified and preoperative MRI reports, defined as the most recent MRI report to the date of surgery with no interval traumatic events, were queried. Records without full MRI reports as read by a radiologist or cases in which a diagnostic arthroscopy was not conducted were excluded. MRI findings were discordant from arthroscopic findings if a lesion identified on diagnostic arthroscopy was not present in the full MRI report. Procedures that were undertaken because of these missed pathologies on MRI were recorded. Results: A total of 640 patients were identified during the study period, and 507 complete records were ultimately included. Preoperative MRI identified patellar osteochondral lesions or cartilage fissures in 333 patients (66%), loose bodies in 119 patients (24%), lateral femoral condyle osteochondral lesions or fissures in 97 patients (19%) and meniscus tears in 47 patients (9%). Among these patients, 172 (34%) had a diagnosis at the time of arthroscopy which was not identified on the preoperative MRI. These arthroscopic findings resulted in 75 loose body removals, 74 patellar shaving chondroplasties, 16 partial meniscectomies, 3 microfractures, 3 osteochondral lesion open reduction internal fixation, and 2 meniscal repairs which would have been missed without diagnostic arthroscopy due to discordant MRI findings. Conclusions: Over one-third of patients at a single institution who underwent diagnostic arthroscopy in the setting of patellar instability surgery had pathology identified which required surgical intervention that was not reported on a preoperative MRI. A comparison of MRI and diagnostic arthroscopy has been extensively reported on for other knee pathologies including ACL tear and lateral meniscal tear; however, there has been no similar investigation of the reliability of MRI for identification of concomitant pathology in the setting of patellar instability to date. The findings of this study highlight the importance of diagnostic arthroscopy in the treatment of patellar instability, the frequency with which this altered treatment, and the high preponderance of discordant MRI findings.

Radiology reporting in rectal cancer using magnetic resonance imaging: Comparison of reporting completeness between different reporting styles and structure.

The radiology report is vital for providing imaging information to guide patient treatment, and template-based reporting can potentially increase the reporting completeness. In 2014, a national reporting template for radiological staging of rectal cancer using magnetic resonance imaging (MRI) was implemented in Sweden. To evaluate the impact of the national reporting template by comparing and analysing differences in content and completeness in MRI reports between 2010 and 2016. Focus was to compare reporting completeness (i) between different reporting years and (ii) between three defined reporting styles. 493 MRI reports were gathered from 10 hospitals in four healthcare regions in Sweden, comprising 243 reports from 2010 and 250 reports from 2016. Reports were classified into three reporting styles: Expanded structured, Minimised structured, and Unstructured, and analysed using qualitative content analysis based on the national template. In 2010, all reports adhered to Unstructured reporting. In 2016, 44, 42, and 164 reports were conformant to Expanded structured, Minimised structured, and Unstructured reporting, respectively. A comparison between the years revealed a reporting completeness of 48% for 2010 reports and 72% for 2016 reports. Among the 2016 reporting styles, Unstructured reporting had the largest gap compared to the national template, with completeness at 64% versus 77.5% for Minimised structured reporting and 93% for Expanded structured reporting. Implementation of template-based reporting according to Expanded structure is key to conform to national decided evidence-based practice for radiological staging of rectal cancer.

Predicting distant metastasis in nasopharyngeal carcinoma using gradient boosting tree model based on detailed magnetic resonance imaging reports.

Development of distant metastasis (DM) is a major concern during treatment of nasopharyngeal carcinoma (NPC). However, studies have demonstrated improved distant control and survival in patients with advanced NPC with the addition of chemotherapy to concomitant chemoradiotherapy. Therefore, precise prediction of metastasis in patients with NPC is crucial. To develop a predictive model for metastasis in NPC using detailed magnetic resonance imaging (MRI) reports. This retrospective study included 792 patients with non-distant metastatic NPC. A total of 469 imaging variables were obtained from detailed MRI reports. Data were stratified and randomly split into training (50%) and testing sets. Gradient boosting tree (GBT) models were built and used to select variables for predicting DM. A full model comprising all variables and a reduced model with the top-five variables were built. Model performance was assessed by area under the curve (AUC). Among the 792 patients, 94 developed DM during follow-up. The number of metastatic cervical nodes (30.9%), tumor invasion in the posterior half of the nasal cavity (9.7%), two sides of the pharyngeal recess (6.2%), tubal torus (3.3%), and single side of the parapharyngeal space (2.7%) were the top-five contributors for predicting DM, based on their relative importance in GBT models. The testing AUC of the full model was 0.75 (95% confidence interval [CI]: 0.69-0.82). The testing AUC of the reduced model was 0.75 (95%CI: 0.68-0.82). For the whole dataset, the full (AUC = 0.76, 95%CI: 0.72-0.82) and reduced models (AUC = 0.76, 95%CI: 0.71-0.81) outperformed the tumor node-staging system (AUC = 0.67, 95%CI: 0.61-0.73). The GBT model outperformed the tumor node-staging system in predicting metastasis in NPC. The number of metastatic cervical nodes was identified as the principal contributing variable.

Watch and wait in rectal cancer patients with residual mucin on magnetic resonance imaging following neoadjuvant therapy.

Neoadjuvant therapy leads to a clinical complete response in a considerable proportion of patients with locally advanced rectal cancer, allowing for possible nonoperative management. The presence of mucin on magnetic resonance imaging (MRI) after neoadjuvant therapy leads to uncertainty about residual disease and appropriateness of a watch-and-wait strategy in patients with no evidence of disease on proctoscopy (endoscopic clinical complete response). MRI reports for locally advanced rectal cancer patients seen between July 2016 and January 2020 at Memorial Sloan Kettering Cancer Center were queried for presence of mucin in the tumor bed on MRI following neoadjuvant therapy. Clinicodemographic, pathologic, and outcome data were compiled and analyzed. Of 71 patients with mucin on posttreatment MRI, 20 had a clinical complete response, and 51 had abnormalities on endoscopy and/or physical exam. One patient with a clinical complete response opted out of watch-and-wait; thus, 19 (27%) patients entered watch-and-wait, and 52 (73%) patients were planned for surgery (non-watch-and-wait). Of the 19 watch-and-wait patients, 15 (79%) have had no local regrowth with median follow-up of 50 months (range = 29-76 months), while 4 (21%) experienced regrowth between 9 and 29 months after neoadjuvant therapy. Of the 52 patients who were planned to have surgery (non-watch-and-wait), 49 underwent resection while 3 developed metastatic disease that precluded curative-intent surgery. Of the 49 patients who underwent surgery, 5 (10%) had a pathologic complete response (including the patient with an endoscopic clinical complete response). The presence of mucin after neoadjuvant therapy for locally advanced rectal cancer does not preclude watch-and-wait management in otherwise appropriate candidates who achieve an endoscopic clinical complete response.

Lesion Distribution in the Metacarpophalangeal and Metatarsophalangeal Region of 341 Horses Using Standing Magnetic Resonance Imaging.

Pain localised to the metacarpophalangeal (MCP) and metatarsophalangeal (MTP) region represents a frequent cause of lameness in sport horses, and standing magnetic resonance imaging (MRI) of these regions is increasingly being acquired. This multicentre retrospective study describes the ranges of abnormalities identified on standing MRI of the MCP/MTP region and compares patterns of abnormalities between forelimbs, hindlimbs and different sports disciplines. In total, 341 MRI reports were reviewed. Subchondral bone plate irregularities, condylar and proximal phalanx pathologies were frequently identified with subchondral bone defect, sclerosis and increased intensity on STIR images often described. Medial pathology was frequently identified in the forelimbs, and more lateral pathology was reported in the hindlimbs, which could potentially reflect differences in the loading patterns. Significant differences in MRI findings were found between different sports activities, with MCP/MTP bone pathology occurring more frequently in MRI reports from race and endurance horses and MCP/MTP soft tissue injuries being reported more frequently in dressage and show-jumping horses, particularly in the suspensory apparatus, including the distal sesamoidean ligaments. The findings of this study identify patterns of MCP/MTP abnormalities detected using standing MRI, with differences seen between forelimbs and hindlimbs and between different sports disciplines.

Exploring chat generated pre-trained transformer-3 ability to interpret MRI knee images and generate reports

Objectives: The study’s objective was to determine if Chat Generated Pre-Trained Transformer-3 (ChatGPT)-4V can interpret magnetic resonance imaging (MRI) knees and generate preliminary reports based on images and clinical history provided by the radiologist. Materials and Methods: This cross-sectional observational study involved selecting 10 MRI knees with representative imaging findings from the institution’s radiology reporting database. Key MRI images were then input into the ChatGPT-4V model, which was queried with four questions: (i) What does the image show?; (ii) What is the sequence?; (iii) What is the key finding?; and, (iv) Finally, the model generated a report based on the provided clinical history and key finding. Responses from ChatGPT-4 were documented and independently evaluated by two musculoskeletal radiologists through Likert scoring. Results: The mean scores for various questions in the assessment were as follows: 2 for “What does the image show?,” 2.10 for “What is the sequence?,” 1.15 for “What is the key finding?,” and the highest mean score of 4.10 for the command “Write a report of MRI of the…” Radiologists consistently gave mean scores ranging from 2.0 to 2.5 per case, with no significant differences observed between different cases (P > 0.05). The interclass correlation coefficient between the two raters was 0.92 (95% Confidence interval: 0.85–0.96). Conclusion: ChatGPT-4V excelled in generating reports based on user-fed clinical information and key findings, with a mean score of 4.10 (good to excellent proficiency). However, its performance in interpreting medical images was subpar, scoring ≤2.10. ChatGPT-4V, as of now, cannot interpret medical images accurately and generate reports.

Auxiliary osseous findings in fetlocks of non-racing sports horses with sagittal groove disease of the proximal phalanx on low-field magnetic resonance imaging.

Sagittal groove disease of the proximal phalanx in equine athletes is commonly considered a bone stress injury. Repetitive hyperextension of the fetlock under high load is thought to contribute to its development. Concurrent changes are often reported in the dorsal sagittal ridge of the third metacarpus/metatarsus (MC3/MT3). To describe the spectrum of associated osseous abnormalities that are present in the fetlock in a large group of horses diagnosed with sagittal groove disease on low-field magnetic resonance imaging (MRI). Retrospective, cross-sectional. MRI images of horses diagnosed with sagittal groove disease at Equitom Equine Clinic between March 2014 and March 2023 were evaluated using semi-quantitative grading schemes and a sagittal groove disease MRI classification system. MRIs of 132 limbs were evaluated, predominantly from warmbloods used for showjumping (n = 83) and dressage (n = 18). Osseous densification and bone oedema-like signal grades were higher in the dorsal sagittal ridge than palmarly/plantarly (p < 0.001 and p < 0.05, respectively). Grades of both osseous densification and bone oedema-like signal in the dorsal sagittal ridge did not significantly differ between the different sagittal groove disease MRI classifications (both p > 0.05). Inclusion based on original MRI reports, absence of control group, small numbers within some grading groups hindering statistical analyses. Findings support the aetiological theories of chronic bone-stress due to loaded fetlock hyperextension however the severity of osseous changes of the dorsal sagittal ridge does not appear to be associated with the severity of sagittal groove disease classification.

Survival in dogs with meningoencephalomyelitis of unknown etiology with and without lesions detected by magnetic resonance imaging.

The prognosis of individual dogs with meningoencephalomyelitis of unknown etiology (MUE) remains difficult to predict. MUE cases with no lesions detected by magnetic resonance imaging (MRI) occur, but it is unknown whether this finding is associated with prognosis. MUE cases without detectable lesions on MRI have a better outcome than cases with detectable lesions. Study included 73 client-owned dogs with MUE presenting to Purdue University Veterinary Hospital from 2010 to 2020. Retrospective study. Dogs with a clinical diagnosis of MUE were identified by medical record search. MRI reports were reviewed for presence or absence of lesions consistent with MUE. Clinical findings at presentation, treatment, disease-specific survival, and outcomes including rates of remission and relapse were compared between cases with normal MRI or abnormal MRI. Overall, 54 dogs (74%) were classified as abnormal MRI, and 19 dogs (26%) were classified as normal MRI cases. Death caused by MUE occurred in 1/19 (5%) normal MRI dogs and 18/54 (33%) abnormal MRI dogs (P = .016). Median survival was >107 months in both groups, but survival was significantly longer in the normal MRI group (P = .019). On multivariate analysis, abnormal MRI was significantly related to death (hazard ratio, 7.71; 95% confidence interval 1.03-58.00, P = .0470), whereas significant relationships with death were not identified for either the use of secondary immunosuppressive medications or cerebrospinal fluid nucleated cell count. MUE dogs with no detectable lesions on MRI have reduced disease-related death compared with dogs with abnormal MRI. The presence or absence of MRI lesions in MUE dogs is prognostically relevant.

A Dual-Gene Reporter-Amplifier Architecture for Enhancing the Sensitivity of Molecular MRI by Water Exchange.

The development of genetic reporters for magnetic resonance imaging (MRI) is essential for investigating biological functions in vivo. However, current MRI reporters have low sensitivity, making it challenging to create significant contrast against the tissue background, especially when only a small fraction of cells express the reporter. To overcome this limitation, we developed an approach for amplifying the sensitivity of molecular MRI by combining a chemogenetic contrast mechanism with a biophysical approach to increase water diffusion through the co-expression of a dual-gene construct comprising an organic anion transporting polypeptide, Oatp1b3, and a water channel, Aqp1. We first show that the expression of Aqp1 amplifies MRI contrast in cultured cells engineered to express Oatp1b3. We demonstrate that the contrast amplification is caused by Aqp1-driven increase in water exchange, which provides the gadolinium ions internalized by Oatp1b3-expressing cells with access to a larger water pool compared with exchange-limited conditions. We further show that our methodology allows cells to be detected using approximately 10-fold lower concentrations of gadolinium than that in the Aqp1-free scenario. Finally, we show that our approach enables the imaging of mixed-cell cultures containing a low fraction of Oatp1b3-labeled cells that are undetectable on the basis of Oatp1b3 expression alone.

Unravelling pituitary tumours in medically treated patients with acromegaly: the impact of systematic MRI reassessment.

In acromegaly, the primary tumor is usually found during magnetic resonance imaging (MRI) of the pituitary gland. A remnant tumor after surgery is, however, harder to depict. When a tumor is missed, the remaining option is usually lifelong pharmacological treatment. To identify tumors by reassessment of all available MRI scans in pharmacologically treated patients, operated or not, and to compare our results with the routine MRI reports. Adult patients diagnosed with acromegaly and managed at a tertiary care center between 2005 and 2021 and currently on pharmacological treatment were included. MRI scans were evaluated in a standardized manner and classified independently by a radiologist and an endocrinologist into "certain," "suspected," or "no tumor." In case of disagreement, consensus was achieved with a senior neuroradiologist. The results were compared using the clinical radiologists' routine MRI reports. We identified certain and suspected tumors in 29/74 and 36/74 patients, respectively. No tumor was identified in nine patients. In five of these, no MRI contrast agent was given. Discrepancy between our results and the routine MRI reports was found in 31/74 patients (P = 0.01). In 22 patients, the routine reports described no tumor while we identified certain tumors in 2/22 patients and suspected tumors in 13/22 patients. In most patients with pharmacologically treated acromegaly, we identified a certain or suspected pituitary tumor. These findings were more frequent compared to the routine MRI reports. Based on our results, patients will be considered for a change in long-term treatment modality.

Using GPT-4 for LI-RADS feature extraction and categorization with multilingual free-text reports.

The Liver Imaging Reporting and Data System (LI-RADS) offers a standardized approach for imaging hepatocellular carcinoma. However, the diverse styles and structures of radiology reports complicate automatic data extraction. Large language models hold the potential for structured data extraction from free-text reports. Our objective was to evaluate the performance of Generative Pre-trained Transformer (GPT)-4 in extracting LI-RADS features and categories from free-text liver magnetic resonance imaging (MRI) reports. Three radiologists generated 160 fictitious free-text liver MRI reports written in Korean and English, simulating real-world practice. Of these, 20 were used for prompt engineering, and 140 formed the internal test cohort. Seventy-two genuine reports, authored by 17 radiologists were collected and de-identified for the external test cohort. LI-RADS features were extracted using GPT-4, with a Python script calculating categories. Accuracies in each test cohort were compared. On the external test, the accuracy for the extraction of major LI-RADS features, which encompass size, nonrim arterial phase hyperenhancement, nonperipheral 'washout', enhancing 'capsule' and threshold growth, ranged from .92 to .99. For the rest of the LI-RADS features, the accuracy ranged from .86 to .97. For the LI-RADS category, the model showed an accuracy of .85 (95% CI: .76, .93). GPT-4 shows promise in extracting LI-RADS features, yet further refinement of its prompting strategy and advancements in its neural network architecture are crucial for reliable use in processing complex real-world MRI reports.

From technical to understandable: Artificial Intelligence Large Language Models improve the readability of knee radiology reports.

The purpose of this study was to evaluate the effectiveness of an Artificial Intelligence-Large Language Model (AI-LLM) at improving the readability of knee radiology reports. Reports of 100 knee X-rays, 100 knee computed tomography (CT) scans and 100 knee magnetic resonance imaging (MRI) scans were retrieved. The following prompt command was inserted into the AI-LLM: 'Explain this radiology report to a patient in layman's terms in the second person:[Report Text]'. The Flesch-Kincaid reading level (FKRL) score, Flesch reading ease (FRE) score and report length were calculated for the original radiology report and the AI-LLM generated report. Any 'hallucination' or inaccurate text produced by the AI-LLM-generated report was documented. Statistically significant improvements in mean FKRL scores in the AI-LLM generated X-ray report (12.7 ± 1.0-7.2 ± 0.6), CT report (13.4 ± 1.0-7.5 ± 0.5) and MRI report (13.5 ± 0.9-7.5 ± 0.6) were observed. Statistically significant improvements in mean FRE scores in the AI-LLM generated X-ray report (39.5 ± 7.5-76.8 ± 5.1), CT report (27.3 ± 5.9-73.1 ± 5.6) and MRI report (26.8 ± 6.4-73.4 ± 5.0) were observed. Superior FKRL scores and FRE scores were observed in the AI-LLM-generated X-ray report compared to the AI-LLM-generated CT report and MRI report, p < 0.001. The hallucination rates in the AI-LLM generated X-ray report, CT report and MRI report were 2%, 5% and 5%, respectively. This study highlights the promising use of AI-LLMs as an innovative, patient-centred strategy to improve the readability of knee radiology reports. The clinical relevance of this study is that an AI-LLM-generated knee radiology report may enhance patients' understanding of their imaging reports, potentially reducing the responder burden placed on the ordering physicians. However, due to the 'hallucinations' produced by the AI-LLM-generated report, the ordering physician must always engage in a collaborative discussion with the patient regarding both reports and the corresponding images. Level IV.