Radiology has usually been the field of medicine that has been at the forefront of technological advances, often being the first to wholeheartedly embrace them. Whether it's from digitization to cloud side architecture, radiology has led the way for adopting the latest advances. With the advent of large language models (LLMs), especially with the unprecedented explosion of freely available ChatGPT, time is ripe for radiology and radiologists to find novel ways to use the technology to improve their workflow. Towards this, we believe these LLMs have a key role in the radiology reading room not only to expedite processes, simplify mundane and archaic tasks, but also to increase the radiologist's and radiologist trainee's knowledge base at a far faster pace. In this article, we discuss some of the ways we believe ChatGPT, and the likes can be harnessed in the reading room.

Although many advancements have been made in imaging modalities that can be used to diagnose pulmonary embolism (PE), computed tomography pulmonary angiography (CTPA) is still the preferred gold standard for promptly diagnosing pulmonary embolism by looking for filling defects caused by the embolus lodged within the main pulmonary artery or its respective branches. The diagnosis is made by the radiologists in emergency settings where quick detection of a PE on CTPA helps the Pulmonary Embolism Response Team (PERT) in quick management. Thus, utmost care is needed to follow standard image acquisition protocols and optimal contrast administration techniques to achieve a contrast opacification of at least 210 Hounsfield units for the radiologists to easily pinpoint an embolus within the pulmonary arteries. Even following proper CTPA scan acquisition guidelines, a CTPA image is prone to several artifacts that can be mistaken for a PE, resulting in a false positive read. In addition to this, many incidental findings, that can be the etiology of chest pain in a PE-suspected patient, are often overlooked by emergency radiologists who try to be as quick as possible in their read so that timely management of PE can be ensued. Taking this into account, our review paper provides the audience with a comprehensive understanding of the clinical aspects of pulmonary embolism and the imaging modalities used for PE detection. The main focus is on CTPA, its acquisition protocols, and the various incidental findings and artifacts to look for while interpreting a CTPA scan. PRéCIS: Beyond the filling defects, a CTPA scan should also be assessed by the radiologists for any incidental findings while keeping in mind several associated pitfalls and artifacts of CTPA.

The American Society of Clinical Oncology (ASCO) updated the guidelines for the treatment of advanced gastroesophageal (GE) cancer in 2023, signifying a major shift towards targeted therapeutics and precision medicine. This article serves as an imaging-based review of recent developments in the care of patients with GE cancer. We cover the epidemiology, the developing treatment paradigms, and the imaging assessment of GE malignancy. In addition, this review aims to familiarize radiologists with the unique adverse effects pertaining to therapeutics, surgeries, radiation therapies, and associated imaging corollaries. A case-based approach will be used to both explore the efficacy of modern treatments and demonstrate their adverse effects, such as chemotherapy-associated pneumonitis, radiation esophagitis, and anastomotic failure. With this comprehensive exploration of gastroesophageal cancer, radiologists will be equipped with the essential tools to inform the treatment decisions made by medical oncologists, radiation oncologists, and surgical oncologists in the new era of precision medicine.

Objective To evaluate the performance of multimodal ChatGPT 4 on a radiology board-style examination containing text and radiologic images. Methods In this prospective exploratory study from October 30 to December 10, 2023, 110 multiple-choice questions containing images designed to match the style and content of radiology board examination like the American Board of Radiology Core or Canadian Board of Radiology examination were prompted to multimodal ChatGPT 4. Questions were further sub stratified according to lower-order (recall, understanding) and higher-order (analyze, synthesize), domains (according to radiology subspecialty), imaging modalities and difficulty (rated by both radiologists and radiologists-in-training). ChatGPT performance was assessed overall as well as in subcategories using Fisher exact test with multiple comparisons. Confidence in answering questions was assessed using a Likert scale (1-5) by consensus between a radiologist and radiologist-in-training. Reproducibility was assessed by comparing two different runs using two different accounts. Results ChatGPT 4 answered 55% (61/110) of image-rich questions correctly. While there was no significant difference in performance amongst the various sub-groups on exploratory analysis, performance was better on lower-order \[61% (25/41)] when compared to higher-order [52% (36/69)\] \[P=.46\]. Among clinical domains, performance was best on cardiovascular imaging [80% (8/10)], and worst on thoracic imaging [30% [3/10)]. Confidence in answering questions was confident/highly confident [89%(98/110)], even when incorrect There was poor reproducibility between two runs, with the answers being different in 14% (15/110) questions. Conclusion Despite no radiology specific pre-training, multimodal capabilities of ChatGPT appear promising on questions containing images. However, the lack of reproducibility among two runs, even with the same questions poses challenges of reliability.### Competing Interest StatementThe authors have declared no competing interest.### Funding StatementThe study did not receive any funding.### Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesI confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.YesAll data produced in the present work are contained in the manuscript

Abstract BACKGROUND Glioblastoma is an infiltrative primary brain tumor with poor prognosis despite multimodal therapy. Recurrence is inevitable secondary to tumor cell infiltration in the peritumoral tissues, beyond contrast enhancing margins, which is the target for surgical resection. We hypothesize that a machine learning model constructed from a diverse, inter-institutional dataset can improve accuracy of generated tumor infiltration maps, thus guiding precision targeted therapies. METHODS 731 MRI scans of treatment-naïve glioblastoma patients from 10 institutions were included. All patients had pre-operative multiparametric-MRI (T1, T1Gd, T2, T2-FLAIR, ADC), and underwent complete resection of the enhancing tumor followed by standard-of-care chemoradiotherapy. 42 patients were used as an independent validation set, and 689 were used for training. Of these 239 patients had histopathologically confirmed recurrence with corresponding MRI scans, which were used as ground-truth for evaluating the location of recurrence using a leave-one-site-out (LSO) method. An AI model combining deep learning and SVM was used to develop a predictive model for infiltration. We validated the generalizability of our results in an unseen, multi-institutional data set. RESULTS Our model predicted locations of recurrence with odds ratio (99% CI) 37.6 (37.1-38.1) on the LSO testing set and 24.3 (23.4-25.2) on the validation set, indicating that areas labeled highly infiltrated were over 37 and 24 times more likely to coincide with future recurrence respectively. CONCLUSIONS We demonstrate that AI-based pattern analysis from multiparametric-MRI can predict tumor infiltration in peritumoral regions with high likelihood of recurrence by decrypting the visually imperceptible heterogeneity of peritumoral tissue. Model performance improved from training on a larger/diverse dataset and combining results of multiple AI methods. Independent validation confirmed the model’s ability to generalize to unseen data. We believe this will serve to advance AI-based biomarkers for predicting future recurrence and facilitate development of multi-modal targeted therapies in this era of precision neuro-oncology.

BACKGROUND AND PURPOSE:Understanding sex-based differences in patients with glioblastoma is necessary for accurate personalized treatment planning to improve patient outcomes. Our purpose was to investigate sex-specific differences in molecular, clinical, and radiologic tumor parameters, as well as survival outcomes in patients with glioblastoma, isocitrate dehydrogenase-1 wild-type (IDH1-WT), grade 4. MATERIALS AND METHODS:Retrospective data of 1832 patients with glioblastoma, IDH1-WT with comprehensive information on tumor parameters was acquired from the Radiomics Signatures for Precision Oncology in Glioblastoma consortium. Data imputation was performed for missing values. Sex-based differences in tumor parameters, such as age, molecular parameters, preoperative Karnofsky performance score (KPS), tumor volumes, epicenter, and laterality were assessed through nonparametric tests. Spatial atlases were generated by using preoperative MRI maps to visualize tumor characteristics. Survival time analysis was performed through log-rank tests and Cox proportional hazard analyses. RESULTS:Glioblastoma was diagnosed at a median age of 64 years in women compared with 61.9 years in men (false discovery rate [FDR] = 0.003). Men had a higher KPS (above 80) as compared with women (60.4% women versus 69.7% men, FDR = 0.044). Women had lower tumor volumes in enhancing (16.7 cm3 versus 20.6 cm3 in men, FDR = 0.001), necrotic core (6.18 cm3 versus 7.76 cm3 in men, FDR = 0.001), and edema regions (46.9 cm3 versus 59.2 cm3 in men, FDR = 0.0001). The right temporal region was the most common tumor epicenter in the overall population. Right as well as left temporal lobes were more frequently involved in men. There were no sex-specific differences in survival outcomes and mortality ratios. Higher age, unmethylated O6-methylguanine-DNA-methyltransferase promoter and undergoing subtotal resection increased the mortality risk in both men and women. CONCLUSIONS:Our study demonstrates significant sex-based differences in clinical and radiologic tumor parameters of patients with glioblastoma. Sex is not an independent prognostic factor for survival outcomes and the tumor parameters influencing patient outcomes are identical for men and women.

Artificial intelligence (AI) has recently become a trending tool and topic regarding productivity especially with publicly available free services such as ChatGPT and Bard. In this report, we investigate if two widely available chatbots chatGPT and Bard, are able to show consistent accurate responses for the best imaging modality for urologic clinical situations and if they are in line with American College of Radiology (ACR) Appropriateness Criteria (AC). All clinical scenarios provided by the ACR were inputted into ChatGPT and Bard with result compared to the ACR AC and recorded. Both chatbots had an appropriate imaging modality rate of of 62% and no significant difference in proportion of correct imaging modality was found overall between the two services (p>0.05). The results of our study found that both ChatGPT and Bard are similar in their ability to suggest the most appropriate imaging modality in a variety of urologic scenarios based on ACR AC criteria. Nonetheless, both chatbots lack consistent accuracy and further development is necessary for implementation in clinical settings. For proper use of these AI services in clinical decision making, further developments are needed to improve the workflow of physicians.

Abstract AIM The goal of this study was to understand sex-specific differences in the molecular, clinical and radiological tumor parameters and survival outcomes of Glioblastoma (GBM) patients within the international GBM dataset, known as the ReSPOND (Radiomic Signatures for PrecisiON Diagnostics) consortium. METHODS Sex-based differences were retrospectively studied in 1922 GBM patients from the ReSPOND consortium which includes information from over 14 institutions across 3 continents. The parameters include age, Methylguanine-DNA Methyltransferase (MGMT) promoter methylation status, isocitrate dehydrogenase 1 (IDH1) mutation status, Karnofsky performance status (KPS), extent of resection (EOR), tumor epicenter, volumes, laterality and spatial extent. Non-parametric tests, log-rank test and cox-proportional hazard analysis were performed to understand sex-based differences in tumor parameters, survival rates and hazard ratios. Spatial atlases were generated to understand radiological parameters such as tumor spatial extent. RESULTS GBM in was diagnosed at a median age of 62.6 years in females compared to 61 years in males (p = 0.001). Additionally, 44% females compared to 37% males (p = 0.04) had methylated MGMT and 79% females compared to 73% males (p = 0.004) had IDH1 wildtype. The tumor volumes were smaller in females (necrotic core, edema, and enhancing tumor) compared to males. Females exhibited a higher prevalence of right hemisphere (39.6%) and right temporal lobe tumors (19.7%), while males showed a higher prevalence of left hemisphere (40.3%) left temporal lobe tumors (23.7%). No significant sex-based differences in OS and PFS was observed in overall sample, although longer PFS was observed in elderly (above 60 years) female patients. CONCLUSION This is a first international large cohort study looking at sex-based differences in GBM patients using the ReSPOND consortium data. Several sex-specific differences in the distribution of various tumor phenotypes were noted, however sex was not a contributing factor in OS and PFS.

Objectives To test the feasibility of using 3D MRF maps with radiomics analysis and machine learning in the characterization of adult brain intra-axial neoplasms. Methods 3D MRF acquisition was performed on 78 patients with newly diagnosed brain tumors including 33 glioblastomas (grade IV), 6 grade III gliomas, 12 grade II gliomas, and 27 patients with brain metastases. Regions of enhancing tumor, non-enhancing tumor, and peritumoral edema were segmented and radiomics analysis with gray-level co-occurrence matrices and gray-level run-length matrices was performed. Statistical analysis was performed to identify features capable of differentiating tumors based on type, grade, and isocitrate dehydrogenase (IDH1) status. Receiver operating curve analysis was performed and the area under the curve (AUC) was calculated for tumor classification and grading. For gliomas, Kaplan-Meier analysis for overall survival was performed using MRF T1 features from enhancing tumor region. Results Multiple MRF T1 and T2 features from enhancing tumor region were capable of differentiating glioblastomas from brain metastases. Although no differences were identified between grade 2 and grade 3 gliomas, differentiation between grade 2 and grade 4 gliomas as well as between grade 3 and grade 4 gliomas was achieved. MRF radiomics features were also able to differentiate IDH1 mutant from the wild-type gliomas. Radiomics T1 features for enhancing tumor region in gliomas correlated to overall survival ( p < 0.05). Conclusion Radiomics analysis of 3D MRF maps allows differentiating glioblastomas from metastases and is capable of differentiating glioblastomas from metastases and characterizing gliomas based on grade, IDH1 status, and survival. Key Points • 3D MRF data analysis using radiomics offers novel tissue characterization of brain tumors . • 3D MRF with radiomics offers glioma characterization based on grade, IDH1 status, and overall patient survival .

Magnetic resonance fingerprinting (MRF) is an evolving quantitative MRI framework consisting of unique data acquisition, processing, visualization, and interpretation steps. MRF is capable of simultaneously producing multiple high-resolution property maps including T1, T2, M0, ADC, and T2* measurements. While a relatively new technology, MRF has undergone rapid development for a variety of clinical applications from brain tumor characterization and epilepsy imaging to characterization of prostate cancer, cardiac imaging, among others. This paper will provide a brief overview of current state of MRF technology including highlights of technical and clinical advances. We will conclude with a brief discussion of the challenges that need to be overcome to establish MRF as a quantitative imaging biomarker.

Purpose This is a radiomics study investigating the ability of texture analysis of MRF maps to improve differentiation between intra-axial adult brain tumors and to predict survival in the glioblastoma cohort. Methods Magnetic resonance fingerprinting (MRF) acquisition was performed on 31 patients across 3 groups: 17 glioblastomas, 6 low-grade gliomas, and 8 metastases. Using regions of interest for the solid tumor and peritumoral white matter on T1 and T2 maps, second-order texture features were calculated from gray-level co-occurrence matrices and gray-level run length matrices. Selected features were compared across the three tumor groups using Wilcoxon rank-sum test. Receiver operating characteristic curve analysis was performed for each feature. Kaplan-Meier method was used for survival analysis with log rank tests. Results Low-grade gliomas and glioblastomas had significantly higher run percentage, run entropy, and information measure of correlation 1 on T1 than metastases (p < 0.017). The best separation of all three tumor types was seen utilizing inverse difference normalized and homogeneity values for peritumoral white matter in both T1 and T2 maps (p < 0.017). In solid tumor T2 maps, lower values in entropy and higher values of maximum probability and high-gray run emphasis were associated with longer survival in glioblastoma patients (p < 0.05). Several texture features were associated with longer survival in glioblastoma patients on peritumoral white matter T1 maps (p < 0.05). Conclusion Texture analysis of MRF-derived maps can improve our ability to differentiate common adult brain tumors by characterizing tumor heterogeneity, and may have a role in predicting outcomes in patients with glioblastoma.

Existing glioblastoma (GB) infiltration models are often limited by lack of true infiltration labels and employ the assumption that edema closer to tumor has higher infiltrative potential relative to distant edema. Here, we propose a semi-supervised learning scheme that incorporates pretraining on the near-far heuristic and spatial pseudo labeling using true infiltration labels for voxel-wise tumor infiltration prediction. Our results show improved classification performance following finetuning on labeled infiltration data compared to training on the near-far heuristic alone and indicate the potential in employing MR fingerprinting-based models to guide GB diagnosis and treatment.

Motivation: Pre-operative glioblastoma (GBM) infiltration prediction models rely on manual infiltration risk (IR) prior segmentation which is tedious, requires expert input, and is highly variable. Goal(s): Automation is needed for fast segmentation. A data-driven method would account for GBM heterogeneity and be independent of specific MRI input for applicability to clinical protocols. Approach: IR priors are grown using modified triplet loss with inter-prior and intra-prior terms to ensure priors are distinct from each other and maintain similarity within individual priors. Results: TripleSeq generated more consistent IR priors compared to manual segmentation. TripleSeq-trained models showed good classification (> 85% mean accuracy) of ground truth infiltration. Impact: Glioblastoma (GBM) infiltration inevitably leads to tumor recurrence and progression. We introduce an automatic method to generate infiltration risk priors for improved GBM infiltration machine learning prediction, which applied pre-operatively can identify at-risk peritumoral regions for targeted neurosurgery and radiotherapy.