Radiology Workflow Research Articles

Streamlining Radiology Reporting: A hands-free approach with voice-to-text and generative AI

ObjectiveIn radiology, report generation is critical for patient management, though can be time-consuming and labor-intensive. This study aims to investigate the feasibility of a hands-free radiology reporting system, leveraging voice-to-text technology and generative AI to improve time efficiency, report standardization, and reduce radiologist workload. Methods100 chest and musculoskeletal radiographs reports were generated using both traditional methods and an automated process using generative AI. To use generative AI, a radiologist dictated their findings into a voice-to-text software (Dragon), creating a raw text transcript. GPT-4 was then used to develop a report based on our institution’s template. Completion time for each traditional report and voice-to-text transcript was recorded. All reports were then evaluated for comprehensiveness, clarity, factual accuracy, and conciseness on a 5-point Likert scale. ResultsThe AI-driven system demonstrated considerable proficiency in transcribing and generating radiology reports, albeit with occasional inaccuracies. While it achieved a high level of precision in standard scenarios, its performance varied in more complex cases. Notably, the system significantly reduced the time taken to generate reports by 38% (p < 0.0001), signifying a potential increase in overall radiological workflow efficiency. ConclusionThis study highlights the potential of voice-to-text and generative AI integration in radiology reporting. Increased time efficiency, even in standard scenarios, can allow radiologists to focus more on complex cases and patient care. However, further development and refinement are required to address comprehensiveness and occasional inaccuracies. Ongoing advancements in AI and speech recognition technologies suggest a positive outlook for future implementations in medical reporting.

Artificial intelligence in diagnostic radiology for dose management : Advances and perspectives using the example of computed tomography

Imaging procedures employing ionizing radiation require compliance with European directives and national regulations in order to protect patients. Each exposure must be indicated, individually adapted, and documented. Unacceptable dose exceedances must be detected and reported. These tasks are time-consuming and require meticulous diligence. Computed tomography (CT) is the most important contributor to medical radiation exposure. Optimizing the patient's dose is therefore mandatory. Use of modern technology and reconstruction algorithms already reduces exposure. Checking the indication, planning, and performing the examination are further important process steps with regard to radiation protection. Patient exposure is usually monitored by dose management systems (DMS). In special cases, arisk assessment is required by calculating the organ doses. Artificial intelligence (AI)-assisted techniques are increasingly used in various steps of the process: they support examination planning, improve patient positioning, and enable automated scan length adjustments. They also provide real-time estimates of individual organ doses. The integration of AI into medical imaging is proving successful in terms of dose optimization in various areas of the radiological workflow, from reconstruction to examination planning and performing exams. However, the use of AI in conjunction with DMS has not yet been considered on alarge scale. AI processes offer promising tools to support dose management. However, their implementation in the clinical setting requires further research, extensive validation, and continuous monitoring.

Applications of artificial intelligence in radiology

Artificial intelligence (AI) is increasingly finding its way into routine radiological work. Presentation of the current advances and applications of AI along the entire radiological patient journey. Systematic literature review of established AI techniques and current research projects, with reference to consensus recommendations. The applications of AI in radiology cover awide range, starting with AI-supported scheduling and indications assessment, extending to AI-enhanced image acquisition and reconstruction techniques that have the potential to reduce radiation doses in computed tomography (CT) or acquisition times in magnetic resonance imaging (MRI), while maintaining comparable image quality. These include computer-aided detection and diagnosis, such as fracture recognition or nodule detection. Additionally, methods such as worklist prioritization and structured reporting facilitated by large language models enable arethinking of the reporting process. The use of AI promises to increase the efficiency of all steps of the radiology workflow and an improved diagnostic accuracy. To achieve this, seamless integration into technical workflows and proven evidence of AI systems are necessary. Applications of AI have the potential to profoundly influence the role of radiologists in the future.

Deep learning-based detection and classification of intracranial tumors on magnetic resonance imaging

AbstractBackgroundWe evaluated the capability of an AI application to independently detect, segment and classify intracranial tumors in MRI.MethodsIn this retrospective single-centre study, 138 patients (65 female and 73 male) with a mean age of 35 ± 26y were included. 97 were diagnosed with an intracranial neoplasm, while 41 exhibited no intracranial pathology. Inclusion criteria were a 1.5 or 3.0T MRI dataset with the following sequences: T2 axial, T1 axial pre- and post-contrast with a slice thickness between 3 and 6 mm and no previous brain surgery. Image analysis was performed by two human readers (R1 = 5 years and R2 = 10 years of experience in brain MRI) and a deep learning (DL)-based AI model. Sensitivity, specificity and accuracy of the AI model and the human readers to detect and correctly classify brain tumors were measured. Histological results served as the gold standard.ResultsThe AI model reached a sensitivity of 93.81% [87.02–97.70] and a specificity of 63.41% [46.94–77.88], while human readers reached 100% [96.27–100.00] and 100% [91.40–100.00], respectively. Human readers provided a significantly higher accuracy rate with R1 0.93 (95% CI: 0.88–0.97) and R2 0.98 (95% CI: 0.94, 0.99) vs. 0.74 (95% CI: 0.66–0.81) for the AI model (P-value &lt;0.001).ConclusionThe underlying DL-based AI algorithm can independently identify and segment intracranial tumors while providing satisfactory results for establishing the correct diagnosis. Despite its current inferiority compared to experienced radiologists, it still experiences ongoing development and it is a step towards developing an artificial intelligence-augmented radiology workflow.

Applying queueing theory to evaluate wait-time-savings of triage algorithms

In the past decade, artificial intelligence (AI) algorithms have made promising impacts in many areas of healthcare. One application is AI-enabled prioritization software known as computer-aided triage and notification (CADt). This type of software as a medical device is intended to prioritize reviews of radiological images with time-sensitive findings, thus shortening the waiting time for patients with these findings. While many CADt devices have been deployed into clinical workflows and have been shown to improve patient treatment and clinical outcomes, quantitative methods to evaluate the wait-time-savings from their deployment are not yet available. In this paper, we apply queueing theory methods to evaluate the wait-time-savings of a CADt by calculating the average waiting time per patient image without and with a CADt device being deployed. We study two workflow models with one or multiple radiologists (servers) for a range of AI diagnostic performances, radiologist’s reading rates, and patient image (customer) arrival rates. To evaluate the time-saving performance of a CADt, we use the difference in the mean waiting time between the diseased patient images in the with-CADt scenario and that in the without-CADt scenario as our performance metric. As part of this effort, we have developed and also share a software tool to simulate the radiology workflow around medical image interpretation, to verify theoretical results, and to provide confidence intervals for the performance metric we defined. We show quantitatively that a CADt triage device is more effective in a busy, short-staffed reading setting, which is consistent with our clinical intuition and simulation results. Although this work is motivated by the need for evaluating CADt devices, the evaluation methodology presented in this paper can be applied to assess the time-saving performance of other types of algorithms that prioritize a subset of customers based on binary outputs.

Radiograph accelerated detection and identification of cancer in the lung (RADICAL): a mixed methods study to assess the clinical effectiveness and acceptability of Qure.ai artificial intelligence software to prioritise chest X-ray (CXR) interpretation

IntroductionDiagnosing and treating lung cancer in early stages is essential for survival outcomes. The chest X-ray (CXR) remains the primary screening tool to identify lung cancers in the UK; however,...

Improved Automated Quality Control of Skeletal Wrist Radiographs Using Deep Multitask Learning.

Radiographic quality control is an integral component of the radiology workflow. In this study, we developed a convolutional neural network model tailored for automated quality control, specifically designed to detect and classify key attributes of wrist radiographs including projection, laterality (based on the right/left marker), and the presence of hardware and/or casts. The model's primary objective was to ensure the congruence of results with image requisition metadata to pass the quality assessment. Using a dataset of 6283 wrist radiographs from 2591 patients, our multitask-capable deep learning model based on DenseNet 121 architecture achieved high accuracy in classifying projections (F1 Score of 97.23%), detecting casts (F1 Score of 97.70%), and identifying surgical hardware (F1 Score of 92.27%). The model's performance in laterality marker detection was lower (F1 Score of 82.52%), particularly for partially visible or cut-off markers. This paper presents a comprehensive evaluation of our model's performance, highlighting its strengths, limitations, and the challenges encountered during its development and implementation. Furthermore, we outline planned future research directions aimed at refining and expanding the model's capabilities for improved clinical utility and patient care in radiographic quality control.

GPT-4 Vision: Multi-Modal Evolution of ChatGPT and Potential Role in Radiology.

GPT-4 Vision (GPT-4V) represents a significant advancement in multimodal artificial intelligence, enabling text generation from images without specialized training. This marks the transformation of ChatGPT as a large language model (LLM) into GPT-4's promised large multimodal model (LMM). As these AI models continue to advance, they may enhance radiology workflow and aid with decision support. This technical note explores potential GPT-4V applications in radiology and evaluates performance for sample tasks.GPT-4V capabilities were tested using images from the web, personal and institutional teaching files, and hand-drawn sketches. Prompts evaluated scientific figure analysis, radiologic image reporting, image comparison, handwriting interpretation, sketch-to-code, and artistic expression. In this limited demonstration of GPT-4V's capabilities, it showed promise in classifying images, counting entities, comparing images, and deciphering handwriting and sketches. However, it exhibited limitations in detecting some fractures, discerning a change in size of lesions, accurately interpreting complex diagrams, and consistently characterizing radiologic findings. Artistic expression responses were coherent. WhileGPT-4V may eventually assist with tasks related to radiology, current reliability gaps highlight the need for continued training and improvement before consideration for any medical use by the general public and ultimately clinical integration. Future iterations could enable a virtual assistant to discuss findings, improve reports, extract data from images, provide decision support based on guidelines, white papers, and appropriateness criteria. Human expertise remain essential for safe practice and partnerships between physicians, researchers, and technology leaders are necessary to safeguard against risks like bias and privacy concerns.

Evaluating Large Language Models for Automated Reporting and Data Systems Categorization: Cross-Sectional Study.

Large language models show promise for improving radiology workflows, but their performance on structured radiological tasks such as Reporting and Data Systems (RADS) categorization remains unexplored. This study aims to evaluate 3 large language model chatbots-Claude-2, GPT-3.5, and GPT-4-on assigning RADS categories to radiology reports and assess the impact of different prompting strategies. This cross-sectional study compared 3 chatbots using 30 radiology reports (10 per RADS criteria), using a 3-level prompting strategy: zero-shot, few-shot, and guideline PDF-informed prompts. The cases were grounded in Liver Imaging Reporting & Data System (LI-RADS) version 2018, Lung CT (computed tomography) Screening Reporting & Data System (Lung-RADS) version 2022, and Ovarian-Adnexal Reporting & Data System (O-RADS) magnetic resonance imaging, meticulously prepared by board-certified radiologists. Each report underwent 6 assessments. Two blinded reviewers assessed the chatbots' response at patient-level RADS categorization and overall ratings. The agreement across repetitions was assessed using Fleiss κ. Claude-2 achieved the highest accuracy in overall ratings with few-shot prompts and guideline PDFs (prompt-2), attaining 57% (17/30) average accuracy over 6 runs and 50% (15/30) accuracy with k-pass voting. Without prompt engineering, all chatbots performed poorly. The introduction of a structured exemplar prompt (prompt-1) increased the accuracy of overall ratings for all chatbots. Providing prompt-2 further improved Claude-2's performance, an enhancement not replicated by GPT-4. The interrun agreement was substantial for Claude-2 (k=0.66 for overall rating and k=0.69 for RADS categorization), fair for GPT-4 (k=0.39 for both), and fair for GPT-3.5 (k=0.21 for overall rating and k=0.39 for RADS categorization). All chatbots showed significantly higher accuracy with LI-RADS version 2018 than with Lung-RADS version 2022 and O-RADS (P<.05); with prompt-2, Claude-2 achieved the highest overall rating accuracy of 75% (45/60) in LI-RADS version 2018. When equipped with structured prompts and guideline PDFs, Claude-2 demonstrated potential in assigning RADS categories to radiology cases according to established criteria such as LI-RADS version 2018. However, the current generation of chatbots lags in accurately categorizing cases based on more recent RADS criteria.

Artificial intelligence in cardiovascular radiology : Image acquisition, image reconstruction and workflow optimization

Artificial intelligence (AI) has the potential to fundamentally change radiology workflow. This review article provides an overview of AI applications in cardiovascular radiology with afocus on image acquisition, image reconstruction, and workflow optimization. First, established applications of AI are presented for cardiovascular computed tomography (CT) and magnetic resonance imaging (MRI). Building on this, we describe the range of applications that are currently being developed and evaluated. The practical benefits, opportunities, and potential risks of artificial intelligence in cardiovascular imaging are critically discussed. The presentation is based on the relevant specialist literature and our own clinical and scientific experience. AI-based techniques for image reconstruction are already commercially available and enable dose reduction in cardiovascular CT and accelerated image acquisition in cardiac MRI. Postprocessing of cardiovascular CT and MRI examinations can already be considerably simplified using established AI-based segmentation algorithms. In contrast, the practical benefits of many AI applications aimed at the diagnosis of cardiovascular diseases are less evident. Potential risks such as automation bias and considerations regarding cost efficiency should also be taken into account. In amarket characterized by great expectations and rapid technical development, it is important to realistically assess the practical benefits of AI applications for your own hospital or practice.

Selecting the Best Radiology Workflow Efficiency Applications.

In the rapidly evolving digital radiology landscape, a surge in solutions has emerged including more than 500 artificial intelligence applications that have received 510k clearance by the FDA. Moreover, there is an extensive number of non-regulated applications, specifically designed to enhance workflow efficiency within radiology departments. These efficiency applications offer tremendous opportunities to resolve operational pain points and improve efficiency for radiology practices worldwide. However, selecting the most effective workflow efficiency applications presents a major challenge due to the multitude of available solutions and unclear evaluation criteria. In this article, we share our perspective on how to structure the broad field of workflow efficiency applications and how to objectively assess individual solutions. Along the different stages of the radiology workflow, we highlight 31 key operational pain points that radiology practices face and match them with features of workflow efficiency apps aiming to address them. A framework to guide practices in assessing and curating workflow efficiency applications is introduced, addressing key dimensions, including a solution's pain point coverage, efficiency claim strength, evidence and credibility, ease of integration, and usability. We apply this framework in a large-scale analysis of workflow efficiency applications in the market, differentiating comprehensive workflow efficiency ecosystems seeking to address a multitude of pain points through a unified solution from workflow efficiency niche apps following a targeted approach to address individual pain points. Furthermore, we propose an approach to quantify the financial benefits generated by different types of applications that can be leveraged for return-on-investment calculations.

Patient-centered radiology reports with generative artificial intelligence: adding value to radiology reporting

The purposes were to assess the efficacy of AI-generated radiology reports in terms of report summary, patient-friendliness, and recommendations and to evaluate the consistent performance of report quality and accuracy, contributing to the advancement of radiology workflow. Total 685 spine MRI reports were retrieved from our hospital database. AI-generated radiology reports were generated in three formats: (1) summary reports, (2) patient-friendly reports, and (3) recommendations. The occurrence of artificial hallucinations was evaluated in the AI-generated reports. Two radiologists conducted qualitative and quantitative assessments considering the original report as a standard reference. Two non-physician raters assessed their understanding of the content of original and patient-friendly reports using a 5-point Likert scale. The scoring of the AI-generated radiology reports were overall high average scores across all three formats. The average comprehension score for the original report was 2.71 ± 0.73, while the score for the patient-friendly reports significantly increased to 4.69 ± 0.48 (p < 0.001). There were 1.12% artificial hallucinations and 7.40% potentially harmful translations. In conclusion, the potential benefits of using generative AI assistants to generate these reports include improved report quality, greater efficiency in radiology workflow for producing summaries, patient-centered reports, and recommendations, and a move toward patient-centered radiology.

Integrating and Adopting AI in the Radiology Workflow: A Primer for Standards and Integrating the Healthcare Enterprise (IHE) Profiles.

The deployment of artificial intelligence (AI) solutions in radiology practice creates new demands on existing imaging workflow. Accommodating custom integrations creates a substantial operational and maintenance burden. These custom integrations also increase the likelihood of unanticipated problems. Standards-based interoperability facilitates AI integration with systems from different vendors into a single environment by enabling seamless exchange between information systems in the radiology workflow. Integrating the Healthcare Enterprise (IHE) is an initiative to improve how computer systems share information across health care domains, including radiology. IHE integrates existing standards-such as Digital Imaging and Communications in Medicine, Health Level Seven, and health care lexicons and ontologies (ie, LOINC, RadLex, SNOMED Clinical Terms)-by mapping data elements from one standard to another. IHE Radiology manages profiles (standards-based implementation guides) for departmental workflow and information sharing across care sites, including profiles for scaling AI processing traffic and integrating AI results. This review focuses on the need for standards-based interoperability to scale AI integration in radiology, including a brief review of recent IHE profiles that provide a framework for AI integration. This review also discusses challenges and additional considerations for AI integration, including technical, clinical, and policy perspectives.

Deep multiscale convolutional feature learning for intracranial hemorrhage classification and weakly supervised localization

ObjectiveThis study evaluated the performance of attentional fusion model-based multiscale features in classifying intracerebral hemorrhage and the localization of bleeding focus based on weakly supervised target localization. MethodsA publicly available dataset provided by the American College of Neuroradiology (ASNR) was used, consisting of 750,000 computed tomography (CT) scans of the brain, manually marked by radiologists for intracranial hemorrhage and five hemorrhage subtypes. A multiscale feature classification and weakly supervised localization framework based on an attentional fusion mechanism were applied, which could be annotated at the slice level and provided intracranial hemorrhage classification and hemorrhage focus localization. ResultsThe designed framework achieved excellent performance for classification and localization. The area under the curve (AUC) for predicting bleeding was 0.973. High AUC values were observed for the five hemorrhage subtypes (epidural AUC = 0.891, subdural AUC = 0.991, subarachnoid AUC = 0.983, intraventricular AUC = 0.995, intraparenchymal AUC = 0.990). This model outperformed the average entry-level radiology trainee compared to previously reported data. ConclusionThe designed method quickly and accurately detected intracerebral hemorrhage, classifying hemorrhage subtypes and locating bleeding points with image-level annotation alone. The results indicate that this framework can significantly reduce diagnostic time while improving the detection of intracerebral hemorrhage in emergencies. It can thus be integrated into the diagnostic radiology workflow in the future.

Radiologically derived 3D virtual models for neurosurgical planning

Three dimensional (3D) virtual models for neurosurgery have demonstrated substantial clinical utility, especially for neuro-oncological cases. Computer-aided design (CAD) modelling of radiological images can provide realistic and high-quality 3D models which neurosurgeons may use pre-operatively for surgical planning. 3D virtual models are useful as they are the basis for other models that build off this design. 3D virtual models are quick to segment but can also be easily added to normal neurosurgical and radiological workflow without disruption. Three anatomically complex neuro-oncology cases that were referred from a single institution by three different neurosurgeons were segmented and 3D virtual models were created for pre-operative surgical planning. A face-to-face interview was performed with the surgeons after the models were delivered to gauge the usefulness of the model in pre-surgical planning. All three neurosurgeons found that the 3D virtual model was useful for presurgical planning. Specifically, the virtual model helped in planning operative positioning, understanding spatial relationship between lesion and surrounding critical anatomy and identifying anatomy that will be encountered intra-operatively in a sequential manner. It provided benefit in Multidisciplinary team (MDT) meetings and patient education for shared decision making.3D virtual models are beneficial for pre-surgical planning and patient education for shared decision making for neurosurgical neuro-oncology cases. We believe this could be further expanded to other surgical specialties. The integration of 3D virtual models into normal workflow as the initial step will provide an easier transition into modalities that build off the virtual models such as printed, virtual, augmented and mixed reality models.

A novel reporting workflow for automated integration of artificial intelligence results into structured radiology reports

ObjectivesArtificial intelligence (AI) has tremendous potential to help radiologists in daily clinical routine. However, a seamless, standardized, and time-efficient way of integrating AI into the radiology workflow is often lacking. This constrains the full potential of this technology. To address this, we developed a new reporting pipeline that enables automated pre-population of structured reports with results provided by AI tools.MethodsFindings from a commercially available AI tool for chest X-ray pathology detection were sent to an IHE-MRRT-compliant structured reporting (SR) platform as DICOM SR elements and used to automatically pre-populate a chest X-ray SR template. Pre-populated AI results could be validated, altered, or deleted by radiologists accessing the SR template. We assessed the performance of this newly developed AI to SR pipeline by comparing reporting times and subjective report quality to reports created as free-text and conventional structured reports.ResultsChest X-ray reports with the new pipeline could be created in significantly less time than free-text reports and conventional structured reports (mean reporting times: 66.8 s vs. 85.6 s and 85.8 s, respectively; both p < 0.001). Reports created with the pipeline were rated significantly higher quality on a 5-point Likert scale than free-text reports (p < 0.001).ConclusionThe AI to SR pipeline offers a standardized, time-efficient way to integrate AI-generated findings into the reporting workflow as parts of structured reports and has the potential to improve clinical AI integration and further increase synergy between AI and SR in the future.Critical relevance statementWith the AI-to-structured reporting pipeline, chest X-ray reports can be created in a standardized, time-efficient, and high-quality manner. The pipeline has the potential to improve AI integration into daily clinical routine, which may facilitate utilization of the benefits of AI to the fullest.Key points• A pipeline was developed for automated transfer of AI results into structured reports.• Pipeline chest X-ray reporting is faster than free-text or conventional structured reports.• Report quality was also rated higher for reports created with the pipeline.• The pipeline offers efficient, standardized AI integration into the clinical workflow.Graphical

Unlocking the Value: Quantifying the Return on Investment of Hospital Artificial Intelligence

PurposeA comprehensive return on investment (ROI) calculator was developed to evaluate the monetary and nonmonetary benefits of an artificial intelligence (AI)–powered radiology diagnostic imaging platform to inform decision makers interested in adopting AI. MethodsA calculator was constructed to calculate comparative costs, estimated revenues, and quantify the clinical value of using an AI platform compared with no use of AI in radiology workflows of a US hospital over a 5-year time horizon. Parameters were determined on the basis of expert interviews and a literature review. Scenario and deterministic sensitivity analyses were conducted to evaluate calculator drivers. ResultsIn the calculator, the introduction of an AI platform into the hospital radiology workflow resulted in labor time reductions and delivery of an ROI of 451% over a 5-year period. The ROI was increased to 791% when radiologist time savings were considered. Time savings for radiologists included more than 15 8-hour working days of waiting time, 78 days in triage time, 10 days in reading time, and 41 days in reporting time. Using the platform also provided revenue benefits for the hospital in bringing in patients for clinically beneficial follow-up scans, hospitalizations, and treatment procedures. Results were sensitive to the time horizon, health center setting, and number of scans performed. Among those, the most influential outcome was the number of additional necessary treatments performed because of AI identification of patients. ConclusionsThe authors demonstrate a substantial 5-year ROI of implementing an AI platform in a stroke management–accredited hospital. The ROI calculator may be useful for decision makers evaluating AI-powered radiology platforms.

Theory of radiologist interaction with instant messaging decision support tools: A sequential-explanatory study.

Radiology specific clinical decision support systems (CDSS) and artificial intelligence are poorly integrated into the radiologist workflow. Current research and development efforts of radiology CDSS focus on 4 main interventions, based around exam centric time points-after image acquisition, intra-report support, post-report analysis, and radiology workflow adjacent. We review the literature surrounding CDSS tools in these time points, requirements for CDSS workflow augmentation, and technologies that support clinician to computer workflow augmentation. We develop a theory of radiologist-decision tool interaction using a sequential explanatory study design. The study consists of 2 phases, the first a quantitative survey and the second a qualitative interview study. The phase 1 survey identifies differences between average users and radiologist users in software interventions using the User Acceptance of Information Technology: Toward a Unified View (UTAUT) framework. Phase 2 semi-structured interviews provide narratives on why these differences are found. To build this theory, we propose a novel solution called Radibot-a conversational agent capable of engaging clinicians with CDSS as an assistant using existing instant messaging systems supporting hospital communications. This work contributes an understanding of how radiologist-users differ from the average user and can be utilized by software developers to increase satisfaction of CDSS tools within radiology.

Formal Radiologist Interpretations of Intraoperative Spine Radiographs Have Low Clinical Value.

Retrospective cohort. To evaluate the clinical relevance, usefulness, and financial implications of intraoperative radiograph interpretation by radiologists in spine surgery. Due to rising healthcare costs, spine surgery is under scrutiny to maximize value-based care. Formal radiographic analysis remains a potential source of unnecessary healthcare costs, especially for intra-operative radiographs. A retrospective cohort analysis was performed on all adult elective spine surgeries at a single institution between July 2020 and July 2021. Demographic and radiographic data was collected, including intraoperative localization and post-instrumentation radiographs. Financial data was obtained through the institution's price estimator. Radiographic characteristics included time from radiographic imaging to completion of radiologist interpretation report, completion of radiologist interpretation report prior to the conclusion of surgical procedure, clinical relevance, and clinical usefulness. Reports were considered clinically relevant if spinal level of the procedure was described and clinically useful if completed prior to conclusion of the procedure and deemed clinically relevant. 481 intraoperative localization and post-instrumentation radiographs from 360 patients revealed a median delay of 128 minutes between imaging and completion of interpretive report. Only 38.9% of reports were completed before conclusion of surgery. There were 79.4% deemed clinically relevant and only 33.5% were clinically useful. Localization reports were completed more frequently before conclusion of surgery (67.2% vs. 34.4%), but with lower clinical relevance (90.1% vs. 98.5%) and clinical usefulness (60.3% vs. 33.6%) than post-instrumentation reports. Each patient was charged $32-$34 for interpretation fee, cumulating a minimum total cost of $15,392. Formal radiographic interpretation of intraoperative spine radiographs was of low clinical utility for spine surgeons. Institutions should consider optimizing radiology workflows to improve timeliness and clinical relevance or evaluate the necessity of reflexive consultation to radiology for intraoperative imaging interpretation to ensure that value-based care is maximized during spine surgeries. 3.

Segmentation of Pneumothorax on Chest CTs Using Deep Learning Based on Unet-Resnet-50 Convolutional Neural Network Structure

Objective: Pneumothorax refers to an abnormal accumulation of air in the pleural cavity. This condition is significant in terms of health and can provide a life-threatening risk, particularly when it is extensive or occurs alongside other medical conditions. Nevertheless, the scarcity of work on chest CT segmentation arises from the challenge of acquiring pixel-level annotations for chest X-rays. This paper presents and assesses a deep learning approach utilizing the Unet-Resnet-50 convolutional neural network architecture for accurately segmenting pneumothoraces on chest computed tomography (CT) images. Methods: We employed a private dataset including 2627 manually annotated slices obtained from 16 patients. We assessed the model's performance by measuring the dice similarity coefficient (DSC or F1 score), accuracy, area under the curve (AUC), precision, and recall on both the validation and test sets. Results: The binary accuracy of the test set was 0.9990; the precision was 0.9681; and the DSC was 0.9644. Although it contains less data (16 patients), we found that our deep learning-based artificial intelligence model has effective and compatible results with the literature. Conclusion: Deep learning models that will be used to detect common pathologies in thoracic surgery practice, such as pneumothorax, to determine their localization and size, will provide faster diagnosis and treatment to patients, and especially improve radiology workflow.