Redefining the structure of structured reporting in radiology

Software-assisted structured reporting and semi-automated TNM classification for NSCLC staging in a multicenter proof of concept study

OBJECTIVES

In this multi-center study, we proposed a structured reporting (SR) framework for non-small cell lung cancer (NSCLC) and developed a software-assisted tool to automatically translate image-based findings and annotations into TNM classifications. The aim of this study was to validate the software-assisted SR tool for NSCLC, assess its potential clinical impact in a proof-of-concept study, and evaluate current reporting standards in participating institutions.

METHODS

A framework for SR and staging of NSCLC was developed in a multi-center collaboration. SR annotations and descriptions were used to generate semi-automated TNM classification. The SR and TNM classification tools were evaluated by nine radiologists on n = 20 representative [18F]FDG PET/CT studies and compared to the free text reporting (FTR) strategy. Results were compared to a multidisciplinary team reference using a generalized linear mixed model (GLMM). Additionally, participants were surveyed on their experience with SR and TNM classification.

RESULTS

Overall, GLMM analysis revealed that readers using SR were 1.707 (CI: 1.137-2.585) times more likely to correctly classify TNM status compared to FTR strategy (p = 0.01) resulting in increased overall TNM correctness in 71.9% (128/178) of cases compared to 62.8% (113/180) FTR. The primary source of variation in classification accuracy was explained by case complexity. Participants rated the potential impact of SR and semi-automated TNM classification as positive across all categories with improved scores after template validation.

CONCLUSION

This multi-center study yielded an effective software-assisted SR framework for NSCLC. The SR and semi-automated classification tool improved TNM classification and were perceived as valuable.

CRITICAL RELEVANCE STATEMENT

Software-assisted SR provides robust input for semi-automated rule-based TNM classification in non-small-cell lung carcinoma (NSCLC), improves TNM correctness compared to FTR, and was perceived as valuable by radiology physicians.

KEY POINTS

SR and TNM classification are underutilized across participating centers for NSCLC staging. Software-assisted SR has emerged as a promising strategy for oncologic assessment. Software-assisted SR facilitates semi-automated TNM classification with improved staging accuracy compared to free-text reports in NSCLC.

Large language models for structured reporting in radiology: past, present, and future

Structured reporting (SR) has long been a goal in radiology to standardize and improve the quality of radiology reports. Despite evidence that SR reduces errors, enhances comprehensiveness, and increases adherence to guidelines, its widespread adoption has been limited. Recently, large language models (LLMs) have emerged as a promising solution to automate and facilitate SR. Therefore, this narrative review aims to provide an overview of LLMs for SR in radiology and beyond. We found that the current literature on LLMs for SR is limited, comprising ten studies on the generative pre-trained transformer (GPT)-3.5 (n = 5) and/or GPT-4 (n = 8), while two studies additionally examined the performance of Perplexity and Bing Chat or IT5. All studies reported promising results and acknowledged the potential of LLMs for SR, with six out of ten studies demonstrating the feasibility of multilingual applications. Building upon these findings, we discuss limitations, regulatory challenges, and further applications of LLMs in radiology report processing, encompassing four main areas: documentation, translation and summarization, clinical evaluation, and data mining. In conclusion, this review underscores the transformative potential of LLMs to improve efficiency and accuracy in SR and radiology report processing. KEY POINTS: Question How can LLMs help make SR in radiology more ubiquitous? Findings Current literature leveraging LLMs for SR is sparse but shows promising results, including the feasibility of multilingual applications. Clinical relevance LLMs have the potential to transform radiology report processing and enable the widespread adoption of SR. However, their future role in clinical practice depends on overcoming current limitations and regulatory challenges, including opaque algorithms and training data.

Automatic structuring of radiology reports with on-premise open-source large language models

OBJECTIVES

Structured reporting enhances comparability, readability, and content detail. Large language models (LLMs) could convert free text into structured data without disrupting radiologists' reporting workflow. This study evaluated an on-premise, privacy-preserving LLM for automatically structuring free-text radiology reports.

MATERIALS AND METHODS

We developed an approach to controlling the LLM output, ensuring the validity and completeness of structured reports produced by a locally hosted Llama-2-70B-chat model. A dataset with de-identified narrative chest radiograph (CXR) reports was compiled retrospectively. It included 202 English reports from a publicly available MIMIC-CXR dataset and 197 German reports from our university hospital. Senior radiologist prepared a detailed, fully structured reporting template with 48 question-answer pairs. All reports were independently structured by the LLM and two human readers. Bayesian inference (Markov chain Monte Carlo sampling) was used to estimate the distributions of Matthews correlation coefficient (MCC), with [-0.05, 0.05] as the region of practical equivalence (ROPE).

RESULTS

The LLM generated valid structured reports in all cases, achieving an average MCC of 0.75 (94% HDI: 0.70-0.80) and F1 score of 0.70 (0.70-0.80) for English, and 0.66 (0.62-0.70) and 0.68 (0.64-0.72) for German reports, respectively. The MCC differences between LLM and humans were within ROPE for both languages: 0.01 (-0.05 to 0.07), 0.01 (-0.05 to 0.07) for English, and -0.01 (-0.07 to 0.05), 0.00 (-0.06 to 0.06) for German, indicating approximately comparable performance.

CONCLUSION

Locally hosted, open-source LLMs can automatically structure free-text radiology reports with approximately human accuracy. However, the understanding of semantics varied across languages and imaging findings.

KEY POINTS

Question Why has structured reporting not been widely adopted in radiology despite clear benefits and how can we improve this? Findings A locally hosted large language model successfully structured narrative reports, showing variation between languages and findings. Critical relevance Structured reporting provides many benefits, but its integration into the clinical routine is limited. Automating the extraction of structured information from radiology reports enables the capture of structured data while allowing the radiologist to maintain their reporting workflow.

Impact of Structured Reporting of Lower Extremity CT Angiography on Report Quality and Workflow Efficiency

We assessed the effects of structured reporting (SR) of lower extremity CT angiography (CTA) on report quality and workflow efficiency compared with conventional reports (CR). Surveys were conducted at an academic radiology department before and after the introduction of an SR template. Participants (n = 39, 21) rated report quality and report creation effort (1: very dissatisfied/low to 10: very satisfied/high) and whether SR represents an improvement over CR (1: completely disagree to 5: completely agree). Four residents and two supervising radiologists created both CR and SR of 40 CTA examinations. Report creation time was measured and the factual accuracy of residents' reports was judged. Report completeness (median 8.0 vs. 7.0, p = 0.016) and clinical usefulness (7.0 vs. 4.0, p = 0.029) were rated higher for SR. Supervising radiologists found report clarity improved by SR (8.0 vs. 4.5, p = 0.029). Report creation effort was unchanged (7.0 vs. 6.0, p > 0.05). SR was considered an improvement over CR (median 4.0, IQR,3.0-5.0). Report supervision was shortened by SR (6.2 ± 2.0 min vs. 10.6 ± 3.5 min, p < 0.001) but total time for report creation remained unchanged (36.6 ± 12.8 min vs. 36.4 ± 11.0 min, p > 0.05). Factual accuracy of residents' SR was deemed higher (8.0/9.5 vs. 7.0/7.0, p = 0.006/ < 0.001). In conclusion, SR has the potential to improve report quality and workflow efficiency for lower extremity CTA.

Standardised and structured reporting in fetal magnetic resonance imaging: recommendations from the Fetal Task Force of the European Society of Paediatric Radiology

Over the last decades, magnetic resonance imaging (MRI) has emerged as a valuable adjunct to prenatal ultrasound for evaluating fetal malformations. Several radiological societies advocate for standardised and structured reporting practices to enhance the uniformity of imaging language. Compared to narrative formats, standardised and structured reports offer enhanced content quality, minimise reader variability, have the potential to save reporting time, and streamline the communication between specialists by employing a shared lexicon. Structured reporting holds promise for mitigating medico-legal liability, while also facilitating rigorous scientific data analyses and the development of standardised databases. While structured reporting templates for fetal MRI are already in use in some centres, specific recommendations and/or guidelines from international societies are scarce in the literature. The purpose of this paper is to propose a standardised and structured reporting template for fetal MRI to assist radiologists, particularly those with less experience, in delivering systematic reports. Additionally, the paper aims to offer an overview of the anatomical structures that necessitate reporting and the prevalent normative values for fetal biometrics found in current literature.

Reshaping free-text radiology notes into structured reports with generative question answering transformers

BACKGROUND

Radiology reports are typically written in a free-text format, making clinical information difficult to extract and use. Recently, the adoption of structured reporting (SR) has been recommended by various medical societies thanks to the advantages it offers, e.g. standardization, completeness, and information retrieval. We propose a pipeline to extract information from Italian free-text radiology reports that fits with the items of the reference SR registry proposed by a national society of interventional and medical radiology, focusing on CT staging of patients with lymphoma.

METHODS

Our work aims to leverage the potential of Natural Language Processing and Transformer-based models to deal with automatic SR registry filling. With the availability of 174 Italian radiology reports, we investigate a rule-free generative Question Answering approach based on the Italian-specific version of T5: IT5. To address information content discrepancies, we focus on the six most frequently filled items in the annotations made on the reports: three categorical (multichoice), one free-text (free-text), and two continuous numerical (factual). In the preprocessing phase, we encode also information that is not supposed to be entered. Two strategies (batch-truncation and ex-post combination) are implemented to comply with the IT5 context length limitations. Performance is evaluated in terms of strict accuracy, f1, and format accuracy, and compared with the widely used GPT-3.5 Large Language Model. Unlike multichoice and factual, free-text answers do not have 1-to-1 correspondence with their reference annotations. For this reason, we collect human-expert feedback on the similarity between medical annotations and generated free-text answers, using a 5-point Likert scale questionnaire (evaluating the criteria of correctness and completeness).

RESULTS

The combination of fine-tuning and batch splitting allows IT5 ex-post combination to achieve notable results in terms of information extraction of different types of structured data, performing on par with GPT-3.5. Human-based assessment scores of free-text answers show a high correlation with the AI performance metrics f1 (Spearman's correlation coefficients>0.5, p-values<0.001) for both IT5 ex-post combination and GPT-3.5. The latter is better at generating plausible human-like statements, even if it systematically provides answers even when they are not supposed to be given.

CONCLUSIONS

In our experimental setting, a fine-tuned Transformer-based model with a modest number of parameters (i.e., IT5, 220 M) performs well as a clinical information extraction system for automatic SR registry filling task. It can extract information from more than one place in the report, elaborating it in a manner that complies with the response specifications provided by the SR registry (for multichoice and factual items), or that closely approximates the work of a human-expert (free-text items); with the ability to discern when an answer is supposed to be given or not to a user query.

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

Background

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.

Purpose

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.

Material and Methods

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.

Results

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.

Conclusion

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.

Development of image-based decision support systems utilizing information extracted from radiological free-text report databases with text-based transformers

OBJECTIVES

To investigate the potential and limitations of utilizing transformer-based report annotation for on-site development of image-based diagnostic decision support systems (DDSS).

METHODS

The study included 88,353 chest X-rays from 19,581 intensive care unit (ICU) patients. To label the presence of six typical findings in 17,041 images, the corresponding free-text reports of the attending radiologists were assessed by medical research assistants ("gold labels"). Automatically generated "silver" labels were extracted for all reports by transformer models trained on gold labels. To investigate the benefit of such silver labels, the image-based models were trained using three approaches: with gold labels only (MG), with silver labels first, then with gold labels (MS/G), and with silver and gold labels together (MS+G). To investigate the influence of invested annotation effort, the experiments were repeated with different numbers (N) of gold-annotated reports for training the transformer and image-based models and tested on 2099 gold-annotated images. Significant differences in macro-averaged area under the receiver operating characteristic curve (AUC) were assessed by non-overlapping 95% confidence intervals.

RESULTS

Utilizing transformer-based silver labels showed significantly higher macro-averaged AUC than training solely with gold labels (N = 1000: MG 67.8 [66.0-69.6], MS/G 77.9 [76.2-79.6]; N = 14,580: MG 74.5 [72.8-76.2], MS/G 80.9 [79.4-82.4]). Training with silver and gold labels together was beneficial using only 500 gold labels (MS+G 76.4 [74.7-78.0], MS/G 75.3 [73.5-77.0]).

CONCLUSIONS

Transformer-based annotation has potential for unlocking free-text report databases for the development of image-based DDSS. However, on-site development of image-based DDSS could benefit from more sophisticated annotation pipelines including further information than a single radiological report.

CLINICAL RELEVANCE STATEMENT

Leveraging clinical databases for on-site development of artificial intelligence (AI)-based diagnostic decision support systems by text-based transformers could promote the application of AI in clinical practice by circumventing highly regulated data exchanges with third parties.

KEY POINTS

• The amount of data from a database that can be used to develop AI-assisted diagnostic decision systems is often limited by the need for time-consuming identification of pathologies by radiologists. • The transformer-based structuring of free-text radiological reports shows potential to unlock corresponding image databases for on-site development of image-based diagnostic decision support systems. • However, the quality of image annotations generated solely on the content of a single radiology report may be limited by potential inaccuracies and incompleteness of this report.

A Systematic Review on Artificial Intelligence Evaluating Metastatic Prostatic Cancer and Lymph Nodes on PSMA PET Scans

Early detection of metastatic prostate cancer (mPCa) is crucial. Whilst the prostate-specific membrane antigen (PSMA) PET scan has high diagnostic accuracy, it suffers from inter-reader variability, and the time-consuming reporting process. This systematic review was registered on PROSPERO (ID CRD42023456044) and aims to evaluate AI's ability to enhance reporting, diagnostics, and predictive capabilities for mPCa on PSMA PET scans. Inclusion criteria covered studies using AI to evaluate mPCa on PSMA PET, excluding non-PSMA tracers. A search was conducted on Medline, Embase, and Scopus from inception to July 2023. After screening 249 studies, 11 remained eligible for inclusion. Due to the heterogeneity of studies, meta-analysis was precluded. The prediction model risk of bias assessment tool (PROBAST) indicated a low overall risk of bias in ten studies, though only one incorporated clinical parameters (such as age, and Gleason score). AI demonstrated a high accuracy (98%) in identifying lymph node involvement and metastatic disease, albeit with sensitivity variation (62-97%). Advantages included distinguishing bone lesions, estimating tumour burden, predicting treatment response, and automating tasks accurately. In conclusion, AI showcases promising capabilities in enhancing the diagnostic potential of PSMA PET scans for mPCa, addressing current limitations in efficiency and variability.

How to Report PSMA PET

Prostate cancer (PCa) is the most common cancer diagnosed in men in most developed countries and a leading cause of cancer-related morbidity and mortality. Prostate-specific membrane antigen positron emission tomography (PSMA-PET) has become a valuable tool in the staging and assessment of disease recurrence in PCa, and more recently for assessment for treatment eligibility to PSMA radioligand therapy (RLT). Harmonization of PSMA-PET interpretation and synoptic reports are needed to communicate concisely and reproducibly PSMA-PET/CT to referring physicians and to support clinician therapeutic management decisions in various stages of the disease. Uniform image interpretation is also important to provide comparable data between clinical trials and to translate such data from research to daily practice. This review provides an overview of the value of PSMA-PET across the different clinical stages of PCa, discusses published reporting criteria for PSMA-PET, identifies pitfalls in reporting PSMA, and provides recommendations for synoptic reports.

Natural language processing to convert unstructured COVID-19 chest-CT reports into structured reports

Background

Structured reporting has been demonstrated to increase report completeness and to reduce error rate, also enabling data mining of radiological reports. Still, structured reporting is perceived by radiologists as a fragmented reporting style, limiting their freedom of expression.

Purpose

A deep learning-based natural language processing method was developed to automatically convert unstructured COVID-19 chest CT reports into structured reports.

Methods

Two hundred-two COVID-19 chest CT were retrospectively reviewed by two experienced radiologists, who wrote for each exam a free-form text radiological report and coherently filled the template provided by the Italian Society of Medical and Interventional Radiology, used as ground-truth. A semi-supervised convolutional neural network was implemented to extract 62 categorical variables from the report. Two iterations were carried-out, the first without fine-tuning, the second one performing a fine-tuning. The performance was measured using the mean accuracy and the F1 mean score. An error analysis was performed to identify errors entirely attributable to incorrect processing of the model.

Results

The algorithm achieved a mean accuracy of 93.7% and an F1 score 93.8% in the first iteration. Most of the errors were exclusively attributable to wrong inference (46%). In the second iteration the model achieved for both parameters 95,8% and percentage of errors attributable to wrong inference decreased to 26%.

Conclusions

The convolutional neural network achieved an optimal performance in the automated conversion of free-form text into structured radiological reports, overcoming all the limitation attributed to structured reporting and finally paving the way for data mining of radiological report.

ESR paper on structured reporting in radiology-update 2023

Structured reporting in radiology continues to hold substantial potential to improve the quality of service provided to patients and referring physicians. Despite many physicians' preference for structured reports and various efforts by radiological societies and some vendors, structured reporting has still not been widely adopted in clinical routine.While in many countries national radiological societies have launched initiatives to further promote structured reporting, cross-institutional applications of report templates and incentives for usage of structured reporting are lacking. Various legislative measures have been taken in the USA and the European Union to promote interoperable data formats such as Fast Healthcare Interoperability Resources (FHIR) in the context of the EU Health Data Space (EHDS) which will certainly be relevant for the future of structured reporting. Lastly, recent advances in artificial intelligence and large language models may provide innovative and efficient approaches to integrate structured reporting more seamlessly into the radiologists' workflow.The ESR will remain committed to advancing structured reporting as a key component towards more value-based radiology. Practical solutions for structured reporting need to be provided by vendors. Policy makers should incentivize the usage of structured radiological reporting, especially in cross-institutional setting.Critical relevance statement Over the past years, the benefits of structured reporting in radiology have been widely discussed and agreed upon; however, implementation in clinical routine is lacking due-policy makers should incentivize the usage of structured radiological reporting, especially in cross-institutional setting.Key points1. Various national societies have established initiatives for structured reporting in radiology.2. Almost no monetary or structural incentives exist that favor structured reporting.3. A consensus on technical standards for structured reporting is still missing.4. The application of large language models may help structuring radiological reports.5. Policy makers should incentivize the usage of structured radiological reporting.

Investigating the impact of structured reporting on the linguistic standardization of radiology reports through natural language processing over a 10-year period

OBJECTIVES

To investigate how a transition from free text to structured reporting affects reporting language with regard to standardization and distinguishability.

METHODS

A total of 747,393 radiology reports dictated between January 2011 and June 2020 were retrospectively analyzed. The body and cardiothoracic imaging divisions introduced a reporting concept using standardized language and structured reporting templates in January 2016. Reports were segmented by a natural language processing algorithm and converted into a 20-dimension document vector. For analysis, dimensionality was reduced to a 2D visualization with t-distributed stochastic neighbor embedding and matched with metadata. Linguistic standardization was assessed by comparing distinct report types' vector spreads (e.g., run-off MR angiography) between reporting standards. Changes in report type distinguishability (e.g., CT abdomen/pelvis vs. MR abdomen) were measured by comparing the distance between their centroids.

RESULTS

Structured reports showed lower document vector spread (thus higher linguistic similarity) compared with free-text reports overall (21.9 [free-text] vs. 15.9 [structured]; - 27.4%; p < 0.001) and for most report types, e.g., run-off MR angiography (15.2 vs. 1.8; - 88.2%; p < 0.001) or double-rule-out CT (26.8 vs. 10.0; - 62.7%; p < 0.001). No changes were observed for reports continued to be written in free text, e.g., CT head reports (33.2 vs. 33.1; - 0.3%; p = 1). Distances between the report types' centroids increased with structured reporting (thus better linguistic distinguishability) overall (27.3 vs. 54.4; + 99.3 ± 98.4%) and for specific report types, e.g., CT abdomen/pelvis vs. MR abdomen (13.7 vs. 37.2; + 171.5%).

CONCLUSION

Structured reporting and the use of factual language yield more homogenous and standardized radiology reports on a linguistic level, tailored to specific reporting scenarios and imaging studies.

CLINICAL RELEVANCE

Information transmission to referring physicians, as well as automated report assessment and content extraction in big data analyses, may benefit from standardized reporting, due to consistent report organization and terminology used for pathologies and normal findings.

KEY POINTS

• Natural language processing and t-distributed stochastic neighbor embedding can transform radiology reports into numeric vectors, allowing the quantification of their linguistic standardization. • Structured reporting substantially increases reports' linguistic standardization (mean: - 27.4% in vector spread) and distinguishability (mean: + 99.3 ± 98.4% increase in vector distance) compared with free-text reports. • Higher standardization and homogeneity outline potential benefits of structured reporting for information transmission and big data analyses.

How to prepare for a bright future of radiology in Europe

Because artificial intelligence (AI)-powered algorithms allow automated image analysis in a growing number of diagnostic scenarios, some healthcare stakeholders have raised doubts about the future of the entire radiologic profession. Their view disregards not only the role of radiologists in the diagnostic service chain beyond reporting, but also the many multidisciplinary and patient-related consulting tasks for which radiologists are solicited. The time commitment for these non-reporting tasks is considerable but difficult to quantify and often impossible to fulfil considering the current mismatch between workload and workforce in many countries. Nonetheless, multidisciplinary, and patient-centred consulting activities could move up on radiologists' agendas as soon as AI-based tools can save time in daily routine. Although there are many reasons why AI will assist and not replace radiologists as imaging experts in the future, it is important to position the next generation of European radiologists in view of this expected trend. To ensure radiologists' personal professional recognition and fulfilment in multidisciplinary environments, the focus of training should go beyond diagnostic reporting, concentrating on clinical backgrounds, specific communication skills with referrers and patients, and integration of imaging findings with those of other disciplines. Close collaboration between the European Society of Radiology (ESR) and European national radiologic societies can help to achieve these goals. Although each adequate treatment begins with a correct diagnosis, many health politicians see radiologic procedures mainly as a cost factor. Radiologic research should, therefore, increasingly investigate the imaging impact on treatment and outcome rather than focusing mainly on technical improvements and diagnostic accuracy alone.Critical relevance statement Strategies are presented to prepare for a successful future of the radiologic profession in Europe, if AI-powered tools can alleviate the current reporting overload: engaging in multidisciplinary activities (clinical and integrative diagnostics), enhancing the value and recognition of radiologists' role through clinical expertise, focusing radiological research on the impact on diagnosis and outcome, and promoting patient-centred radiology by enhancing communication skills.Key points • AI-powered tools will not replace radiologists but hold promise to reduce the current reporting burden, enabling them to reinvest liberated time in multidisciplinary clinical and patient-related tasks.• The skills and resources for these tasks should be considered when recruiting and teaching the next generation of radiologists, when organising departments and planning staffing.• Communication skills will play an increasing role in both multidisciplinary activities and patient-centred radiology.• The value and importance of a correct and integrative diagnosis and the cost of an incorrect imaging diagnosis should be emphasised when discussing with non-medical stakeholders in healthcare.• The radiologic community in Europe should start now to prepare for a bright future of the profession for the benefit of patients and medical colleagues alike.

Mammography Information Systems: A Survey of Breast Imaging Radiologist Satisfaction and Perspectives

OBJECTIVE

To assess use of mammography information systems (MISs) and explore features associated with breast imaging radiologist satisfaction.

METHODS

A 22-question survey regarding MISs was distributed electronically to the Society of Breast Imaging membership between February 16, 2022 and June 28, 2022. Differences in responses between respondents satisfied and dissatisfied with their MIS were analyzed using Pearson chi-squared test, Fisher exact test, and multivariate logistic regression.

RESULTS

The response rate was 11.4% (228/2007). Most respondents used a commercial MIS (195/228, 85.5%). Most used were Epic (47/228, 21%), MagView (47/228, 21%), and PenRad (37/228, 16%). Only 4.4% (10/228) reported that patient tracking was not integrated with results reporting. The majority (129/226, 57%) reported satisfaction with their MIS. Satisfaction correlated (P < 0.05) with features such as picture archiving and communication system integration, structured reporting, access to physician outcomes metrics, and ability to query data. Less commonly reported features such as non-English language options and recognition of laterality and patient mismatch errors also correlated with satisfaction. Lack of these features correlated with dissatisfaction (P < 0.05). Satisfaction also correlated with adequate training (P < 0.001) and technology support (P < 0.001). On multivariate analysis, longer time using the current MIS was independently associated with satisfaction.

CONCLUSION

Most respondents used a commercial MIS and were satisfied with their system. Satisfied users reported several helpful MIS features and adequate training and support. The survey results could help MIS companies when designing new products and inform radiologists and administrators when considering a new MIS.

Advancements in Standardizing Radiological Reports: A Comprehensive Review

Standardized radiological reports stimulate debate in the medical imaging field. This review paper explores the advantages and challenges of standardized reporting. Standardized reporting can offer improved clarity and efficiency of communication among radiologists and the multidisciplinary team. However, challenges include limited flexibility, initially increased time and effort, and potential user experience issues. The efforts toward standardization are examined, encompassing the establishment of reporting templates, use of common imaging lexicons, and integration of clinical decision support tools. Recent technological advancements, including multimedia-enhanced reporting and AI-driven solutions, are discussed for their potential to improve the standardization process. Organizations such as the ACR, ESUR, RSNA, and ESR have developed standardized reporting systems, templates, and platforms to promote uniformity and collaboration. However, challenges remain in terms of workflow adjustments, language and format variability, and the need for validation. The review concludes by presenting a set of ten essential rules for creating standardized radiology reports, emphasizing clarity, consistency, and adherence to structured formats.

PROSER: A Web-Based Peripheral Blood Smear Interpretation Support Tool Utilizing Electronic Health Record Data

OBJECTIVES

Peripheral blood smear (PBS) interpretation represents a cornerstone of pathology practice and resident training but has remained largely static for decades. Here, we describe a novel PBS interpretation support tool.

METHODS

In a mixed-methods quality improvement study, a web-based clinical decision support (CDS) tool to assist pathologists in PBS interpretation, PROSER, was deployed in an academic hospital over a 2-month period in 2022. PROSER interfaced with the hospital system's electronic health record and data warehouse to obtain and display relevant demographic, laboratory, and medication information for patients with pending PBS consults. PROSER used these data along with morphologic findings entered by the pathologist to draft a PBS interpretation using rule-based logic. We evaluated users' perceptions of PROSER with a Likert-type survey.

RESULTS

PROSER displayed 46 laboratory values with corresponding reference ranges and abnormal flags, allowed for entry of 14 microscopy findings, and computed 2 calculations based on laboratory values; it composed automated PBS reports using a library of 92 prewritten phrases. Overall, PROSER was well received by residents.

CONCLUSIONS

In this quality improvement study, we successfully deployed a web-based CDS tool for PBS interpretation. Future work is needed to quantitatively evaluate this intervention's effects on clinical outcomes and resident training.

Automatic Diagnosis of Spinal Disorders on Radiographic Images: Leveraging Existing Unstructured Datasets With Natural Language Processing

STUDY DESIGN

Retrospective study.

OBJECTIVES

Huge amounts of images and medical reports are being generated in radiology departments. While these datasets can potentially be employed to train artificial intelligence tools to detect findings on radiological images, the unstructured nature of the reports limits the accessibility of information. In this study, we tested if natural language processing (NLP) can be useful to generate training data for deep learning models analyzing planar radiographs of the lumbar spine.

METHODS

NLP classifiers based on the Bidirectional Encoder Representations from Transformers (BERT) model able to extract structured information from radiological reports were developed and used to generate annotations for a large set of radiographic images of the lumbar spine (N = 10 287). Deep learning (ResNet-18) models aimed at detecting radiological findings directly from the images were then trained and tested on a set of 204 human-annotated images.

RESULTS

The NLP models had accuracies between 0.88 and 0.98 and specificities between 0.84 and 0.99; 7 out of 12 radiological findings had sensitivity >0.90. The ResNet-18 models showed performances dependent on the specific radiological findings with sensitivities and specificities between 0.53 and 0.93.

CONCLUSIONS

NLP generates valuable data to train deep learning models able to detect radiological findings in spine images. Despite the noisy nature of reports and NLP predictions, this approach effectively mitigates the difficulties associated with the manual annotation of large quantities of data and opens the way to the era of big data for artificial intelligence in musculoskeletal radiology.

Large language models for structured reporting in radiology: performance of GPT-4, ChatGPT-3.5, Perplexity and Bing

Structured reporting may improve the radiological workflow and communication among physicians. Artificial intelligence applications in medicine are growing fast. Large language models (LLMs) are recently gaining importance as valuable tools in radiology and are currently being tested for the critical task of structured reporting. We compared four LLMs models in terms of knowledge on structured reporting and templates proposal. LLMs hold a great potential for generating structured reports in radiology but additional formal validations are needed on this topic.

Impact of a structured reporting template on the quality of HRCT radiology reports for interstitial lung disease

PURPOSE

This QI study compared the completeness of HRCT radiology reports before and after the implementation of a disease-specific structured reporting template for suspected cases of interstitial lung disease (ILD).

MATERIALS AND METHODS

A pre-post study of radiology reports for HRCT of the thorax at a multicenter health system was performed. Data was collected in 6-month period intervals before (June 2019-November 2019) and after (January 2021-June 2021) the implementation of a disease-specific template. The use of the template was voluntary. The primary outcome measure was the completeness of HRCT reports graded based on the documentation of ten descriptors. The secondary outcome measure assessed which descriptor(s) improved after the intervention.

RESULTS

521 HRCT reports before and 557 HRCT reports after the intervention were reviewed. Of the 557 reports, 118 reports (21%) were created using the structured reporting template. The mean completeness score of the pre-intervention group was 9.20 (SD = 1.08) and the post-intervention group was 9.36 (SD = 1.03) with a difference of -0.155, 95% CI [-0.2822, -0.0285, p < 0.0001]. Within the post-intervention group, the mean completeness score of the unstructured reports was 9.25 (SD = 1.07) and the template reports was 9.93 (SD = 0.25) with a difference of -0.677, 95% CI [-0.7871, -0.5671, p < 0.0001]. After the intervention, the use of two descriptors improved significantly: presence of honeycombing from 78.3% to 85.1% (p < 0.0039) and technique from 90% to 96.6% (p < 0.0001).

DISCUSSION

Shifting to disease-specific structured reporting for HRCT exams of suspected ILD is beneficial, as it improves the completeness of radiology reports. Further research on how to improve the voluntary uptake of a disease-specific template is needed to help increase the acceptance of structured reporting among radiologists.

Implementation of structured reporting in clinical routine: a review of 7 years of institutional experience

BACKGROUND

To evaluate the implementation process of structured reporting (SR) in a tertiary care institution over a period of 7 years.

METHODS

We analysed the content of our image database from January 2016 to December 2022 and compared the numbers of structured reports and free-text reports. For the ten most common SR templates, usage proportions were calculated on a quarterly basis. Annual modality-specific SR usage was calculated for ultrasound, CT, and MRI. During the implementation process, we surveyed radiologists and clinical referring physicians concerning their views on reporting in radiology.

RESULTS

As of December 2022, our reporting platform contained more than 22,000 structured reports. Use of the ten most common SR templates increased markedly since their implementation, leading to a mean SR usage of 77% in Q4 2022. The highest percentages of SR usage were shown for trauma CT, focussed assessment with ultrasound for trauma (FAST), and prostate MRI: 97%, 95%, and 92%, respectively, in 2022. Overall modality-specific SR usage was 17% for ultrasound, 13% for CT, and 6% for MRI in 2022. Both radiologists and referring physicians were more satisfied with structured reports and rated SR better than free-text reporting (FTR) on various attributes.

CONCLUSIONS

The increasing SR usage during the period under review and the positive attitude towards SR among both radiologists and clinical referrers show that SR can be successfully implemented. We therefore encourage others to take this step in order to benefit from the advantages of SR.

KEY POINTS

1. Structured reporting usage increased markedly since its implementation at our institution in 2016. 2. Mean usage for the ten most popular structured reporting templates was 77% in 2022. 3. Both radiologists and referring physicians preferred structured reports over free-text reports. 4. Our data shows that structured reporting can be successfully implemented. 5. We strongly encourage others to implement structured reporting at their institutions.

Transformer-based structuring of free-text radiology report databases

OBJECTIVES

To provide insights for on-site development of transformer-based structuring of free-text report databases by investigating different labeling and pre-training strategies.

METHODS

A total of 93,368 German chest X-ray reports from 20,912 intensive care unit (ICU) patients were included. Two labeling strategies were investigated to tag six findings of the attending radiologist. First, a system based on human-defined rules was applied for annotation of all reports (termed "silver labels"). Second, 18,000 reports were manually annotated in 197 h (termed "gold labels") of which 10% were used for testing. An on-site pre-trained model (T_mlm) using masked-language modeling (MLM) was compared to a public, medically pre-trained model (T_med). Both models were fine-tuned on silver labels only, gold labels only, and first with silver and then gold labels (hybrid training) for text classification, using varying numbers (N: 500, 1000, 2000, 3500, 7000, 14,580) of gold labels. Macro-averaged F1-scores (MAF1) in percent were calculated with 95% confidence intervals (CI).

RESULTS

T_mlm,gold (95.5 [94.5-96.3]) showed significantly higher MAF1 than T_med,silver (75.0 [73.4-76.5]) and T_mlm,silver (75.2 [73.6-76.7]), but not significantly higher MAF1 than T_med,gold (94.7 [93.6-95.6]), T_med,hybrid (94.9 [93.9-95.8]), and T_mlm,hybrid (95.2 [94.3-96.0]). When using 7000 or less gold-labeled reports, T_mlm,gold (N: 7000, 94.7 [93.5-95.7]) showed significantly higher MAF1 than T_med,gold (N: 7000, 91.5 [90.0-92.8]). With at least 2000 gold-labeled reports, utilizing silver labels did not lead to significant improvement of T_mlm,hybrid (N: 2000, 91.8 [90.4-93.2]) over T_mlm,gold (N: 2000, 91.4 [89.9-92.8]).

CONCLUSIONS

Custom pre-training of transformers and fine-tuning on manual annotations promises to be an efficient strategy to unlock report databases for data-driven medicine.

KEY POINTS

• On-site development of natural language processing methods that retrospectively unlock free-text databases of radiology clinics for data-driven medicine is of great interest. • For clinics seeking to develop methods on-site for retrospective structuring of a report database of a certain department, it remains unclear which of previously proposed strategies for labeling reports and pre-training models is the most appropriate in context of, e.g., available annotator time. • Using a custom pre-trained transformer model, along with a little annotation effort, promises to be an efficient way to retrospectively structure radiological databases, even if not millions of reports are available for pre-training.

Intraobserver and Interobserver Agreement between Six Radiologists Describing mpMRI Features of Prostate Cancer Using a PI-RADS 2.1 Structured Reporting Scheme

Clinical practice has revealed ambiguities in PI-RADS v2.1 scoring, but a limited number of studies are available that validate the interreader and intrareader reproducibility of the mpMRI PI-RADS lexicon. We decomposed the PI-RADS rules into a set of common data elements to evaluate the inter- and intraobserver agreement in assessing the individual features included in the PI-RADS lexicon. Six radiologists (three highly experienced, three less experienced) in two sessions independently read thirty-two lesions in the peripheral and transition zone using the structured reporting tool, blinded to clinical MRI indication. The highest agreement between radiologists was observed for the abnormality detection, the evaluation of the type of signal intensity, and the characteristic of benign prostatic hyperplasia. Moderate agreement was reported for dynamic contrast-enhanced images. This resulted in a decrease in abnormality detection (PA = 76.5%) and enhancement indication (PA = 77.3%). The lowest agreement was observed for highly subjective features: shape, signal intensity level, and type of lesion margins. The results indicate the limitations of the PI-RADS v2.1 lexicon in relation to interreader and intrareader reproducibility. We have demonstrated that it is possible to develop structured reporting systems standardized according to the PI-RADS lexicon.

Structured report improves radiology residents' performance in reporting chest high-resolution computed tomography: a study in patients with connective tissue disease

PURPOSE To evaluate the performance of radiology residents (RRs) when using a dedicated structured report (SR) template for chest HRCT in patients with suspected connective tissue disease-interstitial lung disease (CTD-ILD), compared to the traditional narrative report (NR). METHODS We retrospectively evaluated 50 HRCT exams in patients with suspected CTD-ILD. A chest-devoted radiologist reported all the HRCT exams as the reference standard, pointing out pulmonary fibrosis findings (i.e., honeycombing, traction bronchiectasis, reticulation, and volume loss), presence and pattern of ILD, and possible other diagnoses. We divided four RRs into two groups according to their expertise level. In each group, RRs reported all HRCT examinations alternatively with NR or SR, noting each report's reporting time. The Cohen's Kappa, Wilcoxon, and McNemar tests were used for statistical analysis. RESULTS Regarding the pulmonary fibrosis findings, we found higher agreement between RRs and the reference standard reader when using SR than NR, regardless of their expertise level, except for volume loss.RRs' accuracy for "other diagnosis" was higher when using SR than NR, moving from 0.48 to 0.66 in the novel group (p = 0.035) and from 0.44 to 0.80 in the expertise group (p < 0.001). No differences in accuracy were found between ILD presence and ILD pattern. The reporting time was significantly lower (p = 0.001) when using SR than NR. CONCLUSION SR is of value in increasing the reporting of critical chest HRCT findings in the complex CTD-ILD scenario and should be used early and systematically during the residency.

Deep Learning-based Assessment of Oncologic Outcomes from Natural Language Processing of Structured Radiology Reports

PURPOSE

To train a deep natural language processing (NLP) model, using data mined structured oncology reports (SOR), for rapid tumor response category (TRC) classification from free-text oncology reports (FTOR) and to compare its performance with human readers and conventional NLP algorithms.

MATERIALS AND METHODS

In this retrospective study, databases of three independent radiology departments were queried for SOR and FTOR dated from March 2018 to August 2021. An automated data mining and curation pipeline was developed to extract Response Evaluation Criteria in Solid Tumors-related TRCs for SOR for ground truth definition. The deep NLP bidirectional encoder representations from transformers (BERT) model and three feature-rich algorithms were trained on SOR to predict TRCs in FTOR. Models' F1 scores were compared against scores of radiologists, medical students, and radiology technologist students. Lexical and semantic analyses were conducted to investigate human and model performance on FTOR.

RESULTS

Oncologic findings and TRCs were accurately mined from 9653 of 12 833 (75.2%) queried SOR, yielding oncology reports from 10 455 patients (mean age, 60 years ± 14 [SD]; 5303 women) who met inclusion criteria. On 802 FTOR in the test set, BERT achieved better TRC classification results (F1, 0.70; 95% CI: 0.68, 0.73) than the best-performing reference linear support vector classifier (F1, 0.63; 95% CI: 0.61, 0.66) and technologist students (F1, 0.65; 95% CI: 0.63, 0.67), had similar performance to medical students (F1, 0.73; 95% CI: 0.72, 0.75), but was inferior to radiologists (F1, 0.79; 95% CI: 0.78, 0.81). Lexical complexity and semantic ambiguities in FTOR influenced human and model performance, revealing maximum F1 score drops of -0.17 and -0.19, respectively.

CONCLUSION

The developed deep NLP model reached the performance level of medical students but not radiologists in curating oncologic outcomes from radiology FTOR.Keywords: Neural Networks, Computer Applications-Detection/Diagnosis, Oncology, Research Design, Staging, Tumor Response, Comparative Studies, Decision Analysis, Experimental Investigations, Observer Performance, Outcomes Analysis Supplemental material is available for this article. © RSNA, 2022.

Structured Reporting in Radiological Settings: Pitfalls and Perspectives

Objective: The aim of this manuscript is to give an overview of structured reporting in radiological settings. Materials and Method: This article is a narrative review on structured reporting in radiological settings. Particularly, limitations and future perspectives are analyzed. RESULTS: The radiological report is a communication tool for the referring physician and the patients. It was conceived as a free text report (FTR) to allow radiologists to have their own individuality in the description of the radiological findings. However, this form could suffer from content, style, and presentation discrepancies, with a probability of transferring incorrect radiological data. Quality, datafication/quantification, and accessibility represent the three main goals in moving from FTRs to structured reports (SRs). In fact, the quality is related to standardization, which aims to improve communication and clarification. Moreover, a “structured” checklist, which allows all the fundamental items for a particular radiological study to be reported and permits the connection of the radiological data with clinical features, allowing a personalized medicine. With regard to accessibility, since radiological reports can be considered a source of research data, SR allows data mining to obtain new biomarkers and to help the development of new application domains, especially in the field of radiomics. Conclusions: Structured reporting could eliminate radiologist individuality, allowing a standardized approach.

Patient Centered Radiology - An Introduction in Form of a Narrative Review

BACKGROUND

Patient centered radiology represents a crucial aspect for modern sustainable radiology. The definition of patient-centered consists of a focus on patients' individual values and wishes with a respectful integration in medical decisions. In this narrative review we try to give a practical introduction into this complex topic with the extension to a person-centered radiology, which additionally encompasses values and wishes of radiological and other medical colleagues.

METHODS

Medline search between 2010 and 2021 using "patient-centered radiology" with additional subjective selection of articles for this narrative review.

RESULTS

Regarding patients' experiences the main literature focus were patients' fears of examinations (movement restrictions, uncertainty). Most patients would prefer a direct communication with the radiologist after the examination. Regarding interdisciplinary communication the radiological expertise and quality is highly appreciated; however, there was a general wish for more structured- or itemized reporting. Concerning working conditions radiologists were satisfied despite high psychosocial working pressure.

CONCLUSION

Most of the literature on this topic consists of surveys evaluating the current state. Studies on interventions such as improved information before examinations or patient-readable reports are still scarce. There is a dilemma between an increasing radiological workload and the simultaneous wish for more patient-centered approaches such as direct radiologist-patient communications in the daily routine. Still on our way to a more value-based radiology we have to focus on patient communications and a patient-centered medicine.

KEY POINTS

· Patient centered radiology has a focus on the integration of patients' individual values and wishes in their decisions.. · Radiologists are clinicians, who an additional diagnostic and therapeutic surplus for patients and referring physicians.. · The recent literature on this topic consists basically on the evaluation of the current status.. · Most patients prefer a direct communication with the radiologist.. · To gain a "value based" radiology we to focus on an optimized communication with patients and referring physicians..

CITATION FORMAT

· Schreyer AG, Schneider K, Dendl LM et al. Patient Centered Radiology - An Introduction in Form of a Narrative Review. Fortschr Röntgenstr 2022; 194: 873 - 881.

Structured bone marrow report as an assessment tool in patients with hematopoietic disorders

BACKGROUND

There are multiple hematological and other entities (metastases, infections) that can affect the bone marrow (BM). The gold standard imaging technique for BM examination is magnetic resonance imaging (MRI). Technological advances have made it possible to digitalize image files and create applications that help to produce higher quality structured reports, facilitating the analysis of data and unifying the criteria collected, making it possible to fill an existing gap. The aim of this study is to present a structured report model applicable to BM studies by MRI.

METHODS

We have carried out a systematic review following the recommendations of the PRISMA checklist report to explore previous publications applying structured BM MRI reporting. Eligibility criteria: the selection of articles carried out by MeSH thesaurus. Original or review articles of BM pathology assessed by MRI. Our group with a wide experience in the evaluation of BM by MRI have designed a model for BM report using eight items: demographic data, diagnostic suspicion, technical data, type of exam initial or control, distribution and patterns involvement, complications and location, total assessment comments.

RESULTS

We have not found articles that reflect the existence of a structured report of BM examination by MRI. Only one descriptive article has been identified on guidelines for acquisition, interpretation and reporting which refers to a single entity. With the selected parameters, a software has been developed that allows to fill in the sections of the structured report with ease and immediacy and to send the result directly to the clinician.

DISCUSSION

Structured reports are the result of applying a logical structure to the radiological report, and the rules of elaboration comprise several criteria: (I) using a uniform language. The standardization of terminology avoids ambiguity in reporting and makes it easier to compare reports. (II) Accurately describe the radiological findings, following a prescribed order with review questions and answers. (III) Drafting using diagnostic screening tables. (IV) Respect the radiologists' workflow by facilitating the work and not hindering it. The final report of this work has been the product of the clinical-radiological collaboration in our working group.

Automated abstraction of myocardial perfusion imaging reports using natural language processing

BACKGROUND

Findings and interpretations of myocardial perfusion imaging (MPI) studies are documented in free-text MPI reports. MPI results are essential for research, but manual review is prohibitively time consuming. This study aimed to develop and validate an automated method to abstract MPI reports.

METHODS

We developed a natural language processing (NLP) algorithm to abstract MPI reports. Randomly selected reports were double-blindly reviewed by two cardiologists to validate the NLP algorithm. Secondary analyses were performed to describe patient outcomes based on abstracted-MPI results on 16,957 MPI tests from adult patients evaluated for suspected ACS.

RESULTS

The NLP algorithm achieved high sensitivity (96.7%) and specificity (98.9%) on the MPI categorical results and had a similar degree of agreement compared to the physician reviewers. Patients with abnormal MPI results had higher rates of 30-day acute myocardial infarction or death compared to patients with normal results. We identified issues related to the quality of the reports that not only affect communication with referring physicians but also challenges for automated abstraction.

CONCLUSION

NLP is an accurate and efficient strategy to abstract results from the free-text MPI reports. Our findings will facilitate future research to understand the benefits of MPI studies but requires validation in other settings.

Informatics Solutions to Mitigate Legal Risk Associated With Communication Failures

Communication failures are a documented cause of malpractice litigation against radiologists. As imaging volumes have increased, and with them the number of findings requiring further workup, radiologists are increasingly expected to communicate with ordering clinicians. However, communication may be unsuccessful for a variety of reasons that expose radiologists to potential malpractice risk. Informatics solutions have the potential to improve communication and decrease this risk. We discuss human-powered, purely automated, and hybrid approaches to closing the communications loop. In addition, we describe the Patient Test Results Information Act (Pennsylvania Act 112) and its implications for closing the loop on noncritical actionable findings.

Structured reporting in radiology: a systematic review to explore its potential

OBJECTIVES

Structured reporting (SR) in radiology reporting is suggested to be a promising tool in clinical practice. In order to implement such an emerging innovation, it is necessary to verify that radiology reporting can benefit from SR. Therefore, the purpose of this systematic review is to explore the level of evidence of structured reporting in radiology. Additionally, this review provides an overview on the current status of SR in radiology.

METHODS

A narrative systematic review was conducted, searching PubMed, Embase, and the Cochrane Library using the syntax 'radiol*' AND 'structur*' AND 'report*'. Structured reporting was divided in SR level 1, structured layout (use of templates and checklists), and SR level 2, structured content (a drop-down menu, point-and-click or clickable decision trees). Two reviewers screened the search results and included all quantitative experimental studies that discussed SR in radiology. A thematic analysis was performed to appraise the evidence level.

RESULTS

The search resulted in 63 relevant full text articles out of a total of 8561 articles. Thematic analysis resulted in 44 SR level 1 and 19 level 2 reports. Only one paper was scored as highest level of evidence, which concerned a double cohort study with randomized trial design.

CONCLUSION

The level of evidence for implementing SR in radiology is still low and outcomes should be interpreted with caution.

KEY POINTS

• Structured reporting is increasingly being used in radiology, especially in abdominal and neuroradiological CT and MRI reports. • SR can be subdivided into structured layout (SR level 1) and structured content (SR level 2), in which the first is defined as being a template in which the reporter has to report; the latter is an IT-based manner in which the content of the radiology report can be inserted and displayed into the report. • Despite the extensive amount of research on the subject of structured reporting, the level of evidence is low.

MRI in female pelvis: an ESUR/ESR survey

Objectives

While magnetic resonance imaging (MRI) is considered the gold standard for the imaging of female pelvis, there is an ongoing debate about the most appropriate indications and optimal imaging protocols. The European Society of Urogenital Radiology (ESUR) launched a survey to evaluate the current utilization of female pelvic MRI in clinical practice.

Methods

The ESUR female imaging subgroup developed an online survey that was then approved by the ESR board and circulated among the ESR members. The questions in the survey encompassed training and experience, indications for imaging and MR imaging protocols, reporting styles and preferences. The results of the survey were tabulated, and subgroups were compared using χ2 test.

Results

A total of 5900 ESR members with an interest in both MRI and female pelvic imaging were invited to participate; 840 (14.23%) members completed the survey. Approximately 50% of respondents were academic radiologists (50.6%) and nearly 60% women (59.69%). One third of the respondents were subspecialized in Gynecological imaging. Nearly half of the survey participants were aware of the presence of ESUR guidelines for imaging of the female pelvis (47.1%). The adoption of the ESUR recommendations was higher among subspecialized and/or academic and/or senior and/or European radiologists compared to all others. The current ESUR recommendations about female pelvic MRI protocols were generally followed. However wide variations in practice were identified with respect to the use of contrast media.

Conclusion

Female pelvic MRI protocol was generally following the ESUR recommendations, especially among subspecialized and academic radiologists. However, the fact that they are followed by only half of the participants highlights the need for wider awareness of these recommendations.

Structured CT reporting of pancreatic ductal adenocarcinoma: impact on completeness of information and interdisciplinary communication for surgical planning

PURPOSE

With the rise in popularity of structured reports in radiology, we sought to evaluate whether free-text CT reports on pancreatic ductal adenocarcinoma (PDAC) staging at our institute met published guidelines and assess feedback of pancreatic surgeons comparing free-text and structured report styles with the same information content.

METHODS

We retrospectively evaluated 298 free-text preoperative CT reports from 2015 to 2017 for the inclusion of key tumor descriptors. Two surgeons independently evaluated 50 free-text reports followed by evaluation of the same reports in a structured format using a 7-question survey to assess the usefulness and ease of information extraction. Fisher's exact test and Chi-square test for independence were utilized for categorical responses and an independent samples t test for comparing mean ratings of report quality as rated on a 5-point Likert scale.

RESULTS

The most commonly included descriptors in free-text reports were tumor location (99%), liver lesions (97%), and suspicious lymph nodes (97%). The most commonly excluded descriptors were variant arterial anatomy and peritoneal/omental nodularity, which were present in only 23% and 42% of the reports, respectively. For vascular involvement, a mention of the presence or absence of perivascular disease with the main portal vein was most commonly included (87%). Both surgeons' rating of overall report quality was significantly higher for structured reports (p < 0.001).

CONCLUSION

Our results indicate that free-text reports may not include key descriptors for staging PDAC. Surgeons rated structured reports that presented the same information as free-text reports but in a template format superior for guiding clinical management, convenience of use, and overall report quality.

Myeloma Response Assessment and Diagnosis System (MY-RADS): strategies for practice implementation

Structured reporting systems have been developed for many organ systems and disease processes beginning with BI-RADS in 1993. Numerous reports indicate that referring health care providers prefer structured reports. Reducing variability of reports from one radiologist to another helps referring physician and patient confidence. Changing radiologists practice habits from completely free text to structured reports can be met with some resistance, but most radiologists quickly find that structured reports make their job easier. Whole-body MR studies are recommended as first-line imaging, by the International Myeloma Working Group (IMWG), for all patients with suspected diagnosis of asymptomatic myeloma and/or initial diagnosis of solitary plasmacytoma. Whole-body MR imaging (WBMRI) has been shown to have equal or greater sensitivity and specificity compared to PET/CT for detection of bone marrow involvement. Changing to WBMRI from other imaging modalities can be difficult for referring providers. Patient acceptance is high. MY-RADS is for myeloma patients who have WBMRI studies done. The intent of the system is to promote uniformity in MR imaging acquisition, diagnostic criteria, and response assessment and to diminish differences in the subsequent interpretation and reporting. A secondary benefit is a report template that provides a guide for interpretation for radiologists who may not have previously dictated these difficult studies. The characterization of bone marrow abnormalities in myeloma patients usually is fairly straightforward. To date, there is no standardized scoring or risk stratification of abnormalities nor is there an imaging atlas of abnormalities.

Structured reporting in radiologic education - Potential of different PI-RADS versions in prostate MRI controlled by in-bore MR-guided biopsies

Objectives:

To evaluate the efficiency of structured reporting in radiologic education – based on the example of different PI-RADS score versions for multiparametric MRI (mpMRI) of the prostate.

Methods:

MpMRI of 688 prostate lesions in 180 patients were retrospectively reviewed by an experienced radiologist and by a student using PI-RADS V1 and V2. Data sets were reviewed for changes according to PI-RADS V2.1. The results were correlated with results obtained by MR-guided biopsy. Diagnostic potency was evaluated by ROC analysis. Sensitivity, specificity and correct-graded samples were evaluated for different cutpoints. The agreement between radiologist and student was determined for the aggregation of the PI-RADS score in three categories. The student’s time needed for evaluation was measured.

Results:

The area under curve of the ROC analysis was 0.782/0.788 (V1/V2) for the student and 0.841/0.833 (V1/V2) for the radiologist. The agreement between student and radiologist showed a Cohen‘s weighted κ coefficient of 0.495 for V1 and 0.518 for V2. Median student’s time needed for score assessment was 4:34 min for PI-RADSv1 and 2:00 min for PI-RADSv2 (p < 0.001). Re-evaluation for V2.1 changed the category in 1.4% of all ratings.

Conclusion:

The capacity of prostate cancer detection using PI-RADS V1 and V2 is dependent on the reader‘s experience. The results from the two observers indicate that structured reporting using PI-RADS and, controlled by histopathology, can be a valuable and quantifiable tool in students‘ or residents’ education. Herein, V2 was superior to V1 in terms of inter-observer agreement and time efficacy.

Advances in knowledge:

Structured reporting can be a valuable and quantifiable tool in radiologic education. Structured reporting using PI-RADS can be used by a student with good performance. PI-RADS V2 is superior to V1 in terms of inter-observer agreement and time efficacy.

CT Angiography Clot Burden Score from Data Mining of Structured Reports for Pulmonary Embolism

Background Many studies emphasize the role of structured reports (SRs) because they are readily accessible for further automated analyses. However, using SR data obtained in clinical routine for research purposes is not yet well represented in literature. Purpose To compare the performance of the Qanadli scoring system with a clot burden score mined from structured pulmonary embolism (PE) reports from CT angiography. Materials and Methods In this retrospective study, a rule-based text mining pipeline was developed to extract descriptors of PE and right heart strain from SR of patients with suspected PE between March 2017 and February 2020. From standardized PE reporting, a pulmonary artery obstruction index (PAOI) clot burden score (PAOI_CBS) was derived and compared with the Qanadli score (PAOI_Q). Scoring time and confidence from two independent readings were compared. Interobserver and interscore agreement was tested by using the intraclass correlation coefficient (ICC) and Bland-Altman analysis. To assess conformity and diagnostic performance of both scores, areas under the receiver operating characteristic curve (AUCs) were calculated to predict right heart strain incidence, as were optimal cutoff values for maximum sensitivity and specificity. Results SR content authored by 67 residents and signed off by 32 consultants from 1248 patients (mean age, 63 years ± 17 [standard deviation]; 639 men) was extracted accurately and allowed for PAOI_CBS calculation in 304 of 357 (85.2%) PE-positive reports. The PAOI_CBS strongly correlated with the PAOI_Q (r = 0.94; P < .001). Use of PAOI_CBS yielded overall time savings (1.3 minutes ± 0.5 vs 3.0 minutes ± 1.7), higher confidence levels (4.2 ± 0.6 vs 3.6 ± 1.0), and a higher ICC (ICC, 0.99 vs 0.95), respectively, compared with PAOI_Q (each, P < .001). AUCs were similar for PAOI_CBS (AUC, 0.75; 95% CI: 0.70, 0.81) and PAOI_Q (AUC, 0.77; 95% CI: 0.72, 0.83; P = .68), with cutoff values of 27.5% for both scores. Conclusion Data mining of structured reports enabled the development of a CT angiography scoring system that simplified the Qanadli score as a semiquantitative estimate of thrombus burden in patients with pulmonary embolism. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Hunsaker in this issue.

CT scan structured report for the study of abdominal wall defects: a fast, easy and practical tool at the service of both surgeons and radiologist

PURPOSE

The advantages offered by structured reporting have already been highlighted in the literature. However, there is still no evidence on the validity of this reporting method for the study of abdominal wall defects. This study aims to show the experience of the Trentino Hernia Team (THT) multidisciplinary group in the development and use of a structured CT scan report for the study of abdominal wall defects.

METHODS

A regional multidisciplinary team (THT group) used a Delphi method to identify and select the most important CT scan parameters needed to describe and stage abdominal wall defects for correct preoperative planning. Based on the selected parameters, a CT scan structured report was worked out and collectively accepted. The first 20 structured reports obtained were individually tested for compilation speed and homogeneity of the data reported by five distinct radiologists. The reports were then evaluated by five different surgeons to test the simplicity of interpretation.

RESULTS

We produced a model of a structured report for the study of the abdominal wall defects and tested it in our hospital network on the first 20 reports. The average completion time was 18 min (range 12-25). There was no heterogeneity among the reported data. The reports were analysed by five distinct surgeons to evaluate completeness and simplicity of interpretation. Each surgeon used a Likert scale from 0 to 5 to evaluate each report, producing average scores of 4.8 and 4.1 for completeness and comprehensibility respectively, with a mean combined total score of 8.9 out of 10.

CONCLUSIONS

Our structured report represents a fundamental tool capable of providing the surgeon with all the measurements of the parameters necessary for correct preoperative planning. At the same time, it is of crucial help for the radiologists representing an easy and fast way to report all the needed parameters using the same standards.

Structured Reporting of Computed Tomography Examinations in Post-Lung Transplantation Patients

OBJECTIVE

The aim of this study was to evaluate the benefits and potential of structured reports (SR) for chest computed tomography after lung transplantation.

METHODS

Free-text reports (FTR) and SR were generated for 49 computed tomography scans. Clinical routine reports were used as FTR. Two pulmonologists rated formal aspects, completeness, clinical utility, and overall quality. Wilcoxon and McNemar tests were used for statistical analysis.

RESULTS

Structured reports received significantly higher ratings for all formals aspects (P < 0.001, respectively). Completeness was higher in SR with regard to evaluation of bronchiectases, bronchial anastomoses, bronchiolitic and fibrotic changes (P < 0.001, respectively), and air trapping (P = 0.012), but not signs of pneumonia (P = 0.5). Clinical utility and overall quality were rated significantly higher for SR than FTR (P < 0.001, respectively). However, report type did not influence initiation of further diagnostic or therapeutic measures (P = 0.307 and 1.0).

CONCLUSIONS

Structured reports are superior to FTR with regard to formal aspects, completeness, clinical utility, and overall satisfaction of referring pulmonologists.

Chest radiographs and machine learning - Past, present and future

Despite its simple acquisition technique, the chest X-ray remains the most common first-line imaging tool for chest assessment globally. Recent evidence for image analysis using modern machine learning points to possible improvements in both the efficiency and the accuracy of chest X-ray interpretation. While promising, these machine learning algorithms have not provided comprehensive assessment of findings in an image and do not account for clinical history or other relevant clinical information. However, the rapid evolution in technology and evidence base for its use suggests that the next generation of comprehensive, well-tested machine learning algorithms will be a revolution akin to early advances in X-ray technology. Current use cases, strengths, limitations and applications of chest X-ray machine learning systems are discussed.

How to Use LI-RADS to Report Liver CT and MRI Observations

Primary liver cancer is the fourth leading cause of cancer-related deaths worldwide, with hepatocellular carcinoma (HCC) comprising the vast majority of primary liver malignancies. Imaging plays a central role in HCC diagnosis and management. As a result, the content and structure of radiology reports are of utmost importance in guiding clinical management. The Liver Imaging Reporting and Data System (LI-RADS) provides guidance for standardized reporting of liver observations in patients who are at risk for HCC. LI-RADS standardized reporting intends to inform patient treatment and facilitate multidisciplinary communication and decisions, taking into consideration individual clinical factors. Depending on the context, observations may be reported individually, in aggregate, or as a combination of both. LI-RADS provides two templates for reporting liver observations: in a single continuous paragraph or in a structured format with keywords and imaging findings. The authors clarify terminology that is pertinent to reporting, highlight the benefits of structured reports, discuss the applicability of LI-RADS for liver CT and MRI, review the elements of a standardized LI-RADS report, provide guidance on the description of LI-RADS observations exemplified with two case-based reporting templates, illustrate relevant imaging findings and components to be included when reporting specific clinical scenarios, and discuss future directions. An invited commentary by Yano is available online. Online supplemental material is available for this article. Work of the U.S. Government published under an exclusive license with the RSNA.

Portal vein thrombosis in patients with chronic liver diseases: From conventional to quantitative imaging

Portal vein thrombosis is a pathological condition characterized by the lumen occlusion of the portal vein and its intrahepatic branches, commonly associated to chronic liver diseases. Portal vein thrombosis is often asymptomatic and discovered as an incidental finding in the follow-up of chronic hepatopathy. Imaging plays a pivotal role in the detection and characterization of portal vein thrombosis in patients with hepatocellular carcinoma. Ultrasound and Color-Doppler ultrasound are usually the first-line imaging modalities for its detection, but they have limits related to operator-experience, patient size, meteorism and the restrained field-of view. Unenhanced cross-sectional imaging doesn't provide specific signs of portal vein thrombosis except under certain specific circumstances. Conventional contrast-enhanced imaging can depict portal vein thrombosis as an endoluminal filling defect best detected in venous phase and can differentiate between non-neoplastic and neoplastic thrombus based on the contrast enhanced uptake, but not always rule-out the malignant nature. Functional and quantitative imaging techniques and software seem to be more accurate. The purpose of this work is to provide the reader with an accurate overview focused on the main imaging features of portal vein thrombosis.

Multispecialty Enterprise Imaging Workgroup Consensus on Interactive Multimedia Reporting Current State and Road to the Future: HIMSS-SIIM Collaborative White Paper

Diagnostic and evidential static image, video clip, and sound multimedia are captured during routine clinical care in cardiology, dermatology, ophthalmology, pathology, physiatry, radiation oncology, radiology, endoscopic procedural specialties, and other medical disciplines. Providers typically describe the multimedia findings in contemporaneous electronic health record clinical notes or associate a textual interpretative report. Visual communication aids commonly used to connect, synthesize, and supplement multimedia and descriptive text outside medicine remain technically challenging to integrate into patient care. Such beneficial interactive elements may include hyperlinks between text, multimedia elements, alphanumeric and geometric annotations, tables, graphs, timelines, diagrams, anatomic maps, and hyperlinks to external educational references that patients or provider consumers may find valuable. This HIMSS-SIIM Enterprise Imaging Community workgroup white paper outlines the current and desired clinical future state of interactive multimedia reporting (IMR). The workgroup adopted a consensus definition of IMR as “interactive medical documentation that combines clinical images, videos, sound, imaging metadata, and/or image annotations with text, typographic emphases, tables, graphs, event timelines, anatomic maps, hyperlinks, and/or educational resources to optimize communication between medical professionals, and between medical professionals and their patients.” This white paper also serves as a precursor for future efforts toward solving technical issues impeding routine interactive multimedia report creation and ingestion into electronic health records.

Validation of imaging reporting and data system of coronavirus disease 2019 lexicons CO-RADS and COVID-RADS with radiologists’ preference: a multicentric study

Background

A retrospective multicentric study gathered 1439 CT chest studies with suspected coronavirus disease 2019 (COVID-19) affection. Three radiologists, blinded to other results, interpreted all studies using both lexicons with documentation of applicability and preferred score in assessing every case. The purpose of the study is to assess COVID-19 standardized assessment schemes’ (CO-RADS and COVID-RADS lexicons) applicability and diagnostic efficacy.

Results

This study included 991 RT-PCR-confirmed CT studies. An almost perfect agreement was found in COVID-RADS among the three observers (Fleiss Kappa = 0.82), opposed by a substantial agreement in CO-RADS (Κ = 0.78). The preference records favor COVID-RADS/CO-RADS in 78.5%/12.5%, 75.5%/24.5%, and 73.4%/24.5% regarding the three radiologists’ records, respectively. The distinguishability between positive and negative RT-PCR cases was 0.92 for COVID-RADS, while it was 0.85 for CO-RADS. On the other hand, both lexicons’ performance regarding clinical diagnosis and clinical suspicion index was 0.93 for COVID-RADS and 0.94 for CO-RADS. A very high to excellent agreement between the three observers for COVID-RADS/CO-RADS preference was concluded (Fleiss Kappa = 0.80 to 0.94). These results were statistically significant (p < 0.001).

Conclusion

Both lexicon scores (CO-RADS and COVID-RADS) were found to be applicable in the COVID-19 structured report with the preference of COVID-RADS in more than 50% of cases. The diagnostic accuracy of COVID-RADS against RT-PCR was higher than that of CO-RADS.