Bridging Communication Gaps Between Radiologists, Referring Physicians, and Patients Through Standardized Structured Cancer Imaging Reporting: The Experience with Female Pelvic MRI Assessment Using O-RADS and a Simulated Cohort Patient Group

[Clinical Ultrasound Part II - Sonopsychology or Psychological Interactions using Ultrasound]

In contrast to cross-sectional imaging using computed tomography, magnetic resonance imaging or positron emission tomography, ultrasound examinations enable direct real-time interaction between examiner and patient and their companions. In this review, we highlight general patient-relevant aspects, whereby endpoints such as emotional factors of general and physical stress caused by the examination are discussed. On the other hand, we take a closer look at specific psychosocial interactions during ultrasound examinations in primary care, gastroenterology, oncology, palliative care, pediatrics, obstetrics and gynecology. Furthermore, we consider ultrasound not only as an intervention in the sense of a needle-guiding procedure, but also as an opportunity to change relationships and initiate lifestyle modifications. The psychological impact of incidental findings and the importance of adequate communication of findings and prognosis is discussed from the patient's perspective.

The impact of different radiology report formats on patient information processing: a systematic review

BACKGROUND

Since radiology reports are primarily written for health professionals, patients may experience difficulties understanding jargon and terminology used, leading to anxiety and confusion.

OBJECTIVES

This review evaluates the impact of different radiology report formats on outcomes related to patient information processing, including perception, decision (behavioral intention), action (actual health behavior), and memory (recall of information).

METHODS

PubMed, Web of Science, EMBASE, and PsycInfo were searched for relevant qualitative and quantitative articles describing or comparing ways of presenting diagnostic radiology reports to patients. Two reviewers independently screened for relevant articles and extracted data from those included. The quality of articles was assessed using the Mixed Methods Appraisal Tool.

RESULTS

Eighteen studies, two qualitative and sixteen quantitative, were included. Sixteen studies compared multiple presentation formats, most frequently traditional unmodified reports (n = 15), or reports with anatomic illustrations (n = 8), lay summaries (n = 6) or glossaries (n = 6). Glossaries, illustrations, lay summaries, lay reports or lay conclusions all significantly improved participants' cognitive perception and perception of communication of radiology reports, compared to traditional reports. Furthermore, these formats increased affective perception (e.g., reduced anxiety and worry), although only significant for lay reports and conclusions.

CONCLUSION

Modifying traditional radiology reports with glossaries, illustrations or lay language enhances patient information processing.

KEY POINTS

Question Identifying the impact of different radiology report formats on outcomes related to patient information processing to enhance patient engagement through online access to radiology reports. Findings Lay language summaries, glossaries with patient-oriented definitions, and anatomic illustrations increase patients' satisfaction with and understanding of their radiology reports. Clinical relevance To increase patients' satisfaction, perceived usefulness and understanding with radiology reports, the use of lay language summaries, glossaries with patient-oriented definitions, and anatomic illustrations is recommended. These modifications decrease patients' unnecessary insecurity, confusion, anxiety and physician consultations after viewing reports.

Diagnostic performance of the O-RADS MRI system for magnetic resonance imaging in discriminating benign and malignant adnexal lesions: a systematic review, meta-analysis, and meta-regression

PURPOSE

After the introduction of the Ovarian-Adnexal Reporting and Data System (O-RADS) for magnetic resonance imaging (MRI), several studies with diverse characteristics have been published to assess its diagnostic performance. This systematic review and meta-analysis aimed to assess the diagnostic performance of O-RADS MRI scoring for adnexal masses, accounting for the risk of selection bias.

METHODS

The PubMed, Scopus, Web of Science, and Cochrane databases were searched for eligible studies. Borderline or malignant lesions were considered malignant. All O-RADS MRI scores ≥4 were considered positive. The quality of the studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. The pooled sensitivity, specificity, and likelihood ratio (LR) values were calculated, considering the risk of selection bias.

RESULTS

Fifteen eligible studies were found, and five of them had a high risk of selection bias. Between-study heterogeneity was low-to-moderate for sensitivity but substantial for specificity (I2 values were 35.5% and 64.7%, respectively). The pooled sensitivity was significantly lower in the studies with a low risk of bias compared with those with a high risk of bias (93.0% and 97.5%, respectively; P = 0.043), whereas the pooled specificity was not different (90.4% for the overall population). The negative and positive LRs were 0.08 [95% confidence interval (CI) 0.05–0.11] and 10.0 (95% CI 7.7–12.9), respectively, for the studies with low risk of bias and 0.03 (95% CI 0.01–0.10) and 10.3 (95% CI 3.8–28.3), respectively, for those with high risk of bias.

CONCLUSION

The overall diagnostic performance of the O-RADS system is very high, particularly for ruling out borderline/malignant lesions, but with a moderate ruling-in potential. Studies with a high risk of selection bias lead to an overestimation of sensitivity.

CLINICAL SIGNIFICANCE

The O-RADS system demonstrates considerable diagnostic performance, particularly in ruling out borderline or malignant lesions, and should routinely be used in practice. The high between-study heterogeneity observed for specificity suggests the need for improvement in the consistent characterization of the benign lesions to reduce false positive rates.

Accuracy of Large Language Model-based Automatic Calculation of Ovarian-Adnexal Reporting and Data System MRI Scores from Pelvic MRI Reports

Background Ovarian-Adnexal Reporting and Data System (O-RADS) for MRI helps assign malignancy risk, but radiologist adoption is inconsistent. Automatic assignment of O-RADS scores from reports could increase adoption and accuracy. Purpose To evaluate the accuracy of large language models (LLMs), after strategic optimization, for automatically calculating O-RADS scores from reports. Materials and Methods This retrospective single-center study from a large quaternary care cancer center included consecutive gadolinium chelate-enhanced pelvic MRI reports with at least one assigned O-RADS score from July 2021 to October 2023. Reports from January 2018 to October 2019 (before O-RADS MRI implementation) were randomly selected for additional testing. Reference standard O-RADS scores were determined by radiologists interpreting reports. After prompt optimization using a subset of reports, two LLM-based strategies were evaluated: few-shot learning with GPT-4 (version 0613; OpenAI) prompted with O-RADS rules ("LLM only") and a hybrid strategy leveraging GPT-4 to classify features fed into a deterministic formula ("hybrid"). Accuracy of each model and originally reported scores were calculated and compared using the McNemar test. Results A total of 284 reports from 284 female patients (mean age, 53.2 years ± 16.3 [SD]) with 372 adnexal lesions were included: 10 reports in the training set (16 lesions), 134 reports in the internal test set 1 (173 lesions; 158 O-RADS assigned), and 140 reports in internal test set 2 (183 lesions). For assigning O-RADS MRI scores, the hybrid model accuracy (97%; 168 of 173) outperformed LLM-only model (90%; 155 of 173; P = .006). For lesions with an originally reported O-RADS score, hybrid model accuracy exceeded that of reporting radiologists (97% [153 of 158] vs 88% [139 of 158]; P = .004). Hybrid model also outperformed LLM-only model for 183 lesions from before O-RADS implementation (95% [173 of 183] vs 87% [159 of 183], respectively; P = .01). Conclusion A hybrid LLM-based application, combining LLM feature classification with deterministic elements, accurately assigned O-RADS MRI scores from report descriptions, exceeding both an LLM-only strategy and the original reporting radiologist. © RSNA, 2025 Supplemental material is available for this article.

Knowledge Graph-Based Few-Shot Learning for Label of Medical Imaging Reports

BACKGROUND

The application of artificial intelligence (AI) in the field of automatic imaging report labeling faces the challenge of manually labeling large datasets.

PURPOSE

To propose a data augmentation method by using knowledge graph (KG) and few-shot learning.

METHODS

A KG of lumbar spine X-ray images was constructed, and 2000 data were annotated based on the KG, which were divided into training, validation, and test sets in a ratio of 7:2:1. The training dataset was augmented based on the synonym/replacement attributes of the KG and was the augmented data was input into the BERT (Bidirectional Encoder Representations from Transformers) model for automatic annotation training. The performance of the model under different augmentation ratios (1:10, 1:100, 1:1000) and augmentation methods (synonyms only, replacements only, combination of synonyms and replacements) was evaluated using the precision and F1 scores. In addition, with the augmentation ratio was fixed, iterative experiments were performed by supplementing the data of nodes that perform poorly in the validation set to further improve model's performance.

RESULTS

Prior to data augmentation, the precision was 0.728 and the F1 score was 0.666. By adjusting the augmentation ratio, the precision increased from 0.912 at a 1:10 augmentation ratio to 0.932 at a 1:100 augmentation ratio (P<.05), while F1 score improved from 0.853 at a 1:10 augmentation ratio to 0.881 at a 1:100 augmentation ratio (P<.05). Additionally, the effectiveness of various augmentation methods was compared at a 1:100 augmentation ratio. The augmentation method that combined synonyms and replacements (F1=0.881) was superior to the methods that only used synonyms (F1=0.815) and only used replacements (F1=0.753) (P<.05). For nodes that exhibited suboptimal performance on the validation set, supplementing the training set with target data improved model performance, increasing the average F1 score to 0.979 (P<.05).

CONCLUSION

Based on the KG, this study trained an automatic labeling model of radiology reports using a few-shot data set. This method effectively reduces the workload of manual labeling, improves the efficiency and accuracy of image data labeling, and provides an important research strategy for the application of AI in the domain of automatic labeling of image reports.

Radiology Reporting Preferences: What Do Referring Clinicians Want?

RATIONALE AND OBJECTIVES

To investigate and discern if preferences and expectations regarding the stylistics of the radiology report varied across roles, specialties, and practice location amongst referring providers.

MATERIALS AND METHODS

A total of 579 referring clinicians were invited to complete our survey electronically and were asked to identify themselves as either physicians or advanced practice providers (APPs), specify their specialty, and primary practice environment. They were asked to rank the three reports on appearance, formatting, level of detail, and overall preference, with additional queries about their preferences regarding literature citation inclusions and placement of dose reduction statements.

RESULTS

477 surveys were completed and returned for analysis, resulting in an 82.2% response rate. The most preferred reporting style was the blended report (62.5%), followed by the narrative report (18.9%) and the highly templated report (18.7%), respectively. There were no statistically significant differences in the most preferred reporting style between provider types (F(1, 475) = [0.69], p = 0.4067), between different practice settings (F(2, 474) = [2.32], p = 0.0995), and between different medical specialties (F(5, 471) = [2.23], p = 0.051). Among the three report styles, blended reporting received the highest satisfaction scores overall. The highly templated report was rated lowest for appearance and detail, while narrative reports received moderate satisfaction scores for appearance and detail. A majority favored inclusion of literature citations and similarly, the placement of dose-optimization statements at the end of the report. Preferences were consistent across specialties and practice settings.

CONCLUSION

This survey highlights that a majority of clinicians across a variety of specialties prefer a mix of structured reporting with narrative elements. The standardization of required metrics included in the radiology report may have far-reaching consequences for future reimbursement.

Role of Natural Language Processing in Automatic Detection of Unexpected Findings in Radiology Reports: A Comparative Study of RoBERTa, CNN, and ChatGPT

RATIONALE AND OBJECTIVES

Large Language Models can capture the context of radiological reports, offering high accuracy in detecting unexpected findings. We aim to fine-tune a Robustly Optimized BERT Pretraining Approach (RoBERTa) model for the automatic detection of unexpected findings in radiology reports to assist radiologists in this relevant task. Second, we compared the performance of RoBERTa with classical convolutional neural network (CNN) and with GPT4 for this goal.

MATERIALS AND METHODS

For this study, a dataset consisting of 44,631 radiological reports for training and 5293 for the initial test set was used. A smaller subset comprising 100 reports was utilized for the comparative test set. The complete dataset was obtained from our institution's Radiology Information System, including reports from various dates, examinations, genders, ages, etc. For the study's methodology, we evaluated two Large Language Models, specifically performing fine-tuning on RoBERTa and developing a prompt for ChatGPT. Furthermore, extending previous studies, we included a CNN in our comparison.

RESULTS

The results indicate an accuracy of 86.15% in the initial test set using the RoBERTa model. Regarding the comparative test set, RoBERTa achieves an accuracy of 79%, ChatGPT 64%, and the CNN 49%. Notably, RoBERTa outperforms the other systems by 30% and 15%, respectively.

CONCLUSION

Fine-tuned RoBERTa model can accurately detect unexpected findings in radiology reports outperforming the capability of CNN and ChatGPT for this task.

O-RADS MRI scoring system: key points for correct application in inexperienced hands

OBJECTIVES

To evaluate the efficacy of the O-RADS MRI criteria in the stratification of risk of malignancy of solid or sonographically indeterminate ovarian masses and assess the interobserver agreement of this classification between experienced and inexperienced radiologists.

METHODS

This single-centre retrospective study included patients from 2019 to 2022 with sonographically indeterminate or solid ovarian masses who underwent MRI with a specific protocol for characterisation according to O-RADS MRI specifications. Each study was evaluated using O-RADS lexicon by two radiologists, one with 17 years of experience in gynaecological radiology and another with 4 years of experience in general radiology. Findings were classified as benign, borderline, or malignant according to histology or stability over time. Diagnostic performance and interobserver agreement were assessed.

RESULTS

A total of 183 patients with US indeterminate or solid adnexal masses were included. Fifty-seven (31%) did not have ovarian masses, classified as O-RADS 1. The diagnostic performance for scores 2-5 was excellent with a sensitivity, specificity, PPV, and NPV of 97.4%, 100%, 96.2%, and 100%, respectively by the experienced radiologist and 96.1%, 92.0%, 93.9%, and 94.8% by the inexperienced radiologist. Interobserver concordance was very high (Kappa index 0.92). Almost all the misclassified cases were due to misinterpretation of the classification similar to reports in the literature.

CONCLUSION

The diagnostic performance of O-RADS MRI determined by either experienced or inexperienced radiologists is excellent, facilitating decision-making with high diagnostic accuracy and high reproducibility. Knowledge of this classification and use of assessment tools could avoid frequent errors due to misinterpretation.

CRITICAL RELEVANCE STATEMENT

Up to 31% of ovarian masses are considered indeterminate by transvaginal US and 32% of solid lesions considered malignant by transvaginal US are benign. The O-RADs MRI accurately classifies these masses, even when used by inexperienced radiologists, thereby avoiding incorrect surgical approaches.

KEY POINTS

• O-RADS MRI accurately classifies indeterminate and solid ovarian masses by ultrasound. • There is excellent interobserver agreement between experienced and non-experienced radiologists. • O-RADS MRI is a helpful tool to assess clinical decision-making in ovarian tumours.