MaRRS : a software system for generating multimedia radiology reports using Adobe Acrobat

10.32920/ryerson.14662371 ◽

2021 ◽

Author(s):

Kristy Moniz

Keyword(s):

Software System ◽

Multimedia Software ◽

Text And Image ◽

Radiological Findings ◽

Image Content ◽

Radiology Report ◽

Adobe Acrobat ◽

Radiology Reports ◽

Medical Reports ◽

Report System

Despite the proliferation of multimedia software technologies, radiology reports continue to lack image content that would improve the ability of referring clinicians to fully interpret and analyze radiological findings. This thesis demonstrates that it is possible to construct a radiology reporting software system that contains both text and image content using only "off-the-shelf" multimedia software. Specifically, a software system is presented that provides enhanced visual multimedia capabilities, structured content, and reduced report production time, using a well-known PDF program, Adobe Acrobat. The system, which we call the Multimedia Radiology Report System, or MaRRs, allows radiologists to quickly and simply create and deliver effective interactive multimedia medical reports. A detailed analysis describing the unique structure and functionality of MaRRS will be presented to demonstrate its advantages for both radiologists and referring clinicians.

Download Full-text

The Importance of Surgeon-reviewed Computed Tomography for Incisional Hernia Detection: A Prospective Study

The American Surgeon ◽

10.1177/000313481408000730 ◽

2014 ◽

Vol 80 (7) ◽

pp. 720-722 ◽

Cited By ~ 5

Author(s):

Rebeccah B. Baucom ◽

William C. Beck ◽

Michael D. Holzman ◽

Kenneth W. Sharp ◽

William H. Nealon ◽

...

Keyword(s):

Computed Tomography ◽

Incisional Hernia ◽

Sensitivity And Specificity ◽

Predictive Value ◽

Radiology Report ◽

Incisional Hernias ◽

Radiology Reports ◽

Sensitivity Specificity ◽

A Prospective Study ◽

The Cost

Patients with incisional hernias or abdominal pain are frequently referred with abdominal computed tomography (CT) scans. The purpose of this study was to determine the sensitivity and specificity of a CT radiology report for the detection of incisional hernias. General surgery patients with a history of an abdominal operation and a recent viewable abdominal CT scan were enrolled prospectively. Patients with a stoma, fistula, or soft tissue infection were excluded. The results of the radiology reports were compared with blinded, surgeon-interpreted CT for each patient. Testing characteristics including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. One hundred eighty-one patients were enrolled with a mean age of 54 years. Sixty-eight per cent were women. Hernia prevalence was 55 per cent, and mean hernia width was 5.2 cm. The radiology report had a sensitivity and specificity of 79 per cent and 94 per cent, respectively, for hernia diagnosis. The PPV and NPV were 94 and 79 per cent, respectively. Reliance on the CT report alone underestimates the presence of incisional hernia. Referring physicians should not use CT as a screening modality for detection of hernias. Referral to a surgeon for evaluation before imaging may provide more accurate diagnosis and potentially decrease the cost of caring for this population.

Download Full-text

Semi-automated De-identification of German Content Sensitive Reports for Big Data Analytics

RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren ◽

10.1055/s-0043-102939 ◽

2017 ◽

Vol 189 (07) ◽

pp. 661-671

Author(s):

Hannes Seuss ◽

Peter Dankerl ◽

Matthias Ihle ◽

Andrea Grandjean ◽

Rebecca Hammon ◽

...

Keyword(s):

Big Data Analytics ◽

Text Structure ◽

Sensitive Data ◽

Performance Training ◽

Radiology Reports ◽

Medical Terms ◽

Different Types ◽

Medical Reports ◽

Pathology Reports ◽

Identification Tool

Purpose Projects involving collaborations between different institutions require data security via selective de-identification of words or phrases. A semi-automated de-identification tool was developed and evaluated on different types of medical reports natively and after adapting the algorithm to the text structure. Materials and Methods A semi-automated de-identification tool was developed and evaluated for its sensitivity and specificity in detecting sensitive content in written reports. Data from 4671 pathology reports (4105 + 566 in two different formats), 2804 medical reports, 1008 operation reports, and 6223 radiology reports of 1167 patients suffering from breast cancer were de-identified. The content was itemized into four categories: direct identifiers (name, address), indirect identifiers (date of birth/operation, medical ID, etc.), medical terms, and filler words. The software was tested natively (without training) in order to establish a baseline. The reports were manually edited and the model re-trained for the next test set. After manually editing 25, 50, 100, 250, 500 and if applicable 1000 reports of each type re-training was applied. Results In the native test, 61.3 % of direct and 80.8 % of the indirect identifiers were detected. The performance (P) increased to 91.4 % (P25), 96.7 % (P50), 99.5 % (P100), 99.6 % (P250), 99.7 % (P500) and 100 % (P1000) for direct identifiers and to 93.2 % (P25), 97.9 % (P50), 97.2 % (P100), 98.9 % (P250), 99.0 % (P500) and 99.3 % (P1000) for indirect identifiers. Without training, 5.3 % of medical terms were falsely flagged as critical data. The performance increased, after training, to 4.0 % (P25), 3.6 % (P50), 4.0 % (P100), 3.7 % (P250), 4.3 % (P500), and 3.1 % (P1000). Roughly 0.1 % of filler words were falsely flagged. Conclusion Training of the developed de-identification tool continuously improved its performance. Training with roughly 100 edited reports enables reliable detection and labeling of sensitive data in different types of medical reports. Key Points: Citation Format

Download Full-text

Radiology report format preferred by requesting physicians: prospective analysis in a population of physicians at a university hospital

Radiologia Brasileira ◽

10.1590/0100-3984.2018.0026 ◽

2019 ◽

Vol 52 (2) ◽

pp. 97-103 ◽

Cited By ~ 2

Author(s):

Denise Maria Rissato Camilo ◽

Tiago Kojun Tibana ◽

Isa Félix Adôrno ◽

Rômulo Florêncio Tristão Santos ◽

Camila Klaesener ◽

...

Keyword(s):

University Hospital ◽

Radiology Report ◽

Radiological Investigation ◽

Residency Programs ◽

Levels Of Detail ◽

Radiology Reports ◽

Structured Reports ◽

Attending Physicians

Abstract Objective: To improve communication between attending physicians and radiologists by defining which information should be included in radiology reports and which reporting format is preferred by requesting physicians at a university hospital. Materials and Methods: Respondents were asked to choose among reports with different formats and levels of detail, related to three hypothetical cases, and questioned as to which characteristics commonly found in radiology reports are appropriate for inclusion. To assign the absolute order of preference of the different reports, the Kemeny-Young method was used. Results: Ninety-nine physicians completed the questionnaires (40.4% were resident physicians; 31.3% were preceptors of residency programs; and 28.3% were professors of medicine). For ultrasound with normal findings, ultrasound showing alterations, and computed tomography, respectively, 54%, 59%, and 53% of the respondents chose structured reports with an impression or comment. According to the respondents, the characteristics that should be included in the radiology report are the quality of the image, details of the clinical presentation, diagnostic impression, examination technique, and information about contrast administration, selected by 92%, 91%, 89%, 72%, and 68%, respectively. Other characteristics that were considered important were recommendations on follow-up and additional radiological or non-radiological investigation. Conclusion: Requesting physicians apparently prefer structured reports with a radiologist impression or comment. Information such as the quality of the examination, the contrast agent used, and suggestions regarding follow-up and additional investigation are valued.

Download Full-text

Discrepancy between reported progressive disease per radiology report and treating oncologist tumor measurements in patients with metastatic renal cell carcinoma (mRCC) receiving sunitinib.

Journal of Clinical Oncology ◽

10.1200/jco.2012.30.5_suppl.420 ◽

2012 ◽

Vol 30 (5_suppl) ◽

pp. 420-420 ◽

Cited By ~ 1

Author(s):

Khaled B. Ali ◽

Shetal N. Shah ◽

Laura S. Wood ◽

Jorge A. Garcia ◽

Robert Dreicer ◽

...

Keyword(s):

Disease Progression ◽

Progressive Disease ◽

Cleveland Clinic ◽

The Body ◽

Drug Discontinuation ◽

Radiology Report ◽

Significant Discrepancy ◽

Radiology Reports ◽

Disease Term ◽

Tumor Measurements

420 Background: The determination of progressive disease (PD) on sunitinib in mRCC by conventional tumor size criteria is often complex. Frequently, radiology reports cite disease progression that does not meet RECIST criteria or does not adequately describe index lesions. Characterization of the frequency and magnitude of this phenomenon has not been previously reported. Methods: The medical records of a subset of mRCC patients treated at The Cleveland Clinic who had received sunitinib for > 12 months were retrospectively reviewed. All Radiology reports from post-baseline scans were reviewed for the presence of text in the body or conclusion of the report consistent with disease progression (specifically the terms ‘progressive’, ‘new’ and/or ‘interval enlargement/worsening’). The date of the report first containing one or more of these terms was recorded, as was the date of RECIST-defined PD determined by the treating Oncologist. Results: Twenty patients were identified in an initial review. Patient characteristics included: 85% male, 100% clear cell histology, 90% prior nephrectomy and 80% with prior systemic therapy. Thirteen patients (65%) had a radiology report citing a progressive disease term prior to treating physician-determined RECIST-defined PD. The median time from first radiology report citing a progressive disease term until RECIST PD per Oncologist measurements was 2.9 months (range, 0 to 12.8 months). Conclusions: There is significant discrepancy between the first mention of disease progression by a Radiology report and when a treating Oncologist measures disease progression per RECIST criteria. This discrepancy could impact patient care by influencing drug discontinuation. These data emphasize the importance of multidisciplinary scan review and tumor measurements by both radiologists and treating physicians. Analysis is ongoing in additional patients.

Download Full-text

A QoS guarantee approach for multimedia software system

International Journal of Computers and Applications ◽

10.1080/1206212x.2018.1486559 ◽

2018 ◽

Vol 42 (6) ◽

pp. 578-588

Author(s):

Aiping Zhou ◽

Hongbing Li

Keyword(s):

Software System ◽

Multimedia Software ◽

Qos Guarantee

Download Full-text

Research of Multi-Data Sources Report Model Based on Data Dictionary

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.532-533.846 ◽

2012 ◽

Vol 532-533 ◽

pp. 846-849

Author(s):

Yu Jing Lu ◽

Qing Hui Hu

Keyword(s):

Data Sources ◽

Software System ◽

Data Dictionary ◽

Application Program ◽

Model Based ◽

Report System ◽

System Data ◽

Data Source

This paper put forward an idea of multi-data sources report model based on data dictionary in order to separate the report from application program. When report changed, we can alter the system data dictionary, data source dictionary or modal file dictionary to adapt to new requests without any changes for application program. This brings to high independence between application program and report system. At the same time we can transplant the report system to different software system without any changes.

Download Full-text

Subspecialized Radiological Reporting Expedites Turnaround Time of Radiology Reports and Increases Productivity

RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren ◽

10.1055/s-0044-100728 ◽

2018 ◽

Vol 190 (07) ◽

pp. 623-629 ◽

Cited By ~ 3

Author(s):

Christoph Stern ◽

Thomas Boehm ◽

Burkhardt Seifert ◽

Nadine Kawel-Boehm

Keyword(s):

Turnaround Time ◽

Radiology Department ◽

Full Time ◽

Imaging Studies ◽

Radiology Report ◽

Chi Square ◽

Radiology Reports ◽

Key Points ◽

Chi Square Test ◽

The Impact

Introduction To assess the impact of changing from general to subspecialized reporting on turnaround time of radiology reports (TAT), the fraction of radiology reports available within 24 hours (R< 24 h) and productivity. Materials and Methods Reporting workflow in our radiology department was changed from general reporting (radiologists report imaging studies of all areas [neuroradiological, abdominal, musculoskeletal imaging et cetera]) to subspecialized reporting (radiologists solely report imaging studies of their subspecialty field [e. g. musculoskeletal]). TAT, R< 24 h and productivity were calculated for a 12-month period of general reporting (January-December 2012) and compared to a 12-month period of subspecialized reporting (April 2014-March 2015) using Mann Whitney U-test, Pearson chi-square test and odds ratios, respectively. Results Report TAT decreased from a median of 17:04 hours (h) during general reporting to 3:38 h during subspecialized reporting, resulting in a 4.7-fold improvement (p < 0.001). R< 24 h improved significantly from 65 % to 87 % (p < 0.001). The odds of a radiology report being available < 24 h was 3.6- fold higher during subspecialized compared to general reporting. Productivity increased from a median of 301 to 376 (reports/full-time radiologist/month) (p = 0.001). Conclusion Changing the workflow from general to subspecialized reporting significantly improved the turnaround time of radiology reports, the fraction of radiology reports available within 24 hours and productivity. Key Points: Citation Format

Download Full-text