Natural language processing of radiology reports to investigate the effects of the COVID-19 pandemic on the incidence and age distribution of fractures.

OBJECTIVE: During the COVID-19 pandemic, the number of patients presenting in hospitals because of emergency conditions decreased. Radiology is thus confronted with the effects of the pandemic. The aim of this study was to use natural language processing (NLP) to automatically analyze the number and distribution of fractures during the pandemic and in the 5 years before the pandemic. MATERIALS AND METHODS: We used a pre-trained commercially available NLP engine to automatically categorize 5397 radiological reports of radiographs (hand/wrist, elbow, shoulder, ankle, knee, pelvis/hip) within a 6-week period from March to April in 2015-2020 into "fracture affirmed" or "fracture not affirmed." The NLP engine achieved an F1 score of 0.81 compared to human annotators. RESULTS: In 2020, we found a significant decrease of fractures in general (p < 0.001); the average number of fractures in 2015-2019 was 295, whereas it was 233 in 2020. In children and adolescents (p < 0.001), and in adults up to 65 years (p = 0.006), significantly fewer fractures were reported in 2020. The number of fractures in the elderly did not change (p = 0.15). The number of hand/wrist fractures (p < 0.001) and fractures of the elbow (p < 0.001) was significantly lower in 2020 compared with the average in the years 2015-2019. CONCLUSION: NLP can be used to identify relevant changes in the number of pathologies as shown here for the use case fracture detection. This may trigger root cause analysis and enable automated real-time monitoring in radiology.

Non-invasive haemoglobin measurement as an index test to detect pre-operative anaemia in elective surgery patients - a prospective study.

Non-invasive haemoglobin measurement using absolute values lacks the precision to be the sole basis for the treatment of pre-operative anaemia. However, it can possibly serve as a screening test, indexing 'anaemia' with high sensitivity when values remain under prespecified cut-off values. Based on previous data, non-invasive haemoglobin cut-off values (146 g.l-1 for women and 152 g.l-1 for men) detect true anaemia with 99% sensitivity. An index test with these prespecified cut-off values was verified by prospective measurement of non-invasive and invasive haemoglobin pre-operatively in elective surgical patients. In 809 patients, this showed an estimated sensitivity (95%CI) of 98.9% (94.1-99.9%) in women and 96.4% (91.0-99.0%) in men. This saved invasive blood tests in 9% of female and 28% of male patients. In female patients, a lower non-invasive haemoglobin cut-off value (138 g.l-1 ) would save 28% of invasive blood tests with a sensitivity of 95%. The target 99% sensitivity would be reached by non-invasive haemoglobin cut-off values of 152 g.l-1 in female and 162 g.l-1 in male patients, saving 3% and 9% of invasive blood tests, respectively. Bias and limits of agreement between non-invasive and laboratory haemoglobin levels were 2 and - 25 to 28 g.l-1 , respectively. Patient and measurement characteristics did not influence the agreement between non-invasive and laboratory haemoglobin levels. Although sensitivity was very high, the index test using prespecified cut-off values just failed to reach the target sensitivity to detect true anaemia. Nevertheless, with respect to blood-sparing effects, the use of the index test in men may be clinically useful, while an index test with a lower cut-off (132 g.l-1 ) could be more clinically appropriate in women.

[Structured reporting in radiology : IT essentials]. / Strukturierte Befundung in der Radiologie : IT-Essentials.

A clinically meaningful use of structured reporting, which in the opinion of numerous scientific societies and experts is a very important prerequisite for the further development of radiological findings, especially under quality aspects, requires corresponding standards for implementation in IT systems. In addition to DICOM ("digital imaging and communication in medicine"), these are other standards for coding, for example RadLex ("radiological lexicon") or the specification of so-called interoperability profiles, as they are being developed by IHE ("integrating the healthcare enterprise"). The management of radiology report templates (MRRT) profiles is the central building block for this. The building blocks for efficient IT implementation, which also allow harmonization, for example at a national level, are currently available. Users in radiology should familiarize themselves with them and demand appropriate solutions from manufacturers.

Workflow-centred open-source fully automated lung volumetry in chest CT.

AIM: To develop a robust open-source method for fully automated extraction of total lung capacity (TLC) from computed tomography (CT) images and to demonstrate its integration into the clinical workflow. MATERIALS AND METHODS: Using only open-source software, an algorithm was developed based on a region-growing method that does not require manual interaction. Lung volumes calculated from reconstructions with different kernels (TLCCT) were assessed. To validate the algorithm calculations, the results were correlated to TLC measured by pulmonary function testing (TLCPFT) in a subgroup of patients for which this information was available within 3 days of the CT examination. RESULTS: A total of 288 patients were analysed retrospectively. Manual review revealed poor segmentation results in 13 (4.5%) patients. In the validation subgroup, the correlation between TLCCT and TLCPFT was r=0.87 (p<0.001). Measurements showed excellent agreement between the two reconstruction kernels with an intraclass correlation coefficient (ICC) of 0.99. Calculation of the volumes took an average of 5 seconds (standard deviation: 3.72 seconds). Integration of the algorithm into the departments of the PACS environment was successful. A DICOM-encapsulated PDF document with measurements and an overlay of the segmentation results was sent to the PACS to allow the radiologists to detect false measurements. CONCLUSIONS: The algorithm developed allows fast and fully automated calculation of lung volume without any additional input from the radiologist. The algorithm delivers excellent segmentation in >95% of cases with significant positive correlations between lung volume on CT and TLC on PFT.

A Hybrid Reporting Platform for Extended RadLex Coding Combining Structured Reporting Templates and Natural Language Processing.

Structured reporting is a favorable and sustainable form of reporting in radiology. Among its advantages are better presentation, clearer nomenclature, and higher quality. By using MRRT-compliant templates, the content of the categorized items (e.g., select fields) can be automatically stored in a database, which allows further research and quality analytics based on established ontologies like RadLex® linked to the items. Additionally, it is relevant to provide free-text input for descriptions of findings and impressions in complex imaging studies or for the information included with the clinical referral. So far, however, this unstructured content cannot be categorized. We developed a solution to analyze and code these free-text parts of the templates in our MRRT-compliant reporting platform, using natural language processing (NLP) with RadLex® terms in addition to the already categorized items. The established hybrid reporting concept is working successfully. The NLP tool provides RadLex® codes with modifiers (affirmed, speculated, negated). Radiologists can confirm or reject codes provided by NLP before finalizing the structured report. Furthermore, users can suggest RadLex® codes from free text that is not correctly coded with NLP or can suggest to change the modifier. Analyzing free-text fields took 1.23 s on average. Hybrid reporting enables coding of free-text information in our MRRT-compliant templates and thus increases the amount of categorized data that can be stored in the database. This enhances the possibilities for further analyses, such as correlating clinical information with radiological findings or storing high-quality structured information for machine-learning approaches.

Development of an IHE MRRT-compliant open-source web-based reporting platform.

OBJECTIVES: To develop a platform that uses structured reporting templates according to the IHE Management of Radiology Report Templates (MRRT) profile, and to implement this platform into clinical routine. METHODS: The reporting platform uses standard web technologies (HTML / JavaScript and PHP / MySQL) only. Several freely available external libraries were used to simplify the programming. The platform runs on a standard web server, connects with the radiology information system (RIS) and PACS, and is easily accessible via a standard web browser. RESULTS: A prototype platform that allows structured reporting to be easily incorporated into the clinical routine was developed and successfully tested. To date, 797 reports were generated using IHE MRRT-compliant templates (many of them downloaded from the RSNA's radreport.org website). Reports are stored in a MySQL database and are easily accessible for further analyses. CONCLUSION: Development of an IHE MRRT-compliant platform for structured reporting is feasible using only standard web technologies. All source code will be made available upon request under a free license, and the participation of other institutions in further development is welcome. KEY POINTS: • A platform for structured reporting using IHE MRRT-compliant templates is presented. • Incorporating structured reporting into clinical routine is feasible. • Full source code will be provided upon request under a free license.

[Incidental findings : Evaluation, management recommendations and legal considerations]. / Zufallsbefunde : Befundung, Managementempfehlungen und rechtliche Überlegungen.

Incidental findings are part of the routine radiological reporting workflow and describe findings which are not primarily the focus of the clinical context or the request of the referring physician. The clinical implications of such incidental findings can be very different, for example simple renal cysts or space-occupying lesions suspected of being tumors. A categorization of clinical findings according to the clinical relevance is therefore recommended. Documentation and communication of clinically relevant incidental findings are a part of the radiological reporting process and essential for reduction of the medicolegal risk. Future information technology-assisted developments, e. g. the Integrating the Healthcare Enterprise (IHE) profiles, will help to standardize such workflows.

[Reporting initiatives. An update on treatment in radiology]. / Reporting Initiatives. Ein Update zur Befundung in der Radiologie.

The written radiological report is the most important means of communication between the radiologist and the referring medical doctor. There is no universal definition of a radiological report concerning its structure and content. The majority of clinicians and radiologists prefer structured reporting rather than free text reports of findings. Structured reporting does not increase the quality of a radiological report but has many advantages in research, teaching and quality management. Using standard RadLex terms facilitates translation and ontological assignment of a report. The Reporting Initiative of the Radiological Society of North America (RSNA) offers free and freely available extensively validated best practices radiology report templates in the new management of radiology report templates (MRRT) format according to the guidelines of the Integrating the Healthcare Enterprise (IHE).

[Teleradiology - update 2014]. / Teleradiologie - Update 2014.

Due to economic considerations and thanks to technological advances there is a growing interest in the integration of teleradiological applications into the regular radiological workflow. The legal and technical hurdles which are still to be overcome are being discussed in politics as well as by national and international radiological societies. The European Commission as well as the German Federal Ministry of Health placed a focus on telemedicine with their recent eHealth initiatives. The European Society of Radiology (ESR) recently published a white paper on teleradiology. In Germany §3 section 4 of the Röntgenverordnung (RöV, X-ray regulations) and DIN 6868-159 set a framework in which teleradiology can also be used for primary reads. These possibilities are already being used by various networks and some commercial providers across Germany. With regards to cross-border teleradiology, which currently stands in contrast to the RöV, many issues remain unsolved.

[Integrating the healthcare enterprise (IHE) for radiology: status 2013]. / IHE (Integrating the Healthcare Enterprise) für die Radiologie - Status 2013.

The term integrating the healthcare enterprise (IHE) has been known for more than 10 years and provides an innovative approach to ensure interoperability based on a synthesis of different standards for defined scenarios. Acceptance and deployment are, however limited in Germany compared with other countries. In this article the basic principles and the potential of IHE are described.

[Registration and monitoring of radiation exposure from radiological imaging]. / Erfassung und Monitoring der radiologischen Strahlenexposition.

Strategies for reducing radiation exposure are an important part of optimizing medical imaging and therefore a relevant quality factor in radiology. Regarding the medical radiation exposure, computed tomography has a special relevance. The use of the integrating the healthcare enterprise (IHE) radiation exposure monitoring (REM) profile is the upcoming standard for organizing and collecting exposure data in radiology. Currently most installed base devices do not support this profile generating the required digital imaging and communication in medicine (DICOM) dose structured reporting (SR). For this reason different solutions had been developed to register dose exposure measurements without having the dose SR object.Registration and analysis of dose-related parameters is required for constantly optimizing examination protocols, especially computed tomography (CT) examinations based on the latest research results in order to minimize the individual radiation dose exposure from medical imaging according to the principle as low as reasonably achievable (ALARA).

[Irreversible image compression in radiology. Current status]. / Irreversible Bilddatenkompression in der Radiologie. Aktueller Status.

Due to increasing amounts of data in radiology methods for image compression appear both economically and technically interesting. Irreversible image compression allows markedly higher reduction of data volume in comparison with reversible compression algorithms but is, however, accompanied by a certain amount of mathematical and visual loss of information. Various national and international radiological societies have published recommendations for the use of irreversible image compression. The degree of acceptable compression varies across modalities and regions of interest.The DICOM standard supports JPEG, which achieves compression through tiling, DCT/DWT and quantization. Although mathematical loss due to rounding up errors and reduction of high frequency information occurs this results in relatively low visual degradation.It is still unclear where to implement irreversible compression in the radiological workflow as only few studies analyzed the impact of irreversible compression on specialized image postprocessing. As long as this is within the limits recommended by the German Radiological Society irreversible image compression could be implemented directly at the imaging modality as it would comply with § 28 of the roentgen act (RöV).

[Report template from the German Society of Urology and the German Radiological Society for standardized, structured reporting of native computed tomography scans in the diagnosis of urinary stones]. / Befundvorlage der Deutschen Gesellschaft für Urologie e. V. und der Deutschen Röntgengesellschaft zur standardisierten strukturierten Befundung von nativen Computertomographien in der Harnsteindiagnostik.

Standardized structured radiological reporting (SSRB) has been promoted in recent years. The aims of SSRB include that reports be complete, clear, understandable, and stringent. Repetitions or superfluous content should be avoided. In addition, there are advantages in the presentation of chronological sequences, tracking and correlations with structured findings from other disciplines and also the use of artificial intelligence (AI)-based methods. The development of the presented template for SSRB of native computed tomography for urinary stones followed the "process for the creation of quality-assured and consensus-based report templates as well as subsequent continuous quality control and updating" proposed by the German Radiological Society (DRG). This includes several stages of drafts, consensus meetings and further developments. The final version was published on the DRG website ( www.befundung.drg.de ). The template will be checked annually by the steering group and adjusted as necessary. The template contains 6 organ domains (e.g., right kidney) for which entries can be made for a total of 21 different items, mostly with selection windows. If "no evidence of stones" is selected for an organ in the first query, the query automatically jumps to the next organ, so that the processing can be processed very quickly despite the potentially high total number of individual queries for all organs. The German, European, and North American Radiological Societies perceive the establishment of a standardized structured diagnosis of tomographic imaging methods not only in oncological radiology as one of the current central tasks. With the present template for the description of computed tomographic findings for urinary stone diagnostics, we are presenting the first version of a urological template. Further templates for urological diseases are to follow.

[Chances and challenges of increasing digitalization of teaching in the discipline anesthesiology from the perspective of students]. / Chancen und Herausforderungen der zunehmenden Digitalisierung der Lehre im Fach Anästhesiologie aus Sicht der Studierenden.

BACKGROUND: The coronavirus pandemic caused a sudden change in medical education worldwide and induced a shift towards digital teaching. Previously, most courses were organized for students in physical presence on campus, while a few institutions already complemented these with blended learning methods, combining digital teaching with clinical presence; however, the use of digital teaching was heterogeneous, ranging from the use of PowerPoint slides to the application of virtual patients and telemedicine. OBJECTIVE: This study aimed to identify challenges and opportunities arising from the different tools used in digital teaching, such as recorded lectures or online seminars, and the role of hands-on clinical experience. In addition, the study examined student attitudes and experiences with the nearly all-digital semester beginning in spring 2020. These findings may help to better understand the impact of digital teaching on students and provide guidance on how to optimize digital medical teaching in the future. METHODS: A questionnaire with a 5-point Likert scale was developed to assess students' experiences with digital teaching at the onset of the COVID-19 pandemic in a cross-sectional study. The questionnaire was distributed to all medical students at the University of Mainz, Germany, who attended an anesthesiology course with asynchronously recorded lectures replacing traditional on-campus lectures during the pandemic. A total of 766 students in 4 courses met these criteria and received the online questionnaire for anonymous and voluntary response. RESULTS: A total number of 141 students responded, resulting in a response rate of 18.4%. Almost all students had access to the appropriate technology to participate in digital courses and 80.9% indicated seeing more recorded lectures compared to previous face-to-face lectures on campus. Moreover, 67.4% reported that they paused the asynchronous lectures to look up additional information and 95.7% stated that they appreciated the possibility to view lectures regardless of time and location. Hence, 84.3% said they would prefer digital lectures over face-to-face lectures in the future; however, 28.4% missed the interaction with teachers during lectures. Thus, 94.3% of the students appreciated the online seminars in terms of theoretical knowledge but the majority missed the practical aspects in the courses. Overall, 78.0% responded that the digital availability of material and digital teaching formats helped them to enhance their independent learning abilities. CONCLUSION: This study highlights several opportunities and challenges associated with digital teaching. The availability of prerecorded lectures at any time and place seems to facilitate access and increases student motivation. It also promotes individualization of student learning. Main disadvantages are the lack of communication with teachers and other students as well as the missing opportunity to reinforce the theoretical knowledge through application in practical courses, which, however, are essential for medical education. Therefore, a possible solution in the future could be the introduction of the "inverted classroom" concept, as it focuses on application and deepening of clinical skills in interactive classes, while the theoretical knowledge acquisition is taught in a digital teaching environment. The present study proposes the introduction of blended learning concepts to enhance the benefits of digital teaching while minimizing the identified disadvantages.

Computed tomography in children: multicenter cohort study design for the evaluation of cancer risk.

Exposure to ionizing radiation is a known risk factor for cancer. Cancer risk is highest after exposure in childhood. The computed tomography is the major contributor to the average, individual radiation exposure. Until now the association has been addressed only in statistical modeling. We present the first feasible study design on childhood cancer risk after exposure to computed tomography.

Necessity of preoperative imaging of the gastro-epiploic arcade prior to esophageal resection.

Vascularization of the gastric tube is essential for healing of the esophagogastric anastomosis after resection and reconstruction in patients with esophageal cancer. Leakage of the anastomosis is significantly associated with perioperative mortality. Knowledge of the vascular anatomy before gastric tube construction is of great importance in patients with previous surgery and potential division of the right gastro-epiploic vessels. 3D-computed tomographic angiography is effective for assessing the suitability of the gastro-epiploic arcade prior to esophagectomy by obtaining a road map of the graft's blood supply, as demonstrated in a 72-year-old patient with adenocarcinoma of the distal esophagus and previous extended right hemicolectomy for colon cancer.

[The DICOM-CD-Project of the German Radiology Association--an overview of the content and results of a pilot study in 2006]. / Das DICOM-CD-Projekt der Deutschen Röntgengesellschaft--eine Ubersicht über die Inhalte und Ergebnisse des Pilottests 2006.

DICOM-CDs are frequently used for medical image data transfer. Many different potential advantages are known, such as improved image quality, handling simplification, and cost optimization. However, there are numerous restrictions in the daily routine. While testing DICOM-CDs at the 2006 German Radiology Congress, we found that more than 70 % of CDs have discrepancies with respect to data structure or content. The German Radiological Association and OFFIS started an initiative to improve the quality of DICOM-CDs. There are three main objectives: To provide requirements for vendors of CD-writing systems, to establish user guidelines for the handling of DICOM-CDs, and to develop a test procedure for DICOM-CDs. Radiologists using such systems should be aware of these developments and use them for RFP's.