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.

[Natural language processing in radiology : Neither trivial nor impossible]. / Natural Language Processing in der Radiologie : Weder trivial noch unerreichbare Magie.

BACKGROUND: The need for application expertise in natural language processing (NLP) is increasing in radiology. This way, in a complementary fashion to structured reporting using templates, the necessary database for quality assurance and continuous process optimization can be generated. OBJECTIVE: Possibilities and challenges of the application of NLP from the radiology point of view are explained. MATERIALS AND METHODS: The requirements and expectations for NLP systems are identified and demonstrated using a case study. RESULTS: For an effective use of this technology, NLP tasks for the interpretation of text using RadLex, an intuitive usage and feedback option as well as transparent quality of the NLP results are important. DISCUSSION: Using suitable NLP systems, targeted information can be extracted from large amounts of free text with manageable manual effort and high quality.

[Medicine in the digital age : Telemedicine in medical school education]. / Medizin im digitalen Zeitalter : Telemedizin in der studentischen Lehre.

BACKGROUND: The increasing digitization of our lives and work has also reached medicine and is changing the profession of medical doctors. The modern forms of communication and cooperation in everyday medical practice demand new skills and qualifications. GOALS: To enable future doctors to comply with this digitally competent profile, an innovative blended learning curriculum was developed and first implemented at the University Medical Center Mainz in summer semester 2017-Medicine in the Digital Age. MATERIALS AND METHODS: The teaching concept encompasses five modules, each consisting of an e­learning unit and a 3-hour classroom course. This publication presents the teaching concept, the initial implementation and evaluation of the module "Telemedicine". RESULTS: The competency development in the field of telemedicine showed a significant increase for the subcomponents "knowledge" and "skills". The neutral attitude towards telemedicine at the beginning of the module could be changed to a positive opinion after the session. DISCUSSION: The teaching of digital skills is a relevant component of future curriculum development in medical studies and also a challenge for continuing medical education.

[Basics and applications of Natural Language Processing (NLP) in radiology]. / Grundlagen und Einsatzmöglichkeiten von Natural Language Processing (NLP) in der Radiologie.

BACKGROUND: Due to the increasing demands in radiology, applications that enable quality assurance and continuous process optimization are required. OBJECTIVE: The principles of Natural Language Processing (NLP) as a computer-based method for structuring of free text reports are explained and application scenarios are sketched. MATERIALS UND METHODS: The structuring of free texts succeeds by several theories, linguistic techniques (word meanings, word context, negations), statistical methods with rules and currently with deep learning approaches. Medical encyclopedias, such as RadLex®, are suitable for coding findings. NLP was used in our own radiology clinic to check the quality of 3756 CT reports. RESULTS: In our case study, NLP proved to be a helpful, automated tool for internal quality testing. DISCUSSION: NLP offers numerous application scenarios for decision support and for quality management in radiology.

[IT systems in radiology and IT systems for radiologists]. / IT-Systeme in der Radiologie und IT-Systeme für den Radiologen.

Radiology plays an important role in introduction and use of information technology (IT) systems in the daily clinical routine. The radiology information system (RIS) and picture archiving and communication system (PACS) are the main systems used in a digital radiology department. In this article the basic principles and functions of these systems and trends in development are described.

Prognostic value of deep learning-derived body composition in advanced pancreatic cancer-a retrospective multicenter study.

BACKGROUND: Despite the prognostic relevance of cachexia in pancreatic cancer, individual body composition has not been routinely integrated into treatment planning. In this multicenter study, we investigated the prognostic value of sarcopenia and myosteatosis automatically extracted from routine computed tomography (CT) scans of patients with advanced pancreatic ductal adenocarcinoma (PDAC). PATIENTS AND METHODS: We retrospectively analyzed clinical imaging data of 601 patients from three German cancer centers. We applied a deep learning approach to assess sarcopenia by the abdominal muscle-to-bone ratio (MBR) and myosteatosis by the ratio of abdominal inter- and intramuscular fat to muscle volume. In the pooled cohort, univariable and multivariable analyses were carried out to analyze the association between body composition markers and overall survival (OS). We analyzed the relationship between body composition markers and laboratory values during the first year of therapy in a subgroup using linear regression analysis adjusted for age, sex, and American Joint Committee on Cancer (AJCC) stage. RESULTS: Deep learning-derived MBR [hazard ratio (HR) 0.60, 95% confidence interval (CI) 0.47-0.77, P < 0.005] and myosteatosis (HR 3.73, 95% CI 1.66-8.39, P < 0.005) were significantly associated with OS in univariable analysis. In multivariable analysis, MBR (P = 0.019) and myosteatosis (P = 0.02) were associated with OS independent of age, sex, and AJCC stage. In a subgroup, MBR and myosteatosis were associated with albumin and C-reactive protein levels after initiation of therapy. Additionally, MBR was also associated with hemoglobin and total protein levels. CONCLUSIONS: Our work demonstrates that deep learning can be applied across cancer centers to automatically assess sarcopenia and myosteatosis from routine CT scans. We highlight the prognostic role of our proposed markers and show a strong relationship with protein levels, inflammation, and anemia. In clinical practice, automated body composition analysis holds the potential to further personalize cancer treatment.

[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).

[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).

[Continuing medical education (CME) in neurology. Concept of the German Society of Neurology (DGN) and the Neurology Section of the Professional League of German Neurologic Medicine (BVDN)]. / Kontinuierliche medizinische Fortbildung (CME) in der Neurologie. Konzept der Deutschen Gesellschaft für Neurologie (DGN) und der Sektion Neurologie im Berufsverband Deutscher Nervenärzte (BVDN).

Continuous medical education in Neurology (CME-Neurology) has been promoted in a concept organized by both the German society of neurology, German association for occupational interests of neurologists and psychiatrists). CME-Neurology has been started in January 1999 and is closely adapted to the CME guidelines of neurology section of UEMS and EFNS. The program shall serve to the maintenance and upgrading of knowledge skills and competence of postgraduate training in neurology.

What makes age diverse teams effective? Results from a six-year research program.

Based on a new model of productivity in age diverse tams, findings from a six-year research program are reported in which data from more than 745 natural teams with 8,848 employees in three different fields (car production, administrative work, financial services) were collected. Moreover, central assumptions of this model were tested with a representative survey of the German workforce (N = 2,000). Results support both significant advantages and disadvantages for age-mixed teams. Based on the findings, the following preconditions for the effectiveness of age diverse teams are identified: high task complexity, low salience and high appreciation of age diversity, a positive team climate, low age-discrimination, ergonomic design of work places, and the use of age differentiated leadership. Based on these insights, we developed a new training for supervisors, which addresses the aforementioned aspects and seeks to improve team performance and health of team members. It was found that the training reduces age stereotypes, team conflicts and enhances innovation. Thus, we can conclude that effective interventions for a successful integration of elderly employees in work groups are available and that combinations of measures that address ergonomic design issues, team composition and leadership are to be strongly recommended for practice.

Impact of perceptual ability and mental imagery training on simulated laparoscopic knot-tying in surgical novices using a Nissen fundoplication model.

BACKGROUND: Performing minimally invasive surgery requires training and visual-spatial intelligence. The aim of our study was to examine the impact of visual-spatial perception and additional mental training on the simulated laparoscopic knot-tying task performed by surgical novices. METHODS: A total of 40 medical students randomly assigned to two groups underwent two sessions of laparoscopic basic training on a VR simulator (SimSurgery®, Oslo, Norway). The variables time and tip trajectory (total path length of the instrument tip trajectory) were used to assess the performance of the intracorporeal knot-tying task using a laparoscopic Nissen fundoplication model. The experimental group completed additional mental practice during the interval between the two training sessions. All performed a cube subtest of a standard intelligence test (I-S-T 2000 R) to evaluate visual-spatial ability. RESULTS: All participants achieved an improvement in time (t = 9.861; p < 0.001) and tip trajectory (t = 6.833; p < 0.001) in the second training session. High scores on the visual-spatial test correlated with a faster performance (r = -0.557; p < 0.001) and more precise movements (r = -0.377; p = 0.016). Comparison of the two groups did not show any statistical significant differences in the parameters time and tip trajectory. CONCLUSIONS: Visual-spatial intelligence tested by a cube test correlated with simulated laparoscopic knot-tying skills in surgical novices. Additional mental practice did not improve the overall knot-tying performance. Further studies are therefore required to determine whether mental practice might be beneficial for experienced laparoscopic surgeons or for more complex tasks.