610 Medizin, Gesundheit
Refine
Document Type
- Journal article (97)
- Conference proceeding (86)
- Book chapter (12)
- Doctoral Thesis (2)
- Book (1)
- Patent / Standard / Guidelines (1)
- Report (1)
Is part of the Bibliography
- yes (200)
Institute
- Informatik (127)
- Life Sciences (50)
- Technik (15)
- ESB Business School (7)
Publisher
Objectives: Content-based access (CBA) to medical image archives, i.e. data retrieval by means of image-based numerical features computed automatically, has capabilities to improve diagnostics, research and education. In this study, the applicability of CBA methods in dentomaxillofacial radiology is evaluated.
Methods: Recent research has discovered numerical features that were successfully applied for an automatic categorization of radiographs. In our experiments, oral and maxillofacial radiographs were obtained from the day-to-day routine of a university hospital and labelled by an experienced dental radiologist regarding the technique and direction of imaging, as well as the displayed anatomy and biosystem. In total, 2000 radiographs of 71 classes with at least 10 samples per class were analysed. A combination of co-occurrence-based texture features and correlation-based similarity measures was used in leaving-one-out experiments for automatic classification. The impact of automatic detection and separation of multi-field images and automatic separability of biosystems were analysed.
Results: Automatic categorization yielded error rates of 23.20%, 7.95% and 4.40% with respect to a correct match within the first, fifth and tenth best returns. These figures improved to 23.05%, 7.00%, 4.20%, and 20.05%, 5.65% and 3.25% if automatic decomposition was applied and the classifier was optimized to the dentomaxillofacial imagery, respectively. The dentulous and implant systems were difficult to distinguish. Experiments on non-dental radiographs (10 000 images of 57 classes) yielded 12.6%, 5.6% and 3.6%.
Conclusion: Using the same numerical features as in medical radiology, oral and maxillofacial radiographs can be reliably indexed by global texture features for CBA and data mining.
The medical automatic annotation task issued by the cross language evaluation forum (CLEF) aims at a fair comparison of state-of-the art algorithms for medical content-based image retrieval (CBIR). The contribution of this work is twofold: at first, a logical decomposition of the CBIR task is presented, and key elements to support the relevant steps are identified: (i) implementation of algorithms for feature extraction, feature comparison, and classifier combination, (ii) visualization of extracted features and retrieval results, (iii) generic evaluation of retrieval algorithms, and (iv) optimization of the parameters for the retrieval algorithms and their combination. Data structures and tools to address these key elements are integrated into an existing framework for image retrieval in medical applications (IRMA). Secondly, baseline results for the CLEF annotation tasks 2005–2007 are provided applying the IRMA framework, where global features and corresponding distance measures are combined within a nearest neighbor approach. Using identical classifier parameters and combination weights for each year shows that the task difficulty decreases over the years. The declining rank of the baseline submission also indicates the overall advances in CBIR concepts. Furthermore, a rough comparison between participants who submitted in only one of the years becomes possible.
The pre-, intra- and postoperative determination of the entity and dignity of salivary gland tumors (ST) based solely on histomorphological criteria is not reliably in all cases. The spectra of Raman spectroscopy (RS) contain information about the molecular composition of the examined tissue. The aim of the work was to establish an RS-based measurement setup and a workflow for the differentiation of salivary gland tumor tissue and salivary gland tissue. In addition, the barriers of translating RS in salivary gland diagnostics are discussed. 10 µm thick, native cryo-tissue sections of Warthin tumors (n=5) and pleomorphic adenomas (n=4) were examined using RS in both tumor tissue and healthy salivary gland tissue and the data were evaluated in a multivariate data analysis. All measurements were histomorphologically localized in a corresponding HE section. A "principal component" analysis (PCA) of the RS data and coupled discriminant analysis enabled both a distinction between tumor and non-tumor tissue as well as the differentiation of the various tumor entities (based on the histopathological assessment) with a high level of accuracy (93% ). In summary, it could be shown that the RS measurements could be used to reliably distinguish between ST and healthy salivary gland tissue. Another important result is that tissue processing is possible reliably using standard pathological methods. The high number of different ST entities represents a biostatistical challenge. Approaches to the solution include multi-level statistical models and simultaneous correlation with histomorphological criteria.
While the potential of Artificial Intelligence (AI) - particularly Natural Language Processing (NLP) models - for detecting symptoms of depression from text has been vastly researched, only a few studies examine such potential for the detection of social anxiety symptoms. We investigated the ability of the large language model (LLM) GPT-4 to correctly infer social anxiety symptom strength from transcripts obtained from semi-structured interviews. N = 51 adult participants were recruited from a convenience sample of the German population. Participants filled in a self-report questionnaire on social anxiety symptoms (SPIN) prior to being interviewed on a secure online teleconference platform. Transcripts from these interviews were then evaluated by GPT-4. GPT-4 predictions were highly correlated (r = 0.79) with scores obtained on the social anxiety self-report measure. Following the cut-off conventions for this population, an F1 accuracy score of 0.84 could be obtained. Future research should examine whether these findings hold true in larger and more diverse datasets.
Background: Digitalization in disaster medicine holds significant potential to accelerate rescue operations and ultimately save lives. Mass casualty incidents demand rapid and accurate information management to coordinate effective responses. Currently, first responders manually record triage results on patient cards, and brief information is communicated to the command post via radio communication. Although this process is widely used in practice, it involves several time-consuming and error-prone tasks. To address these issues, we designed, implemented, and evaluated an app-based mobile triage system. This system allows users to document responder details, triage categories, injury patterns, GPS locations, and other important information, which can then be transmitted automatically to the incident commanders.
Objective: This study aims to design and evaluate an app-based mobile system as a triage and coordination tool for emergency and disaster medicine, comparing its effectiveness with the conventional paper-based system.
Methods: A total of 38 emergency medicine personnel participated in a within-subject experimental study, completing 2 triage sessions with 30 patient cards each: one session using the app-based mobile system and the other using the paper-based tool. The accuracy of the triages and the time taken for each session were measured. Additionally, we implemented the User Experience Questionnaire along with other items to assess participants’ subjective ratings of the 2 triage tools.
Results: Our 2 (triage tool) × 2 (tool order) mixed multivariate analysis of variance revealed a significant main effect for the triage tool (P<.001). Post hoc analyses indicated that participants were significantly faster (P<.001) and more accurate (P=.005) in assigning patients to the correct triage category when using the app-based mobile system compared with the paper-based tool. Additionally, analyses showed significantly better subjective ratings for the app-based mobile system compared with the paper-based tool, in terms of both school grading (P<.001) and across all 6 scales of the User Experience Questionnaire (all P<.001). Of the 38 participants, 36 (95%) preferred the app-based mobile system. There was no significant main effect for tool order (P=.24) or session order (P=.06) in our model.
Conclusions: Our findings demonstrate that the app-based mobile system not only matches the performance of the conventional paper-based tool but may even surpass it in terms of efficiency and usability. This advancement could further enhance the potential of digitalization to optimize processes in disaster medicine, ultimately leading to the possibility of saving more lives.
Titanium-based additive manufacturing of medical implants has attracted considerable attention over the past decade due to numerous advantages over standard manufacturing. Regarding the surface modification and biofunctionalization of additive manufactured titanium materials carried out by the application of coatings, however, very limited research has been reported so far. The interaction between the adherent tissues and the implant takes place at the interface between them, therefore the tissues response is strongly mediated and controlled by the surface properties of the implanted material. To the best of the authors' knowledge, this is the first study on the surface modification of additively manufactured titanium materials with ultrathin polyelectrolyte multilayer coatings. The application of these coating with a thickness of only a few nanometers proved to be able to impart chemical homogeneity to the surface and allowed targeted modification of the hydrophilicity of the additively manufactured titanium materials without changing their macro-topography and bulk properties. An important and first-of-its-kind finding of the present study, which is being reported for the first time, is the adhesion strength of polyelectrolyte coatings to the surface of additively manufactured titanium materials that were found to meet the requirements of the ISO regulations for coatings, applied to metal implants. The non-cytotoxicity and high adhesion strength classify the polyelectrolyte multilayer coatings as very promising for application as coatings of additively manufactured medical devices.
It was found that the material properties of the multi-material substrates can be specifically influenced by the systematic addition of three photopolymers (Tissue Matrix, Vero, Agilus). Mechanical-dynamic properties very close to those of the biological system can be achieved. Densities of 1100 to 1180 kg/m³, Young’s modulus of 0.1 to 25 MPa and Poisson’s ratio of around 0.3 have been achived. Target values for human ligaments reported in the literature vary, with densities ranging from 1100 to 1200 kg/m³, Young’s modulus from 0.05 to 21 MPa, damping ratio from 0.003 to 0.05, and Poisson’s ratio of around 0.3.
Development of a stochastic finite element model for use in the diagnosis of middle-ear pathologies
(2024)
The calibrated model accurately reproduces the mean and variance of middle-ear measurements like impedance, reflectance, stapes and umbo transfer function. Ligament and joint material parameters have a significant effect on the variance of these measurements, while variations in center of mass positions, for example, have less effect. The neural network trained on the simulated data shows promise for diagnostics, achieving 86-100% sensitivity and 85-93% specificity for detecting otosclerosis and disarticulation, which is similar to the performance of classifiers trained on measured immittance data.
Purpose
Surgical interventions and the intraoperative environment can vary greatly. A system that reliably recognizes the situation in the operating room should therefore be flexibly applicable to different surgical settings. To achieve this, transferability should be focused during system design and development. In this paper, we demonstrated the feasibility of a transferable, scenario-independent situation recognition system (SRS) by the definition and evaluation based on non-functional requirements.
Methods
Based on a high-level concept for a transferable SRS, a proof of concept implementation was demonstrated using scenarios. The architecture was evaluated with a focus on non-functional requirements of compatibility, maintainability, and portability. Moreover, transferability aspects beyond the requirements, such as the effort to cover new scenarios, were discussed in a subsequent argumentative evaluation.
Results
The evaluation demonstrated the development of an SRS that can be applied to various scenarios. Furthermore, the investigation of the transferability to other settings highlighted the system’s characteristics regarding configurability, interchangeability, and expandability. The components can be optimized step by step to realize a versatile and efficient situation recognition that can be easily adapted to different scenarios.
Conclusion
The prototype provides a framework for scenario-independent situation recognition, suggesting greater applicability and transferability to different surgical settings. For the transfer into clinical routine, the system’s modules need to be evolved, further transferability challenges be addressed, and comprehensive scenarios be integrated.
Current noninvasive methods of clinical practice often do not identify the causes of conductive hearing loss due to pathologic changes in the middle ear with sufficient certainty. Wideband acoustic immittance (WAI) measurement is noninvasive, inexpensive and objective. It is very sensitive to pathologic changes in the middle ear and therefore promising for diagnosis. However, evaluation of the data is difficult because of large interindividual variations. Machine learning methods like Convolutional neural networks (CNN) which might be able to deal with this overlaying pattern require a large amount of labeled measurement data for training and validation. This is difficult to provide given the low prevalence of many middle-ear pathologies. Therefore, this study proposes an approach in which the WAI training data of the CNN are simulated with a finite-element ear model and the Monte-Carlo method. With this approach, virtual populations of normal, otosclerotic, and disarticulated ears were generated, consistent with the averaged data of measured populations and well representing the qualitative characteristics of individuals. The CNN trained with the virtual data achieved for otosclerosis an AUC of 91.1 %, a sensitivity of 85.7 %, and a specificity of 85.2 %. For disarticulation, an AUC of 99.5 %, sensitivity of 100 %, and specificity of 93.1 % was achieved. Furthermore, it was estimated that specificity could potentially be increased to about 99 % in both pathological cases if stapes reflex threshold measurements were used to confirm the diagnosis. Thus, the procedures’ performance is comparable to classifiers from other studies trained with real measurement data, and therefore the procedure offers great potential for the diagnosis of rare pathologies or early-stages pathologies. The clinical potential of these preliminary results remains to be evaluated on more measurement data and additional pathologies.