Informatik
Refine
Year of publication
- 2022 (85) (remove)
Document Type
- Conference proceeding (50)
- Journal article (31)
- Book chapter (2)
- Doctoral Thesis (1)
- Anthology (1)
Is part of the Bibliography
- yes (85)
Institute
- Informatik (85)
Publisher
- Springer (24)
- Hochschule Reutlingen (10)
- Elsevier (7)
- IEEE (6)
- De Gruyter (4)
- University of Hawai'i at Manoa (3)
- Association for Computing Machinery (2)
- Association for Information Systems (2)
- IADIS (2)
- IARIA (2)
Handling complexity in modern software engineering : editorial introduction to issue 32 of CSIMQ
(2022)
The potential of the Internet and related digital technologies, such as the Internet of Things (IoT), cognition and artificial intelligence, data analytics, services computing, cloud computing, mobile systems, collaboration networks, and cyber-physical systems, are both strategic drivers and enablers of modern digital platforms with fast-evolving ecosystems of intelligent services for digital products. This issue of CSIMQ presents three recent articles on modern software engineering. First, we focus on continuous software development and place it in the context of software architectures and digital transformation. The first contribution is followed by the description of the basis of specific security requirements and adequate digital monitoring mechanisms. Finally, we present a practical example of the digital management of livestock farming.
Intraoperative imaging can assist neurosurgeons to define brain tumours and other surrounding brain structures. Interventional ultrasound (iUS) is a convenient modality with fast scan times. However, iUS data may suffer from noise and artefacts which limit their interpretation during brain surgery. In this work, we use two deep learning networks, namely UNet and TransUNet, to make automatic and accurate segmentation of the brain tumour in iUS data. Experiments were conducted on a dataset of 27 iUS volumes. The outcomes show that using a transformer with UNet is advantageous providing an efficient segmentation modelling long-range dependencies between each iUS image. In particular, the enhanced TransUNet was able to predict cavity segmentation in iUS data with an inference rate of more than 125 FPS. These promising results suggest that deep learning networks can be successfully deployed to assist neurosurgeons in the operating room.
Glioblastomas are the most aggressive fast-growing primary brain cancer which originate in the glial cells of the brain. Accurate identification of the malignant brain tumor and its sub-regions is still one of the most challenging problems in medical image segmentation. The Brain Tumor Segmentation Challenge (BraTS) has been a popular benchmark for automatic brain glioblastomas segmentation algorithms since its initiation. In this year, BraTS 2021 challenge provides the largest multi-parametric (mpMRI) dataset of 2,000 pre-operative patients. In this paper, we propose a new aggregation of two deep learning frameworksnamely, DeepSeg and nnU-Net for automatic glioblastoma recognition in pre-operative mpMRI. Our ensemble method obtains Dice similarity scores of 92.00, 87.33, and 84.10 and Hausdorff Distances of 3.81, 8.91, and 16.02 for the enhancing tumor, tumor core, and whole tumor regions, respectively, on the BraTS 2021 validation set, ranking us among the top ten teams. These experimental findings provide evidence that it can be readily applied clinically and thereby aiding in the brain cancer prognosis, therapy planning, and therapy response monitoring. A docker image for reproducing our segmentation results is available online at (https://hub.docker.com/r/razeineldin/deepseg21).
Purpose
Artificial intelligence (AI), in particular deep neural networks, has achieved remarkable results for medical image analysis in several applications. Yet the lack of explainability of deep neural models is considered the principal restriction before applying these methods in clinical practice.
Methods
In this study, we propose a NeuroXAI framework for explainable AI of deep learning networks to increase the trust of medical experts. NeuroXAI implements seven state-of-the-art explanation methods providing visualization maps to help make deep learning models transparent.
Results
NeuroXAI has been applied to two applications of the most widely investigated problems in brain imaging analysis, i.e., image classification and segmentation using magnetic resonance (MR) modality. Visual attention maps of multiple XAI methods have been generated and compared for both applications. Another experiment demonstrated that NeuroXAI can provide information flow visualization on internal layers of a segmentation CNN.
Conclusion
Due to its open architecture, ease of implementation, and scalability to new XAI methods, NeuroXAI could be utilized to assist radiologists and medical professionals in the detection and diagnosis of brain tumors in the clinical routine of cancer patients. The code of NeuroXAI is publicly accessible at https://github.com/razeineldin/NeuroXAI.
Purpose
Artificial intelligence (AI), in particular deep learning (DL), has achieved remarkable results for medical image analysis in several applications. Yet the lack of human-like explanations of such systems is considered the principal restriction before utilizing these methods in clinical practice (Yang, Ye, & Xia, 2022).
Methods
Explainable Artificial Intelligence (XAI) provides a human-explainable and interpretable description of the “black-box” nature of DL (Gulum, Trombley, & Kantardzic, 2021). An effective XAI diagnosis generator, namely NeuroXAI (refer to Fig. 1), has been developed to extract 3D explanations from convolutional neural networks (CNN) models of brain gliomas (Zeineldin et al., 2022). By providing visual justification maps, NeuroXAI can help make DL models transparent and thus increase the trust of medical experts.
Results
NeuroXAI has been applied to two applications of the most widely investigated problems in brain imaging analysis, i.e. image classification and segmentation using magnetic resonance imaging (MRI). Visual attention maps of multiple XAI methods have been generated and compared for both applications, which could help to provide transparency about the performance of DL systems.
Conclusion
NeuroXAI helps to understand the prediction process of 3D CNN networks for brain glioma using human-understandable explanations. Results revealed that the investigated DL models behave in a logical human-like manner and can improve the analytical process of the MRI images systematically. Due to its open architecture, ease of implementation, and scalability to new XAI methods, NeuroXAI could be utilized to assist medical professionals in the detection and diagnosis of brain tumors. NeuroXAI code is publicly accessible at https://github.com/razeineldin/NeuroXAI
Mobile apps for sustainability in grocery shopping: increasing acceptance through gameification
(2022)
Sustainability has become an important topic in social sciences research as well as in the societal debate. Research in general indicates a high sensitivity of sustainability issues in broad parts of the society, however a change of consumption habits can hardly be overserved. It can be argued that technology, such as mobile apps, can play an important role to increase more sustainable behaviors and consumption habits, as they facilitate such behaviors, bring transparency to an unclear field and reduce complexity. Our research hence approaches an important research gap, especially as currently existing apps show a lack of functionalities and UX. By using a Design Science Research (DSR) approach applying Chou’s Octalysis framework, we systematically analyzed eight apps in the field of sustainability and two general gamification apps as reference points complementing our findings with issues discussed in literature and could identify a broad range of functionalities. This comprehensive analysis allowed us to develop an initial mockup of a potential app, which then was tested within a user-group of ten users by using a semi structured interview approach. Our findings contribute to knowledge by highlighting the importance of user experience on the acceptance of mobile apps, as well as, by showcasing how gamification can contribute to a sustained use of mobile apps in this specific context.
Adoption of artificial intelligence (AI) has risen sharply in recent years but many firms are not successful in realising the expected benefits or even terminate projects before completion. While there are a number of previous studies that highlight challenges in AI projects, critical factors that lead to project failure are mostly unknown. The aim of this study is therefore to identify distinct factors that are critical for failure of AI projects. To address this, interviews with experts in the field of AI from different industries are conducted and the results are analyzed using qualitative analysis methods. The results show that both, organizational and technological issues can cause project failure. Our study contributes to knowledge by reviewing previously identified challenges in terms of their criticality for project failure based on new empirical data, as well as, by identifying previously unknown factors.
There have been substantial research efforts for algorithms to improve continuous and automated assessment of various health-related questions in recent years. This paper addresses the deployment gap between those improving algorithms and their usability in care and mobile health applications. In practice, most algorithms require significant and founded technical knowledge to be deployed at home or support healthcare professionals. Therefore, the digital participation of persons in need of health care professionals lacks a usable interface to use the current technological advances. In this paper, we propose applying algorithms taken from research as web-based microservices following the common approach of a RESTful service to bridge the gap and make algorithms accessible to caregivers and patients without technical knowledge and extended hardware capabilities. We address implementation details, interpretation and realization of guidelines, and privacy concerns using our self-implemented example. Also, we address further usability guidelines and our approach to those.
Turning students into Industry 4.0 entrepreneurs: design and evaluation of a tailored study program
(2022)
Startups in the field of Industry 4.0 could be a huge driver of innovation for many industry sectors such as manufacturing. However, there is a lack of education programs to ensure a sufficient number of well-trained founders and thus a supply of such startups. Therefore, this study presents the design, implementation, and evaluation of a university course tailored to the characteristics of Industry 4.0 entrepreneurship. Educational design-based research was applied with a focus on content and teaching concept. The study program was first implemented in 2021 at a German university of applied sciences with 25 students, of which 22 participated in the evaluation. The evaluation of the study program was conducted with a pretest–posttest-design targeting three areas: (1) knowledge about the application domain, (2) entrepreneurial intention and (3) psychological characteristics. The entrepreneurial intention was measured based on the theory of planned behavior. For measuring psychological characteristics, personality traits associated with entrepreneurship were used. Considering the study context and the limited external validity of the study, the following can be identified in particular: The results show that a university course can improve participants' knowledge of this particular area. In addition, perceived behavioral control of starting an Industry 4.0 startup was enhanced. However, the results showed no significant effects on psychological characteristics.
Background
Personalized medicine requires the integration and analysis of vast amounts of patient data to realize individualized care. With Surgomics, we aim to facilitate personalized therapy recommendations in surgery by integration of intraoperative surgical data and their analysis with machine learning methods to leverage the potential of this data in analogy to Radiomics and Genomics.
Methods
We defined Surgomics as the entirety of surgomic features that are process characteristics of a surgical procedure automatically derived from multimodal intraoperative data to quantify processes in the operating room. In a multidisciplinary team we discussed potential data sources like endoscopic videos, vital sign monitoring, medical devices and instruments and respective surgomic features. Subsequently, an online questionnaire was sent to experts from surgery and (computer) science at multiple centers for rating the features’ clinical relevance and technical feasibility.
Results
In total, 52 surgomic features were identified and assigned to eight feature categories. Based on the expert survey (n = 66 participants) the feature category with the highest clinical relevance as rated by surgeons was “surgical skill and quality of performance” for morbidity and mortality (9.0 ± 1.3 on a numerical rating scale from 1 to 10) as well as for long-term (oncological) outcome (8.2 ± 1.8). The feature category with the highest feasibility to be automatically extracted as rated by (computer) scientists was “Instrument” (8.5 ± 1.7). Among the surgomic features ranked as most relevant in their respective category were “intraoperative adverse events”, “action performed with instruments”, “vital sign monitoring”, and “difficulty of surgery”.
Conclusion
Surgomics is a promising concept for the analysis of intraoperative data. Surgomics may be used together with preoperative features from clinical data and Radiomics to predict postoperative morbidity, mortality and long-term outcome, as well as to provide tailored feedback for surgeons.