TY  - JOUR
AB  - BACKGROUND: Segmentation models for clinical data experience severe performance degradation when trained on a single client from one domain and distributed to other clients from different domain. Federated Learning (FL) provides a solution by enabling multi-party collaborative learning without compromising the confidentiality of clients' private data. METHODS: In this paper, we propose a cross-domain FL method for Weakly Supervised Semantic Segmentation (FL-W3S) of white blood cells in microscopic images. We perform model training on multiple clients with different data distributions to obtain a global aggregated model using only image-level class labels for semantic segmentation of white blood cells. A multi-class token transformer model learns the relationship between patch tokens and class tokens during collaborative learning and generates class-specific localization maps for mask predictions. To rectify the localization maps, we use patch-level pairwise affinity obtained from patch-to-patch transformer attention. RESULTS: We evaluate performance of the proposed semantic segmentation method on two different datasets of white blood cells from different domains. Our experimental results show that for two datasets, there is 2.56% and 1.39% increase in performance of the proposed method over existing state-of-the-art methods. CONCLUSION: The combination of federated learning for collaborative model training while preserving data privacy, alongside white blood cell segmentation techniques for precise cell identification, enhances diagnostic accuracy and personalized treatment strategies in clinical applications, particularly in hematology and pathology. More specifically, it involves isolating white blood cell from blood smear for further analysis such as automated blood cell counting, morphological analysis, cell classification, disease diagnosis and monitoring.
AU  - Madni, H.A.*
AU  - Umer, R.M.
AU  - Zottin, S.*
AU  - Marr, C.
AU  - Foresti, G.L.*
C1  - 73162
C2  - 56938
CY  - Elsevier House, Brookvale Plaza, East Park Shannon, Co, Clare, 00000, Ireland
TI  - FL-W3S: Cross-domain federated learning for weakly supervised semantic segmentation of white blood cells.
JO  - Int. J. Med. Inform.
VL  - 195
PB  - Elsevier Ireland Ltd
PY  - 2025
SN  - 1386-5056
ER  - 

TY  - JOUR
AB  - INTRODUCTION: In German and international research networks different approaches concerning patient consent are applied. So far it is time-consuming to find out to what extent data from these networks can be used for a specific research project. To make the contents of the consents queryable, we aimed for a permission-based approach (Opt-In) that can map both the permission and the withdrawal of consent contents as well as make it queryable beyond project boundaries. MATERIALS AND METHODS: The current state of research was analysed in terms of approach and reusability. Selected process models for defining consent policies were abstracted in a next step. On this basis, a standardised semantic terminology for the description of consent policies was developed and initially agreed with experts. In a final step, the resulting code was evaluated with regards to different aspects of applicability. RESULTS: A first and extendable version for a Semantic Consent Code (SCC) based on 3-axis (CLASS, ACTION, PURPOSE) was developed, consolidated und published. The added value achieved by the SCC was illustrated using the example of real consents from large national research associations (Medical Informatics Initiative and NUM NAPKON/NUKLEUS). The applicability of the SCC was successfully evaluated in terms of the manual semantic mapping of consents by briefly trained personnel and the automated interpretability of consent policies according to the SCC (and vice versa). In addition, a concept for the use of the SCC to simplify consent queries in heterogeneous research scenarios was presented. CONCLUSIONS: The Semantic Consent Code has already successfully undergone initial evaluations. As the published 3-axis code SCC is an essential preliminary work to standardising initially diverse consent texts and contents and can iteratively be extended in multiple ways in terms of content and technical additions. It should be extended in cooperation with the potential user community.
AU  - Bialke, M.*
AU  - Hampf, C.*
AU  - Blumentritt, A.*
AU  - Moser, F.M.*
AU  - Lang, S.*
AU  - Stehn, A.*
AU  - Sargsyan, E.
AU  - Hoffmann, W.*
AU  - Kraus, M.
C1  - 71212
C2  - 56010
TI  - #consented - A semantic consent code to facilitate consistent documentation and implementation of consent in collaborative medical research.
JO  - Int. J. Med. Inform.
VL  - 190
PY  - 2024
SN  - 1386-5056
ER  - 

TY  - JOUR
AB  - Introduction It is estimated that more than 382 million people suffer from diabetes across the globe, most of which are between the age of 40 and 59 years. ICT can play a key role in better management of diabetes and in patient empowerment. Patient empowerment involves patients to a greater extent in their own healthcare process and disease management becomes an integrated part of their daily life. Self-management opens the possibility for patients to contribute to their own healthcare as well as to be more in control of their disease. Objectives The objective of our study was to explore the impact of an ICT-based patient empowerment framework in diabetes self-management. Methods A modular patient empowerment framework that fosters diabetes self-management was designed and implemented. The framework incorporates expert knowledge in the form of clinical guidelines, and it supports patients in the specification of personalized activities that are based on medical recommendations and personal goals, and in the collection of observations of daily living. The usability and usefulness of the proposed framework were assessed in a pilot study with the participation of 60 patients and 12 health professionals. Results The study revealed that a patient empowerment approach based on self-management ICT tools is useful and accepted by both the patients and the physicians. For those patients who were already disciplined in their disease management the piloted solution served as a facilitator for data logging. For the rest, it served as an incentive for better adherence to disease management principles. The ICT tools prompted many patients into becoming more physically active and into making dietary habits' adjustments. However, this impact proved to be tightly correlated with the sociocultural background of the subjects. The study also demonstrated that even in patient-centric self-management interventions the physicians still have a key role to play. However, the acceptance of such interventions by the healthcare professionals depends not only on the level of impact in their patients’ disease management but also on the level of impact in their workflow. Conclusions It is evident that a patient empowerment approach based on self-management ICT tools is useful and accepted by patients and physicians. Further, there are clear indications that ICT frameworks such as the one presented in this paper support patients in behavioral changes and in better disease management. Finally, it was realized that self-management solutions should be built around the objective not only to educate and guide patients in disease self-management, but also to assist them in exploring the decision space and to provide insight and explanations about the impact of their own values on the decision.
AU  - Lamprinos, I.*
AU  - Demski, H.
AU  - Mantwill, S.*
AU  - Kabak, Y.*
AU  - Hildebrand, C.
AU  - Plößnig, M.*
C1  - 48441
C2  - 41094
CY  - Clare
SP  - 31-43
TI  - Modular ICT-based patient empowerment framework for self-management of diabetes: Design perspectives and validation results.
JO  - Int. J. Med. Inform.
VL  - 91
PB  - Elsevier Ireland Ltd
PY  - 2016
SN  - 1386-5056
ER  - 

TY  - JOUR
AB  - Health information systems supporting shared care are going to be distributed and interoperable. Dealing with sensitive personal medical information, such information systems have to provide appropriate security services, allowing only authorised users restricted access rights to the patients’ data according to the ‘need to know’ principle. Especially in healthcare, chip card based information systems occur in the shape of patient data cards providing informational self determination and mobility of the users as well as quality, integrity, accountability, and availability of the data stored on the card, thus improving the shared care of patients.
AU  - Blobel, B.*
AU  - Pharow, P.*
AU  - Spiegel, V.*
AU  - Engel, K.*
AU  - Engelbrecht, R.
C1  - 21878
C2  - 20105
SP  - 401-415
TI  - Securing interoperability between chip card based medical information systems and health networks.
JO  - Int. J. Med. Inform.
VL  - 64
IS  - 2-3
PY  - 2001
SN  - 1386-5056
ER  - 

TY  - JOUR
AU  - Blobel, B.*
AU  - Dudeck, J.*
AU  - Engelbrecht, R.
AU  - Gell, G.*
AU  - Prokosch, H.-U.*
C1  - 21879
C2  - 20104
SP  - 67
TI  - Special Issue : MIE 2000 Medical Infobahn for Europe.
JO  - Int. J. Med. Inform.
VL  - 64
IS  - 2-3
PY  - 2001
SN  - 1386-5056
ER  - 

TY  - JOUR
AU  - Ingernerf, J.*
AU  - Reiner, J.
AU  - Seik, B.*
C1  - 21877
C2  - 20106
SP  - 223-240
TI  - Standardized terminological services enabling semantic interoperability between distributed and heterogeneous systems.
JO  - Int. J. Med. Inform.
VL  - 64
PY  - 2001
SN  - 1386-5056
ER  -