- Titel
- Advanced Image Reconstruction for Electrical Impedance Tomography via Ensemble Learning with Consideration of Measurement Data Quality and Prior-Knowledge-Guided Denoising
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:ch1-qucosa2-1016282
- Schriftenreihe
- Scientific Reports on Measurement and Sensor Technology
- Bandnummer
- Volume 41
- Datum der Einreichung
- 10.10.2025
- Datum der Verteidigung
- 16.12.2025
- ISBN
- 978-3-96100-308-2
- E-ISBN
- 978-3-96100-309-9
- E-ISSN
- 2509-5110
- ISSN
- 2509-5102
- DOI
- https://doi.org/10.51382/978-3-96100-309-9
- Abstract (EN)
- Electrical Impedance Tomography (EIT) is a non-invasive imaging method with significant potential for lung state assessment, yet constrained by insufficient image quality. Image reconstruction is a non-linear, ill-posed inverse problem, highly sensitive to measurement perturbations. Existing methods fail to address the dual challenge of conductivity accuracy and structural boundary preservation simultaneously, while post-processing approaches remain computationally intensive and lack prior-knowledge integration, causing persistent residual artifacts. This thesis introduces a holistic framework tackling multiple reconstruction stages. A Gaussian Process regression-based pre-processing achieves 99.97% Mean Squared Error reduction, improving Signal-to-Noise Ratio from 1 dB to 36 dB. An ensemble learning strategy combines a 1D-Residual-CNN-GRU optimized for conductivity accuracy with an enhanced U-Net for structural preservation, integrated via Ridge regression stacking, yielding 3.7% Image Correlation Coefficient (ICC) improvement and 60.8% Relative Image Error (RIE) reduction over state-of-the-art methods. A prior-knowledge-guided post-processing applies targeted denoising, achieving 2.9% ICC improvement and 16.7% RIE reduction. Extended to lung state assessment, the ensemble module achieves 2.9% ICC improvement and 79.3% RIE reduction. Experimental validation on water tank setups and custom PCB thoracic phantoms confirms robustness under real measurement conditions.
- Freie Schlagwörter (EN)
- Electrical Impedance Tomography, measurement deviation compensation, advanced ensemble learning, prior-knowledge-guided denoising, lung state assessment
- Klassifikation (DDC)
- 600
- 620
- Normschlagwörter (GND)
- Impedanztomografie, Bildrekonstruktion, Künstliche Intelligenz, Kompensationsmethode, Rauschunterdrückung, Lunge, Diagnose
- GutachterIn
- Prof. Dr. Olfa Kanoun
- Prof. Dr. Marco Jose Da Silva
- BetreuerIn Hochschule / Universität
- Prof. Dr. Olfa Kanoun
- BetreuerIn - externe Einrichtung
- Prof. Dr. Najoua Essoukri Ben Amara
- Verlag
- Universitätsverlag Chemnitz, Chemnitz
- Den akademischen Grad verleihende / prüfende Institution
- Technische Universität Chemnitz, Chemnitz
- Förder- / Projektangaben
- Ministry of Higher Education and Scientific Research of Tunisia (MESRS)
Téléassistance des personnes en Insuffisance Respiratoire par une ventilation Adaptée aux Mesures de bio-impédance tomographiques thoraciques
(TIRAM)
ID: PRFCOV19-D5P3 - German Academic Exchange Service & Federal Ministry for Economic Cooperation and Development (DAAD & BMZ)
Praxispartnerschaften zwischen Hochschulen und Unternehmen in Deutschland und in Afrika
Praxispartnerschaften zwischen Hochschulen und Unternehmen in Deutschland und in Afrika
(Hi-Q)
ID: #57424451 - Sächsische Aufbaubank, Abt. Europäischer Sozialfonds (ESF)
REACT-ESF Nachwuchsforschergruppe
3D Elektrische Impedanztomografie für Lungenmonitoring im Rahmen der Post-Covid-Therapie
(ELIOT)
ID: #2420156 - Version / Begutachtungsstatus
- publizierte Version / Verlagsversion
- URN Qucosa
- urn:nbn:de:bsz:ch1-qucosa2-1016282
- Veröffentlichungsdatum Qucosa
- 25.03.2026
- Dokumenttyp
- Dissertation
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
CC BY 4.0- Inhaltsverzeichnis
1 Introduction 2 Theoretical Background 3 State of the art of EIT image reconstruction 4 Novel image reconstruction framework 5 Performance evaluation of the proposed advanced ensemble learning for EIT 6 Experimental validation of the novel image reconstruction framework 7 Application in lung state assessment 8 Conclusion Appendix