Title: Self-supervised noise reduction for low dose full interior propagation-based phase-contrast CTs
Speaker: Johannes Thalhammer (Pfeiffer group)
Date and Time: Tuesday, 6 May 2025, 13:00
Abstract: Neural network-based denoising shows great potential for enhancing image quality in low-dose computed tomography (CT). However, training these models usually requires clean target datasets, which are often not available. To tackle this issue, we explore a self-supervised approach inspired by Neighbor2Neighbor, which we adapt for the inverse problem of computed tomography. Our method is applied to full interior propagation-based phase-contrast CT images of excised calf lungs, demonstrating effective denoising without the need for ground truth data.
More information
The MIBE Seminar will take place in our lecture hall E.126 (Boltzmannstr. 11, 85748 Garching) and will be live streamed via zoom.
The zoom details for all online seminar talks this semester are:
Meeting Name: MIBE Seminar Talks, Tuesdays 1:00 pm
https://tum-conf.zoom.us/j/69851298624?pwd=TURFMGQ5N3pDZ0ZGVkVHejFTMFJhUT09
Meeting-ID: 698 5129 8624
Password: mibe
The MIBE Seminar counts as subject specific qualification for doctoral candidates.
Register here.
Further Program SUMMER TERM 2025
The seminar series is being continued in the summer term 2025, further talks will be published here soon.