1 July 2021 in Medical Image Analysis
The two-dimensional nature of mammography makes estimation of the overall breast density challenging, and estimation of the true patient-specific radiation dose impossible. Digital breast tomosynthesis (DBT), a pseudo-3D technique, is now commonly used in breast cancer screening and diagnostics. Still, the severely limited 3rd dimension information in DBT has not been used, until now, to estimate the true breast density or the patient-specific dose. This study proposes a reconstruction algorithm for DBT based on deep learning specifically optimized for these tasks. The algorithm, which we name DBToR, is based on unrolling a proximal-dual optimization method. The proximal operators are replaced with convolutional neural networks and prior knowledge is included in the model. This extends previous work on a deep learning-based reconstruction model by providing both the primal and the dual blocks with breast thickness information, which is available in DBT. Training and testing of the model were performed using virtual patient phantoms from two different sources. Reconstruction performance, and accuracy in estimation of breast density and radiation dose, were estimated, showing high accuracy (density <±3%; dose <±20%) without bias, significantly improving on the current state-of-the-art. This work also lays the groundwork for developing a deep learning-based reconstruction algorithm for the task of image interpretation by radiologists.
20 November 2017 in Theory of Computing Systems
We introduce computable actions of computable groups and prove the following versions of effective Birkhoff’s ergodic theorem. Let Γ be a computable amenable group, then there always exists a canonically computable tempered two-sided Følner sequence (Fn)n≥ 1 in Γ. For a computable, measure-preserving, ergodic action of Γ on a Cantor space \(\{ 0,1\}^{\mathbb N}\) endowed with a computable probability measure μ, it is shown that for every bounded lower semicomputable function f on \(\{0,1\}^{\mathbb {N}}\) and for every Martin-Löf random \(\omega \in \{0,1\}^{\mathbb {N}}\) the equality $$\underset{n \to \infty}{\lim} \frac{1}{|F_{n}|} \sum\limits_{g \in F_{n}} f(g \cdot \omega) = \int\limits f d \mu $$ holds, where the averages are taken with respect to a canonically computable tempered two-sided Følner sequence (Fn)n≥ 1. We also prove the same identity for all lower semicomputable f’s in the special case when Γ is a computable group of polynomial growth and Fn := B(n) is the Følner sequence of balls around the neutral Γ.
8 May 2025 in The Astrophysical Journal
Spatially resolved polarization measurements of extended X-ray sources are expanding our understanding of the emission mechanisms and magnetic field properties involved. Such measurements have been possible in the past few years thanks to the Imaging X-ray Polarimetry Explorer (IXPE). However, the analysis of extended sources suffers a systematic effect known as polarization leakage, which artificially affects the measured polarization signal. To address this issue, we built a hybrid reconstruction algorithm, which combines machine learning and analytic techniques to improve the reconstruction of photoelectron tracks in the Gas Pixel Detector and to significantly mitigate polarization leakage. This work presents the first application of this hybrid method to experimental data, including both calibration lab measurements and IXPE observational data. We confirmed the reliable performance of the hybrid method for both cases. Additionally, we demonstrated the algorithm’s effectiveness in reducing the polarization leakage effect through the analysis of the IXPE observation of the supernova remnant G21.5-0.9. By enabling more reliable polarization measurements, this method can potentially yield deeper insights into the magnetic field structures, particle acceleration processes, and emission mechanisms at work within extended X-ray sources.