arXiv subjects

Franz Pfeiffer

Publications and source records attributed to Franz Pfeiffer.

25 records · Page 2Linked to original sources

arXiv2023

Optimizing Convolutional Neural Networks for Chronic Obstructive Pulmonary Disease Detection in Clinical Computed Tomography Imaging

We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7,194 CT images (3,597 with COPD; 3,597 healthy controls) from 78 subjects were selected retrospectively (10.2018-12.2021) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3,392, 1,114, and 2,688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n=7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.

eess.IV↗

arXiv2022

Task-specific Performance Prediction and Acquisition Optimization for Anisotropic X-ray Dark-field Tomography

Anisotropic X-ray Dark-field Tomography (AXDT) is a recently developed imaging modality that enables the visualization of oriented microstructures using lab-based X-ray grating interferometer setups. While there are very promising application scenarios, for example in materials testing of fibrous composites or in medical diagnosis of brain cell connectivity, AXDT faces challenges in practical applicability due to the complex and time-intensive acquisitions required to fully sample the anisotropic X-ray scattering functions. However, depending on the specific imaging task at hand, a full sampling may not be required, allowing for reduced acquisitions. In this work we are investigating a performance prediction approach for AXDT using task-specific detectability indices. Based on this approach we present a task-driven acquisition optimization method that enables reduced acquisition schemes while keeping the task-specific image quality high. We demonstrate the feasibility and efficacy of the method in experiments with simulated and experimental data.

physics.med-ph↗

arXiv2022

WNet: A data-driven dual-domain denoising model for sparse-view computed tomography with a trainable reconstruction layer

Deep learning based solutions are being succesfully implemented for a wide variety of applications. Most notably, clinical use-cases have gained an increased interest and have been the main driver behind some of the cutting-edge data-driven algorithms proposed in the last years. For applications like sparse-view tomographic reconstructions, where the amount of measurement data is small in order to keep acquisition time short and radiation dose low, reduction of the streaking artifacts has prompted the development of data-driven denoising algorithms with the main goal of obtaining diagnostically viable images with only a subset of a full-scan data. We propose WNet, a data-driven dual-domain denoising model which contains a trainable reconstruction layer for sparse-view artifact denoising. Two encoder-decoder networks perform denoising in both sinogram- and reconstruction-domain simultaneously, while a third layer implementing the Filtered Backprojection algorithm is sandwiched between the first two and takes care of the reconstruction operation. We investigate the performance of the network on sparse-view chest CT scans, and we highlight the added benefit of having a trainable reconstruction layer over the more conventional fixed ones. We train and test our network on two clinically relevant datasets and we compare the obtained results with three different types of sparse-view CT denoising and reconstruction algorithms.

eess.IV↗

arXiv2021

Estimating Total Lung Volume from Pixel-level Thickness Maps of Chest Radiographs Using Deep Learning

Purpose: To estimate the total lung volume (TLV) from real and synthetic frontal chest radiographs (CXR) on a pixel level using lung thickness maps generated by a U-Net deep learning model. Methods: This retrospective study included 5,959 chest CT scans from two public datasets: the lung nodule analysis 2016 (n=656) and the Radiological Society of North America (RSNA) pulmonary embolism detection challenge 2020 (n=5,303). Additionally, 72 participants were selected from the Klinikum Rechts der Isar dataset (October 2018 to December 2019), each with a corresponding chest radiograph taken within seven days. Synthetic radiographs and lung thickness maps were generated using forward projection of CT scans and their lung segmentations. A U-Net model was trained on synthetic radiographs to predict lung thickness maps and estimate TLV. Model performance was assessed using mean squared error (MSE), Pearson correlation coefficient (r), and two-sided Student's t-distribution. Results: The study included 72 participants (45 male, 27 female, 33 healthy: mean age 62 years [range 34-80]; 39 with chronic obstructive pulmonary disease: mean age 69 years [range 47-91]). TLV predictions showed low error rates ($MSE_{Public-Synthetic}$=0.16 $L^2$, $MSE_{KRI-Synthetic}$=0.20 $L^2$, $MSE_{KRI-Real}$=0.35 $L^2$) and strong correlations with CT-derived reference standard TLV ($n_{Public-Synthetic}$=1,191, r=0.99, P<0.001; $n_{KRI-Synthetic}$=72, r=0.97, P<0.001; $n_{KRI-Real}$=72, r=0.91, P<0.001). The Luna16 test data demonstrated the highest performance, with the lowest mean squared error (MSE = 0.09 $L^2$) and strongest correlation (r = 0.99, P <0.001) for TLV estimation. Conclusion: The U-Net-generated pixel-level lung thickness maps successfully estimated TLV for both synthetic and real radiographs.

eess.IV↗

arXiv2020

X-ray dark-field signal reduction due to hardening of the visibility spectrum

X-ray dark-field imaging enables a spatially-resolved visualization of ultra-small-angle X-ray scattering. Using phantom measurements, we demonstrate that a material's effective dark-field signal may be reduced by modification of the visibility spectrum by other dark-field-active objects in the beam. This is the dark-field equivalent of conventional beam-hardening, and is distinct from related, known effects, where the dark-field signal is modified by attenuation or phase shifts. We present a theoretical model for this group of effects and verify it by comparison to the measurements. These findings have significant implications for the interpretation of dark-field signal strength in polychromatic measurements.

physics.med-ph↗

arXiv2020

Dual-energy X-ray dark-field material decomposition

Dual-energy imaging is a clinically well-established technique that offers several advantages over conventional X-ray imaging. By performing measurements with two distinct X-ray spectra, differences in energy-dependent attenuation are exploited to obtain material-specific information. This information is used in various imaging applications to improve clinical diagnosis. In recent years, grating-based X-ray dark-field imaging has received increasing attention in the imaging community. The X-ray dark-field signal originates from ultra small-angle scattering within an object and thus provides information about the microstructure far below the spatial resolution of the imaging system. This property has led to a number of promising future imaging applications that are currently being investigated. However, different microstructures can hardly be distinguished with current X-ray dark-field imaging techniques, since the detected dark-field signal only represents the total amount of ultra small-angle scattering. To overcome these limitations, we present a novel concept called dual-energy X-ray dark-field material decomposition, which transfers the basic material decomposition approach from attenuation-based dual-energy imaging to the dark-field imaging modality. We develop a physical model and algorithms for dual-energy dark-field material decomposition and evaluate the proposed concept in experimental measurements. Our results suggest that by sampling the energy-dependent dark-field signal with two different X-ray spectra, a decomposition into two different microstructured materials is possible. Similar to dual-energy imaging, the additional microstructure-specific information could be useful for clinical diagnosis.

physics.med-ph↗

arXiv2019

A theoretical framework for comparing noise characteristics of spectral, differential phase-contrast and spectral differential phase-contrast X-ray imaging

Spectral and grating-based differential phase-contrast X-ray imaging are two emerging technologies that offer additional information compared with conventional attenuation-based X-ray imaging. In the case of spectral imaging, energy-resolved measurements allow the generation of material-specific images by exploiting differences in the energy-dependent attenuation. Differential phase-contrast imaging uses the phase shift that an X-ray wave exhibits when traversing an object as contrast generation mechanism. Recently, we have investigated the combination of these two imaging techniques (spectral differential phase-contrast imaging) and demonstrated potential advantages compared with spectral imaging. In this work, we present a noise analysis framework that allows the prediction of (co-) variances and noise power spectra for all three imaging methods. Moreover, the optimum acquisition parameters for a particular imaging task can be determined. We use this framework for a performance comparison of all three imaging methods. The comparison is focused on (projected) electron density images since they can be calculated with all three imaging methods. Our study shows that spectral differential phase-contrast imaging enables the calculation of electron density images with strongly reduced noise levels compared with the other two imaging methods for a large range of clinically relevant pixel sizes. In contrast to conventional differential phase-contrast imaging, there are no long-range noise correlations for spectral differential phase-contrast imaging. This means that excessive low frequency noise can be avoided. We confirm the analytical predictions by numerical simulations.

physics.med-ph↗