Dual Energy CT is a modern imaging technique that is utilized in clinical practice to acquire spectral information for various diagnostic purposes including the identification, classification, and characterization of different liver lesions. It provides additional information that, when compared to the information available from conventional CT datasets, has the potential to benefit existing computer vision techniques by improving their accuracy and reliability. In order to evaluate the additional value of spectral versus conventional datasets when being used as input for machine learning algorithms, we implemented a weakly-supervised Convolutional Neural Network (CNN) that learns liver lesion localization and classification without pixel-level ground truth annotations. We evaluated the lesion classification (healthy, cyst, hypodense metastasis) and localization performance of the network for various conventional and spectral input datasets obtained from the same CT scan. The best results for lesion localization were found for the spectral datasets with distances of 8.22 ± 10.72 mm, 8.78 ± 15.21 mm and 8.29 ± 12.97 mm for iodine maps, 40 keV and 70 keV virtual mono-energetic images, respectively, while lesion localization distances of 10.58 ± 17.65 mm were measured for the conventional dataset. In addition, the 40 keV virtual mono-energetic datasets achieved the highest overall lesion classification accuracy of 0.899 compared to 0.854 measured for the conventional datasets. The enhanced localization and classification results that we observed for spectral CT data demonstrates that combining machine-learning technology with spectral CT information may improve the clinical workflow as well as the diagnostic accuracy.
Computed tomography (CT) is a valuable imaging modality for pulmonary imaging. Fast acquisition times and sharp cross-sectional images guarantee high diagnostic confidence. With the introduction of low-dose CT, it has been established as standard for lung screening of heavy smokers in many countries around the world. However, at some point the limits for dose reduction with conventional CT are reached and further reduction would suffer from poor image quality. Sparsesampling CT is one technology that would allow a further radiation dose reduction by reducing the number of acquired projection images. Recently, the feasibility of a fast pulsing X-ray tube for CT has been demonstrated, indicating that sparse sampling could become available in future generations of CT scanners. Therefore, we investigated the effect of sparse sampling by a stepwise reduction of the projection images. A lung phantom with synthetic pulmonary nodules was scanned with a clinical CT system. Sparse sampling was simulated by removing projection images prior to reconstruction. The phantom was scanned at the iso-center and at the highest possible table position (off-center). The modulation transfer function (MTF) was determined for different degrees of sparse sampling. Image quality was evaluated by comparing the reduced dose simulations against the full dose image using the structural similarity index (SSIM). MTF was stable down to using 1/4th of the projection images (4-times sparse sampling, SpS-4) with high degradation at the off-center position (full sampling (FS) 10% MTF, iso-center: 0.64; off-center: 0.47). SSIM indicates a small image quality degradation of FS images compared to sparse-sampling images at low radiation doses at the iso-center (35 mAs; FS: 0.91; SpS-4: 0.93) and stronger degradations at the off-center position (35 mAs; FS: 0.65; SpS-4: 0.84). In conclusion, sparse sampling provides stable MTF results down to 1/4th of the projection images. At low dose levels (iso-center: ≤43 mAs; off-center: ≤86 mAs), sparse sampling performs better in terms of SSIM compared to FS.
Computed Tomography (CT) is one of the most important imaging modalities in the medical domain. Ongoing demand for reduction of the X-ray radiation dose and advanced reconstruction algorithms induce ultra-low dose CT acquisitions more and more. However, though advanced reconstructions lead to improved image quality, the ratio between electronic detector noise and incoming signal decreases in ultra-low dose scans causing a degradation of the image quality and, therefore, building a boundary for radiation dose reduction. Future generations of CT scanners may allow sparse sampled data acquisitions, where the source can be switched on and off at any source position. Sparse sampled CT acquisitions could reduce photon starvation in ultra-low dose scans by distributing the energy of skipped projections to the remaining ones. In this work, we simulated sparse sampled CT acquisitions from clinical projection raw data and evaluated the diagnostic value of the reconstructions compared to conventional CT. Therefore, we simulated radiation dose reduction with different degrees of sparse sampling and with a tube current simulator. Up to four experienced radiologists rated the diagnostic quality of each dataset. By a dose reduction to 25% of the clinical dosage, images generated with 4-times sparse sampling – meaning a gap of three projections between two sampling positions – were consistently rated as diagnostic, while about 20% of the ratings for conventional CT were non-diagnostic. Therefore, our data give an initial indication that with sparse sampling a reduction to 25% of the clinical dose is feasible without loss of diagnostic value.
Kai Mei, Benedikt Schwaiger, Felix Kopp, Sebastian Ehn, Alexandra Gersing, Jan Kirschke, Daniela Munzel, Alexander Fingerle, Ernst Rummeny, Franz Pfeiffer, Thomas Baum, Peter Noël
Dual-layer spectral computed tomography (CT) provides a novel clinically available concept for material decomposition (calcium hydroxyapatite, HA) and thus to estimate the bone mineral density (BMD) based on non-dedicated clinical examinations. In this study, we assessed whether HA specific BMD measurements with dual-layer spectral CT are accurate in phantoms and vertebral specimens.
Dual-layer spectral CT was performed at different tube current settings (500, 250, 125 and 50 mAs) with a tube voltage of 120 kVp. Ex-vivo human vertebrae (n = 13) and a phantom containing different known HA concentrations were placed in a semi-anthropomorphic abdomen phantom. BMD was derived with an in-house developed algorithm from spectral-based virtual monoenergetic images at 50 keV and 200 keV. Values were compared to the HA concentrations of the phantoms and conventional quantitative CT (QCT) measurements using a reference phantom, respectively.
Above 125 mAs, which is the radiation exposure level of clinical examinations, errors for phantom measurements based on spectral information were less than 5%, compared to known concentrations. In vertebral specimens, high correlations were found between BMD values assessed with spectral CT and conventional QCT (correlation coefficients > 0.96; p < 0.001 for all).
These results suggest a high accuracy of quantitate HA-specific BMD measurements based on dual-layer spectral CT examinations without the need for a reference phantom, thus demonstrating their feasibility in clinical routine.
In the medical imaging domain, image quality assessment is usually carried out by human observers (HuO) performing a clinical task in reader studies. To overcome time-consuming reader studies numerical model observers (MO) were introduced and are now widely used in the CT research community to predict the performance of HuOs. In the recent years, machine learning based MOs showed promising results for SPECT. Therefore, we built a neural network, a socalled softmax regression model based on machine learning, as MO for x-ray CT. Performance was evaluated by comparing to one of the most prevalent MOs, the channelized Hotelling observer (CHO). CT image data labeled with confidence ratings assessed in a reader study for a detection-task of signals of different sizes, different noise levels and different reconstruction algorithms were used to train and test the MOs. Data was acquired with a clinical CT scanner. For each of four different x-ray radiation exposures, there were 208 repeated scans of a Catphan phantom. The neural network based MO (NN-MO) as well as the CHO showed good agreement with the performance in the reader study.
The trabecular bone microstructure is a key to the early diagnosis and advanced therapy monitoring of osteoporosis. Regularly measuring bone microstructure with conventional multi-detector computer tomography (MDCT) would expose patients with a relatively high radiation dose. One possible solution to reduce exposure to patients is sampling fewer projection angles. This approach can be supported by advanced reconstruction algorithms, with their ability to achieve better image quality under reduced projection angles or high levels of noise. In this work, we investigated the performance of iterative reconstruction from sparse sampled projection data on trabecular bone microstructure in in-vivo MDCT scans of human spines. The computed MDCT images were evaluated by calculating bone microstructure parameters. We demonstrated that bone microstructure parameters were still computationally distinguishable when half or less of the radiation dose was employed.
The trabecular bone microstructure is an important factor in the development of osteoporosis. It is well known that its deterioration is one effect when osteoporosis occurs. Previous research showed that the analysis of trabecular bone microstructure enables more precise diagnoses of osteoporosis compared to a sole measurement of the mineral density. Microstructure parameters are assessed on volumetric images of the bone acquired either with high-resolution magnetic resonance imaging, high-resolution peripheral quantitative computed tomography or high-resolution computed tomography (CT), with only CT being applicable to the spine, which is one of clinically most relevant fracture sites. However, due to the high radiation exposure for imaging the whole spine these measurements are not applicable in current clinical routine. In this work, twelve vertebrae from three different donors were scanned with standard and low radiation dose. Trabecular bone microstructure parameters were assessed for CT images reconstructed with statistical iterative reconstruction (SIR) and analytical filtered backprojection (FBP). The resulting structure parameters were correlated to the biomechanically determined fracture load of each vertebra. Microstructure parameters assessed for low-dose data reconstructed with SIR significantly correlated with fracture loads as well as parameters assessed for standard-dose data reconstructed with FBP. Ideal results were achieved with low to zero regularization strength yielding microstructure parameters not significantly different from those assessed for standard-dose FPB data. Moreover, in comparison to other approaches, superior noise-resolution trade-offs can be found with the proposed methods.
In CT, the magnitude of enhancement is proportional to the amount of contrast medium (CM) injected. However, high doses of iodinated CM pose health risks, ranging from mild side effects to serious complications such as contrast-induced nephropathy (CIN). This work presents a method that enables the reduction of CM dosage, without affecting the diagnostic image quality. The technique proposed takes advantage of the additional spectral information provided by photon-counting CT systems. In the first step, we apply a material decomposition technique on the projection data to discriminate iodine from other materials. Then, we estimated the noise of the decomposed image by calculating the Cramér-Rao lower bound of the parameter estimator. Next, we iteratively reconstruct the iodine-only image by using the decomposed image and the estimation of noise as an input into a maximum-likelihood iterative reconstruction algorithm. Finally, we combine the iodine-only image with the original image to enhance the contrast of low iodine concentrations. The resulting reconstructions show a notably improved contrast in the final images. Quantitatively, the combined image has a significantly improved CNR, while the measured concentrations are closer to the actual concentrations of the iodine. The preliminary results from our technique show the possibility of reducing the clinical dosage of iodine, without affecting the diagnostic image quality.
In recent years, dual-energy computed tomography (DECT) has been widely used in the clinical routine due to improved diagnostics capability from additional spectral information. One promising application for DECT is CT colonography (CTC) in combination with computer-aided diagnosis (CAD) for detection of lesions and polyps. While CAD has demonstrated in the past that it is able to detect small polyps, its performance is highly dependent on the quality of the input data. The presence of artifacts such as beam-hardening and noise in ultra-low-dose CTC may severely degrade detection performances of small polyps. In this work, we investigate and compare virtual monochromatic images, generated by image-based decomposition and projection-based decomposition, with respect to CAD performance. In the image-based method, reconstructed images are firstly decomposed into water and iodine before the virtual monochromatic images are calculated. On the contrary, in the projection-based method, the projection data are first decomposed before calculation of virtual monochromatic projection and reconstruction. Both material decomposition methods are evaluated with regards to the accuracy of iodine detection. Further, the performance of the virtual monochromatic images is qualitatively and quantitatively assessed. Preliminary results show that the projection-based method does not only have a more accurate detection of iodine, but also delivers virtual monochromatic images with reduced beam hardening artifacts in comparison with the image-based method. With regards to the CAD performance, the projection-based method yields an improved detection performance of polyps in comparison with that of the image-based method.
The recent advancements in the graphics card technology raised the performance of parallel computing and contributed to the introduction of iterative reconstruction methods for x-ray computed tomography in clinical CT scanners. Iterative maximum likelihood (ML) based reconstruction methods are known to reduce image noise and to improve the diagnostic quality of low-dose CT. However, iterative reconstruction of a region of interest (ROI), especially ML based, is challenging. But for some clinical procedures, like cardiac CT, only a ROI is needed for diagnostics. A high-resolution reconstruction of the full field of view (FOV) consumes unnecessary computation effort that results in a slower reconstruction than clinically acceptable. In this work, we present an extension and evaluation of an existing ROI processing algorithm. Especially improvements for the equalization between regions inside and outside of a ROI are proposed. The evaluation was done on data collected from a clinical CT scanner. The performance of the different algorithms is qualitatively and quantitatively assessed. Our solution to the ROI problem provides an increase in signal-to-noise ratio and leads to visually less noise in the final reconstruction. The reconstruction speed of our technique was observed to be comparable with other previous proposed techniques. The development of ROI processing algorithms in combination with iterative reconstruction will provide higher diagnostic quality in the near future.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.