Screening is an effective way to detect lung cancer early and can improve the survival rate significantly. The low-dose computed tomography (LdCT) is demanding for lung screening to ensure the exam radiation as low as reasonably possible. The statistical image reconstruction has shown great advantages in LdCT imaging, where many types of priors can be used as constrain for optimal images. The tissue-specific Markov random field (MRF) type texture prior (MRFt) was proposed in our previous work to address the clinical related texture information. For the chest scans, four tissue texture were extracted from regions of lung, bone, fat and muscle respectively. In this work, we focus on the region of interest, i.e. lung for the lung cancer screening. The quantitative texture analysis of normal and abnormal lung tissue was performed to address the following issues of the proposed MRFt model: (1) a more comprehensive understanding of the lung tissue texture (2) what MRF prior we should use for the abnormal lung tissue. Experiments results showed that normal lung tissue has texture similarity among different subjects. The robust similarity among humans laid the feasibility of building the lung tissue database for the LdCT imaging which has no previous FdCT scans. Different abnormal lung tissue varies significantly. There is no way to get the prior knowledge of lung nodules until the CT exam was performed.
Low-dose denoising is an effective method that utilizes the power of CT for screening while avoiding high radiation exposure. Several research work has reported the feasibility of deep learning based denoising, but none of them have explored the influence of different network designs on the denoising performance. In this work, we explored the impact of three commonly adapted network design concepts in denoising: (1) Network structure, (2) Residual learning, and (3) Training loss. We evaluated the network performance using the dataset containing 76 real patient scans from Mayo Clinic Low-dose CT dataset. Experimental results demonstrated that residual blocks and residual learning are recommended to be utilized in design, while pooling is not recommended. In addition, among the classical training losses, the mean absolute error (L1) loss outperforms the mean squared error (MSE) loss.
Dual energy CT (DECT) expands applications of CT imaging in its capability to acquire two datasets, one at high and the other at low energy, and produce decomposed material images of the scanned objects. Bayesian theory applied for statistical DECT reconstruction has shown great potential for giving the accurate decomposed material fraction images directly from projection measurements. It provides a natural framework to include various kinds of prior information for improved image reconstruction with its optimal selected hyper parameter by a trial-error style. To eliminate the cumbersome style, in this work, we propose a parameter-free Bayesian reconstruction algorithm for DECT (PfBR-DE). In our approach, the physical meaning of the hyper parameter can be interpreted as the ratio of the data variance α and the prior tolerance σ by formulating the probability distribution functions of the data fidelity and prior expectation. With an alternative optimization scheme, the data variance, prior tolerance and decomposed material images can be jointly estimated. Experimental results with the abdomen phantom demonstrate the PfBR-DE method can obtain the comparable quantity decomposed material images with the conventional methods without freely adjustable hyper parameter.
Machine learning, especially convolutional neural network (CNN) approach has been successfully applied in noise suppression in natural image. However, shifting from natural image to medical image filed remains challenging due to specific difficulties such as training samples limitation, clinically meaningful image quality requirement and so on. To address this challenge, one possible solution is to incorporate our human prior knowledge into the machine learning model to better benefit its power. Therefore, in this work, we propose one prior knowledge driven machine learning based approach for positron emission tomography (PET) sinogram data denoising. Two main properties of PET sinogram data were considered in CNN architecture design, which are the Poisson statistics of the data and different correlation strength in the detector and view directions. Specially, for the statistical property, the sparse non-local method was used. For the correlation property, separate convolution was applied in two directions respectively. Experimental results showed the proposed model outperform the CNN model without prior knowledge. Results also demonstrate our insight of applying human knowledge strength the power of machine learning in medical imaging field.
Purpose: Bayesian theory provides a sound framework for ultralow-dose computed tomography (ULdCT) image reconstruction with two terms for modeling the data statistical property and incorporating a priori knowledge for the image that is to be reconstructed. We investigate the feasibility of using a machine learning (ML) strategy, particularly the convolutional neural network (CNN), to construct a tissue-specific texture prior from previous full-dose computed tomography.
Approach: Our study constructs four tissue-specific texture priors, corresponding with lung, bone, fat, and muscle, and integrates the prior with the prelog shift Poisson (SP) data property for Bayesian reconstruction of ULdCT images. The Bayesian reconstruction was implemented by an algorithm called SP-CNN-T and compared with our previous Markov random field (MRF)-based tissue-specific texture prior algorithm called SP-MRF-T.
Results: In addition to conventional quantitative measures, mean squared error and peak signal-to-noise ratio, structure similarity index, feature similarity, and texture Haralick features were used to measure the performance difference between SP-CNN-T and SP-MRF-T algorithms in terms of the structure and tissue texture preservation, demonstrating the feasibility and the potential of the investigated ML approach.
Conclusions: Both training performance and image reconstruction results showed the feasibility of constructing CNN texture prior model and the potential of improving the structure preservation of the nodule comparing to our previous regional tissue-specific MRF texture prior model.
Bayesian theory lies down a sound framework for ultralow-dose computed tomography (ULdCT) image reconstruction with two terms for modeling the data statistical property and incorporating a priori knowledge for the tobe- reconstructed image. This study investigates the feasibility of using machine learning strategy, particularly the convolutional neural network (CNN), to construct a tissue-specific texture prior from previous full-dose CT (FdCT) and integrates the prior with the pre-log shift Poisson (SP) data property for Bayesian reconstruction of ULdCT images. The Bayesian reconstruction was implemented by an algorithm, called SP-CNN-T, and compared with our previous Markov random field (MRF) based tissue-specific texture prior algorithm, called SP-MRF-T. Both training performance and image reconstruction results showed the feasibility of constructing CNN texture prior model and the potential of improving the structure preservation of the nodule comparing to our previous regional tissue-specific MRF texture prior model. Quantitative structure similarity index (SSIM) and texture Haralick features (HF) were used to measure the performance difference between SP-CNN-T and SP-MRF-T algorithms, demonstrating the feasibility and the potential of the investigated machine learning approach.
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.