Tomography, X-Ray Computed

Medical professionals use CT images to get information about the size, shape, and location of any lung nodules. This information will help radiologist and oncologist to identify the type of cancer and create a treatment plan. However, most of the time, the diagnosis regarding the types of lung cancer is error-prone and time-consuming. One way to address these problems is by using convolutional neural networks. In this Thesis, we developed a convolutional neural network that can detect abnormalities in lung CT scans and further categorize the abnormalities to benign, malignant adenocarcinoma and malignant squamous cell carcinoma. Our network is based on DenseNet, which utilizes dense connections between layers (dense blocks), so that all layers are connected. Because of all layers being connected, different layers can reuse features from previous layers which speeds up the process and make this network computationally efficient. To retrain this network we used CT images for 314 patients (over 1500 CT images) consistent of 42 Lung Adenocarcinoma and 78 Squamous Cell Carcinoma, 118 Non cancer and 76 benign were acquired from the National Lung Screening Trial (NLST). These images were divided to two categories of Training and Validation with 70% being training dataset and 30% as validation dataset. We trained our network on Training dataset and then checked the accuracy of our model using the validation dataset. Our model was able to categorize lung cancer with an accuracy of 88%. Afterwards we calculated the the confusion matrix, Precision (Sensitivity), Recall (Positivity) and F1 score of our model for each category. Our model is able to classify Normal CT images with Normal Accuracy of 89% Precision of 94% and F1 score of 93%. For benign nodules Accuracy was 92% precision of 97% and F1 score 86%, while for Adenocarcinoma and squamous cell cancer the Accuracy was 98% and 93%, Precision 85% and 84% and F1 score 92% and 86.9%. The relatively high accuracy of our model shows that convolutional neural networks can be a valuable tool for the classification of lung cancer, especially in a small city or underdeveloped rural hospital settings and can play a role in achieving healthcare equality.

The accuracy of proton dose computation in the treatment planning system relies on the conversion from the Hounsfield units (HU) of each voxel in the patient CT scan to the proton stopping power ratio (SPR). The aim of this study is to investigate the potential improvement in determining proton SPR using single energy computed tomography (SECT) to reduce the uncertainty in predicting the proton range in patients. Factors which may cause CT number variations in the calibration curve have been examined. The HU-SPR calibration curve was determined based on HU of human body tissues using the stoichiometric method. The uncertainties in SPR were divided into two major categories: The inherent uncertainty, and the CT number uncertainty. The root mean square errors of the inherent uncertainties were estimated 0.02%, 0.61% and 0.26% for lung tissues, soft tissues (excluding Thyroid), and bone tissues, respectively. The total uncertainties due to the inherent uncertainty and CT imaging errors were estimated 1.50%. The average calibration curve of two sized phantoms (head and body) were used in the treatment planning system to mitigate beam hardening effect through the attenuating media. A higher accuracy of the SPR prediction using the stoichiometric method is suggested through comparison with the predicted SPRs that derived from the direct calibration approach.

The Computer Tomography (CT) scanned images are very important for the Treatment Planning System (TPS) to provide the electron density of the different types of tissues that the radiation penetrates in the path to the tumor to be treated. This electron density is converted to an attenuation coefficient, which varies with tissue for each structure and even varies by the tissue volume. The purpose of this research is to evaluate the CT numbers, and convert them into relative electron densities. Twenty-five patients’ data and CT numbers were evaluated in the CT scanner and in Eclipse and were converted into relative electron density and compared with each other. The differences between the relative electron density in the Eclipse was found to be from 0 up to 6% between tissue equivalent materials, the final result for all equivalent tissue materials was about 2%. For the patients’ data, the percentage difference of CT number versus electron density was found to be high for high relative electron density organs, namely the final average result for the spine was 8%, less for pelvis, and less for rib while for the other organs it was even less. The very lowest was 0.3% compared with 1% which is acceptable for clinical standards.

Reducing the amount of radiation in X-ray computed tomography has been an
active area of research in the recent years. The reduction of radiation has the downside of
degrading the quality of the CT scans by increasing the ratio of the noise. Therefore, some
techniques must be utilized to enhance the quality of images. In this research, we approach
the denoising problem using two class of algorithms and we reduce the noise in CT scans
that have been acquired with 75% less dose to the patient compared to the normal dose
scans.
Initially, we implemented wavelet denoising to successfully reduce the noise in
low-dose X-ray computed tomography (CT) images. The denoising was improved by
finding the optimal threshold value instead of a non-optimal selected value. The mean
structural similarity (MSSIM) index was used as the objective function for the
optimization. The denoising performance of combinations of wavelet families, wavelet
orders, decomposition levels, and thresholding methods were investigated. Results of this study have revealed the best combinations of wavelet orders and decomposition levels for
low dose CT denoising. In addition, a new shrinkage function is proposed that provides
better denoising results compared to the traditional ones without requiring a selected
parameter.
Alternatively, convolutional neural networks were employed using different
architectures to resolve the same denoising problem. This new approach improved
denoising even more in comparison to the wavelet denoising.