Search results

(1 - 2 of 2)
Machine learning applications to video surveillance camera placement and medical imaging quality assessment
Title
Machine learning applications to video surveillance camera placement and medical imaging quality assessment
Creator
Lorente Gomez, Iris
Date
2022
Description
In this work, we used machine learning techniques and data analysis to approach two applications. The first one, in collaboration with the...
Show moreIn this work, we used machine learning techniques and data analysis to approach two applications. The first one, in collaboration with the Chicago Police Department (CPD), involves analyzing and quantifying the effect that the installation of cameras had on crime, and developing a predictive model with the goal of optimizing video surveillance camera location in the streets. While video surveillance has become increasingly prevalent in policing, its intended effect on crime prevention has not been comprehensively studied in major cities in the US. In this study, we retrospectively analyzed the crime activities in the vicinity of 2,021 surveillance cameras installed between 2005 and 2016 in the city of Chicago. Using Difference-in-Differences (DiD) analysis, we examined the daily crime counts that occurred within the fields-of-view of these cameras over a 12-month period, both before and after the cameras were installed. We also investigated their potential effect on crime displacement and diffusion by examining the crime activities in a buffer zone (up to 900 ft) extended from the cameras. The results show that, collectively, there was an 18.6% reduction in crime counts within the direct viewsheds of all of the study cameras (excluding District 01 where the Loop -Chicago's business center- is located). In addition, we adapted the methodology to quantify the effect of individual cameras. The quantified effect on crime is the prediction target of our 2-stage machine learning algorithm that aims to estimate the effect that installing a videocamera in a given location will have on crime. In the first stage, we trained a classifier to predict if installing a videocamera in a given location will result in a statistically significant decrease in crime. If so, the data goes through a regression model trained to estimate the quantified effect on crime that the camera installation will have. Finally, we propose two strategies, using our 2-stage predictive model, to find the optimal locations for camera installations given a budget. Our proposed strategies result in a larger decrease in crime than a baseline strategy based on choosing the locations with higher crime density.The second application that forms this thesis belongs to the field of model observers for medical imaging quality assessment. With the advance of medical imaging devices and technology, there is a need to evaluate and validate new image reconstruction algorithms. Image quality is traditionally evaluated by using numerical figures of merit that indicate similarity between the reconstruction and the original. In medical imaging, a good reconstruction strategy should be one that helps the radiologist perform a correct diagnosis. For this reason, medical imaging reconstruction strategies should be evaluated on a task-based approach by measuring human diagnosis accuracy. Model observers (MO) are algorithms capable of acting as human surrogates to evaluate reconstruction strategies, reducing significantly the time and cost of organizing sessions with expert radiologists. In this work, we develop a methodology to estimate a deep learning based model observer for a defect localization task using a synthetic dataset that simulates images with statistical properties similar to trans-axial sections of X-ray computed tomography (CT). In addition, we explore how the models access diagnostic information from the images using psychophysical methods that have been previously employed to analyze how the humans extract the information. Our models are independently trained for five different humans and are able to generalize to images with noise statistic backgrounds that were not seen during the model training stage. In addition, our results indicate that the diagnostic information extracted by the models matches the one extracted by the humans.
Show less
DEEP LEARNING IMAGE-DENOISING FOR IMPROVING DIAGNOSTIC ACCURACY IN CARDIAC SPECT
Title
DEEP LEARNING IMAGE-DENOISING FOR IMPROVING DIAGNOSTIC ACCURACY IN CARDIAC SPECT
Creator
Liu, Junchi
Date
2022
Description
Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is a noninvasive imaging modality widely utilized...
Show moreMyocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is a noninvasive imaging modality widely utilized for diagnosis of coronary artery diseases (CAD) in nuclear medicine. Because of the concern of potential radiation risks, the imaging dose administered to patients is limited in SPECT-MPI. Due to the low count statistics in acquired data, SPECT images can suffer from high levels of noise. In this study, we investigate the potential benefit of applying deep learning (DL) techniques for denoising in SPECT-MPI studies. Owing to the lack of ground truth in clinical studies, we adopt a noise-to-noise (N2N) training approach for denoising in full-dose studies. Afterwards, we investigate the benefit of applying N2N DL on reduced-dose studies to improve the detection accuracy of perfusion defects. To address the great variability in noise level among different subjects, we propose a scheme to account for the inter-subject variabilities in training a DL denoising network to improve its generalizability. In addition, we propose a dose-blind training approach for denoising at multiple reduced-dose levels. Moreover, we investigate several training schemes to address the issue that defect and non-defect image regions are highly unbalanced in a data set, where the overwhelming majority by non-defect regions tends to have a more pronounced contribution to the conventional loss function. We investigate whether these training schemes can effectively improve preservation of perfusion defects and yield better defect detection accuracy. In the experiments we demonstrated the proposed approaches with a set of 895 clinical acquisitions. The results show promising performance in denoising and improving the detectability of perfusion-defects with the proposed approaches.
Show less