Computerized detection of lung nodules with an enhanced false positive reduction scheme

This thesis is based on the original investigations of the author in the field of computerized lung nodule detection in computed tomography (CT) images. The methodologies discussed in this thesis include two main topics: region of interest detection and enhanced false positive (FP) reduction. The system, which is developed to be a supplementary diagnostic tool for radiologists, first spots all the regions suspected to be nodules in the lung. Then it pins down the candidates with the highest possibility of being nodules through a series of rule based filtering stages. Finally, an enhanced false positive reduction system, which is in fact designed as a hybrid scheme based on learning algorithms, reduces the false positive detections further. The overall system performs with 72% sensitivity and 2.42 FP/slice, which competes with state-of-the-art methods. The system was tested on a database consisting of 24 pediatric clinical subjects with 1190 images and 154 metastatic nodules.

Computerized detection of lung nodules with an enhanced false positive reduction scheme

This thesis is based on the original investigations of the author in the field of computerized lung nodule detection in computed tomography (CT) images. The methodologies discussed in this thesis include two main topics: region of interest detection and enhanced false positive (FP) reduction. The system, which is developed to be a supplementary diagnostic tool for radiologists, first spots all the regions suspected to be nodules in the lung. Then it pins down the candidates with the highest possibility of being nodules through a series of rule based filtering stages. Finally, an enhanced false positive reduction system, which is in fact designed as a hybrid scheme based on learning algorithms, reduces the false positive detections further. The overall system performs with 72% sensitivity and 2.42 FP/slice, which competes with state-of-the-art methods. The system was tested on a database consisting of 24 pediatric clinical subjects with 1190 images and 154 metastatic nodules.

Eye Tracking Interaction on Unmodified Mobile VR Headsets Using the Selfie Camera

Input methods for interaction in smartphone-based virtual and mixed reality (VR/MR) are currently based on uncomfortable head tracking controlling a pointer on the screen. User fixations are a fast and natural input method for VR/MR interaction. Previously, eye tracking in mobile VR suffered from low accuracy, long processing time, and the need for hardware add-ons such as anti-reflective lens coating and infrared emitters. We present an innovative mobile VR eye tracking methodology utilizing only the eye images from the front-facing (selfie) camera through the headset’s lens, without any modifications. Our system first enhances the low-contrast, poorly lit eye images by applying a pipeline of customised low-level image enhancements suppressing obtrusive lens reflections. We then propose an iris region-of-interest detection algorithm that is run only once. This increases the iris tracking speed by reducing the iris search space in mobile devices. We iteratively fit a customised geometric model to the iris to refine its coordinates. We display a thin bezel of light at the top edge of the screen for constant illumination. A confidence metric calculates the probability of successful iris detection. Calibration and linear gaze mapping between the estimated iris centroid and physical pixels on the screen results in low latency, real-time iris tracking. A formal study confirmed that our system’s accuracy is similar to eye trackers in commercial VR headsets in the central part of the headset’s field-of-view. In a VR game, gaze-driven user completion time was as fast as with head-tracked interaction, without the need for consecutive head motions. In a VR panorama viewer, users could successfully switch between panoramas using gaze.

Detection of Choroidalneovascularization (Cnv) in Retina Oct Images Using Vgg16 and Densenet Cnn

In this study, we intend to diagnose Choroidal Neovascularization in retinal Optical Coherence Tomography (OCT) images using Deep Learning Architectures. Optical Coherence Tomography (OCT) images can be used to differentiate between a healthy eye and an eye with CNV disease. DenseNet and Vgg16 Architectures of Deep Learning were used in the study and the hyper parameters of both of the architectures were changed to diagnose the disease properly. After the detection of the disease, the diseased OCT images are segmented from the background for the Region of Interest detection using Python OpenCV library that is used for the processing of images. The results of implementation of the Architectures showed that Vgg16 showed better results in detecting the images rather than Dense Net Architecture with an accuracy percentage of 97.53% approximately a percent greater than Dense Net.