In this work, an enhanced ResNet deep learning network, depth-ResNet, has been developed to classify the five types of Tuberculosis (TB) lung CT images. Depth-ResNet takes 3D CT images as a whole and processes the volumatic blocks along depth directions. It builds on the ResNet-50 model to obtain 2D features on each frame and injects depth information at each process block. As a result, the averaged accuracy for classification is 71.60% for depth-ResNet and 68.59% for ResNet. The datasets are collected from the ImageCLEF 2018 competition with 1008 training data in total, where the top reported accuracy was 42.27%.

A novel application of the Hough transform (HT) neighborhood approach to collinear segment detection was proposed in [1]. It, however, suffered from one major weakness in that it could not provide an effective solution to the case of segment intersection. This paper analyzes a vital prerequisite step, disturbance elimination in the Hough space, and shows why, this method alone, is incapable of distinguishing the true segment endpoints. To address the problem, a unique HT butterfly separation method is proposed in this correspondence, as an essential complement to the above publication.

A new approach for the detection of head motions during PET scanning is presented. The proposed system includes 4 modules, which are: input module, face segmentation, facial landmark detection, and head movement estimation. The developed system is tested on pictures monitoring a subject's head while simulating PET scanning (n=12) and face images of subjects with different skin colours (n=31). Experimental results show that the centres of chosen facial landmarks (eye corners and middle point of nose basement) can be detected with high precision (1plusmn0.64 pixels). Processing of 2D images with known moving parameters demonstrates that the parameter movement in terms of rotation and translation along X, Y, and Z directions can be obtained very accurately via the developed methods.