Dr Peter Summons

Pneumoconiosis is a group of occupational lung diseases induced by mineral dust inhalation and subsequent lung tissue reactions. It can eventually cause irreparable lung damage, as well as gradual and permanent physical impairments. It has affected millions of workers in hazardous industries throughout the world, and it is a leading cause of occupational death. It is difficult to diagnose early pneumoconiosis because of the low sensitivity of chest radiographs, the wide variation in interpretation between and among readers, and the scarcity of B-readers, which all add to the difficulty in diagnosing these occupational illnesses. In recent years, deep machine learning algorithms have been extremely successful at classifying and localising abnormality of medical images. In this study, we proposed an ensemble learning approach to improve pneumoconiosis detection in chest X-rays (CXRs) using nine machine learning classifiers and multi-dimensional deep features extracted using CheXNet-121 architecture. There were eight evaluation metrics utilised for each high-level feature set of the associated cross-validation datasets in order to compare the ensemble performance and state-of-the-art techniques from the literature that used the same cross-validation datasets. It is observed that integrated ensemble learning exhibits promising results (92.68% accuracy, 85.66% Matthews correlation coefficient (MCC), and 0.9302 area under the precision¿recall (PR) curve), compared to individual CheXNet-121 and other state-of-the-art techniques. Finally, Grad-CAM was used to visualise the learned behaviour of individual dense blocks within CheXNet-121 and their ensembles into three-color channels of CXRs. We compared the Grad-CAM-indicated ROI to the ground-truth ROI using the intersection of the union (IOU) and average-precision (AP) values for each classifier and their ensemble. Through the visualisation of the Grad-CAM within the blue channel, the average IOU passed more than 90% of the pneumoconiosis detection in chest radiographs.

Early detection of pneumoconiosis in X-Rays has been a challenging task that leads to high inter- and intra-reader variability. Motivated by the success of deep learning in general and medical image classification, this paper proposes an approach to automatically detect pneumoconiosis using a deep feature based binary classifier. The features are extracted from X-rays using deep transfer learning, comprising both low and high-level feature sets. For this, a CNN model pre-trained with a transfer learning from a CheXNet model was initially used to extract deep features from the X-Ray images, then the deep features were mapped to higher-dimensional feature spaces for classification using Support Vector Machine (SVM) and CNN based feature aggregation methods. In order to cross validate the proposed method, the training and testing images were randomly split into three folds before each experiment. Nine evaluation metrics were employed to compare the performance of the proposed method and state-of-the-art methods from the literature that used the same datasets. The experimental results show that the proposed framework outperformed others, achieving an accuracy of 92.68% in the automated detection of pneumoconiosis.

Objective: To explore the experiences of older people receiving home care package (HCP) support following the introduction of consumer-directed care (CDC) by the Australian government on 1 July 2015. Methods: Thirty-one older people with existing HCP support from two service providers in regional New South Wales, Australia, participated in a face-to-face interview and/or a qualitative survey. Results: Analysis revealed the theme of Choices: Preferences, constraints, balancing and choosing. Participants described choosing to live at home with HCP support; however, they were constrained by poor communication and information about service changes and options, personal budgets and access to future care. HCP services remained largely unchanged during transition to CDC. Conclusion: Many aspects of the initial implementation of CDC were challenging for older people. Clear, relevant and timely communication and information about CDC and its consequences for consumers appear to be needed to enhance CDC.

This paper examines some of the problems confronted in evolving a population of three dimensional computer generated shapes according to a set of desired constraints. The eventual aim is to automatically search a design or problem space for a viable solution or range of solutions to 3-D shapes. Such shapes are often used in generating computer images. Such images are needed in engineering and science and are useful in visualizing output from computer models. There may be applications within the domains of aesthetic design. Previously, most of the successful attempts to evolve three-dimensional computer generated form have used systems of genetic encoding with a high degree of complexity in the link between the Genotype (the genetic endowment of the individual solution) and the Phenotype (the constellation of all available individual solutions), and have mapped the complete volume of the shape. An approach described is to encode the shape surface. This has the potential to considerably simplify the mapping of the Phenotype to Genotype. The new approach is inspired by the principle behind the operation of a ¿shape grabber¿. In this a mathematical array consisting of a ¿point cloud¿ of Cartesian coordinates is created corresponding to those mapped on the surface of a real object. The former can then be used by a CAD program to plot a polygonal mesh and produce a 3-D representation of the original object. The new approach uses a direction vector, the magnitude of which becomes a floating point¿ gene¿ within the Genetic algorithm. The endpoint of the latter defines a point within the point cloud. An enhancement of this model could use an evolved Lindenmayer System to define a point in the cloud. This study compares the Volumetric and Surface Models of shape encoding and surface evolution and points to new exciting possibilities.