Automated aerial inspection guidance with improved turn planning

Aerial inspection of pipelines, powerlines, and other large linear infrastructure networks has emerged in a number of civilian remote sensing applications. Challenges relate to automating inspection flight for under-actuated aircraft with LiDAR/camera sensor constraints whilst subjected to wind disturbances. This paper presents new improved turn planning strategies with guidance suitable for automation of linear infrastructure inspection able to reduce inspection flight distance by including wind information. Simulation and experimental flight tests confirmed the flight distance saving, and the proposed guidance strategies exhibited good tracking performance in a range of wind conditions.

Validating a novel, low cost, automated malnutrition screening system as a predictor of nutritional risk in the Oncology Day Care Unit

Background Cancer-related malnutrition is associated with increased morbidity, poorer tolerance of treatment, decreased quality of life, increased hospital admissions, and increased health care costs (Isenring et al., 2013). This study’s aim was to determine whether a novel, automated screening system was a useful tool for nutrition screening when compared against a full nutrition assessment using the Patient-Generated Subjective Global Assessment (PG-SGA) tool. Methods A single site, observational, cross-sectional study was conducted in an outpatient oncology day care unit within a Queensland tertiary facility, with three hundred outpatients (51.7% male, mean age 58.6 ± 13.3 years). Eligibility criteria: ≥18 years, receiving anticancer treatment, able to provide written consent. Patients completed the Malnutrition Screening Tool (MST). Nutritional status was assessed using the PG-SGA. Data for the automated screening system was extracted from the pharmacy software program Charm. This included body mass index (BMI) and weight records dating back up to six months. Results The prevalence of malnutrition was 17%. Any weight loss over three to six weeks prior to the most recent weight record as identified by the automated screening system relative to malnutrition resulted in 56.52% sensitivity, 35.43% specificity, 13.68% positive predictive value, 81.82% negative predictive value. MST score 2 or greater was a stronger predictor of nutritional risk relative to PG-SGA classified malnutrition (70.59% sensitivity, 69.48% specificity, 32.14% positive predictive value, 92.02% negative predictive value). Conclusions Both the automated screening system and the MST fell short of the accepted professional standard for sensitivity (80%) or specificity (60%) when compared to the PG-SGA. However, although the MST remains a better predictor of malnutrition in this setting, uptake of this tool in the Oncology Day Care Unit remains challenging.

A data mining approach to improve the automated quality of data

This thesis describes the development of a robust and novel prototype to address the data quality problems that relate to the dimension of outlier data. It thoroughly investigates the associated problems with regards to detecting, assessing and determining the severity of the problem of outlier data; and proposes granule-mining based alternative techniques to significantly improve the effectiveness of mining and assessing outlier data.

Automated surface sampling of lipids from worn contact lenses coupled with tandem mass spectrometry

The deposition of biological material (biofouling) onto polymeric contact lenses is thought to be a major contributor to lens discomfort and hence discontinuation of wear. We describe a method to characterize lipid deposits directly from worn contact lenses utilizing liquid extraction surface analysis coupled to tandem mass spectrometry (LESA-MS/MS). This technique effected facile and reproducible extraction of lipids from the contact lens surfaces and identified lipid molecular species representing all major classes present in human tear film. Our data show that LESA-MS/MS is a rapid and comprehensive technique for the characterization of lipid-related biofouling on polymer surfaces.

A novel, automated nutrition screening system as a predictor of nutritional risk in an oncology day treatment unit (ODTU)

Purpose Paper-based nutrition screening tools can be challenging to implement in the ambulatory oncology setting. The aim of this study was to determine the validity of the Malnutrition Screening Tool (MST) and a novel, automated nutrition screening system compared to a ‘gold standard’ full nutrition assessment using the Patient-Generated Subjective Global Assessment (PG-SGA). Methods An observational, cross-sectional study was conducted in an outpatient oncology day treatment unit (ODTU) within an Australian tertiary health service. Eligibility criteria were as follows: ≥18 years, receiving outpatient anticancer treatment and English literate. Patients self-administered the MST. A dietitian assessed nutritional status using the PGSGA, blinded to the MST score. Automated screening system data were extracted from an electronic oncology prescribing system. This system used weight loss over 3 to 6 weeks prior to the most recent weight record or age-categorised body mass index (BMI) to identify nutritional risk. Sensitivity and specificity against PG-SGA (malnutrition) were calculated using contingency tables and receiver operating curves. Results There were a total of 300 oncology outpatients (51.7 % male, 58.6±13.3 years). The area under the curve (AUC) for weight loss alone was 0.69 with a cut-off value of ≥1 % weight loss yielding 63 % sensitivity and 76.7 % specificity. MST (score ≥2) resulted in 70.6 % sensitivity and 69.5 % specificity, AUC 0.77. Conclusions Both the MST and the automated method fell short of the accepted professional standard for sensitivity (~≥80 %) derived from the PG-SGA. Further investigation into other automated nutrition screening options and the most appropriate parameters available electronically is warranted to support targeted service provision.

The impact of OCR accuracy on automated cancer classification of pathology reports

Objective To evaluate the effects of Optical Character Recognition (OCR) on the automatic cancer classification of pathology reports. Method Scanned images of pathology reports were converted to electronic free-text using a commercial OCR system. A state-of-the-art cancer classification system, the Medical Text Extraction (MEDTEX) system, was used to automatically classify the OCR reports. Classifications produced by MEDTEX on the OCR versions of the reports were compared with the classification from a human amended version of the OCR reports. Results The employed OCR system was found to recognise scanned pathology reports with up to 99.12% character accuracy and up to 98.95% word accuracy. Errors in the OCR processing were found to minimally impact on the automatic classification of scanned pathology reports into notifiable groups. However, the impact of OCR errors is not negligible when considering the extraction of cancer notification items, such as primary site, histological type, etc. Conclusions The automatic cancer classification system used in this work, MEDTEX, has proven to be robust to errors produced by the acquisition of freetext pathology reports from scanned images through OCR software. However, issues emerge when considering the extraction of cancer notification items.

Clinician-driven automated classification of limb fractures from free-text radiology reports

The aim of this research is to report initial experimental results and evaluation of a clinician-driven automated method that can address the issue of misdiagnosis from unstructured radiology reports. Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to disperse information resources and vast amounts of manual processing of unstructured information, a point-of-care accurate diagnosis is often difficult. A rule-based method that considers the occurrence of clinician specified keywords related to radiological findings was developed to identify limb abnormalities, such as fractures. A dataset containing 99 narrative reports of radiological findings was sourced from a tertiary hospital. The rule-based method achieved an F-measure of 0.80 and an accuracy of 0.80. While our method achieves promising performance, a number of avenues for improvement were identified using advanced natural language processing (NLP) techniques.

Strain variation amongst clinical and potable water isolates of M.kansasii using automated repetitive unit PCR

Mycobacterium kansasii is a pulmonary pathogen that has been grown readily from municipal water, but rarely isolated from natural waters. A definitive link between water exposure and disease has not been demonstrated and the environmental niche for this organism is poorly understood. Strain typing of clinical isolates has revealed seven subtypes with Type 1 being highly clonal and responsible for most infections worldwide. The prevalence of other subtypes varies geographically. In this study 49 water isolates are compared with 72 patient isolates from the same geographical area (Brisbane, Australia), using automated repetitive unit PCR (Diversilab) and ITS RFLP. The clonality of the dominant clinical strain type is again demonstrated but with rep-PCR, strain variation within this group is evident comparable with other reported methods. There is significant heterogeneity of water isolates and very few are similar or related to the clinical isolates. This suggests that if water or aerosol transmission is the mode of infection, then point source contamination likely occurs from an alternative environmental source.

Automated classification of limb fractures from free-text radiology reports using a clinician-informed gazetteer methodology

Background Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to dispersed information resources and a vast amount of manual processing of unstructured information, accurate point-of-care diagnosis is often difficult. Aims The aim of this research is to report initial experimental evaluation of a clinician-informed automated method for the issue of initial misdiagnoses associated with delayed receipt of unstructured radiology reports. Method A method was developed that resembles clinical reasoning for identifying limb abnormalities. The method consists of a gazetteer of keywords related to radiological findings; the method classifies an X-ray report as abnormal if it contains evidence contained in the gazetteer. A set of 99 narrative reports of radiological findings was sourced from a tertiary hospital. Reports were manually assessed by two clinicians and discrepancies were validated by a third expert ED clinician; the final manual classification generated by the expert ED clinician was used as ground truth to empirically evaluate the approach. Results The automated method that attempts to individuate limb abnormalities by searching for keywords expressed by clinicians achieved an F-measure of 0.80 and an accuracy of 0.80. Conclusion While the automated clinician-driven method achieved promising performances, a number of avenues for improvement were identified using advanced natural language processing (NLP) and machine learning techniques.

Controlled automated discovery of collections of business process models

Automated process discovery techniques aim at extracting process models from information system logs. Existing techniques in this space are effective when applied to relatively small or regular logs, but generate spaghetti-like and sometimes inaccurate models when confronted to logs with high variability. In previous work, trace clustering has been applied in an attempt to reduce the size and complexity of automatically discovered process models. The idea is to split the log into clusters and to discover one model per cluster. This leads to a collection of process models – each one representing a variant of the business process – as opposed to an all-encompassing model. Still, models produced in this way may exhibit unacceptably high complexity and low fitness. In this setting, this paper presents a two-way divide-and-conquer process discovery technique, wherein the discovered process models are split on the one hand by variants and on the other hand hierarchically using subprocess extraction. Splitting is performed in a controlled manner in order to achieve user-defined complexity or fitness thresholds. Experiments on real-life logs show that the technique produces collections of models substantially smaller than those extracted by applying existing trace clustering techniques, while allowing the user to control the fitness of the resulting models.

Automated species recognition in environmental recordings

Faunal vocalisations are vital indicators for environmental change and faunal vocalisation analysis can provide information for answering ecological questions. Therefore, automated species recognition in environmental recordings has become a critical research area. This thesis presents an automated species recognition approach named Timed and Probabilistic Automata. A small lexicon for describing animal calls is defined, six algorithms for acoustic component detection are developed, and a series of species recognisers are built and evaluated.The presented automated species recognition approach yields significant improvement on the analysis performance over a real world dataset, and may be transferred to commercial software in the future.

Decision strategies for automated visual collision avoidance

This paper provides a preliminary analysis of an autonomous uncooperative collision avoidance strategy for unmanned aircraft using image-based visual control. Assuming target detection, the approach consists of three parts. First, a novel decision strategy is used to determine appropriate reference image features to track for safe avoidance. This is achieved by considering the current rules of the air (regulations), the properties of spiral motion and the expected visual tracking errors. Second, a spherical visual predictive control (VPC) scheme is used to guide the aircraft along a safe spiral-like trajectory about the object. Lastly, a stopping decision based on thresholding a cost function is used to determine when to stop the avoidance behaviour. The approach does not require estimation of range or time to collision, and instead relies on tuning two mutually exclusive decision thresholds to ensure satisfactory performance.

Development and evaluation of the Ontrack Diabetes Program : an automated, web-based type 2 diabetes self-management and dysphoria intervention

This research was conducted in the area of Clinical and Health Psychology. The study involved the development and evaluation of a novel, web-based program aimed to improve Type 2 diabetes self-management and mood. The program was developed as an original technological intervention aimed to improve access to support for rural and remote communities, and is currently being trialled across Australia with a larger sample size. The researcher aims to continue research into the field of clinical psychology, and in particular is interested in working on further interventions to support those with comorbid physical and mental health conditions.

Automated diagnosis of Age-related Macular Degeneration using greyscale features from digital fundus images

Age-related Macular Degeneration (AMD) is one of the major causes of vision loss and blindness in ageing population. Currently, there is no cure for AMD, however early detection and subsequent treatment may prevent the severe vision loss or slow the progression of the disease. AMD can be classified into two types: dry and wet AMDs. The people with macular degeneration are mostly affected by dry AMD. Early symptoms of AMD are formation of drusen and yellow pigmentation. These lesions are identified by manual inspection of fundus images by the ophthalmologists. It is a time consuming, tiresome process, and hence an automated diagnosis of AMD screening tool can aid clinicians in their diagnosis significantly. This study proposes an automated dry AMD detection system using various entropies (Shannon, Kapur, Renyi and Yager), Higher Order Spectra (HOS) bispectra features, Fractional Dimension (FD), and Gabor wavelet features extracted from greyscale fundus images. The features are ranked using t-test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance (CBBD), Receiver Operating Characteristics (ROC) curve-based and Wilcoxon ranking methods in order to select optimum features and classified into normal and AMD classes using Naive Bayes (NB), k-Nearest Neighbour (k-NN), Probabilistic Neural Network (PNN), Decision Tree (DT) and Support Vector Machine (SVM) classifiers. The performance of the proposed system is evaluated using private (Kasturba Medical Hospital, Manipal, India), Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) datasets. The proposed system yielded the highest average classification accuracies of 90.19%, 95.07% and 95% with 42, 54 and 38 optimal ranked features using SVM classifier for private, ARIA and STARE datasets respectively. This automated AMD detection system can be used for mass fundus image screening and aid clinicians by making better use of their expertise on selected images that require further examination.