Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Biosecurity (1)
- Computational biology and bioinformatics (1)
- Diseases (1)
- Image processing (1)
- Infectious diseases (1)
- banana pathogen (1)
- invasive alien species (1)
- yellow Sigatoka (1)
Institute
Coronavirus disease 2019 (COVID-19) is a global pandemic posing significant health risks. The diagnostic test sensitivity of COVID-19 is limited due to irregularities in specimen handling. We propose a deep learning framework that identifies COVID-19 from medical images as an auxiliary testing method to improve diagnostic sensitivity. We use pseudo-coloring methods and a platform for annotating X-ray and computed tomography images to train the convolutional neural network, which achieves a performance similar to that of experts and provides high scores for multiple statistical indices (F1 scores > 96.72% (0.9307, 0.9890) and specificity >99.33% (0.9792, 1.0000)). Heatmaps are used to visualize the salient features extracted by the neural network. The neural network-based regression provides strong correlations between the lesion areas in the images and five clinical indicators, resulting in high accuracy of the classification framework. The proposed method represents a potential computer-aided diagnosis method for COVID-19 in clinical practice.
The banana leaf spotting disease yellow Sigatoka is established and actively controlled in Australia through intensive chemical treatments and diseased leaf removal. In the State of Queensland, the State government imposes standards for de-leafing to minimise the risk of the disease spreading in 6 banana pest quarantine areas. Of these, the Northern Banana Pest Quarantine Area is the most significant in terms of banana production. Previous regulations imposed obligations on owners of banana plants within this area to remove leaves from plants with visible spotting on more than 15 per cent of any leaf during the wet season. Recently, this leaf disease threshold has been lowered to 5 per cent. In this paper we examine the likely impact this more-costly regulation will have on the spread of the disease. We estimate that the average net benefit of reducing the diseased leaf threshold is only likely to be $1.4 million per year over the next 30 years, expressed as the annualised present value of tightened regulation. This result varies substantially when the timeframe of the analysis is changed, with shorter time frames indicating poorer net returns from the change in protocols. Overall, the benefit of the regulation change is likely to be minor.