Human papilloma virus detection in oropharyngeal carcinomas with in situ hybridisation using hand crafted morphological features and deep central attention residual networks.

Human Papilloma Virus (HPV) is a major risk factor for the development of oropharyngeal cancer. Automatic detection of HPV in digitized pathology tissues using in situ hybridisation (ISH) is a difficult task due to the variability and complexity of staining patterns as well as the presence of imaging and staining artefacts. This paper proposes an intelligent image analysis framework to determine HPV status in digitized samples of oropharyngeal cancer tissue micro-arrays (TMA). The proposed pipeline mixes handcrafted feature extraction with a deep learning for epithelial region segmentation as a preliminary step. We apply a deep central attention learning technique to segment epithelial regions and within those assess the presence of regions representing ISH products. We then extract relevant morphological measurements from those regions which are then input into a supervised learning model for the identification of HPV status. The performance of the proposed method has been evaluated on 2009 TMA images of oropharyngeal carcinoma tissues captured with a ×20 objective. The experimental results show that our technique provides around 91% classification accuracy in detecting HPV status when compared with the histopatholgist gold standard. We also tested the performance of end-to-end deep learning classification methods to assess HPV status by learning directly from the original ISH processed images, rather than from the handcrafted features extracted from the segmented images. We examined the performance of sequential convolutional neural networks (CNN) architectures including three popular image recognition networks (VGG-16, ResNet and Inception V3) in their pre-trained and trained from scratch versions, however their highest classification accuracy was inferior (78%) to the hybrid pipeline presented here.

Unsupervised morphological segmentation of tissue compartments in histopathological images.

Algorithmic segmentation of histologically relevant regions of tissues in digitized histopathological images is a critical step towards computer-assisted diagnosis and analysis. For example, automatic identification of epithelial and stromal tissues in images is important for spatial localisation and guidance in the analysis and characterisation of tumour micro-environment. Current segmentation approaches are based on supervised methods, which require extensive training data from high quality, manually annotated images. This is often difficult and costly to obtain. This paper presents an alternative data-independent framework based on unsupervised segmentation of oropharyngeal cancer tissue micro-arrays (TMAs). An automated segmentation algorithm based on mathematical morphology is first applied to light microscopy images stained with haematoxylin and eosin. This partitions the image into multiple binary 'virtual-cells', each enclosing a potential 'nucleus' (dark basins in the haematoxylin absorbance image). Colour and morphology measurements obtained from these virtual-cells as well as their enclosed nuclei are input into an advanced unsupervised learning model for the identification of epithelium and stromal tissues. Here we exploit two Consensus Clustering (CC) algorithms for the unsupervised recognition of tissue compartments, that consider the consensual opinion of a group of individual clustering algorithms. Unlike most unsupervised segmentation analyses, which depend on a single clustering method, the CC learning models allow for more robust and stable detection of tissue regions. The proposed framework performance has been evaluated on fifty-five hand-annotated tissue images of oropharyngeal tissues. Qualitative and quantitative results of the proposed segmentation algorithm compare favourably with eight popular tissue segmentation strategies. Furthermore, the unsupervised results obtained here outperform those obtained with individual clustering algorithms.

Antibacterial effect of gold nanoparticles against Corynebacterium pseudotuberculosis.

Corynebacterium pseudotuberculosis is the etiological agent of chronic caseous lymphadenitis. The bacterium infects goats and sheep causing great economic loss worldwide annually. The present work aims to evaluate the efficiency of gold nanoparticles (AuNPs) and AuNPs - laser combined therapy as antibacterial approaches against C. pseudotuberculosis bacteria in vitro. Gold nanoparticles 25 nm were synthesized by co-precipitation method and characterized by different techniques including; Transmission Electron Microscope (TEM), X-ray Diffraction and Dynamic Light Scattering. Three concentrations of AuNPs (50, 100 and 200 µg/mL) were utilized for estimating the bacterial growth rate and the Minimum Inhibitory Concentration (MIC). The mechanism of interaction between AuNPs and bacteria was evaluated by transmission electron microscopic image analysis. Confocal Laser Scanning Microscopic technique was used to study the cytotoxic action of AuNPs and laser against C. psudotuberculosis. Results revealed that MIC of AuNPs and AuNPs - laser combined therapy were 200 µg/mL and 100 µg/mL respectively. TEM image analysis illustrated that gold nanoparticles penetrated the thick wall of C. psudotuberculosis and accumulated as intracellular agglomerates. Laser light enhanced the antimicrobial activity of gold nanoparticles by at least one fold due to its photo thermal combined effect that might be used as an effective antibacterial approach against C. pseudotuberculosis.

Classifying Cognitive Profiles Using Machine Learning with Privileged Information in Mild Cognitive Impairment.

Early diagnosis of dementia is critical for assessing disease progression and potential treatment. State-or-the-art machine learning techniques have been increasingly employed to take on this diagnostic task. In this study, we employed Generalized Matrix Learning Vector Quantization (GMLVQ) classifiers to discriminate patients with Mild Cognitive Impairment (MCI) from healthy controls based on their cognitive skills. Further, we adopted a "Learning with privileged information" approach to combine cognitive and fMRI data for the classification task. The resulting classifier operates solely on the cognitive data while it incorporates the fMRI data as privileged information (PI) during training. This novel classifier is of practical use as the collection of brain imaging data is not always possible with patients and older participants. MCI patients and healthy age-matched controls were trained to extract structure from temporal sequences. We ask whether machine learning classifiers can be used to discriminate patients from controls and whether differences between these groups relate to individual cognitive profiles. To this end, we tested participants in four cognitive tasks: working memory, cognitive inhibition, divided attention, and selective attention. We also collected fMRI data before and after training on a probabilistic sequence learning task and extracted fMRI responses and connectivity as features for machine learning classifiers. Our results show that the PI guided GMLVQ classifiers outperform the baseline classifier that only used the cognitive data. In addition, we found that for the baseline classifier, divided attention is the only relevant cognitive feature. When PI was incorporated, divided attention remained the most relevant feature while cognitive inhibition became also relevant for the task. Interestingly, this analysis for the fMRI GMLVQ classifier suggests that (1) when overall fMRI signal is used as inputs to the classifier, the post-training session is most relevant; and (2) when the graph feature reflecting underlying spatiotemporal fMRI pattern is used, the pre-training session is most relevant. Taken together these results suggest that brain connectivity before training and overall fMRI signal after training are both diagnostic of cognitive skills in MCI.

Incorporating privileged information through metric learning.

In some pattern analysis problems, there exists expert knowledge, in addition to the original data involved in the classification process. The vast majority of existing approaches simply ignore such auxiliary (privileged) knowledge. Recently a new paradigm-learning using privileged information-was introduced in the framework of SVM+. This approach is formulated for binary classification and, as typical for many kernel-based methods, can scale unfavorably with the number of training examples. While speeding up training methods and extensions of SVM+ to multiclass problems are possible, in this paper we present a more direct novel methodology for incorporating valuable privileged knowledge in the model construction phase, primarily formulated in the framework of generalized matrix learning vector quantization. This is done by changing the global metric in the input space, based on distance relations revealed by the privileged information. Hence, unlike in SVM+, any convenient classifier can be used after such metric modification, bringing more flexibility to the problem of incorporating privileged information during the training. Experiments demonstrate that the manipulation of an input space metric based on privileged data improves classification accuracy. Moreover, our methods can achieve competitive performance against the SVM+ formulations.

Adaptive metric learning vector quantization for ordinal classification.

Many pattern analysis problems require classification of examples into naturally ordered classes. In such cases, nominal classification schemes will ignore the class order relationships, which can have a detrimental effect on classification accuracy. This article introduces two novel ordinal learning vector quantization (LVQ) schemes, with metric learning, specifically designed for classifying data items into ordered classes. In ordinal LVQ, unlike in nominal LVQ, the class order information is used during training in selecting the class prototypes to be adapted, as well as in determining the exact manner in which the prototypes get updated. Prototype-based models in general are more amenable to interpretations and can often be constructed at a smaller computational cost than alternative nonlinear classification models. Experiments demonstrate that the proposed ordinal LVQ formulations compare favorably with their nominal counterparts. Moreover, our methods achieve competitive performance against existing benchmark ordinal regression models.