Breast cancer is one of the most common diseases in women worldwide. Many studies have been conducted to predict survival indicators, however these analyses were predominantly performed using basic statistical methods. As an alternative, this study used machine learning techniques build models for detecting and visualising significant prognostic indicators breast rate.A large hospital-based dataset retrieved from University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with...

Breast cancer survival prediction can have an extreme effect on selection of best treatment protocols. Many approaches such as statistical or machine learning models been employed to predict the prospects patients, but newer algorithms deep be tested with aim improving and accuracy. In this study, we used breast in 4,902 patient records from University Malaya Medical Centre Cancer Registry. The results indicated that multilayer perceptron (MLP), random forest (RF) decision tree (DT)...

Ficus is one of the largest genera in plant kingdom reaching to about 1000 species worldwide. While taxonomic keys are available for identifying most Ficus, it very difficult and time consuming interpretation by a nonprofessional thus requires highly trained taxonomists. The purpose current study develop an efficient baseline automated system, using image processing with pattern recognition approach, identify three which have similar leaf morphology. Leaf images from different namely F....

Copepods are planktonic organisms that play a major role in the marine food chain. Studying community structure and abundance of copepods relation to environment is essential evaluate their contribution mangrove trophodynamics coastal fisheries. The routine identification can be very technical, requiring taxonomic expertise, experience much effort which time-consuming. Hence, there an urgent need introduce novel methods approaches automate classification copepod specimens. This study aims...

The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective relatively low-cost method for the early diagnosis cancer. accuracy is, however, highly dependent on quality systems experience users (radiologists). use deep convolutional neural network approaches has provided solutions efficient analysis images. In this study, we propose a new framework cancer with attention module modified VGG16 architecture. adopted mechanism enhances feature...

Monogeneans are flatworms (Platyhelminthes) that primarily found on gills and skin of fishes. Monogenean parasites have attachment appendages at their haptoral regions help them to move about the body surface feed gill debris. Haptoral organs consist sclerotized hard parts such as hooks, anchors marginal hooks. species differentiated based bars, anchors, reproductive parts' (male female copulatory organs) morphological characters soft anatomical parts. The complex structure these diagnostic...

Abstract Background Coffee contains several compounds that have the potential to influence breast cancer risk and survival. However, epidemiologic data on relation between coffee survival are sparse inconsistent. Results We show component HHQ has significant apoptotic effect MDA-MB-231 MCF-7 cells in vitro , ROS generation, change mitochondrial membrane permeability, upregulation of Bax Caspase-8 as well down regulation PGK1 PKM2 expression may be important apoptosis-inducing mechanisms. The...

Advances in medical domain has led to an increase of clinical data production which offers enhancement opportunities for research sector. In this paper, we propose expand the scope Electronic Medical Records University Malaya Center (UMMC) using different techniques establishing interoperability functions between multiple departments involving diagnosis, screening and treatment breast cancer building automatic systems audits as well potential mining enhance future.Quality Implementation...

Background. Fish species may be identified based on their unique otolith shape or contour. Several pattern recognition methods have been proposed to classify fish through morphological features of the contours. However, there has no fully-automated identification model with accuracy higher than 80%. The purpose current study is develop a model, contours, identify high classification accuracy. Methods. Images right sagittal otoliths 14 from three families namely Sciaenidae, Ariidae, and...

PPARs are ligand activated transcription factors. PPAR γ agonists have been reported as a new and potentially efficacious treatment of inflammation, diabetes, obesity, cancer, AD, schizophrenia. Since cancer cells show dysregulation glycolysis they manageable through changes in metabolic environment. Interestingly, several the genes involved maintaining environment central energy generation pathway regulated or predicted to be by . The use synthetic ligands drugs their recent...

Complex diseases such as cancer are usually governed by dynamic and simultaneous modifications of multiple genes. Since sphingolipids potent bioactive molecules regulate many important pathophysiological processes carcinogenesis, we studied the gene pair correlations 36 genes (31 in sphingolipid metabolic pathway 5 encoding sphingosine-1-phosphate receptors) between breast patients healthy controls. It is remarkable to observe that expressions were widely strongly correlated controls but...

Pathology reports represent a primary source of information for cancer registries. University Malaya Medical Centre (UMMC) is tertiary hospital responsible training pathologists; thus narrative reporting becomes important. However, the unstructured free-text made extraction process tedious clinical audits and data analysis-related research. This study aims to develop an automated natural language processing (NLP) algorithm summarize existing breast pathology report from UMMC narrower...

Tryptophan metabolism plays essential roles in both immunomodulation and cancer development. Indoleamine 2,3-dioxygenase, a rate-limiting enzyme the metabolic pathway, is overexpressed different types of cancer. To get better understanding involvement tryptophan development, we evaluated expression pairwise correlation 62 genes pathway across 12 Only gene AOX1, encoding aldehyde oxidase 1, was ubiquitously downregulated, Furthermore, observed that were widely strongly correlated normal...

Combined multiple 2D views (proximal, anterior and ventral aspects) of the sagittal otolith are proposed here as a method to capture shape information for fish classification. Classification performance single view compared with combined show improved classification accuracy latter, nine species Sciaenidae. The effects description methods (shape indices, Procrustes analysis elliptical Fourier analysis) on were evaluated. perform better than indices when is considered, but all equally well...

Radiology reporting is narrative, and its content depends on the clinician's ability to interpret images accurately. A tertiary hospital, such as anonymous institute, focuses writing reports narratively part of training for medical personnel. Nevertheless, free-text make it inconvenient extract information clinical audits data mining. Therefore, we aim convert unstructured breast radiology into structured formats using natural language processing (NLP) algorithm. This study used 327...

Abstract Background Digitised monogenean images are usually stored in file system directories an unstructured manner. In this paper we propose a semantic representation of these the form Monogenean Haptoral Bar Image (MHBI) ontology, which annotated with taxonomic classification, diagnostic hard part and image properties. The data used basically species found fish, thus built simple Fish ontology to demonstrate how host (fish) can be linked MHBI ontology. This will enable linking information...

Life science ontologies play an important role in Semantic Web. Given the diversity fish species and associated wealth of information, it is imperative to develop ontology capable linking integrating this information automated fashion. As such, we introduce Fish Ontology (FO), classification architecture existing taxa which provides taxonomic on unknown based metadata restrictions. It designed support knowledge discovery, provide semantic annotation fisheries resources, data integration,...

Background. Fish species may be identified based on their unique otolith shape or contour. Several pattern recognition methods have been proposed to classify fish through morphological features of the contours. However, there has no fully-automated identification model with accuracy higher than 80%. The purpose current study is develop a model, contours, identify high classification accuracy. Methods. Images right sagittal otoliths 14 from three families namely Sciaenidae, Ariidae, and...