ABSTRACT
BACKGROUND: Thyroid nodules are more common than previously realised, and the rate of prevalence is hugely impacted by the method of detection and their easy access. No single test is sufficient to access the thyroid nodule at any given time. Hence this necessitates the need for clinicians to use an evidence-based protocol for their assessment and diagnosis. AIMS AND OBJECTIVE: To determine the likelihood of malignancy in individuals who have thyroid nodules of any size, by a) performing a triple assessment, including a history and physical examination, an ultrasound of the neck and fine needle aspiration and cytology (FNAC) b) predicting the percentage of correlation between findings of malignancy on FNAC and final histopathological diagnosis c) identifying and validate individual risk factors in the clinical examination and ultrasound imaging that point towards a nodule being malignant Methods: Patients presenting with thyroid nodules in a clinically euthyroid state were studied over a time period of 18 months. Seventy-five patients were included in this study. Patients having external cytology and ultrasonography reports were reassessed if they consented to the study. If the pathologists thought the smears were sufficient, slide reviews were accepted. A senior consultant conducted the clinical evaluation. Prior to doing the FNACs, the designated radiologist performed the majority of the ultrasonograms. If the physicians believed it was necessary, ultrasound-guided FNACs were performed. According to Bethesda criteria, the cytology was reported. The outcome of the histopathological analysis was used as the gold standard for diagnosis in this investigation. RESULT: Out of 75 patients included in the study, the older age group (50-70) patients had mostly malignant lesions (92%). In the younger age group (20-39), about 77% had benign lesions. Benign lesions were more common in females than males according to the histopathology study. Seventy-three percent of fixed swellings turned out to be malignant. About 86% of patients who had extrathyroidal extension ended up being found to have malignant lesions but even 41% of patients who didn't have any extrathyroidal extension also turned out to be having malignant lesions. However, the presence of pressure symptoms didn't necessarily translate to being an indicator of malignancy. Ninety-seven percent of patients who had punctate microcalcifications turned out to have malignant lesions. Hypoechogenicity on imaging also is an important marker of malignancy, with about 87% of patients who had hypoechogenicity having malignant lesions proven on histopathology. All the patients who had solid lesions on imaging were proven to have malignant lesions. About 77% of patients who had cystic features ended up having benign lesions. Hence, it is a very significant marker. Intranodular vascularity, taller than wider lesions and positive lymph nodes on imaging were proven to have malignant lesions. FNAC is an important diagnostic tool. It is made out that the reporting of FNAC more or less matched the histopathological diagnosis in almost all categories. CONCLUSION: There are definite correlations in the role of triple assessment as a standard protocol in the diagnosis of thyroid nodules and guiding its management.
ABSTRACT
Over the last decade, the field of bioinformatics has been increasing rapidly. Robust bioinformatics tools are going to play a vital role in future progress. Scientists working in the field of bioinformatics conduct a large number of researches to extract knowledge from the biological data available. Several bioinformatics issues have evolved as a result of the creation of massive amounts of unbalanced data. The classification of precursor microRNA (pre miRNA) from the imbalanced RNA genome data is one such problem. The examinations proved that pre miRNAs (precursor microRNAs) could serve as oncogene or tumor suppressors in various cancer types. This paper introduces a Hybrid Deep Neural Network framework (H-DNN) for the classification of pre miRNA in imbalanced data. The proposed H-DNN framework is an integration of Deep Artificial Neural Networks (Deep ANN) and Deep Decision Tree Classifiers. The Deep ANN in the proposed H-DNN helps to extract the meaningful features and the Deep Decision Tree Classifier helps to classify the pre miRNA accurately. Experimentation of H-DNN was done with genomes of animals, plants, humans, and Arabidopsis with an imbalance ratio up to 1:5000 and virus with a ratio of 1:400. Experimental results showed an accuracy of more than 99% in all the cases and the time complexity of the proposed H-DNN is also very less when compared with the other existing approaches.
Subject(s)
MicroRNAs , Neural Networks, Computer , Animals , Computational Biology/methods , MicroRNAs/geneticsABSTRACT
Subunit segmenting and modelling in medical sign language is one of the important studies in linguistic-oriented and vision-based Sign Language Recognition (SLR). Many efforts were made in the precedent to focus the functional subunits from the view of linguistic syllables but the problem is implementing such subunit extraction using syllables is not feasible in real-world computer vision techniques. And also, the present recognition systems are designed in such a way that it can detect the signer dependent actions under restricted and laboratory conditions. This research paper aims at solving these two important issues (1) Subunit extraction and (2) Signer independent action on visual sign language recognition. Subunit extraction involved in the sequential and parallel breakdown of sign gestures without any prior knowledge on syllables and number of subunits. A novel Bayesian Parallel Hidden Markov Model (BPaHMM) is introduced for subunit extraction to combine the features of manual and non-manual parameters to yield better results in classification and recognition of signs. Signer independent action aims in using a single web camera for different signer behaviour patterns and for cross-signer validation. Experimental results have proved that the proposed signer independent subunit level modelling for sign language classification and recognition has shown improvement and variations when compared with other existing works.
