A dual self-attentive transformer U-Net model for precise pancreatic segmentation and fat fraction estimation Ashok Shanmugam, Prianka Ramachandran Radhabai, Kavitha KVN, Agbotiname Lucky Imoize BMC Medical Imaging, 2025 Accurately segmenting the pancreas from abdominal computed tomography (CT) images is crucial for detecting and managing pancreatic diseases, such as diabetes and tumors. Type 2 diabetes and metabolic syndrome are associated with pancreatic fat accumulation. Calculating the fat fraction aids in the investigation of β-cell malfunction and insulin resistance. The most widely used pancreas segmentation technique is a U-shaped network based on deep convolutional neural networks (DCNNs). They struggle to capture long-range biases in an image because they rely on local receptive fields. This research proposes a novel dual Self-attentive Transformer Unet (DSTUnet) model for accurate pancreatic segmentation, addressing this problem. This model incorporates dual self-attention Swin transformers on both the encoder and decoder sides to facilitate global context extraction and refine candidate regions. After segmenting the pancreas using a DSTUnet, a histogram analysis is used to estimate the fat fraction. The suggested method demonstrated excellent performance on the standard dataset, achieving a DSC of 93.7% and an HD of 2.7 mm. The average volume of the pancreas was 92.42, and its fat volume fraction (FVF) was 13.37%.
An Approach Towards Abnormal Heart Rate Variability Detection Through Pseudo-Shifter Enabled Neural Computing Ashok S, Hemkumar J, Rahul D, Sivakumar D, Prabhu V 2025 International Conference on Computing and Communication Technologies Iccct 2025, 2025 The growing population, recent studies have highlighted a significant rise in cardiovascular attacks compared to previous years, reflecting an alarming trend that increases annually. This escalating prevalence underscores the urgent need for effective systems for cardiovascular disease detection and prevention. The proposed system addresses critical limitations in existing state-of-the-art approaches, particularly in achieving accurate predictions of heart abnormalities, which remain a common and persistent health threat. Leveraging a standard dataset, the system is designed to detect heart abnormalities in various patterns, ensuring comprehensive diagnostic coverage. Developed using advanced digital architecture, the system prioritizes high-speed data sampling and low-power operation, making it both efficient and scalable. A key innovation in this approach is the implementation of a low-power pseudo shifter-enabled pattern analysis algorithm (PAA), which enhances pattern detection while optimizing power consumption. The system achieved an impressive area coverage of just 1.23 mm2, reflecting its compact and efficient design. By employing an ideal mechanism to analyze and optimize inputs, the proposed platform represents a significant advancement in cardiovascular healthcare, offering a precise, energy-efficient, and scalable solution to address this growing medical challenge.
3D CT Liver Images Lesion Extraction and Classification for Using 3D-CNN with GLRLM S. Jayarathna, R. Sowmiya, G. Nallasivan, G. Sahaana, S. Ashok, R. Saravanakumar International Conference on Advanced Computing Technologies Icoact 2025, 2025 The imaging technique known as computed tomography (CT) is often considered to be the most reliable way for non-invasive diagnosis. Through the use of three-dimensional (3D) computed tomography images, we were able to categorize aggressive tumors that were found in the liver for the aim of this research. When it comes to the three-dimensional (3D) CT image, the dimension reduction is accomplished by the use of principal component analysis (PCA). The Random Forest Algorithm is responsible for identifying the abnormal hepatic region, and a median filter is used to reduce the amount of noise occurring. Methods of data augmentation are also employed in this process. To extract Gray Level Run Length Matrix (GLRLM) features, using Pyradiomics python package. These features are then fed into a 3D-CNN classifier to classify malignant tumors and haemangiomas. Our model was found to have greater performance after being compared to the findings of other models. This was revealed after the comparison was made. For the training dataset, our model has an accuracy of 97.2%, and for the test dataset, it has an accuracy of 98.25%. This accuracy is determined by the performance metrics that our model incorporates.
An effective no-reference image quality index prediction with a hybrid Artificial Intelligence approach for denoised MRI images Prianka Ramachandran Radhabai, Kavitha KVN, Ashok Shanmugam, Agbotiname Lucky Imoize BMC Medical Imaging, 2024 As the quantity and significance of digital pictures in the medical industry continue to increase, Image Quality Assessment (IQA) has recently become a prevalent subject in the research community. Due to the wide range of distortions that Magnetic Resonance Images (MRI) can experience and the wide variety of information they contain, No-Reference Image Quality Assessment (NR-IQA) has always been a challenging study issue. In an attempt to address this issue, a novel hybrid Artificial Intelligence (AI) is proposed to analyze NR-IQ in massive MRI data. First, the features from the denoised MRI images are extracted using the gray level run length matrix (GLRLM) and EfficientNet B7 algorithm. Next, the Multi-Objective Reptile Search Algorithm (MRSA) was proposed for optimal feature vector selection. Then, the Self-evolving Deep Belief Fuzzy Neural network (SDBFN) algorithm was proposed for the effective NR-IQ analysis. The implementation of this research is executed using MATLAB software. The simulation results are compared with the various conventional methods in terms of correlation coefficient (PLCC), Root Mean Square Error (RMSE), Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC), and Mean Absolute Error (MAE). In addition, our proposed approach yielded a quality number approximately we achieved significant 20% improvement than existing methods, with the PLCC parameter showing a notable increase compared to current techniques. Moreover, the RMSE number decreased by 12% when compared to existing methods. Graphical representations indicated mean MAE values of 0.02 for MRI knee dataset, 0.09 for MRI brain dataset, and 0.098 for MRI breast dataset, showcasing significantly lower MAE values compared to the baseline models.
A hybrid thyroid tumor type classification system using feature fusion, multilayer perceptron and bonobo optimization B. Shankarlal, S. Dhivya, K. Rajesh, S. Ashok Journal of X Ray Science and Technology, 2024 BACKGROUND: Thyroid tumor is considered to be a very rare form of cancer. But recent researches and surveys highlight the fact that it is becoming prevalent these days because of various factors. OBJECTIVES: This paper proposes a novel hybrid classification system that is able to identify and classify the above said four different types of thyroid tumors using high end artificial intelligence techniques. The input data set is obtained from Digital Database of Thyroid Ultrasound Images through Kaggle repository and augmented for achieving a better classification performance using data warping mechanisms like flipping, rotation, cropping, scaling, and shifting. METHODS: The input data after augmentation goes through preprocessing with the help of bilateral filter and is contrast enhanced using dynamic histogram equalization. The ultrasound images are then segmented using SegNet algorithm of convolutional neural network. The features needed for thyroid tumor classification are obtained from two different algorithms called CapsuleNet and EfficientNetB2 and both the features are fused together. This process of feature fusion is carried out to heighten the accuracy of classification. RESULTS: A Multilayer Perceptron Classifier is used for classification and Bonobo optimizer is employed for optimizing the results produced. The classification performance of the proposed model is weighted using metrics like accuracy, sensitivity, specificity, F1-score, and Matthew’s correlation coefficient. CONCLUSION: It can be observed from the results that the proposed multilayer perceptron based thyroid tumor type classification system works in an efficient manner than the existing classifiers like CANFES, Spatial Fuzzy C means, Deep Belief Networks, Thynet and Generative adversarial network and Long Short-Term memory.
Brain image compression and reconstruction system using deep learning S. Seenuvasamurthi, S. Ashok, B. Shankarlal, A. Mohamed Abbas, Ashok Vajravelu International Journal of Medical Engineering and Informatics, 2024 New perspectives on brain structure and function can only be gained through the rapid advancement of brain imaging technology. Throughout history, this has been the case. It is common practise in medicine to employ image processing in the early stages of diagnosis and treatment. In classification and segmentation tasks, deep neural networks (DNNs) have so far proven to be exceptional. Functional ultrasound (fUS) is a novel imaging technique that enables the observation of neuronal activity across the brain in awake, ambulatory rats. To achieve adequate blood flow sensitivity in the brain microvasculature, fUS relies on lengthy ultrasonic data collecting at high frame rates, placing a load on the sampling and processing hardware. Parallel MRI is introduced in broad terms, with an emphasis on the classical understanding of image space and k-space-based techniques.
Multipurpose IoT Tracker B. Sarala, Inbamalar T. M, Amala Justus Selvam M, S. Ashok, Chettiyar VaniVivekanand, M. Perarasi Proceedings of the 5th International Conference on Data Intelligence and Cognitive Informatics Icdici 2024, 2024
Inter-Vehicular Communication Using Split Ring Resonator Ashok S, Palanivel S, Prasanth P, Prianka R R, Prabhu. V, Vijayakumar Peroumal Proceedings of the 2nd International Conference on Intelligent and Innovative Technologies in Computing Electrical and Electronics Iciitcee 2024, 2024
Parkinson's Disease Prediction Using Machine Learning Algorithm Sandhiya S, Ashok. S, G. Vishnu Vardhan Rao, Prabhu V, K. Mohanraj, R. Azhagumurugan 3rd International Conference on Power Energy Control and Transmission Systems Icpects 2022 Proceedings, 2022
Printed text to voice communication for vision defect people using artificial intelligence International Journal of Scientific and Technology Research, 2019
A low power and high speed pipeline architecture using adaptive median filter for noise reduction in image processing Journal of Chemical and Pharmaceutical Sciences, 2016
FPGA implemenatrion of 9 tab 2D daubechies wavelet filter using algebraic integer International Journal of Control Theory and Applications, 2016
