Browsing by Author "Devi, T.G."

Now showing 1 - 6 of 6

Analysis &evaluation of Image filtering Noise reduction technique for Microscopic Images
(Institute of Electrical and Electronics Engineers Inc., 2020) Devi, T.G.; Patil, N.
Image processing in the field of microscopy is gaining popularity with the use of advanced techniques used for accurate classification of cells. The abnormalities in the image can be detected accurately after the image has been processed using digital image processing techniques. Preprocessing is an important step in which the noise and other undesirable content will be removed. Preprocessing is essential because the noise will cause inaccuracy in the image processing techniques. Filtering the image to denoise is the first step in preprocessing. The accuracy of denoising using filters determines the quality of the entire image processing cycle. This paper proposes filters to denoise the microscopic images. In this paper, two filters - Wiener and Median filters are compared for accuracy in denoising the image in the preprocessing stage of the cell classification. The Wiener filter and the Median filter were implemented and compared for Peak Signal to Noise Ratio (PSNR) which can be used for better image classification in the later stages. The proposed method was tested using 35 real time images which has Gaussian noise. The two filters perform for the collected dataset whereas the median filter gives highest PSNR outperforming the Wiener filter. Â© 2020 IEEE.
Gaussian Blurring Technique for Detecting and Classifying Acute Lymphoblastic Leukemia Cancer Cells from Microscopic Biopsy Images
(MDPI, 2023) Devi, T.G.; Patil, N.; Rai, S.; Philipose, C.S.
Visual inspection of peripheral blood samples is a critical step in the leukemia diagnostic process. Automated solutions based on artificial vision approaches can accelerate this procedure, while also improving accuracy and uniformity of response in telemedicine applications. In this study, we propose a novel GBHSV-Leuk method to segment and classify Acute Lymphoblastic Leukemia (ALL) cancer cells. GBHSV-Leuk is a two staged process. The first stage involves pre-processing, which uses the Gaussian Blurring (GB) technique to blur the noise and reflections in the image. The second stage involves segmentation using the Hue Saturation Value (HSV) technique and morphological operations to differentiate between the foreground and background colors, which improve the accuracy of prediction. The proposed method attains 96.30% accuracy when applied on the private dataset, and 95.41% accuracy when applied on the ALL-IDB1 public dataset. This work would facilitate early detection of ALL cancer. © 2023 by the authors.
Optimization-based convolutional neural model for the classification of white blood cells
(Springer Nature, 2024) Devi, T.G.; Patil, N.
White blood cells (WBCs) are one of the most significant parts of the human immune system, and they play a crucial role in diagnosing the characteristics of pathologists and blood-related diseases. The characteristics of WBCs are well-defined based on the morphological behavior of their nuclei, and the number and types of WBCs can often determine the presence of diseases or illnesses. Generally, there are different types of WBCs, and the accurate classification of WBCs helps in proper diagnosis and treatment. Although various classification models were developed in the past, they face issues like less classification accuracy, high error rate, and large execution. Hence, a novel classification strategy named the African Buffalo-based Convolutional Neural Model (ABCNM) is proposed to classify the types of WBCs accurately. The proposed strategy commences with collecting WBC sample databases, which are preprocessed and trained into the system for classification. The preprocessing phase removes the noises and training flaws, which helps improve the dataset's quality and consistency. Further, feature extraction is performed to segment the WBCs, and African Buffalo fitness is updated in the classification layer for the correct classification of WBCs. The proposed framework is modeled in Python, and the experimental analysis depicts that it achieved 99.12% accuracy, 98.16% precision, 99% sensitivity, 99.04% specificity, and 99.02% f-measure. Furthermore, a comparative assessment with the existing techniques validated that the proposed strategy obtained better performances than the conventional models. © The Author(s) 2024.
Real-time microscopy image-based segmentation and classification models for cancer cell detection
(Springer, 2023) Devi, T.G.; Patil, N.; Rai, S.; Philipose, C.P.
Image processing techniques and algorithms are extensively used for biomedical applications. Convolution Neural Network (CNN) is gaining popularity in fields such as the analysis of complex documents and images, which qualifies the approach to be used in biomedical applications. The key drawback of the CNN application is that it can’t call the previous layer output following the layer’s input. To address this issue, the present research has proposed the novel Modified U-Net architecture with ELU Activation Framework (MU-EAF) to detect and classify cancerous cells in the blood smear images. The system is trained with 880 samples, of which 220 samples were utilized in the validation model, and 31 images were utilized to verify the proposed model. The identified mask output of the segmentation model in the predicted mask fits the classification model to identify the cancer cell occurrence in the collected images. In addition, the segmentation evaluation is done by matching each pixel of the ground truth mask (labels) to the predicted labels from the model. The performance metrics for evaluating the segmentation of images are pixel accuracy, dice coefficient (F1-score), and Jaccard coefficient. Moreover, the model is compared with VGG-16 and simple modified CNN models, which have four blocks, each consisting of a convolutional layer, batch normalization, and activation layer with RELU activation function that are implemented and for assessing the same images used for the proposed model. The proposed model shows higher accuracy in comparison. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Segmentation and classification of white blood cancer cells from bone marrow microscopic images using duplet-convolutional neural network design
(Springer, 2023) Devi, T.G.; Patil, N.; Rai, S.; Philipose, C.P.
Cancer is a disease linked to the untamed and rapid division of cells in the body. Cancer detection through conventional methods like complete blood count is a tedious and time-consuming task prone to human errors. The introduction of image processing techniques and computer-aided diagnostics is beneficial to this field as the results obtained by utilizing these methods are quick and accurate. The proposed method in this paper uses a design Convolutional Leaky RELU with CatBoost and XGBoost (CLR-CXG) to segment the images and extract the important features that help in classification. The binary classification algorithm and gradient boosting algorithm CatBoost (Categorical Boost) and XGBoost (Extreme Gradient Boost) are implemented individually. Moreover, Convolutional Leaky RELU with CatBoost (CLRC) is designed to decrease bias and provide high accuracy, while Convolutional Leaky RELU with XGBoost (CLRXG) is designed for classification or regression prediction problems which will increase the speed of executing the algorithm and improve its performance. Thus the CLR-CXG classifies the test images into Acute Lymphoblastic Leukemia (ALL) or Multiple Myeloma (MM). Finally, the CLRC algorithm achieved 100% accuracy in classifying cancer cells, and the recorded run time is 10s. Moreover, the CLRXG algorithm has gained an accuracy of 97.12% for classifying cancer cells and 12 s for executing the process. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Survey ofÂ Leukemia Cancer Cell Detection Using Image Processing
(Springer Science and Business Media Deutschland GmbH, 2022) Devi, T.G.; Patil, N.; Rai, S.; Philipose, C.S.
Cancer is the development of abnormal cells that divide at an abnormal pace, uncontrollably. Cancerous cells have the ability to destroy other normal tissues and can spread throughout the body. Cancer cells can develop in various parts of the body. The paper focuses on leukemia which is a type of blood cancer. Blood cancer usually start in the bone marrow where the blood is produced in the body. The types of blood cancer are: Leukemia, Non-Hodgkin lymphoma, Hodgkin lymphoma, and Multiple myeloma. Leukemia is a type of blood cancer that originates in the bone marrow. Leukemia is seen when the body produces an abnormal amount of white blood cells that hinder the bone marrow from creating red blood cells and platelets. Several detection methods to identify the cancerous cells have been proposed. Identification of the cancer cells through cell image processing is very complex. The use of computer aided image processing allows the images to be viewed in 2D and 3D making it easier to identify the cancerous cells. The cells have to undergo segmentation and classification in order to identify the cancerous tumours. Several papers propose segmentation methods, classification methods and some propose both. The purpose of this survey is to review various papers that use either conventional methods or machine learning methods to detect the cells as cancerous and non-cancerous. Â© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.