Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
17 results
Search Results
Item Depthwise Separable Convolutional Neural Network Model for Intra-Retinal Cyst Segmentation(Institute of Electrical and Electronics Engineers Inc., 2019) Girish, G.N.; Saikumar, B.; Roychowdhury, S.; Kothari, A.R.; Rajan, J.Intra-retinal cysts (IRCs) are significant in detecting several ocular and retinal pathologies. Segmentation and quantification of IRCs from optical coherence tomography (OCT) scans is a challenging task due to present of speckle noise and scan intensity variations across the vendors. This work proposes a convolutional neural network (CNN) model with an encoder-decoder pair architecture for IRC segmentation across different cross-vendor OCT scans. Since deep CNN models have high computational complexity due to a large number of parameters, the proposed method of depthwise separable convolutional filters aids model generalizability and prevents model over-fitting. Also, the swish activation function is employed to prevent the vanishing gradient problem. The optima cyst segmentation challenge (OCSC) dataset with four different vendor OCT device scans is used to evaluate the proposed model. Our model achieves a mean Dice score of 0.74 and mean recall/precision rate of 0.72/0.82 across different imaging vendors and it outperforms existing algorithms on the OCSC dataset. © 2019 IEEE.Item Retinal-Layer Segmentation Using Dilated Convolutions(Springer Science and Business Media Deutschland GmbH, 2020) Guru Pradeep Reddy, T.; Ashritha, K.S.; Prajwala, T.M.; Girish, G.N.; Kothari, A.R.; Koolagudi, S.G.; Rajan, J.Visualization and analysis of Spectral Domain Optical Coherence Tomography (SD-OCT) cross-sectional scans has gained a lot of importance in the diagnosis of several retinal abnormalities. Quantitative analytic techniques like retinal thickness and volumetric analysis are performed on cross-sectional images of the retina for early diagnosis and prognosis of retinal diseases. However, segmentation of retinal layers from OCT images is a complicated task on account of certain factors like speckle noise, low image contrast and low signal-to-noise ratio amongst many others. Owing to the importance of retinal layer segmentation in diagnosing ophthalmic diseases, manual segmentation techniques have been proposed and adopted in clinical practice. Nonetheless, manual segmentations suffer from erroneous boundary detection issues. This paper thus proposes a fully automated semantic segmentation technique that uses an encoder–decoder architecture to accurately segment the prominent retinal layers. © 2020, Springer Nature Singapore Pte Ltd.Item An Automated Approach for Screening COVID-19 from Thermal Images Using Convolutional Neural Network(Springer Science and Business Media Deutschland GmbH, 2022) Srivastava, D.K.; Pawan, S.J.; Rajan, J.The world has seen the disastrous effect caused by COVID-19 on humankind. The rapidity of COVID-19 transmission, re-infections, post-COVID-19 symptoms, and the emergence of new COVID-19 strands have disrupted the global healthcare systems. Consequently, screening for COVID-19 cases has become of the utmost importance. As temperature and mask checks help significantly to prevent the rapid spread of COVID-19, automating this process in public places has become indispensable. In this work, we propose an end-to-end approach for mask detection followed by temperature for efficient screening. The proposed model achieved 93.5%, 96.7%, and 97.7% precision, recall, and mAP when trained on the thermal surveillance dataset and tested on a lightning dataset consisting of images with varying intensities. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Automated Molecular Subtyping of Breast Cancer Through Immunohistochemistry Image Analysis(Springer Science and Business Media Deutschland GmbH, 2023) Niyas, S.; Priya, S.; Oswal, R.; Mathew, T.; Kini, J.R.; Rajan, J.Molecular subtyping has a significant role in cancer prognosis and targeted therapy. However, the prevalent manual procedure for this has disadvantages, such as deficit of medical experts, inter-observer variability, and high time consumption. This paper suggests a novel approach to automate molecular subtyping of breast cancer using an end-to-end deep learning model. Immunohistochemistry (IHC) images of the tumor tissues are analyzed using a three-stage system to determine the subtype. A modified Res-UNet CNN architecture is used in the first stage to segregate the biomarker responses. This is followed by using a CNN classifier to determine the status of the four biomarkers. Finally, the biomarker statuses are combined to determine the specific subtype of breast cancer. For each IHC biomarker, the performance of segmentation models is analyzed qualitatively and quantitatively. In addition, the patient-level biomarker prediction results are also assessed. The findings of the suggested technique demonstrate the potential of computer-aided techniques to diagnose the subtypes of breast cancer. The proposed automated molecular subtyping approach can accelerate pathology procedures, considerably reduce pathologists’ workload, and minimize the overall cost and time required for diagnosis and treatment planning. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Attention Assisted Patch-Wise CNN for the Segmentation of Fluids from the Retinal Optical Coherence Tomography Images(Springer Science and Business Media Deutschland GmbH, 2024) Anoop, B.N.; Parida, S.; Ajith, B.; Girish, G.N.; Kothari, A.R.; Kavitha, M.S.; Rajan, J.Optical Coherence Tomography (OCT) is an important imaging modality in ophthalmology to visualize the abnormalities present in the retina. One of the major reasons for blindness is the accumulation of fluids in the various layers of the retina called retinal cysts. Accurate estimation of the type of cyst and its volume is important for effective treatment planning. In this paper, we propose attention assisted convolutional neural network-based architecture to detect and quantify three types of retinal cysts namely the intra-retinal cyst, sub-retinal cyst and pigmented epithelial detachment from the OCT images of the human retina. The proposed architecture has an encoder-decoder structure with an attention and a multi-scale module. The qualitative and quantitative performance of the model is evaluated on the publicly available RETOUCH retinal OCT fluid detection challenge data set. The proposed model outperforms the state-of-the-art methods in terms of precision, recall, and dice coefficient. Furthermore, the proposed model is computationally efficient due to its less number of model parameters. © Springer Nature Switzerland AG 2024.Item Computational methods for automated mitosis detection in histopathology images: A review(Elsevier Sp. z o.o., 2021) Mathew, T.; Kini, J.R.; Rajan, J.Mitosis detection is an important step in pathology procedures in the context of cancer diagnosis and prognosis. Prevalent process for this task is by manually observing Hematoxylin and Eosin (H & E) stained histopathology sections on glass slides through a microscope by trained pathologists. This conventional approach is tedious, error-prone, and has shown high inter-observer variability. With the advancement of computational technologies, automating mitosis detection by the use of image processing algorithms has attracted significant research interest. In the past decade, several methods appeared in the literature, addressing this problem and they have shown encouraging incremental progress towards a clinically usable solution. Mitosis count is an important parameter in grading of breast cancer and glioma, unlike other cancer types. Driven by the availability of multiple public datasets and open contests, most of the methods in literature address mitosis detection in breast cancer images. This paper is a comprehensive review of the methods published in the area of automated mitotic cell detection in H & E stained histopathology images of breast cancer in the last 10 years. We also discuss the current trends and future prospects of this clinically relevant task, augmenting humanity's fight against cancer. © 2020 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of SciencesItem Segmentation of intra-retinal cysts from optical coherence tomography images using a fully convolutional neural network model(Institute of Electrical and Electronics Engineers Inc., 2019) Girish, G.N.; Thakur, B.; Chowdhury, S.R.; Kothari, A.R.; Rajan, J.Optical coherence tomography (OCT) is an imaging modality that is used extensively for ophthalmic diagnosis, near-histological visualization, and quantification of retinal abnormalities such as cysts, exudates, retinal layer disorganization, etc. Intra-retinal cysts (IRCs) occur in several macular disorders such as, diabetic macular edema, retinal vascular disorders, age-related macular degeneration, and inflammatory disorders. Automated segmentation of IRCs poses challenges owing to variations in the acquisition system scan intensities, speckle noise, and imaging artifacts. Several segmentation methods have been proposed in the literature for IRC segmentation on vendor-specific OCT images that lack generalizability across imaging systems. In this paper, we propose a fully convolutional network (FCN) model for vendor-independent IRC segmentation. The proposed method counteracts image noise variabilities and trains FCN models on OCT sub-images from the OPTIMA cyst segmentation challenge dataset (with four different vendor-specific images, namely, Cirrus, Nidek, Spectralis, and Topcon). Further, optimal data augmentation and model hyperparametrization are shown to prevent over-fitting for IRC area segmentation. The proposed method is evaluated on the test dataset with a recall/precision rate of 0.66/0.79 across imaging vendors. The Dice correlation coefficient of the proposed method outperforms that of the published algorithms in the OPTIMA cyst segmentation challenge with a Dice rate of 0.71 across the vendors. © 2013 IEEE.Item Segmentation of focal cortical dysplasia lesions from magnetic resonance images using 3D convolutional neural networks(Elsevier Ltd, 2021) Niyas, S.; Chethana Vaisali, S.; Show, I.; Chandrika, T.G.; Vinayagamani, S.; Kesavadas, C.; Rajan, J.Computer-aided diagnosis using advanced Artific ial Intelligence (AI) techniques has become much popular over the last few years. This work automates the segmentation of Focal Cortical Dysplasia (FCD) lesions from three-dimensional (3D) Magnetic Resonance (MR) images. FCD is a type of neuronal malformation in the brain cortex and is the leading cause of intractable epilepsy, irrespective of gender or age differences. Since the neuron related abnormalities are usually resistant to drug therapy, surgical resection has been the main treatment approach for patients with intractable epilepsy. Automating the identification and segmentation of FCD is useful for neuroradiologists in pre-surgical evaluations. Convolutional Neural Networks (CNNs) have the ability to learn appropriate features from the training data without any human intervention. But, most of the state-of-the-art FCD segmentation approaches use two-dimensional (2D) CNN models despite the availability of 3D Magnetic resonance imaging (MRI) volumes, and hence fail to leverage the inter-slice information present in the MRI volumes. The major hurdles in considering a 3D CNN model are the need for a large 3D dataset, big memory, and high computation cost. A deep 3D CNN segmentation model, which can extract inter-slice information and overcomes the drawbacks of conventional 3D CNN methods to an extent, is proposed in this paper. The model uses a 3D version of U-Net with residual blocks that works on shallow depth 3D sub-volumes generated from MRI volumes. The proposed method shows superior performance over the state-of-the-art FCD segmentation methods in both qualitative and quantitative analysis. © 2021 Elsevier LtdItem Stroke classification from computed tomography scans using 3D convolutional neural network(Elsevier Ltd, 2022) Neethi, A.S.; Niyas, S.; Kannath, S.K.; Mathew, J.; Anzar, A.M.; Rajan, J.Stroke is a cerebrovascular condition with a significant morbidity and mortality rate and causes physical disabilities for survivors. Once the symptoms are identified, it requires a time-critical diagnosis with the help of the most commonly available imaging techniques. Computed tomography (CT) scans are used worldwide for preliminary stroke diagnosis. It demands the expertise and experience of a radiologist to identify the stroke type, which is critical for initiating the treatment. This work attempts to gather those domain skills and build a model from CT scans to diagnose stroke. The non-contrast computed tomography (NCCT) scan of the brain comprises volumetric images or a 3D stack of image slices. So, a model that aims to solve the problem by targeting a 2D slice may fail to address the volumetric nature. We propose a 3D-based fully convolutional classification model to identify stroke cases from CT images that take into account the contextual longitudinal composition of volumetric data. We formulate a custom pre-processing module to enhance the scans and aid in improving the classification performance. Some of the significant challenges faced by 3D CNN are the less number of training samples, and the number of scans is mostly biased in favor of normal patients. In this work, the limitation of insufficient training volume and class imbalanced data have been rectified with the help of a strided slicing approach. A block-wise design was used to formulate the proposed network, with the initial part focusing on adjusting the dimensionality, at the same time retaining the features. Later on, the accumulated feature maps were effectively learned utilizing bundled convolutions and skip connections. The results of the proposed method were compared against 3D CNN stroke classification models on NCCT, various 3D CNN architectures on other brain imaging modalities, and 3D extensions of some of the classical CNN architectures. The proposed method achieved an improvement of 14.28% in the F1-score over the state-of-the-art 3D CNN stroke classification model. © 2022 Elsevier LtdItem A novel deep classifier framework for automated molecular subtyping of breast carcinoma using immunohistochemistry image analysis(Elsevier Ltd, 2022) Mathew, T.; Niyas, S.; Johnpaul, C.I.; Kini, J.; Rajan, J.Breast carcinoma has various subtypes based on the genetic factors involved in the pathogenesis of the malignancy. Identifying the exact subtype and providing targeted treatment to the patient can improve the survival chances. Molecular subtyping through immunohistochemistry analysis is a pathology procedure to determine the subtype of breast cancer. The existing manual procedure is tedious and involves assessing the status of the four vital molecular biomarkers present in the tumor tissues. In this paper, a deep learning-based framework for automated molecular subtyping of breast cancer is proposed. Digital slide images of the four biomarkers are separately processed by the proposed framework. In the preprocessing stage, the non-informative background regions from the images are separated. The patches extracted from the foreground regions are classified into target classes using convolutional neural network models trained for this purpose. Classification results are post-processed to predict the status of all the four biomarkers. The predictions for the individual biomarkers are finally consolidated as per clinical guidelines to determine the subtype of the cancer. The proposed system is evaluated for the performance of individual biomarker status prediction and patient-level subtype classification.For patient-level evaluation of biomarkers ER, PR, K67, and HER2, the proposed method gives F1 Scores 1.00, 1.00, 0.90, and 0.94 respectively, whereas for molecular subtyping an F1 score of 0.89 is obtained. In both these aspects, the proposed framework has given significant results that show the effectiveness of our approach. © 2022 Elsevier Ltd