Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item 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 An empirical study of the impact of masks on face recognition(Elsevier Ltd, 2022) Jeevan, G.; Zacharias, G.C.; Nair, M.S.; Rajan, J.Face recognition has a wide range of applications like video surveillance, security, access control, etc. Over the past decade, the field of face recognition has matured and grown at par with the latest advancements in technology, particularly deep learning. Convolution Neural Networks have surpassed human accuracy in Face Recognition on popular evaluation tests such as LFW. However, most existing models evaluate their performance with an assumption of the availability of full facial information. The COVID-19 pandemic has laid forth challenges to this assumption, and to the performance of existing methods and leading-edge algorithms in the field of face recognition. This is in the wake of an explosive increase in the number of people wearing face masks. The reduced amount of facial information available to a recognition system from a masked face impacts their discrimination ability. In this context, we design and conduct a series of experiments comparing the masked face recognition performances of CNN architectures available in literature and exploring possible alterations in loss functions, architectures, and training methods that can enable existing methods to fully extract and leverage the limited facial information available in a masked face. We evaluate existing CNN-based face recognition systems for their performance against datasets composed entirely of masked faces, in contrast to the existing standard evaluations where masked or occluded faces are a rare occurrence. The study also presents evidence denoting an increased impact of network depth on performance compared to standard face recognition. Our observations indicate that substantial performance gains can be achieved by the introduction of masked faces in the training set. The study also inferred that various parameter settings determined suitable for standard face recognition are not ideal for masked face recognition. Through empirical analysis we derived new value recommendations for these parameters and settings. © 2021 Elsevier LtdItem Deep learning-based automated mitosis detection in histopathology images for breast cancer grading(John Wiley and Sons Inc, 2022) Mathew, T.; Ajith, B.; Kini, J.; Rajan, J.Cancer grade is an indicator of the aggressiveness of cancer. It is used for prognosis and treatment decisions. Conventionally cancer grading is performed manually by experienced pathologists via microscopic examination of pathology slides. Among the three factors involved in breast cancer grading (mitosis count, nuclear atypia, and tubule formation), mitotic cell counting is the most challenging task for pathologists. It is possible to automate this task by applying computational algorithms on pathology slides images. Lack of sufficiently large datasets and class imbalance between mitotic and non-mitotic cells in slide images are the two major challenges in developing effective deep learning-based methods for mitosis detection. In this paper, we propose a new approach and a method based on that to address these challenges. The high training data requirement of the advanced deep neural network is met by combining two datasets from different sources after a color-normalization process. Class imbalance is addressed by the augmentation of the mitotic samples in a context-preserving manner. Finally, a customized convolutional neural network classifier is used to classify the candidate cells into the target classes. We have used the publicly available datasets MITOS-ATYPIA and MITOS for the experiments. Our method outperforms most of the recent methods that are based on independent datasets and at the same time offers adaptability to the combination of datasets from different sources. © 2022 Wiley Periodicals LLC.Item Forecasting Land-Use and Land-Cover Change Using Hybrid CNN-LSTM Model(Institute of Electrical and Electronics Engineers Inc., 2024) Varma, B.; Naik, N.; Chandrasekaran, K.; Venkatesan, M.; Rajan, J.Land-use and land-cover (LULC) information helps analyze future trends and is essential for environmental management and sustainable planning. Time-series satellite images are employed in this study to forecast changes in LULC. Deep-learning (DL) frameworks have been widely used for modeling dynamic LULC changes at the regional level. However, improving the accuracy of the existing prediction models is necessary. This letter proposes an integrated convolutional neural network (CNN) and long short-term memory network (LSTM) known as a hybrid CNN-LSTM model to address the fine-scale LULC prediction requirement. The efficiency of the proposed approach was examined using LULC data for the Dakshina Kannada District of Karnataka State, India. The proposed model achieved an overall accuracy of 95.11% and a kappa coefficient of 0.92, based on the ground-truth data for 2014. The model's predictions for 2035, based on data from 2005 to 2014, revealed the following trends: Urbanization exhibited a pattern of rapid expansion and increased growth. The integrated CNN-LSTM model extracted spatial and temporal features for effectively predicting LULC changes. Infrastructure development, population density, and enhanced economic activities were the major driving factors of changes in LULC for the study region. Robust LULC change forecasting will strengthen LULC evaluations, aid in understanding complex land-use systems, and empower decision-makers to formulate effective land management strategies in the coming years. © 2004-2012 IEEE.Item A Dual-Stage Semi-Supervised Pre-Training Approach for Medical Image Segmentation(Institute of Electrical and Electronics Engineers Inc., 2024) Aralikatti, R.C.; Pawan, S.J.; Rajan, J.Deep neural networks have played a vital role in developing automated methods for addressing medical image segmentation. However, their reliance on labeled data impedes the practicability. Semi-Supervised learning is gaining attention for its intrinsic ability to extract valuable information from labeled and unlabeled data with improved performance. Recently, consistency regularization methods have gained interest due to their efficient learning procedures. They are, however, confined to data or network-level perturbations, negating the benefit of having both forms in a single framework. In light of this, we ask an intriguing but unexplored question: Can we have both network-level and data-level perturbation in the semi-supervised framework? To this end, we present a holistic approach that integrates data-level perturbation in the model pre-training stage, followed by implicit network-level perturbation in the fine-tuning stage. Furthermore, we incorporate networks with manifold learning paradigms throughout the training to facilitate the formation of robust data representations by ensuring local and global semantic affinities adhering to the theory of consensus. Notably, this may be the first attempt in the semi-supervised medical image segmentation archetype to use data and network-level perturbation with a model pre-training strategy. We extensively validated the efficacy of the proposed framework on three benchmark datasets, namely the Automated Cardiac Diagnosis Challenge, ISIC-2018, and Left Atrial Segmentation Challenge datasets, subjected to severely low-sampled labeled data. Notably, in ACDC (4%), ISIC-2018 (5%), and LA (6%) labeled cases, the proposed method outperforms the second-best method by 2.95%, 1.31%, and 0.71% in the Dice Similarity Metric. © 2023 IEEE.