Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
12 results
Search Results
Item Automatic seizure detection by modified line length and Mahalanobis distance function(Elsevier Ltd, 2018) Pathak, A.; Ramesh, A.; Mitra, A.; Majumdar, K.Automatic seizure detection with high accuracy and in linear time has profound implications on therapeutic intervention mechanisms. In this work taking into account 12 popular seizure detection algorithms we have shown that line length is one feature that is extractable in linear time from EEG signals and capable of automatic seizure onset detection with highest accuracy among linear time extractable features. Also line length is less prone to give false positives. The detection accuracy has been ascertained by ROC curve analysis on Freiburg Seizure Prediction Project data containing intracranial EEG recordings of 87 seizures from 21 patients with sufficient interictal signals. Next, we have modified the classical line length feature extraction algorithm to improve its accuracy without any additional computational burden. Finally, we have applied both classical line length (LL) and modified line length (MLL) on all focal channels and detected seizures on multidimensional focal channel signals by Mahalanobis distance function (MDF). Both detected 73 out of 87 seizures. Area under the ROC curve (AUC), detection delay and false positive for LL and MLL are 0.951, 11.903 s, 0.201/h and 0.954, 11.698 s, 0.198/h respectively. Since LL has already been incorporated into an FDA approved commercially available closed loop intervention system, even this minute improvement may have significant healthcare implications. © 2018 Elsevier LtdItem Automatic detection and localization of Focal Cortical Dysplasia lesions in MRI using fully convolutional neural network(Elsevier Ltd, 2019) Bijay Dev, K.M.; Pawan, P.S.; Niyas, S.; Vinayagamani, S.; Kesavadas, C.; Rajan, J.Focal cortical dysplasia (FCD) is the leading cause of drug-resistant epilepsy in both children and adults. At present, the only therapeutic approach in patients with drug-resistant epilepsy is surgery. Hence, the quantification of FCD via non-invasive imaging techniques helps physicians to decide on surgical interventions. The properties like non-invasiveness and capability to produce high-resolution images makes magnetic resonance imaging an ideal tool for detecting the FCD to an extent. The FCD lesions vary in size, shape, and location for different patients and make the manual detection time consuming and sensitive to the experience of the observer. Automatic segmentation of FCD lesions is challenging due to the difference in signal strength in images acquired with different machines, noise, and other kinds of distortions such as motion artifacts. Most of the methods proposed in the literature use conventional machine learning and image processing techniques in which their accuracy relies on the trained features. Hence, feature extraction should be done more precisely which requires human expertise. The ability to learn the appropriate features/representations from the training data without any human interventions makes the convolutional neural network (CNN) the suitable method for addressing these drawbacks. As far as we are aware, this work is the first one to use a CNN based model to solve the aforementioned problem using only MRI FLAIR images. We customized the popular U-Net architecture and trained the proposed model from scratch (using MRI images acquired with 1.5T and 3T scanners). FCD detection rate (recall) of the proposed model is 82.5 (33/40 patients detected correctly). © 2019Item Reducing the effect of wrist variation on pattern recognition of Myoelectric Hand Prostheses Control through Dynamic Time Warping(Elsevier Ltd, 2020) Powar, O.S.; Chemmangat, K.For upper limb prostheses, research carried out earlier mainly focused on increasing the classification accuracy of the hand movements; but there exist a little work done on factors affecting it in real-time control such as wrist variation. Amputees with functional wrist use their prostheses in multiple wrist positions. Since the Electromyography (EMG) data is taken while the subject is performing the motion in different wrist position, it can degrade the performance of the Pattern Recognition (PR) system. In this work, a wrist independent PR scheme has been developed. In this regard, Dynamic Time Warping (DTW) is used to overcome the effects due to wrist variation. The performance of the DTW scheme as a PR system is validated using two training methods; with classification accuracy as a performance measure on data taken from the database of ten intact subjects for six hand motions carried out at three different wrist orientations. On the database, an average classification accuracy of about 93.3% was obtained while trained using EMG data from all possible wrist positions. The effectiveness of the method is demonstrated in terms of classification accuracy and processing time when compared with the Time-domain power spectral descriptors (TD-PSD) method which outperformed other methods in the literature for reducing the impact of wrist variation on EMG based PR. The results show that the DTW can be a computationally cheap and accurate PR system for real-time hand movement classification. © 2019 Elsevier LtdItem NucleiSegNet: Robust deep learning architecture for the nuclei segmentation of liver cancer histopathology images(Elsevier Ltd, 2021) Lal, S.; Das, D.; Alabhya, K.; Kanfade, A.; Kumar, A.; Kini, J.R.The nuclei segmentation of hematoxylin and eosin (H&E) stained histopathology images is an important prerequisite in designing a computer-aided diagnostics (CAD) system for cancer diagnosis and prognosis. Automated nuclei segmentation methods enable the qualitative and quantitative analysis of tens of thousands of nuclei within H&E stained histopathology images. However, a major challenge during nuclei segmentation is the segmentation of variable sized, touching nuclei. To address this challenge, we present NucleiSegNet - a robust deep learning network architecture for the nuclei segmentation of H&E stained liver cancer histopathology images. Our proposed architecture includes three blocks: a robust residual block, a bottleneck block, and an attention decoder block. The robust residual block is a newly proposed block for the efficient extraction of high-level semantic maps. The attention decoder block uses a new attention mechanism for efficient object localization, and it improves the proposed architecture's performance by reducing false positives. When applied to nuclei segmentation tasks, the proposed deep-learning architecture yielded superior results compared to state-of-the-art nuclei segmentation methods. We applied our proposed deep learning architecture for nuclei segmentation to a set of H&E stained histopathology images from two datasets, and our comprehensive results show that our proposed architecture outperforms state-of-the-art methods. As part of this work, we also introduced a new liver dataset (KMC liver dataset) of H&E stained liver cancer histopathology image tiles, containing 80 images with annotated nuclei procured from Kasturba Medical College (KMC), Mangalore, Manipal Academy of Higher Education (MAHE), Manipal, Karnataka, India. The proposed model's source code is available at https://github.com/shyamfec/NucleiSegNet. © 2020 Elsevier LtdItem An effective feature extraction with deep neural network architecture for protein-secondary-structure prediction(Springer, 2021) Jayasimha, A.; Mudambi, R.; Pavan, P.; Lokaksha, B.M.; Bankapur, S.; Patil, N.With the increased importance of proteins in day-to-day life, it is imperative to know the protein functions. Deciphering protein structure elucidates protein functions. Experimental approaches for protein-structure analysis are expensive and time-consuming, and require high dexterity. Thus, finding a viable computational approach is vital. Due to the high complexity of predicting protein structure (tertiary structure) directly, research in this field aims at the protein-secondary-structure prediction which is directly related to its tertiary structure. This research aims at exploring a plethora of features, namely position-specific scoring matrices, hidden Markov model alignment matrices, and physicochemical properties, that carry rich information required to predict the secondary structure. Furthermore, it aims at exploring a suitable combination of the features which could capture diverse information about the protein secondary structure. Finally, a cascaded convolutional neural network and bidirectional long short-term memory architecture is fit on the models, and two evaluation metrics, namely, Q8 score and segment overlap score, are benchmarked on various datasets. Our proposed model trained on data of CB6133 dataset and tested on CB513 dataset beats the benchmark models by a minimum of 2.9%. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.Item Swarm optimisation-based bag of visual words model for content-based X-ray scan retrieval(Inderscience Publishers, 2022) Karthik, K.; Kamath S․, S.Classification and retrieval of medical images (MedIR) are emerging applications of computer vision for enabling intelligent medical diagnostics. Medical images are multi-dimensional and require specialised processing for the extraction of features from their manifold underlying content. Existing models often fail to consider the inherent characteristics of data and have thus often fallen short when applied to medical images. In this paper, we present a MedIR approach based on the bag of visual words (BoVW) model for content-based medical image retrieval. When it comes to any medical approach models, an imbalance in the dataset is one of the issues. Hence the perspective is also considering a balanced set of categories from an imbalanced dataset. The proposed work on BoVW model extracts features from each image are used to train supervised machine learning classifier for X-ray medical image classification and retrieval. During the experimental validation, the proposed model performed well with the classification accuracy of 89.73% and a good retrieval result using our filter-based approach. © © 2022 Inderscience Enterprises Ltd.Item Automated hard exudate segmentation using neural encoders and attention mechanisms for diabetic retinopathy diagnosis(Inderscience Publishers, 2023) Gawas, P.; Sowmya Kamath, S.Diabetic retinopathy (DR) is a complication caused by increased blood glucose levels, which causes retinal damage in diabetic patients’ eyes. If not discovered and treated early, it can lead to vision loss. Hard exudates (HE) are one of its characteristic signs. Identification of HE is a paramount step in early diagnosis of DR. In this work, the suitability of U-Net-based deep CNN with different encoder configurations and attention gates (AG) is experimented, for HE segmentation. The proposed models were benchmarked on the standard IDRiD dataset. To overcome the challenges related to the limited dataset, data augmentation techniques were also applied to generate image patches and used for model training. Extensive experiments on the dataset revealed that U-Net with AG achieved an accuracy of 98.8%. The U-Net with ResNet50 as the encoder backbone achieved an accuracy of 98.64%. The findings show that the presented models are effective and suitable for early-stage clinical diagnosis. © © 2023 Inderscience Enterprises Ltd.Item A novel procedure to automate the removal of PLI and motion artifacts using mode decomposition to enhance pattern recognition of sEMG signals for myoelectric control of prosthesis(Institute of Physics, 2024) Kumar Koppolu, P.; Chemmangat, K.Hand Movement Recognition (HMR) with sEMG is crucial for artificial hand prostheses. HMR performance mostly depends on the feature information that is fed to the classifiers. However, sEMG often captures noise like power line interference (PLI) and motion artifacts. This may extract redundant and insignificant feature information, which can degrade HMR performance and increase computational complexity. This study aims to address these issues by proposing a novel procedure for automatically removing PLI and motion artifacts from experimental sEMG signals. This will make it possible to extract better features from the signal and improve the categorization of various hand movements. Empirical mode decomposition and energy entropy thresholding are utilized to select relevant mode components for artifact removal. Time domain features are then used to train classifiers (kNN, LDA, SVM) for hand movement categorization, achieving average accuracies of 92.36%, 93.63%, and 98.12%, respectively, across subjects. Additionally, muscle contraction efforts are classified into low, medium, and high categories using this technique. Validation is performed on data from ten subjects performing eight hand movement classes and three muscle contraction efforts with three surface electrode channels. Results indicate that the proposed preprocessing improves average accuracy by 9.55% with the SVM classifier, significantly reducing computational time. © 2024 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.Item Ensemble Machine Learning Approaches for Automated Fungal Keratitis Diagnosis Using In Vivo Confocal Microscopy Images(John Wiley and Sons Inc, 2025) Sowmya Kamath, S.; Reji, S.; Vaibhava Lakshmi, V.; Supreetha, S.; Gawas, P.; Mayya, V.; Hazarika, M.Fungal keratitis (FK) is a severe ocular infection that can lead to significant vision problems or blindness if not diagnosed and treated promptly. Early and accurate detection of FK is essential for effective management. Traditional diagnostic methods are often time-consuming and require specialized laboratory resources. Recently, advances in artificial intelligence and computer vision have enabled automated diagnosis of FK using slit-lamp images. In this article, a comprehensive evaluation of state-of-the-art techniques adopted for classifying FK using in vivo confocal microscopy (IVCM) images is presented. Detailed experiments and performance evaluation of various machine learning models are systematically performed, with a focus on evaluating the effect of diverse techniques for image processing, data augmentation, hyperparameters and model finetuning to assess each model's strengths and limitations. Experiments revealed that applying green channel preprocessing with a 12-feature set achieved 99% accuracy using Random Forest, highlighting its effectiveness in FK detection, while complex techniques like histogram modelling reduced accuracy to 64%. Robust models like AdaBoost and RUSBoost maintained high F1-scores, demonstrating adaptability to imbalanced medical datasets, and to real-world clinical scenarios. © 2025 The Author(s). Healthcare Technology Letters published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.Item Improving the performance of multi-stage HER2 breast cancer detection in hematoxylin-eosin images based on ensemble deep learning(Elsevier Ltd, 2025) Pateel, G.P.; Senapati, K.; Pandey, A.K.Background: Breast cancer is the most frequently diagnosed cancer among women worldwide, and histopathology is the gold standard in diagnosing the disease. Hematoxylin and Eosin (HE) staining, routinely employed to observe the overall tissue structure, is an affordable and commonly practiced cancer diagnosis. In contrast, Immunohistochemistry (IHC), which detects the increased presence of particular antigens linked to the mutation, can require multiple tests to conduct and is relatively costly. Generally, in computer-aided diagnosis, the conventional methods rely on a single network to extract features. However, these methods have significant limitations and fail to generalize. Methods: In this study, we propose an automated novel weighted average algorithm called HER2-ETNET, which ensembles the chosen three pre-trained deep learning models, DenseNet 201, GoogLeNet, and ResNet-50, to classify breast histopathology HE images into multi-class Human Epidermal Growth Factor Receptor-2 (HER2) status (HER2-0+, HER2-1+, HER2-2+, HER2-3+). The proposed method has the potential to bypass the IHC laboratory test. In this study, we form a weight matrix by fusing together, the scores of False Positive Rate (FPR) and False Negative Rate (FNR) of both training and validation sets, and the computed weights are assigned to the three base learners. This is in contrast to the previous works, in which the weights were generally assigned empirically to the chosen deep learning models, which might be erroneous. Result: The proposed approach is evaluated on the unseen test set, and it achieves accuracy, precision, recall and AUC of 97.44%, 97.32%, 97.39%, and 99.75% respectively. Conclusion: The proposed framework outperforms all the existing methods on the same dataset and is proven to be the reliable method in detecting the HER2 status (HER2-0+, HER2-1+, HER2-2+, HER2-3+) from HE images. This also proves that, HE stained images contain adequate information for efficiently detecting the HER2 status in breast cancer. © 2024 Elsevier Ltd