Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
8 results
Search Results
Item Image Analysis of Nuclei Histopathology Using Deep Learning: A Review of Segmentation, Detection, and Classification(Springer, 2023) Kadaskar, M.; Patil, N.Deep learning has recently advanced in its applicability to computer vision challenges, and medical imaging has become the most used technique in histopathology image analysis. Nuclei instance segmentation, detection, and classification are one such task. Reliable analysis of these image slides is critical in cancer identification, treatment, and care. Researchers have recently been interested in this issue. This study reviews the categorization and investigation of strategies utilized in recent works to improve the effectiveness of automated nuclei segmentation, detection, and classification in histopathology images. It critically examines state-of-the-art deep learning techniques, analyzes the trends, identifies the challenges, and highlights and helps with the future directions for research. The taxonomy includes deep learning techniques, enhancement, and optimization methods. The survey findings will help to overcome the challenges of nuclei segmentation, detection, and classification while improving the performance of models and, thus, aid future research plans. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item An enhanced protein secondary structure prediction using deep learning framework on hybrid profile based features(Elsevier Ltd, 2020) Kumar, P.; Bankapur, S.; Patil, N.Accurate protein secondary structure prediction (PSSP) is essential to identify structural classes, protein folds, and its tertiary structure. To identify the secondary structure, experimental methods exhibit higher precision with the trade-off of high cost and time. In this study, we propose an effective prediction model which consists of hybrid features of 42-dimensions with the combination of convolutional neural network (CNN) and bidirectional recurrent neural network (BRNN). The proposed model is accessed on four benchmark datasets such as CB6133, CB513, CASP10, and CAP11 using Q3, Q8, and segment overlap (Sov) metrics. The proposed model reported Q3 accuracy of 85.4%, 85.4%, 83.7%, 81.5%, and Q8 accuracy 75.8%, 73.5%, 72.2%, and 70% on CB6133, CB513, CASP10, and CAP11 datasets respectively. The results of the proposed model are improved by a minimum factor of 2.5% and 2.1% in Q3 and Q8 accuracy respectively, as compared to the popular existing models on CB513 dataset. Further, the quality of the Q3 results is validated by structural class prediction and compared with PSI-PRED. The experiment showed that the quality of the Q3 results of the proposed model is higher than that of PSI-PRED. © 2019 Elsevier B.V.Item Cardamom Plant Disease Detection Approach Using EfficientNetV2(Institute of Electrical and Electronics Engineers Inc., 2022) Sunil, C.K.; Jaidhar, C.D.; Patil, N.Cardamom is a queen of spices. It is indigenously grown in the evergreen forests of Karnataka, Kerala, Tamil Nadu, and the northeastern states of India. India is the third largest producer of cardamom. Plant diseases cause a catastrophic influence on food production safety; they reduce the eminence and quantum of agricultural products. Plant diseases may cause significantly high loss or no harvest in dreadful cases. Various diseases and pests affect the growth of cardamom plants at different stages and crop yields. This study concentrated on two diseases of cardamom plants, Colletotrichum Blight and Phyllosticta Leaf Spot of cardamom and three diseases of grape, Black Rot, ESCA, and Isariopsis Leaf Spot. Various methods have been proposed for plant disease detection, and deep learning has become the preferred method because of its spectacular accomplishment. In this study, U2-Net was used to remove the unwanted background of an input image by selecting multiscale features. This work proposes a cardamom plant disease detection approach using the EfficientNetV2 model. A comprehensive set of experiments was carried out to ascertain the performance of the proposed approach and compare it with other models such as EfficientNet and Convolutional Neural Network (CNN). The experimental results showed that the proposed approach achieved a detection accuracy of 98.26%. © 2013 IEEE.Item Utilizing Deep Learning Models and Transfer Learning for COVID-19 Detection from X-Ray Images(Springer, 2023) Agrawal, S.; Venkatesh, V.; Nara, M.; Patil, N.COVID-19 has been a global pandemic. Flattening the curve requires intensive testing, and the world has been facing a shortage of testing equipment and medical personnel with expertise. There is a need to automate and aid the detection process. Several diagnostic tools are currently being used for COVID-19, including X-Rays and CT-scans. This study focuses on detecting COVID-19 from X-Rays. We pursue two types of problems: binary classification (COVID-19 and No COVID-19) and multi-class classification (COVID-19, No COVID-19 and Pneumonia). We examine and evaluate several classic models, namely VGG19, ResNet50, MobileNetV2, InceptionV3, Xception, DenseNet121, and specialized models such as DarkCOVIDNet and COVID-Net and prove that ResNet50 models perform best. We also propose a simple modification to the ResNet50 model, which gives a binary classification accuracy of 99.20% and a multi-class classification accuracy of 86.13%, hence cementing the ResNet50’s abilities for COVID-19 detection and ability to differentiate pneumonia and COVID-19. The proposed model’s explanations were interpreted via LIME which provides contours, and Grad-CAM, which provides heat-maps over the area(s) of interest of the classifier, i.e., COVID-19 concentrated regions in the lungs, and realize that LIME explains the results better. These explanations support our model’s ability to generalize. The proposed model is intended to be deployed for free use. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item Tomato plant disease classification using Multilevel Feature Fusion with adaptive channel spatial and pixel attention mechanism(Elsevier Ltd, 2023) Sunil, C.K.; Jaidhar, C.D.; Patil, N.Agriculture's productivity has decreased in the last decade due to climate change and inappropriate usage of water, fertilizer, and pesticides, which stimulate plant diseases. Plant pathogens are the prime threat to agriculture; diseases causes the development of plant and affects the quality and yield of the crop. To enhance crop yield and quality, early perceive the pathogens and insinuation of the proper medications are essential. Deep learning approaches produce promising results for classifying the input images, and the results vary for many reasons, such as data imbalance and fewer or identical features among other classes of the dataset. In this work, tomato plant disease classification is proposed by using Multilevel Feature Fusion Network (MFFN). It employs ResNet50, MFFN, and Adaptive Attention Mechanism, which combines channel, spatial, and pixel attention to classify the tomato plant leaf images. The proposed deep learning-based approach is trained and tested on a tomato plant leaves dataset and achieved 99.88% training accuracy, 99.88% validation accuracy, and 99.83% external testing accuracy. It outperformed the existing approaches relevant to the tomato plant dataset. Further, this work also proposes a pesticide prescription module that provides pesticide information based on the type of leaf disease. © 2023 Elsevier LtdItem ANet: Nuclei Instance Segmentation and Classification with Attention-Based Network(Springer, 2024) Kadaskar, M.; Patil, N.The segmentation and classification of nuclei in haematoxylin and eosin-stained images is critical for diagnosing cancer and other disorders. Developing automated methods is necessary for the quantitative analysis of whole-slide images and further downstream analysis. However, many challenges are to be solved, such as varying morphology and observer differences. To address these concerns, we present ANet, an encoder–decoder structure based on attention mechanisms for nuclear segmentation and classification that makes use of information in high-dimensional features improved by attention. These blocks generate meaningful feature activation and eliminate irrelevant information to produce finer maps. It segments the touching, clustered, and overlapping nuclei and classifies them using upsampling branches. Our method includes components such as PreAct-ResNet50, residual attention, convolutional block attention module, and dense attention unit. We demonstrate how our approach achieves cutting-edge performance on several multi-tissue histopathology datasets such as Kumar, CoNSeP, and CPM17. We also demonstrate our model’s generalization capabilities on other combinations of datasets, including CPM15 and TNBC. ANet demonstrates a notable improvement of 1.14%, 2.70%, 1.41%, and 1.29% in Dice, AJI, SQ, and PQ scores, respectively, for the CPM17 dataset. In addition, it achieves a 1.18% improvement in AJI score for the Kumar dataset. Despite the inherent challenges in nuclei classification within the CoNSeP dataset, ANet yields outstanding results, showcasing a substantial improvement of 9.74%, 3.97%, and 0.80% in F1 scores for the inflammatory, spindle, and miscellaneous classes. Furthermore, ANet exhibits strong generalization across the CPM dataset, TNBC, and Combined CoNSeP, with improvements observed in the majority of metrics. The given improvement is justifiable, as are the interpretable visual results. The proposed method is of great potential for analyzing histopathology images, demonstrated by an increment of performance in multiple metrics. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.Item Detection of heart arrhythmia with electrocardiography(Springer, 2024) Jat, T.; Patil, N.; Bhat, P.Early detection of cardiac arrhythmia, a prevalent form of cardiovascular disease (CVD) impacting millions globally, is heavily reliant on the accurate analysis of heartbeats. Physicians often recommend that patients wear Holter monitors for 24 h or longer to observe concerning cardiac issues, resulting in the collection of substantial amounts of electrocardiogram (ECG) data. Consequently, there is a need to automate the process of interpreting ECGs to detect cardiac abnormalities efficiently. Current state-of-the-art studies rely on handcrafted feature extraction, which may not effectively capture the intricate temporal relationships inherent in ECG signal data. To address this limitation and facilitate the diagnosis of cardiac diseases, this study proposes a technique that converts electrocardiogram signals into images, subsequently training a deep learning model on the generated images. Image encoding techniques such as Gramian Angular Difference Field (GADF), Gramian Angular Summation Field (GASF) and Markov Transition Field (MTF) are employed to translate the ECG signals into images. The highest accuracy, 96.71%, was achieved by training the Convolutional Neural Network (CNN) model using the concatenation of these three image encoding techniques. The proposed approach is assessed using ECG recordings from the MIT-BIH Arrhythmia Database to detect heart arrhythmia, demonstrating the efficacy of the approach. © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2024.Item Class-Balanced Protein Interaction Site Prediction Using Global and Local Features with XGBoost and Deep Learning(Springer, 2025) Kulkarni, B.C.; Sai, B.S.; Kolagad, V.; Patil, N.; Bhat, P.Inter-protein interactions are critical in biological pathways. Determining the protein–protein interaction (PPI) sites is vital for comprehending protein behavior and designing medications. Traditional experimental protocols for pinpointing these sites are prolonged and costly, making computational approaches an efficient alternative. However, many computational methods fail to resolve the problem of class imbalance in PPI datasets and focus predominantly on local contextual features, ignoring global sequence information. In this work, we address class imbalance in PPI site prediction by applying a series of balancing techniques: selective thinning of the majority class, Tomek Links to remove noisy samples near the class boundary, and random augmentation of the minority class. We then further balance the data using Synthetic Minority Over-sampling Technique (SMOTE) and Generative Adversarial Networks (GANs), with GANs showing a slight edge in improving data quality and reducing noise. Our approach incorporates four key features: secondary structure, raw protein sequence, Position-Specific Scoring Matrix (PSSM), and Relative Solvent Accessibility (RSA). We use both nearby contextual and holistic sequence features for training two models: XGBoost and a Deep Neural Network (DNN). The performance of the models was assessed using accuracy, Matthews correlation coefficient (MCC), precision, recall, and F-score. We correlate the impact of using balanced versus unbalanced datasets and measure the share of global features in enhancing model performance. The findings demonstrate that class balancing significantly upgrades prediction performance. The XGBoost model realized an accuracy of 0.831 and precision of 0.417, outperforming the DNN in these metrics. The DNN model attained a higher recall of 0.723 and an F-score of 0.485, exemplifying its effectiveness in accurately detecting true PPI sites. Both models showcased a good MCC of 0.30, corroborating the effectiveness of the introduced balancing strategies and the assimilation of global features in robust PPI site prediction. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.