Information Systems, Computer Science, Computer Engineering
58
Scopus Publications
3245
Scholar Citations
18
Scholar h-index
26
Scholar i10-index
Scopus Publications
Explainable vision transformer framework for multi-class classification and prognostic interpretation of oral cancer in histopathology images Chandrakanta Mahanty, Chin-Shiuh Shieh, Mong-Fong Horng, Anusha Nallamalla, S Gopal Krishna Patro, Shafat Khan, Trmesgen Engida Discover Oncology, 2026 Oral cancer, particularly Oral Squamous Cell Carcinoma (OSCC), remains a major global health concern due to its high prevalence, late diagnosis, and limited prognostic precision in conventional histopathological evaluation. Although deep learning has been showing promising results in automated cancer classification, most current models, especially CNN-based architectures, generally lack interpretability, generalization capability, and prognostic insight, hence limiting their clinical applicability. To address these shortcomings, this work introduces an Explainable Vision Transformer framework (MMX-ViT) for multi-class classification and prognostic interpretation of oral cancer in histopathology images. The proposed model fuses convolutional feature extraction with transformer-based global attention using an Adaptive Cross-Fusion Module (ACFM), allowing efficient multi-scale learning of cellular and tissue-level features. The MMX-ViT model was trained and evaluated on a publicly available oral cancer histopathology dataset, extended in this study into four diagnostic categories, and compared with eight state-of-the-art architectures. It reached a high classification performance of 98.45%, with an AUC of 0.99, thus surpassing all the baseline methods. Explainability analysis based on Grad-CAM + + , SHAP, and Transformer Attention Rollout techniques demonstrated that biologically relevant areas of attention were identified by the model, such as dysplastic nuclei, keratin pearls, and invasion zones in stroma, with an XCI (Explainability Consistency Index) value of 94%. The model proposed here represents a major progress towards the establishment of reliable and interpretable AI-based diagnosis of oral cancer.
A unified multi modal transformer framework for breast cancer recurrence prediction and survival analysis Saleem Malik, S. Gopal Krishna Patro, Ahmed Kateb Jumaah Al-Nussairi, Chandrakanta Mahanty, Mohamed Ghouse, Akila Thiyagarajan, Ahmed Adnan Hadi, Anwar Khan, Mohit Mittal, Amanuel Zewude Scientific Reports, 2026 Breast cancer recurrence prediction is an important feature of post-treatment therapy, requiring accurate identification of both recurrence risk and time-to-event outcomes. In this paper, we offer a unified deep learning system that jointly performs survival analysis and multi-class recurrence classification, enabling full risk stratification for breast cancer patients. The proposed model includes a Transformer-based survival module to estimate time-until-recurrence, and an attention-guided classification module to differentiate between second primary cancer, low-risk, and high-risk recurrence instances. A multi-modal dataset comprising clinical, molecular, demographic, and lifestyle data is created from established sources like METABRIC, GSE2034, GSE2990, BCSC, and the Breast Cancer Coimbra dataset. The model uses cross-modal feature fusion, autoencoder-based dimensionality reduction, and attention-based feature attribution for applicability and accessibility. Experimental results show better accuracy, precision, recall, and F1-score of 99.12%, 98.75%, 99.08%, and 98.91%, outperforming standard machine learning and survival models. This unified paradigm gives doctors a powerful, interpretable tool for early intervention and personalized breast cancer treatment.
PatchSight–ImmuneMap–LifeSpan as a unified AI framework for breast cancer diagnosis, immune profiling and prognostic prediction Ahmed Kateb Jumaah Al-Nussairi, Ali B. M. Ali, Saleem Malik, S Gopal Krishna Patro, Chandrakanta Mahanty, Kasim Sakran Abass, Iman Basheti, Adis Abebaw Dessalegn, Khursheed Muzammil, Sanjay Kumar Discover Oncology, 2026 Breast cancer diagnosis, immune cell profile, and survival forecasting are important but usually done separately, limiting clinical interpretation. This work combines histopathological diagnosis, immunological microenvironment analysis, and prognostic modeling into a data-driven pipeline. The proposed system involves three phases: PatchSight Classifier uses an optimized InceptionResNetV2 network with patch-based augmentation and transfer learning to classify benign and malignant breast tissue from the BreakHis dataset; ImmuneMap Detector uses Faster R-CNN on immunohistochemistry images from the LYSTO dataset to detect and quantify tumor-infiltrating lymphocytes; and LifeSpan Prognosticator integrates diagnostic and immune features. The PatchSight Classifier outperformed VGG-16, DenseNet-121, and baseline InceptionResNetV2 models with 98.76% accuracy and 0.98 F1-score at 400× magnification. ResNet-101’s ImmuneMap Detector had 98% detection accuracy and low lymphocyte counting inaccuracy. The LifeSpan Prognosticator identified survival-influencing biomarkers with a C-index above 0.90. This comprehensive computational pathology system improves diagnostic precision, immunological assessment, and survival prediction with interpretable, high-accuracy models. We provide end-to-end decision assistance for early detection, immunological assessment, and personalized breast cancer prognosis.
Leveraging retinal vessel segmentation for improved disease classification Rahul Ray, S Gopal Krishna Patro, Sudarson Jena, Atul Vikas Lakra, Mohammad Khishe, Mekhrbonu Rakhimova, Bakhodir Rakhimov Intelligence Based Medicine, 2026 This research study provides an accurate analysis of retinal disease detection on Fundus image vessel segmentation dataset (FIVEs) considering segmentation and classification task into the account. The development of an AI based application in ophthalmology can achieved by using FIVEs dataset due to it’s fined image resolution quality and precise annotations. ResUNet, U-Net, PSPNet and SegNet are the models being evaluated for the segmentation purpose. However, SegNet outperforms other models with efficient results of the highest mean intersection over union (Mean IoU) of 0.4558 and accuracy of 0.9335 and making it a best suitable model to perform this type of task. A custom designed convolutional neural network (CNN) outperformed other traditional models like VGG16, ResNet50, and EfficientNet with a classification accuracy of 91.6%, precision of 93%, recall rate of 0.88 and F1 score of 0.94. This demonstrates that the proposed model is most efficient in detecting and diagnosing different categories of retinal diseases. The novelty in this approach is the combined sophisticated methodology of segmentation and classification for a better accurate retinal diagnosis system. The performance of the classification model can be improved by the better features extracted from the segmentation task. This proposed study highlights the use of AI based solutions in the field of ophthalmic disease diagnosis and medical technologies can be considered for early treatment of detected disease. This proposed approach highlights the integration of both segmentation and classification task and achieves enhanced features extraction and gaining significant classification results as compared to previously proposed methodologies which concentrates on segmentation and classification task individually. • •Joint optimization of segmentation and classification • •SegNet achieved highest Mean IoU (0.4558) • •Custom CNN outperformed VGG16 and ResNet50 • •Achieved 0.94 F1-score in multiclass classification • •End-to-end intelligent diagnostic pipeline
TransFusion-BCNet: A transformer-driven multi-modal fusion and explainable deep learning framework for breast cancer diagnosis Ahmed Kateb Jumaah Al-Nussairi, Saleem Malik, Yasser Taha Alzubaidi, S Gopal Krishna Patro, Kasim Sakran Abass, Iman Basheti, Mohammad Khishe Intelligence Based Medicine, 2026 Most AI breast cancer detection systems use single-modality imaging algorithms, limiting clinical reliability. Early and accurate detection improves therapy and mortality. These challenges are addressed by Transformer-driven multi-modal fusion and explainable deep learning system, TransFusion-BCNet for breast cancer diagnosis. The framework consists of three parts. The TriFusion-Transformer (TriFT) performs three-tier fusion: intra-modality fusion across multiple mammogram views and imaging sources, inter-modality fusion combining mammogram, ultrasound, MRI, and clinical features, and decision-level fusion for robust outcome prediction. TriFT detects complicated connections across heterogeneous modalities, unlike classical fusion. Second, we present the FusionAttribution Map (FAMap), a dual-level interpretability mechanism that generates imaging data region-level saliency maps and modality-level contribution scores to evaluate input source influence. This openness helps clinicians understand where and which modality drives predictions. Third, the MetaFusion Optimizer (MFO) adjusts fusion weights, network depth, and learning parameters via evolutionary search and gradient-based fine-tuning. Traditional optimizers lack model generalization and training stability. This staged technique improved both. TransFusion-BCNet outperforms CNN–Transformer hybrids with 99.4% accuracy, 99.0% precision, 99.2% recall, and 99.1% F1-score in extensive CBIS-DDSM ,BUSI, TCGA-BRCA and RIDER Breast MRI datasets. With TriFT, FAMap, and MFO, TransFusion-BCNet provides a robust, transparent, and clinically interpretable diagnostic framework, improving AI in breast cancer screening and decision assistance. • Transformer-driven multi-tier fusion framework • Dual-level interpretability with FAMap • MetaFusion optimizer for stability and balance • State-of-the-art accuracy across multimodal datasets
A Sugeno-fuzzy integral fusion framework for brain tumor identification using transfer learning models Nikhil Govil, S Gopal Krishna Patro, Arabinda Dash, Ahmed Kateb Jumaah Al-Nussairi, Ahmed Adnan Hadi, Md. Amir, Samim Sherzod Computer Methods in Biomechanics and Biomedical Engineering Imaging and Visualization, 2026 Identification of a brain tumour is a very crucial task in medical diagnostics. It requires timely and accurate detection for effective treatment that improves the outcomes of patients. This challenge involves handling the variability and complexity of tumour imagery with high precision. The present work addresses these challenges by presenting a new framework that integrates TL with the Sugeno-Fuzzy Integral (SFI) for enhanced BT classification. Three different advanced TL models, namely ResNet-164, SqueezeNet, and DenseNet-201, will be used, combined with the SFI to aggregate their predictions for improving the accuracy of BT classification. For experimentation, two datasets are used: Dataset 1 consists of three tumour classes, namely glioma, pituitary, and meningioma, while Dataset 2 consists of four classes, adding the normal class. Preparation of the dataset included resizing, filtering, and balancing the dataset, followed by training and testing with a split of 70:30. Then, the developed model was tested on two MRI benchmark datasets, where classification accuracy of 99.19% was achieved for a three-class dataset and 98.92% for a four-class dataset, outperforming both individual and traditional ensemble models.
SailMutLoc: a sailfish-mutation enhanced optimization algorithm for student performance prediction Ashjan Hamad Alsabhan, Saleem Malik, S. Gopal Krishna Patro, Chandrakanta Mahanty, Ahmed Adnan Hadi, Mohamed Ghouse, Akila Thiyagarajan, Mohit Mittal, Mohammad Khishe Ain Shams Engineering Journal, 2026 Feature selection enables educational data mining provide personalised support and enhance student performance. When using high-dimensional educational datasets, traditional feature selection techniques have premature convergence and inadequate feature sets. Inefficient feature selection occurs when these algorithms don’t balance exploration and exploiting. We propose the SailMutLoc algorithm, an integrated optimization method based on sailfish behaviour and enhanced by mutation operators and local search, to address these issues. SailMutLoc combines the Sailfish Algorithm (SFA)’s global search with the SCM’s fine-tuning precision and mutation-driven exploration. Iterative Local Search (ILS) increases local optimization results. SailMutLoc explores feature space without local optimum solutions since mutation makes things unpredictable. In studies using real-world educational datasets, SailMutLoc outperformed standard approaches in classification accuracy, computing time, and feature quality. In educational data mining, SailMutLoc can handle vast feature spaces and improve student performance forecasts.
Ransomware Threat Detection Using Machine Learning Techniques Anchal Singh, Simar Preet Singh, Deepika Sharma, S. Gopal Krishna Patro 2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
Enhanced Machine Learning Techniques of PCOS Hormonal Prediction Vijaya Bharathi Manjeti, Sowmya Sri Gorrepati, Sai Srikar Machiraju, Rohita Gottumukkala, A Bhagavan Venkata Sri Sai Apuroop., S. Gopal Krishna Patro 2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
Enhancing Security in SDLC with DevOps Tools and Practices Vijaya Bharathi Manjeti, Sohith Penumajji, Srija Reddy Patlolla, Yogeswara Sai Srinath Abburi, Jayavardhan Teppala, S. Gopal Krishna Patro 2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
A Novel DCGAN-Based Approach for High-Quality Cartoon Avatar Generation Rakesh Salakapuri, S Gopal Krishna Patro, Adarsh Shetkar, Panduranga Vital Terlapu, Siva Naga Raju B, Nagaratna P Hegde 2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
Enhancing Financial Forecasting with a Hybrid LSTM-Graph Neural Network Model Chinnakamanam Ranjith Kumar, Bhawani Sankar Panigrahi, Abdul Sattar, Puttagunta Karthikeya, A Para Brama Reddy, Biswajit Brahma, Shibani Tripathy, S. Gopal Krishna Patro 2025 International Conference on Next Generation of Green Information and Emerging Technologies Giet 2025, 2025
A Sugeno-fuzzy integral fusion framework for brain tumor identification using transfer learning models N Govil, SGK Patro, A Dash, AKJ Al-Nussairi, AA Hadi, M Amir, S Sherzod Computer Methods in Biomechanics and Biomedical Engineering: Imaging … , 2026 2026
Leveraging Retinal Vessel Segmentation for Improved Disease Classification R Ray, SGK Patro, S Jena, AV Lakra, M Khishe, M Rakhimova, ... Intelligence-Based Medicine, 100391 , 2026 2026
Explainable vision transformer framework for multi-class classification and prognostic interpretation of oral cancer in histopathology images C Mahanty, CS Shieh, MF Horng, A Nallamalla, S Patro, S Khan, T Engida Discover Oncology , 2026 2026
A unified multi modal transformer framework for breast cancer recurrence prediction and survival analysis S Malik, SGK Patro, AKJ Al-Nussairi, C Mahanty, M Ghouse, ... Scientific Reports , 2026 2026 Citations: 1
Weed Detection Approach for Soybeans Using Fuzzy Ensemble and Image Similarity GVS Narayana, SK Kuanar, P Patel, SGK Patro, AO Salau Journal of Crop Health 78 (1), 20 , 2026 2026
PatchSight–ImmuneMap–LifeSpan as a unified AI framework for breast cancer diagnosis, immune profiling and prognostic prediction AKJ Al-Nussairi, ABM Ali, S Malik, SGK Patro, C Mahanty, KS Abass, ... Discover Oncology , 2026 2026 Citations: 1
TransFusion-BCNet: A Transformer-Driven Multi-Modal Fusion and Explainable Deep Learning Framework for Breast Cancer Diagnosis AKJ Al-Nussairi, S Malik, YT Alzubaidi, SGK Patro, KS Abass, I Basheti, ... Intelligence-Based Medicine, 100346 , 2026 2026
SailMutLoc: a sailfish-mutation enhanced optimization algorithm for student performance prediction AH Alsabhan, S Malik, SGK Patro, C Mahanty, AA Hadi, M Ghouse, ... Ain Shams Engineering Journal 17 (1), 103898 , 2026 2026 Citations: 2
Design of an Improved Model Using Hybrid Swarm Optimization Capsule Networks and Quantum Inspired Spiking Neural Networks for Multi-Modal Prostate Cancer Diagnosis S Pathy, NK Rout, N Parida, D Dansana, SGK Patro 2025 OITS International Conference on Information Technology (OCIT), 58-62 , 2025 2025
Stacking Ensemble Learning for Reliable Brain Tumor Diagnosis Using MRI and Deep Transfer Models S Tripathy, MG Kakita, C Mahanty, SGK Patro 2025 OITS International Conference on Information Technology (OCIT), 930-935 , 2025 2025
Dynamic Hybrid Recommendation Approach for Improving Accuracy in E-Commerce with Limited User Data SGK Patro Next-Generation Computing Systems and Technologies 1 (2), 62-78 , 2025 2025
Corrigendum to “A new method for prediction of Vigna mungo millet disease based on deep learning”[Curr. Plant Biol. 44 (2025) 100562] R Kumar, C Mahanty, BS Panigrahi, SGK Patro, TM Tuan, LH Son Current Plant Biology, 100574 , 2025 2025
Predicting Drug Shortages for Healthcare Supply Chain Optimization Using Machine Learning A Gujjari, S Ramasubbareddy, P Srilatha, SGK Patro 2025 Eighth International Conference on Image Information Processing (ICIIP … , 2025 2025
LS-BMO-HDBSCAN as a hybrid memetic bacterial intelligence framework for efficient data clustering AKJ Al-Nussairi, AA Abdulazez, AA Hadi, S Malik, SGK Patro, C Mahanty, ... Scientific Reports 15 (1), 40686 , 2025 2025 Citations: 1
A new method for prediction of Vigna mungo millet disease based on deep learning R Kumar, C Mahanty, BS Panigrahi, SGK Patro, TM Tuan, LH Son Current Plant Biology, 100562 , 2025 2025
Graphene oxide (rGO) nano-particles: Removal of suspended solid wastes from wastewater and enhancement of soil fertility in millet fields SGK Patro, A Hota, H Sahu, FM Alfaisal, A Razak Journal of the Indian Chemical Society, 102181 , 2025 2025 Citations: 1
Quantum-Inspired gravitationally guided particle swarm optimization for feature selection and classification S Malik, SGK Patro, C Mahanty, A Lasisi, QN Naveed, A Buradi, AF Emma, ... Scientific Reports 15 (1), 34155 , 2025 2025 Citations: 8
Enhancing Security in SDLC with DevOps Tools and Practices VB Manjeti, S Penumajji, SR Patlolla, YSS Abburi, J Teppala, SGK Patro 2025 International Conference on Next Generation of Green Information and … , 2025 2025 Citations: 1
Enhancing Financial Forecasting with a Hybrid LSTM-Graph Neural Network Model CR Kumar, BS Panigrahi, A Sattar, P Karthikeya, APB Reddy, B Brahma, ... 2025 International Conference on Next Generation of Green Information and … , 2025 2025
Enhanced Machine Learning Techniques of PCOS Hormonal Prediction VB Manjeti, SS Gorrepati, SS Machiraju, R Gottumukkala, ... 2025 International Conference on Next Generation of Green Information and … , 2025 2025 Citations: 1
MOST CITED SCHOLAR PUBLICATIONS
Normalization: A Preprocessing Stage S Patro, KK Sahu arXiv preprint arXiv:1503.06462 , 2015 2015 Citations: 2364
A hybrid action-related K-nearest neighbour (HAR-KNN) approach for recommendation systems SGK Patro, BK Mishra, SK Panda, R Kumar, HV Long, D Taniar, ... IEEE Access 8, 90978-90991 , 2020 2020 Citations: 98
Artificial intelligence based modelling and hybrid optimization of linseed oil biodiesel with graphene nanoparticles to stringent biomedical safety and environmental standards PM Rao, SH Dhoria, SGK Patro, RK Gopidesi, MQ Alkahtani, S Islam, ... Case Studies in Thermal Engineering 51, 103554 , 2023 2023 Citations: 67
Machine and deep learning methods for concrete strength Prediction: A bibliometric and content analysis review of research trends and future directions R Kumar, E Althaqafi, SGK Patro, V Simic, A Babbar, D Pamucar, ... Applied Soft Computing 164, 111956 , 2024 2024 Citations: 60
Performance, Combustion, and Emission analysis of diesel engine fuelled with pyrolysis oil blends and n-propyl alcohol-RSM optimization and ML modelling KS Kumar, R Surakasi, SGK Patro, N Govil, MK Ramis, A Razak, ... Journal of Cleaner Production 434, 140354 , 2024 2024 Citations: 58
Analyzing the impact of loan features on bank loan prediction using R andom F orest algorithm D Dansana, SGK Patro, BK Mishra, V Prasad, A Razak, AW Wodajo Engineering Reports 6 (2), e12707 , 2024 2024 Citations: 54
Advancing educational data mining for enhanced student performance prediction: a fusion of feature selection algorithms and classification techniques with dynamic feature … S Malik, SGK Patro, C Mahanty, R Hegde, QN Naveed, A Lasisi, A Buradi, ... Scientific Reports 15 (1), 8738 , 2025 2025 Citations: 43
Cold start aware hybrid recommender system approach for E-commerce users SGK Patro, BK Mishra, SK Panda, R Kumar, HV Long, D Taniar Soft Computing 27 (4), 2071-2091 , 2023 2023 Citations: 43
Constructed wetland challenges for the treatment of industrial wastewater in smart cities: A sensitive solution A Hota, SGK Patro, AJ Obaid, S Khatak, R Kumar Sustainable Energy Technologies and Assessments 55, 102967 , 2023 2023 Citations: 37
Internet of medical things-based COVID-19 detection in CT images fused with fuzzy ensemble and transfer learning models C Mahanty, R Kumar, SGK Patro New Generation Computing 40 (4), 1125-1141 , 2022 2022 Citations: 37
Brain tumor classification using an ensemble of deep learning techniques SGK Patro, N Govil, S Saxena, BK Mishra, AT Zamani, AB Miled, ... IEEE Access 12, 162094-162106 , 2024 2024 Citations: 32
Technical Analysis on Financial Forecasting SGK Patro, PP Sahoo, I Panda, KK Sahu arXiv preprint arXiv:1503.03011 , 2015 2015 Citations: 30
Removing fluoride ions from wastewater by Fe3O4 nanoparticles: Modified Rhodophytes (red algae) as biochar A Hota, SGK Patro, SK Panda, MA Khan, MA Hasan, S Islam, M Alsubih, ... Journal of Water Process Engineering 58, 104776 , 2024 2024 Citations: 26
PETLFC: Parallel ensemble transfer learning based framework for COVID-19 differentiation and prediction using deep convolutional neural network models P Misra, N Panigrahi, S Gopal Krishna Patro, AO Salau, SS Aravinth Multimedia Tools and Applications 83 (5), 14211-14233 , 2024 2024 Citations: 26
Groundwater quality analysis and drinkability prediction using artificial intelligence N Panigrahi, SGK Patro, R Kumar, M Omar, TT Ngan, NL Giang, BT Thu, ... Earth Science Informatics 16 (2), 1701-1725 , 2023 2023 Citations: 25
Knowledge-based preference learning model for recommender system using adaptive neuro-fuzzy inference system SGK Patro, BK Mishra, SK Panda, R Kumar, HV Long, TM Tuan Journal of Intelligent & Fuzzy Systems 39 (3), 4651-4665 , 2020 2020 Citations: 24
Blockchain framework with IoT device using federated learning for sustainable healthcare systems B Bhasker, PM Rao, P Saraswathi, SGK Patro, JK Bhutto, S Islam, ... Scientific Reports 15 (1), 26736 , 2025 2025 Citations: 22
BSMACRN: Design of an efficient blockchain-based security model for improving attack-resilience of cognitive radio ad-hoc networks D Dansana, PK Behera, SGK Patro, QN Naveed, A Lasisi, AW Wodajo IEEE Access 12, 10047-10058 , 2024 2024 Citations: 19
BDDTPA: Blockchain-driven deep traffic pattern analysis for enhanced security in cognitive radio ad-hoc networks D Dansana, PK Behera, AA Darem, Z Ashraf, AT Zamani, MN Ahmed, ... Ieee Access 11, 98202-98216 , 2023 2023 Citations: 17
Deep feature extraction based cascading model for the classification of Fusarium stalk rot and charcoal rot disease in maize plant A Dash, PK Sethy, SGK Patro, AO Salau Informatics in Medicine Unlocked 42, 101363 , 2023 2023 Citations: 14
