Anto Lourdu Xavier Raj Arockia Selvarathinam

Dr. Anto Lourdu Xavier Raj Arockia Selvarathinam

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 February 2026 in MethodsX
Verified
Journal Article
Open access
SRSannasi Chakravarthy S R
Sannasi Chakravarthy S R
HRHarikumar Rajaguru
Harikumar Rajaguru
Rajesh Kumar DhanarajRajesh Kumar Dhanaraj
Rajesh Kumar Dhanaraj
ASAnto Lourdu Xavier Raj Arockia Selvarathinam
Anto Lourdu Xavier Raj Arockia Selvarathinam
Dragan PamucarDragan Pamucar
Dragan Pamucar
Breast cancer remains the most prevalent malignancy among women worldwide. The timely detection of this cancer type is critical for improving survival outcomes. Despite advancements, mammogram classification using deep learning strategies still faces challenges. These include inter-view feature inconsistency, loss of diagnostic details, and limited interpretability. In order to address these issues, MammoFusion-Net, a dual-branch deep learning framework, is proposed for mammogram-based breast cancer classification. Using residual convolutional streams, the framework processes craniocaudal (CC) and mediolateral oblique (MLO) views independently. This supports preservation of view-specific anatomical information. In the proposed framework, a Gates Cross-View Fusion mechanism adaptively integrates features across views. As a result of experimental analysis, the proposed framework achieved 92.116 % (VinDr-Mammo dataset) and 95.556 % (INBreast dataset) of improved classification performance. • Employs a dual-branch architecture to independently process CC and MLO views using residual convolutional streams. • Integrates Gated Cross-View Fusion and attention mechanisms adaptively and refines multi-view features for stronger discrimination. • Demonstrates the explainability of the model through Grad-CAM visualizations that highlight lesion-relevant regions.

8 July 2026 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
STSandeep Kumar Thota
Sandeep Kumar Thota
ULUmesh Kumar Lilhore
Umesh Kumar Lilhore
SSSumitra Sureliya
Sumitra Sureliya
ASAnto Lourdu Xavier Raj Arockia Selvarathinam
Anto Lourdu Xavier Raj Arockia Selvarathinam
ARA Rasmi
A Rasmi
SSSarita Simaiya
Sarita Simaiya
Automated analysis of cervical cytology images remains challenging due to substantial variability in cell morphology, staining quality, and imaging conditions, as well as the difficulty of simultaneously capturing global contextual relationships, fine-grained cellular morphology, and spatial dependencies among neighbouring cells. While recent deep learning approaches have explored convolutional neural networks, transformers, and hybrid architectures, many existing models rely on single attention mechanisms or static feature fusion, limiting their ability to jointly represent contextual and morphological cues. This study presents a hybrid deep learning framework that integrates Swin Transformer V2, EfficientNetV2-S, and a Dual-Attention BiLSTM module to enhance cervical cell classification performance. The Swin Transformer V2 component employs hierarchical shifted-window self-attention, enabling efficient modeling of long-range contextual relationships across cellular regions, while EfficientNetV2-S captures fine-grained nuclear and cytoplasmic morphological features through computationally efficient convolutional encoding. To complement these representations, a Dual-Attention BiLSTM module is introduced to model spatial–sequential dependencies among neighbouring feature embeddings while simultaneously emphasizing diagnostically relevant spatial regions and feature channels. This design enables more discriminative characterization of complex cytological structures compared with conventional hybrid architectures. The proposed hybrid model was systematically evaluated across five benchmark datasets SipakMed, Herlev, ISBI 2014, Mendeley LBC, and the recently introduced RIVA (2025) collectively comprising more than 22,800 annotated cervical cell instances from both conventional Pap smear and liquid-based cytology preparations. Extensive cross-dataset experiments demonstrate consistent improvements in classification accuracy and strong generalization across heterogeneous imaging conditions and acquisition protocols. In addition, interpretability analyses using attention visualization techniques indicate that the model focuses on clinically meaningful nuclear and cytoplasmic regions. Overall, the proposed framework provides a robust and interpretable approach for automated cervical cytology analysis and offers a scalable foundation for future AI-assisted cervical cancer screening and digital pathology applications.

2 March 2026 in International Journal of Computational Intelligence Systems
Verified
Journal Article
Open access
PDF file
ULUmesh Kumar Lilhore
Umesh Kumar Lilhore
SSSarita Simaiya
Sarita Simaiya
GNG. Lakshmi Narayanan
G. Lakshmi Narayanan
ASAnto Lourdu Xavier Raj Arockia Selvarathinam
Anto Lourdu Xavier Raj Arockia Selvarathinam
ARA. Rasmi
A. Rasmi
HGHeba Gaber
Heba Gaber
Ovarian cancer is often diagnosed at later stages due to subtle symptoms and complex imaging, resulting in lower survival rates. This study proposes a novel cloud-based deep learning framework for early ovarian cancer detection using the using the UBC-OCEAN histopathology dataset, which consists of Hematoxylin and Eosin (H&E)–stained ovarian cancer tissue images acquired as Whole Slide Images (WSIs) and Tissue Microarrays (TMAs). Our hybrid model combines Convolutional Neural Networks (CNNs), Transformers, and Graph Neural Networks (GNNs) to capture detailed local features, understand long-range relationships, and identify spatial tumor patterns. The CNN focuses on feature extraction, the Transformer captures contextual relationships, and the GNN highlights spatial connections between lesions. This multi-stage approach significantly improves the detection of small and difficult-to-identify malignant patterns in histopathological images. The system operates on a secure cloud platform, ensuring real-time processing of high-resolution medical images. Patient data is protected using AES-256 encryption, TLS for secure data transfer, and two-factor authentication (2FA) for access control. Federated Learning enables collaborative model training across institutions while maintaining data privacy and compliance with HIPAA and GDPR. Our model achieves exceptional performance with a sensitivity of 98.43% and specificity of 98.71%, outperforming existing models like ResNet-50, VGG16, and InceptionV3. Additionally, the security framework blocks 99.49% of unauthorized access, ensuring robust data protection. This research demonstrates the potential of integrating hybrid deep learning methods with secure cloud systems for the early detection of ovarian cancer in clinical settings.