Challa Veera Venkata Ramana

Diagnosing breast cancer with mammography continues to be an incidentally challenging process because of the numerous different ways of acquiring the images, the vast difference in appearance between lesions, and the minimal use of historical information regarding patients being considered when making a diagnosis. In addition, many current deep learning algorithms use static weight values based on the most recent image taken only, often failing to relate a current case to similar historical examples and to incorporate retrieval-based contextual evidence during inference. ViT-MultiRAGNet is a retrieval-augmented Vision Transformer framework designed to integrate multi-view 2D mammographic features with memory-bank-based contextual evidence from historically similar cases. The proposed approach enhances diagnostic accuracy by combining global 2D mammographic features, semantic lesion representations, and historical case evidence retrieved from a fold-wise memory bank during inference. Multi-view 2D mammograms were processed using a Vision Transformer encoder to extract global contextual features, while a retrieval-augmented memory bank was used to identify diagnostically similar historical cases for evidence-guided feature enrichment. A Retrieval-Augmented Generation (RAG) module retrieves the top-k most similar feature embeddings from a fold-wise training memory bank and combines them with the current query representation using multi-head cross-attention. The evaluation of the models included utilizing accuracy, area under the receiver operating curve (AUC-ROC), Dice Coefficient, and F1 score metrics at a 95% bootstrapped confidence interval using five-fold stratified cross-validation, with findings assessed using Wilcoxon signed-rank statistical tests. The accuracy of ViT-MultiRAGNet is calculated as a value of 0.978 ± 0.009 and AUC-ROC 0.998 ± 0.009 (Wilcoxon p < 0.01), which is significantly higher than unimodal benchmarks and fusion techniques on the RTM dataset. The calculations for the CBIS-DDSM evaluation were 0.961 ± 0.011 for accuracy and 0.989 ± 0.010 for AUC-ROC. The calculations for segmentation evaluation were 0.882 (RTM) and 0.795 (CBIS-DDSM), however both have a higher degree of alignment at the edge. The RAG mechanism improved retrieval-guided fusion compared with simple feature concatenation while maintaining efficient inference performance of 0.31 seconds per image. The combination of ViT-based global 2D mammographic representation, retrieval-augmented fusion, and memory-guided contextual evidence improves diagnostic performance, robustness, and clinical interpretability. This Framework appears to be a good candidate for an Evidence-based Decision Support System which will provide a transparent method of helping clinicians make decisions regarding screening and diagnosis of breast cancer.

The fundamental requirement for the initial recognition of a mammogram is the accurate segmentation and classification of breast lesions in mammograms, especially when small or hard-to-identify lesions are involved. We present here a methodology that uses statistical analysis of variability to upgrade the execution of automated detection of breast lesions through a new model, called LAM-CATNet (Lambda-Aware Multi-scale Cross-Attention Swin Transformer Network). LAM-CATNet is designed with the intent of creating a transformer fusion model that applies statistical intensity modelling with a distribution function for deriving the data from the mammogram as well as deriving features with deep learning to produce segmented mammograms and classify lesions based on that segmentation. It is crucial to identify accurately and consistently segment breast cancer lesions that are detected in mammograms so that they can be detected early, particularly in small or difficult-to-identify cancers. This work examines statistical variability and improves diagnostic performance in automated breast lesion analysis with LAM-CATNet, a Lambda Distribution-Guided Transformer-Fused Hybrid Segmentation Network. As shown, the proposed LAM-CATNet outperformed both the baseline hybrid model and the conventional models by achieving Dice coefficients for the segmentation of 0.786 (CBIS-DDSM) and 0.869 (MIAS). For classification, the network achieved an accuracy of 94.7% and an area under the ROC curve of 98.2%. The attention map visualizations provided increased interpretability of the model regarding clinical decision confidence, as attention was focused on relevant areas of the lesion. In overall, LAM-CATNet improves automated breast lesion segmentation and classification by integrating transformer-based global context modelling along with conventional U-Net local feature extraction and lambda statistical principle. Its high interpretability for clinical use, consistent statistical reasoning, and high performance demonstrates potential as a supportive tool for computer-aided diagnosis, subject to further clinical validation in breast cancer screening using mammography.

Detecting and delineating renal lesions accurately remains a significant clinical problem due to the variety of kidney pathology and subtle differences in CT image interpretation. In this paper, we present the design of a next-generation hybrid model called GDT-SwinKid (Gamma Distribution-based Swin Transformer for Renal Lesions), which integrates the hierarchical feature attention mechanisms of Swin Transforms with a modified U-Net decoder and employs advanced statistical modeling (specifically through an adaptive Gamma distribution). The design of GDT-SwinKid allows for both precise extraction of fine details regarding kidney lesions, as well as achieving overall contextual awareness using cross-attention and Gamma-modulated feature refinement to address the drawbacks of existing approaches. Through extensive validation utilizing a large set of clinical datasets, GDT-SwinKid achieved better performance through segmentation and classification, obtaining Dice coefficients as high as 0.95, with AUC values approaching 0.99, when compared to leading transformers and convolutional models. An absolute improvement of 5–9% in Dice coefficient compared to conventional U-Net and Swin Transformer baselines, and an increase in AUC-ROC values approaching 0.99, outperforming existing hybrid and transformer-based methods on the same CT kidney dataset. The inclusion of explainable attention maps and deep supervision provides increased trust and accountability while enabling the rapid and robust integration of GDT-SwinKid into diagnostic pipelines for kidney imaging. GDT-SwinKid combines statistical sensitivity, hierarchical attention and clinical transparency to provide a new standard for automated kidney lesion analysis and to increase the reliability and use of newly developed AI techniques in renal imaging.

An low-voltage, solution-based spin cast-processed two-terminal bi-stable memory device was fabricated by using organic-inorganic-organic tri-layer structure (MEHPPV/ZnO/MEHPPV) onto indium tin oxide coated glass. Tri-layer device structure displayed the significant switching characteristics. The absence of degradation after 1 h retention test at 120 °C was noticed. The consistent memory behavior was noticed even after 50 cycles. Electron tunneling mechanism was utilized for describing switching mechanism of the device. The result emphasizes that the class of memory devices have been fabricated with organic-inorganic-organic nanocomposites, which has led to considerable research and development efforts to the scene of latent applications.