TransDiff-HiSeg: An Adaptive Transformer-Diffusion Framework for Medical Image Segmentation in Sustainable Healthcare Pratishtha Verma, Hema Latha Undam, Naween Kumar, Surbhi Bhatia Khan, Oumaima Saidani, et al. Computational Intelligence, 2026 Medical image segmentation is pivotal in clinical diagnosis and treatment planning. However, conventional CNN‐based methods often struggle with capturing global context and handling noise, especially in complex or ambiguous anatomical regions. To address these limitations, we propose a hybrid framework that synergistically combines Transformer and diffusion models, capitalizing on their strengths in long‐range dependency modeling and denoising. In this work, we introduce TransDiff‐HiSeg, a novel Transformer‐guided Diffusion segmentation framework that integrates a conditioned diffusion model, binarized cross transformer, and adaptive feature fusion blocks. The framework comprises a parallel encoder built with convolution and transformer blocks for robust feature extraction and noise suppression, and a decoder of stacked convolutional blocks to reconstruct high‐resolution segmentation. Our model emphasizes sustainable healthcare by achieving improved segmentation accuracy with reduced computational overhead, making it suitable for long‐term clinical integration. Extensive experiments on multi‐organ and brain tumor segmentation tasks demonstrate that TransDiff‐HiSeg consistently outperforms state‐of‐the‐art methods, achieving superior Dice, Accuracy, and HD95 scores while maintaining a lightweight impact. These results validate the efficacy and sustainability of our approach in real‐world medical image segmentation scenarios.
Driving Digital Transformation in Quick Service Laboratory Supply Chains Through Statistical Anomaly Detection Saeed Alzahrani, Surbhi B. Khan, Mohammed Alojail, Nidhi Bhatia Transactions on Emerging Telecommunications Technologies, 2026 Quick Service Laboratories (QSL) provide the necessary diagnostic services that have to be performed within limited time frames and rely on coordinated solutions across its supply chain to operate successfully. The application of standard supply chain management approaches often fails to recognize the variable and unpredictable nature of QSL operations, which significantly contributes to stockouts, delays, or surplus inventory. This study looks into a different approach to the traditional methodologies of supply chain management by investigating the means when machine learning algorithms with the purpose of discovering anomalous behavior patterns are applied to QSL supply chain practices and generate value. In examining and evaluating the historical demand forecasting patterns, inventory levels, and operational performance metrics will be more easily identifiable as anomalous behaviors or dissenting levels such as demand spikes, unanticipated inventory shortfall levels, and atypical arrival patterns of inventory to generate disruption to laboratory operations. Machine learning models can be supervised or unsupervised to learn normal operation behaviors, and even detect anomalies in real time through model training. These models facilitate proactive interventions that would improve inventory management and distribution planning, as well as service delivery in general. When building on the results of our detection modeling, we found that machine learning anomaly detection could provide actionable suggestions and improved supply chain resiliency, and reduce stockouts and excess inventory, all while maintaining more controlled service levels. Our comparative evaluation of conventional monitoring and forecasting methods demonstrates superior capabilities over traditional methods in our results, by resorting to fully utilizing the complexity of simple linear and rare events found in QSL supply chains and their digital transformation story.
Improved Alzheimer's Detection with a Modified Multi-Focus Attention Mechanism using Computational Techniques Purushottam Kumar Pandey, Jyoti Pruthi, Surbhi Bhatia Khan, Nora A. Alkhaldi, Daniel Saraee Recent Patents on Engineering, 2026 Alzheimer disease is a common type of dementia which shrinks the brain cells and eventually causes death. It disturbs the life quality of patients with progressive symptoms such as memory loss, conversation, etc. It is vital to identify the disease earlier to get precise treatment. Besides, it is significant to locate the forms of Alzheimer's such as AD (Alzheimer Disease), CN (Cognitive Normal), and MCI (Mild Cognitive Impairment). Traditionally, manual screening of Alzheimer's is carried out by qualified physicians, which is a time-consuming mechanism, expensive, and prone to human error. To resolve the issue, several conventional researches attempted to attain better efficiency in the Alzheimer classification but were limited through accuracy, speed, and inefficacy. To address the challenge of classifying Alzheimer's in its various forms (AD, CN, and MCI), the proposed system utilizes the Modified Multi-Focus Attention and Hierarchical Scalerated Convolutional Neural Network (HSCN) mechanisms within the ResNet-101 model. The system undergoes testing with custom datasets such as OASIS, AIBL, and ADNI, and the classification performance is assessed using efficiency factors to gauge the effectiveness of the research. Background: Alzheimer is a century-old disease, still there is no concrete method to diagnose the disease. Many time diagnosis takes large time and the patient has been referred to many doctors. Objective: The objective of the study is to create a prediction model using deep learning which will be able to classify the patient into three different classes, CN, MCI,, and AD. The model is trained on hetero dataset, ADNI, AIBL,, and OASIS. Method: For the deep learning model, we have used Resnet 101 in which the convolution layer is changed to Hierarchical Scalerated CNN and the bottleneck layer is changed to modified multi-focus attention. The preprocessing of the image is also done as the initial step of process. Results: Our model accuracy is more than 99% for all three datasets used for the research. Conclusion: The model is trained for MRI from different datasets, the same model should be used for PET scans for Alzheimer's diagnosis, and the same model can be used to diagnose other disease patients which will be very useful for mankind.
