An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation

Proper segmentation of organs-at-risk is important for radiation therapy, surgical planning, and diagnostic decision-making in medical image analysis. While deep learning-based segmentation architectures have made significant progress, they often fail to balance segmentation accuracy with computational efficiency. Most of the current state-of-the-art methods either prioritize performance at the cost of high computational complexity or compromise accuracy for efficiency. This paper addresses this gap by introducing an efficient dual-line decoder segmentation network (EDLDNet). The proposed method features a noisy decoder, which learns to incorporate structured perturbation at training time for better model robustness, yet at inference time only the noise-free decoder is executed, leading to lower computational cost. Multi-Scale convolutional Attention Modules (MSCAMs), Attention Gates (AGs), and Up-Convolution Blocks (UCBs) are further utilized to optimize feature representation and boost segmentation performance. By leveraging multi-scale segmentation masks from both decoders, we also utilize a mutation-based loss function to enhance the model's generalization. Our approach outperforms SOTA segmentation architectures on four publicly available medical imaging datasets. EDLDNet achieves SOTA performance with an 84.00% Dice score on the Synapse dataset, surpassing baseline model like UNet by 13.89% in Dice score while significantly reducing Multiply-Accumulate Operations (MACs) by 89.7%. Compared to recent approaches like EMCAD, our EDLDNet not only achieves higher Dice score but also maintains comparable computational efficiency. The outstanding performance across diverse datasets establishes EDLDNet's strong generalization, computational efficiency, and robustness. The source code, pre-processed data, and pre-trained weights will be available at https://github.com/riadhassan/EDLDNet .

A Statistical Framework for Model Selection in LSTM Networks

Long Short-Term Memory (LSTM) neural network models have become the cornerstone for sequential data modeling in numerous applications, ranging from natural language processing to time series forecasting. Despite their success, the problem of model selection, including hyperparameter tuning, architecture specification, and regularization choice remains largely heuristic and computationally expensive. In this paper, we propose a unified statistical framework for systematic model selection in LSTM networks. Our framework extends classical model selection ideas, such as information criteria and shrinkage estimation, to sequential neural networks. We define penalized likelihoods adapted to temporal structures, propose a generalized threshold approach for hidden state dynamics, and provide efficient estimation strategies using variational Bayes and approximate marginal likelihood methods. Several biomedical data centric examples demonstrate the flexibility and improved performance of the proposed framework.

Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Media

Ethnic media, which caters to diaspora communities in host nations, serves as a vital platform for these communities to both produce content and access information. Rather than utilizing the language of the host nation, ethnic media delivers news in the language of the immigrant community. For instance, in the USA, Bangla ethnic media presents news in Bangla rather than English. This research delves into the prospective integration of large language models (LLM) and multi-lingual machine translations (MMT) within the ethnic media industry. It centers on the transformative potential of using LLM in MMT in various facets of news translation, searching, and categorization. The paper outlines a theoretical framework elucidating the integration of LLM and MMT into the news searching and translation processes for ethnic media. Additionally, it briefly addresses the potential ethical challenges associated with the incorporation of LLM and MMT in news translation procedures.