T-MPEDNet: Unveiling the Synergy of Transformer-aware Multiscale Progressive Encoder-Decoder Network with Feature Recalibration for Tumor and Liver Segmentation

2025-07-25

AI Summary

To address the accuracy bottleneck in liver and tumor segmentation from CT images—caused by tumor heterogeneity and high anatomical variability of the liver—this paper proposes a novel framework integrating a multi-scale progressive encoder-decoder architecture with a Transformer-based dynamic attention mechanism. Key innovations include a channel-wise feature recalibration module to enhance discriminative representation learning, coupled with multi-scale feature fusion and morphologically guided boundary refinement to improve long-range contextual modeling and boundary localization precision. Evaluated on the LiTS and 3DIRCADb benchmarks, the method achieves Dice similarity coefficients of 97.6%/89.1% (liver/tumor) on LiTS and 98.3%/83.3% on 3DIRCADb—surpassing 12 state-of-the-art methods across all metrics. These results demonstrate substantial improvements in both robustness and segmentation accuracy, particularly for challenging tumor regions and irregular liver boundaries.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Precise and automated segmentation of the liver and its tumor within CT scans plays a pivotal role in swift diagnosis and the development of optimal treatment plans for individuals with liver diseases and malignancies. However, automated liver and tumor segmentation faces significant hurdles arising from the inherent heterogeneity of tumors and the diverse visual characteristics of livers across a broad spectrum of patients. Aiming to address these challenges, we present a novel Transformer-aware Multiscale Progressive Encoder-Decoder Network (T-MPEDNet) for automated segmentation of tumor and liver. T-MPEDNet leverages a deep adaptive features backbone through a progressive encoder-decoder structure, enhanced by skip connections for recalibrating channel-wise features while preserving spatial integrity. A Transformer-inspired dynamic attention mechanism captures long-range contextual relationships within the spatial domain, further enhanced by multi-scale feature utilization for refined local details, leading to accurate prediction. Morphological boundary refinement is then employed to address indistinct boundaries with neighboring organs, capturing finer details and yielding precise boundary labels. The efficacy of T-MPEDNet is comprehensively assessed on two widely utilized public benchmark datasets, LiTS and 3DIRCADb. Extensive quantitative and qualitative analyses demonstrate the superiority of T-MPEDNet compared to twelve state-of-the-art methods. On LiTS, T-MPEDNet achieves outstanding Dice Similarity Coefficients (DSC) of 97.6% and 89.1% for liver and tumor segmentation, respectively. Similar performance is observed on 3DIRCADb, with DSCs of 98.3% and 83.3% for liver and tumor segmentation, respectively. Our findings prove that T-MPEDNet is an efficacious and reliable framework for automated segmentation of the liver and its tumor in CT scans.

Problem

• Automated segmentation of liver and tumors in CT scans
• Addressing tumor heterogeneity and diverse liver characteristics
• Improving boundary precision in liver and tumor segmentation

Innovation

• Transformer-aware multiscale progressive encoder-decoder network
• Dynamic attention mechanism for long-range context
• Morphological boundary refinement for precise segmentation