DPCrossU-Net: a dual-branch parallel CNN–Transformer network for lung nodule segmentation - Takeaways - MDSpire

DPCrossU-Net: a dual-branch parallel CNN–Transformer network for lung nodule segmentation

  • By

  • Xiya Guan

  • Wen Zhu

  • Fangxiang Wu

  • June 9, 2026

Share

  • 1

    DPCrossU-Net is a dual-branch parallel encoder-decoder network that integrates CNN and Vision Transformer representations for lung nodule segmentation.

  • 2

    The network employs a Cross-Attentive Fusion module to combine local texture and global semantic features effectively.

  • 3

    Experiments on the LIDC-IDRI dataset show DPCrossU-Net achieves a Dice score of 85.89%, outperforming baseline U-Net models.

  • 4

    Multi-scale atrous convolutions enhance sensitivity to small nodules, while a Detail Context Fusion block improves boundary reconstruction.

  • 5

    DPCrossU-Net addresses the challenges of segmenting lung nodules by combining local detail and global context modeling in a unified framework.

Original Source(s)

DPCrossU-Net: a dual-branch parallel CNN–Transformer network for lung nodule segmentation

  • by Xiya Guan, Wen Zhu, Fangxiang Wu

  • June 9, 2026

Related Content

3D intratumoral heterogeneity-based quantitative score from chest CT for preoperative prediction of visceral pleural invasion in lung adenocarcinoma: a multicenter study

Case Report: Spontaneous Dissection of the Renal Pelvis and Ureter

Differential diagnosis of testicular embryonal rhabdomyosarcoma and testicular seminoma with enhanced CT: a retrospective study