English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate lung nodule segmentation is crucial for early-stage lung cancerdiagnosis, as it can substantially enhance patient survival rates. Computedtomography (CT) images are widely employed for early diagnosis in lung noduleanalysis. However, the heterogeneity of lung nodules, size diversity, and thecomplexity of the surrounding environment pose challenges for developing robustnodule segmentation methods. In this study, we propose an efficient end-to-endframework, the multi-encoder-based self-adaptive hard attention network(MESAHA-Net), for precise lung nodule segmentation in CT scans. MESAHA-Netcomprises three encoding paths, an attention block, and a decoder block,facilitating the integration of three types of inputs: CT slice patches,forward and backward maximum intensity projection (MIP) images, and region ofinterest (ROI) masks encompassing the nodule. By employing a novel adaptivehard attention mechanism, MESAHA-Net iteratively performs slice-by-slice 2Dsegmentation of lung nodules, focusing on the nodule region in each slice togenerate 3D volumetric segmentation of lung nodules. The proposed framework hasbeen comprehensively evaluated on the LIDC-IDRI dataset, the largest publiclyavailable dataset for lung nodule segmentation. The results demonstrate thatour approach is highly robust for various lung nodule types, outperformingprevious state-of-the-art techniques in terms of segmentation accuracy andcomputational complexity, rendering it suitable for real-time clinicalimplementation.

MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan