CAAF-ResUNet: Adaptive Attention Fusion with Boundary-Aware Loss for Lung Nodule Segmentation

• 出版年: Medicina
• 主要な著者: Thang Quoc Pham, Thai Hoang Le, Khai Dinh Lai, Dat Quoc Ngo, Tan Van Pham, Quang Hong Hua, Khang Quang Le, Huyen Duy Mai Le, Tuyen Ngoc Lam Nguyen
• フォーマット: 論文
• 言語: 英語
• 出版事項: MDPI AG 2025-06-01
• 主題: lung nodule segmentation; adaptive attention controller; adaptive attention fusion; boundary-aware loss functions
• オンライン･アクセス: https://www.mdpi.com/1648-9144/61/7/1126
• ISSN: 1010-660X; 1648-9144

<i>Background and Objectives</i>: The accurate segmentation of pulmonary nodules in computed tomography (CT) remains a critical yet challenging task due to variations in nodule size, shape, and boundary ambiguity. This study proposes CAAF-ResUNet (Context-Aware Adaptive Attention Fusion ResUNet), a novel deep learning model designed to address these challenges through adaptive feature fusion and edge-sensitive learning. <i>Materials and Methods</i>: Central to our approach is the Adaptive Attention Controller (AAC), which dynamically adjusts the contribution of channel and position attention based on contextual features in each input. To further enhance boundary localization, we incorporate three complementary boundary-aware loss functions: Sobel, Laplacian, and Hausdorff. <i>Results</i>: An extensive evaluation of two benchmark datasets demonstrates the superiority of the proposed model, achieving Dice scores of 90.88% on LUNA16 and 85.92% on LIDC-IDRI, both exceeding prior state-of-the-art methods. A clinical validation of a dataset comprising 804 CT slices from 35 patients at the University Medical Center of Ho Chi Minh City confirmed the model’s practical reliability, yielding a Dice score of 95.34% and a notably low Miss Rate of 4.60% under the Hausdorff loss configuration. <i>Conclusions</i>: These results establish CAAF-ResUNet as a robust and clinically viable solution for pulmonary nodule segmentation, offering enhanced boundary precision and minimized false negatives, two critical properties in early-stage lung cancer diagnosis and radiological decision support.