EUVIMEDEUVIMED entdecken
Crossref

Enhanced anchor‐free pulmonary nodule detection utilizing distribution prediction and task‐aligned learning strategies

Ling Ma, Yichen Ji, Jiaxin Lu, Xingyu Feng, Zhiqi Li, Tao Wei, Lizhi Liu, Shijie Zhao

Medical Physics · 2026-04 · 53 (4)

DOI: 10.1002/mp.70438 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 16.04.2026. Verfasst von Ling Ma und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Software, Nankai University, Tianjin, China. Hauptthemen laut MEDLINE: Lung Neoplasms, Multiple Pulmonary Nodules, Deep Learning, Imaging, Three-Dimensional. Die Arbeit nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Efficient lung cancer screening relies on the automated and precise detection of pulmonary nodules in computed tomography (CT) images. Conventional anchor‐based methodologies often rely on pre‐defined anchor boxes, resulting in complex design and constrained adaptability to nodules of varying sizes. In contrast, anchor‐free models, characterized by their simpler design, have garnered increasing interest. However, existing anchor‐free methods may suffer from spatial misalignment across tasks and limited adaptability to diverse nodule shapes.

Purpose

This study proposes a novel anchor‐free model, named DistAlignNet, which integrates distribution prediction and task‐aligned learning to address challenges such as spatial misalignment and the diversity of nodule shapes.

Methods

Our model utilizes a one‐stage object detection architecture, enabling automatic learning of nodule shapes without explicit anchor box definitions. The model is optimized for both classification and localization tasks. In the localization task, we incorporate distribution prediction to improve noise robustness and adapt to the distinctive shape patterns of each nodule. In addition, we introduce a task‐aligned learning strategy to mitigate inconsistencies between different tasks and dynamically adjust the label assignment process.

Results

Experimental evaluations were performed on the publicly available LUNA16 dataset, where our model achieved an average Competition performance metric (CPM) score of 0.924. Compared with the SCPM‐Net model that reported the strongest performance among the existing approaches, the statistical analysis yielded and , with a Cohen's of 1.582, reflecting a statistically significant improvement. These results show that our model achieves superior performance compared with state‐of‐the‐art anchor‐based and anchor‐free methods for pulmonary nodule detection.

Conclusions

Quantitative results and qualitative assessments demonstrate the effectiveness of our model, indicating its potential for clinical deployment in pulmonary nodule detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsMultiple Pulmonary NodulesDeep LearningImaging, Three-DimensionalTomography, X-Ray ComputedDatasets as TopicHumans

Stichwörter der Autor:innen

anchor‐free detectiondistribution predictionlung nodule detectiontask alignment learning

Autor:innen und Institutionen

  • College of Software, Nankai University, Tianjin, China.
  • Research and Development Institute of Northwestern Polytechnical University in Shenzhen, Shenzhen, China.
  • School of Automation, Northwestern Polytechnical University, Xi'an, Shaanxi, China.
  • Department of Radiology, Sun Yat-Sen University Cancer Center, Guangzhou, Guangdong, China.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation
  • Shenzhen Science and Technology Program
  • National Science and Technology Major Project of China
  • Science and Technology Support Project of Guizhou Province
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Shenzhen Science and Technology Innovation Program

Zitieren

APA

Ma, L., Ji, Y., Lu, J., Feng, X., Li, Z., Wei, T., Liu, L., & Zhao, S. (2026). Enhanced anchor‐free pulmonary nodule detection utilizing distribution prediction and task‐aligned learning strategies. Medical Physics, 53(4). https://doi.org/10.1002/mp.70438

Vancouver

Ma L, Ji Y, Lu J, Feng X, Li Z, Wei T, et al. Enhanced anchor‐free pulmonary nodule detection utilizing distribution prediction and task‐aligned learning strategies. Medical Physics. 2026;53(4). doi:10.1002/mp.70438

BibTeX
@article{Ma2026,
  author = {Ma, Ling and Ji, Yichen and Lu, Jiaxin and Feng, Xingyu and Li, Zhiqi and Wei, Tao and Liu, Lizhi and Zhao, Shijie},
  title = {Enhanced anchor‐free pulmonary nodule detection utilizing distribution prediction and task‐aligned learning strategies},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {4},
  doi = {10.1002/mp.70438}
}
Kostenlos starten →