EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Improved Weighted Cross-Entropy-Based Convolutional Neural Network for Auxiliary Diagnosis of Pneumonia

Zhenyu Song, Zhanling Shi, Xuemei Yan, Bin Zhang, Shuangbao Song, Cheng Tang

Electronics · 24.07.2024 · 13 (15) · 2929

DOI: 10.3390/electronics13152929 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 24.07.2024. Verfasst von Zhenyu Song und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qinglan Project of Jiangsu Universities, Talent Development Project of Taizhou University, Natural Science Foundation of Jiangsu Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pneumonia has long been a significant concern in global public health. With the advancement of convolutional neural networks (CNNs), new technological methods have emerged to address this challenge. However, the application of CNNs to pneumonia diagnosis still faces several critical issues. First, the datasets used for training models often suffer from insufficient sample sizes and imbalanced class distributions, leading to reduced classification performance. Second, although CNNs can automatically extract features and make decisions from complex image data, their interpretability is relatively poor, limiting their widespread use in clinical diagnosis to some extent. To address these issues, a novel weighted cross-entropy loss function is proposed, which calculates weights via an inverse proportion exponential function to handle data imbalance more efficiently. Additionally, we employ a transfer learning approach that combines pretrained CNN model parameter fine-tuning to improve classification performance. Finally, we introduce the gradient-weighted class activation mapping method to enhance the interpretability of the model’s decisions by visualizing the image regions of focus. The experimental results indicate that our proposed approach significantly enhances CNN performance in pneumonia diagnosis tasks. Among the four selected models, the accuracy rates improved to over 90%, and visualized results were provided.

Förderung

  • Qinglan Project of Jiangsu Universities
  • Talent Development Project of Taizhou University
  • Natural Science Foundation of Jiangsu Province of China
  • Young Science and Technology Talent Support Project of Taizhou
  • National Natural Science Foundation of China

Zitieren

APA

Song, Z., Shi, Z., Yan, X., Zhang, B., Song, S., & Tang, C. (2024). An Improved Weighted Cross-Entropy-Based Convolutional Neural Network for Auxiliary Diagnosis of Pneumonia. Electronics, 13(15), 2929. https://doi.org/10.3390/electronics13152929

Vancouver

Song Z, Shi Z, Yan X, Zhang B, Song S, Tang C. An Improved Weighted Cross-Entropy-Based Convolutional Neural Network for Auxiliary Diagnosis of Pneumonia. Electronics. 2024;13(15):2929. doi:10.3390/electronics13152929

BibTeX
@article{Song2024,
  author = {Song, Zhenyu and Shi, Zhanling and Yan, Xuemei and Zhang, Bin and Song, Shuangbao and Tang, Cheng},
  title = {An Improved Weighted Cross-Entropy-Based Convolutional Neural Network for Auxiliary Diagnosis of Pneumonia},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {15},
  pages = {2929},
  doi = {10.3390/electronics13152929}
}
Kostenlos starten →