EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Impact of Voxel Normalization on a Machine Learning-Based Method: A Study on Pulmonary Nodule Malignancy Diagnosis Using Low-Dose Computed Tomography (LDCT)

Chia-Chi Hsiao, Chen-Hao Peng iD, Fu-Zong Wu iD, Da-Chuan Cheng iD

Diagnostics · 18.12.2023 · 13 (24) · 3690

DOI: 10.3390/diagnostics13243690 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 18.12.2023. Verfasst von Chia-Chi Hsiao und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Kaohsiung Veterans General Hospital, Kaohsiung 813414, Taiwan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kaohsiung Veterans General Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung cancer (LC) stands as the foremost cause of cancer-related fatality rates worldwide. Early diagnosis significantly enhances patient survival rate. Nowadays, low-dose computed tomography (LDCT) is widely employed on the chest as a tool for large-scale lung cancer screening. Nonetheless, a large amount of chest radiographs creates an onerous burden for radiologists. Some computer-aided diagnostic (CAD) tools can provide insight to the use of medical images for diagnosis and can augment diagnostic speed. However, due to the variation in the parameter settings across different patients, substantial discrepancies in image voxels persist. We found that different voxel sizes can create a compromise between model generalization and diagnostic efficacy. This study investigates the performance disparities of diagnostic models trained on original images and LDCT images reconstructed to different voxel sizes while making isotropic. We examined the ability of our method to differentiate between benign and malignant nodules. Using 11 features, a support vector machine (SVM) was trained on LDCT images using an isotropic voxel with a side length of 1.5 mm for 225 patients in-house. The result yields a favorable model performance with an accuracy of 0.9596 and an area under the receiver operating characteristic curve (ROC/AUC) of 0.9855. In addition, to furnish CAD tools for clinical application, future research including LDCT images from multi-centers is encouraged.

Schlagwörter

Stichwörter der Autor:innen

computer-aided diagnosisisotropic voxel reconstructionlung cancerlung nodule classificationradiomics

Autor:innen und Institutionen

  • Department of Radiology, Kaohsiung Veterans General Hospital, Kaohsiung 813414, Taiwan.
  • Department of Biomedical Imaging and Radiological Science, China Medical University, Taichung 40400, Taiwan.

ORCID-Profile: Chen-Hao Peng, Fu-Zong Wu, Da-Chuan Cheng

Förderung

  • Kaohsiung Veterans General Hospital

Zitieren

APA

Hsiao, C. C., Peng, C. H., Wu, F. Z., & Cheng, D. C. (2023). Impact of Voxel Normalization on a Machine Learning-Based Method: A Study on Pulmonary Nodule Malignancy Diagnosis Using Low-Dose Computed Tomography (LDCT). Diagnostics, 13(24), 3690. https://doi.org/10.3390/diagnostics13243690

Vancouver

Hsiao CC, Peng CH, Wu FZ, Cheng DC. Impact of Voxel Normalization on a Machine Learning-Based Method: A Study on Pulmonary Nodule Malignancy Diagnosis Using Low-Dose Computed Tomography (LDCT). Diagnostics. 2023;13(24):3690. doi:10.3390/diagnostics13243690

BibTeX
@article{Hsiao2023,
  author = {Hsiao, Chia-Chi and Peng, Chen-Hao and Wu, Fu-Zong and Cheng, Da-Chuan},
  title = {Impact of Voxel Normalization on a Machine Learning-Based Method: A Study on Pulmonary Nodule Malignancy Diagnosis Using Low-Dose Computed Tomography (LDCT)},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {24},
  pages = {3690},
  doi = {10.3390/diagnostics13243690}
}
Kostenlos starten →