Affiliations: [a] Radiology Department, Ninghai First Hospital Medicare and Health Group, Ningbo, China | [b] College of Digital Technology and Engineering, Ningbo University of Finance and Economics, Ningbo, China
Correspondence:
[*]
Corresponding author: Dongquan Liu, Radiology Department, Ninghai First Hospital Medicare and Health Group, Ningbo, China. E-mail: dongquan_liu77@outlook.com.
Note: [1] Note: This article received an addendum post publication with DOI: 10.3233/THC249001, available at http://doi.org/ 10.3233/THC-249001.
Abstract: BACKGROUND: Pulmonary nodule, one of the most common clinical phenomena, is an irregular circular lesion with a diameter of ⩽ 3 cm in the lungs, which can be classified as benign or malignant. Differentiating benign and malignant pulmonary nodules has an essential effect on clinical medical diagnosis. OBJECTIVE: To explore the clinical value and diagnostic effects of the lung nodule classification and segmentation algorithm based on deep learning in differentiating benign and malignant pulmonary nodules. METHODS: A deep learning model with a fine-grained classification manner for the discrimination of pulmonary models in Dr.Wise Lung Analyzer. This study retrospectively enrolled 120 patients with pulmonary nodules detected by chest spiral CT from March 2021 to September 2022 in the radiology department of Ninghai First Hospital. The DL-based method and physicians’ accuracy, sensitivity, and specificity results were compared using the pathological results as the gold standard. The ROC curve of the deep learning model was plotted, and the AUCs were calculated. RESULTS: On 120 CT images, pathologically diagnosed 81 malignant nodules and 122 benign modules. The AUCs of radiologists’ diagnostic approach and DL-base method for differentiating patients were 0.62 and 0.81; radiologists’ diagnostic approach and DL-base method achieved AUCs of 0.75 and 0.90 for benign and malignant pulmonary nodules differentiate. The accuracy, sensitivity, and specificity with the deep learning model were 73.33%, 78.75%, and 62.50%, respectively, while the accuracy, sensitivity, and specificity with the physician’s diagnosis were 63.33%, 66.25%, and 57.500. CONCLUSION: There was no significant difference between the diagnosis results of the proposed DL-based method and the radiologists’ diagnostic approach in differentiating benign and malignant lung nodules on spiral CT (P< 0.05).
Keywords: Benign and malignant pulmonary nodule, deep learning, diagnosis, early diagnosis
