Benign and malignant pulmonary part-solid nodules: differentiation via thin-section computed tomography

Li, Wang-jia; Lv, Fajin; Tan, Yiwen; Fu, B.; Chu, Zhi‐gang

doi:10.21037/qims-21-145

Cited by 18 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we found that female was closely associated with malignant pulmonary nodules (p = 0.01), which was in line with previous studies ( 30 – 32 ). The results of our studies showed that a well-defined border was also significantly associated with malignant GGNs, inconsistent with previous in vivo studies ( 33 ). Besides, our results on air branchogram were in conflict with previous studies ( 34 ).…”

Section: Discussioncontrasting

confidence: 99%

Development, Validation, and Comparison of Image-Based, Clinical Feature-Based and Fusion Artificial Intelligence Diagnostic Models in Differentiating Benign and Malignant Pulmonary Ground-Glass Nodules

et al. 2022

View full text Add to dashboard Cite

ObjectiveThis study aimed to develop effective artificial intelligence (AI) diagnostic models based on CT images of pulmonary nodules only, on descriptional and quantitative clinical or image features, or on a combination of both to differentiate benign and malignant ground-glass nodules (GGNs) to assist in the determination of surgical intervention.MethodsOur study included a total of 867 nodules (benign nodules: 112; malignant nodules: 755) with postoperative pathological diagnoses from two centers. For the diagnostic models to discriminate between benign and malignant GGNs, we adopted three different artificial intelligence (AI) approaches: a) an image-based deep learning approach to build a deep neural network (DNN); b) a clinical feature-based machine learning approach based on the clinical and image features of nodules; c) a fusion diagnostic model integrating the original images and the clinical and image features. The performance of the models was evaluated on an internal test dataset (the “Changzheng Dataset”) and an independent test dataset collected from an external institute (the “Longyan Dataset”). In addition, the performance of automatic diagnostic models was compared with that of manual evaluations by two radiologists on the ‘Longyan dataset’.ResultsThe image-based deep learning model achieved an appealing diagnostic performance, yielding AUC values of 0.75 (95% confidence interval [CI]: 0.62, 0.89) and 0.76 (95% CI: 0.61, 0.90), respectively, on both the Changzheng and Longyan datasets. The clinical feature-based machine learning model performed well on the Changzheng dataset (AUC, 0.80 [95% CI: 0.64, 0.96]), whereas it performed poorly on the Longyan dataset (AUC, 0.62 [95% CI: 0.42, 0.83]). The fusion diagnostic model achieved the best performance on both the Changzheng dataset (AUC, 0.82 [95% CI: 0.71-0.93]) and the Longyan dataset (AUC, 0.83 [95% CI: 0.70-0.96]), and it achieved a better specificity (0.69) than the radiologists (0.33-0.44) on the Longyan dataset.ConclusionThe deep learning models, including both the image-based deep learning model and the fusion model, have the ability to assist radiologists in differentiating between benign and malignant nodules for the precise management of patients with GGNs.

show abstract

Section: Discussioncontrasting

confidence: 99%

Development, Validation, and Comparison of Image-Based, Clinical Feature-Based and Fusion Artificial Intelligence Diagnostic Models in Differentiating Benign and Malignant Pulmonary Ground-Glass Nodules

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This study found that among 30 mGGN cases, the detection rate was significantly higher in the invasive adenocarcinoma group compared with the PGL group (35.38% vs 14.89%), indicating that mGGNs are more likely to progress to adenocarcinoma. According to previous findings, GGNs with clear boundary, lobulated shape and scattered irregular solid components are prone to vicious transformation (Li et al 2022b ). Some GGNs in this study showed irregular solid components on electron density images, which was confirmed by postoperative pathology as invasive adenocarcinoma (Fig.…”

Section: Discussionmentioning

confidence: 80%

Dual-layer spectral detector CT (SDCT) can improve the detection of mixed ground-glass lung nodules

Zhang

Yin

Kang

et al. 2023

J Cancer Res Clin Oncol

View full text Add to dashboard Cite

Background Mixed ground-glass lung nodules are a high-risk factor for lung adenocarcinoma. This study aimed to analyze the value of SDCT electron density imaging in the detection of mixed ground-glass lung nodules (GGNs). Method 150 patients with GGNs confirmed by chest SDCT and surgical pathology were retrospectively analyzed. GGNs were screened by two senior radiologists by the double-blind method based on conventional CT and SDCT electron density images. Average CT values and electron density (ED) values of GGNs were measured for all, solid and ground-glass. Result Thirty pGGN cases determined by conventional CT were found to be mGGN on electron density images, including 23 in the invasive adenocarcinoma group (detection rate of 35.38%), which was significantly higher than that of the PGL group (14.89%, P < 0.05). In electron density images, average CT values and ED values in the PGL and invasive adenocarcinoma groups with pGGNs were no difference. The average CT value and ED value were significantly higher in the mGGN invasive adenocarcinoma group compared with the PGL group ( P < 0.05). Meanwhile, ROC curve analysis of average CT value and ED value revealed AUC values for mGGN infiltration of 0.759 and 0.752. Conclusion SDCT can improve GGN visualization and increase the detection rate of mGGN compared with conventional CT. Attention should be paid to invasive adenocarcinoma for lung GGNs detected as mGGNs with high average CT value or ED value.

show abstract

“…It has been reported that well-defined border and heterogeneous GGO, and multiple, irregular, scattered, and eccentric internal solid components were significant indicators of malignant mGGNs, while ill-defined border and homogeneous GGO, and single, round and central internal solid components were predictors of benign ones. 35 In this study, the four mGGNs caused by fungal infection were ill-defined and the internal solid components were irregular or scattered, which did not meet the typical features of benign or malignant ones and thus may be misdiagnosed. In view of the nature of infection, short-term follow-up may provide some additional information in differentiating them.…”

Section: Discussionmentioning

confidence: 71%

Clinical and Computed Tomography Characteristics of Solitary Pulmonary Nodules Caused by Fungi: A Comparative Study

Jang¹,

Lv²,

Lv³

et al. 2022

IDR

Self Cite

View full text Add to dashboard Cite

Benign and malignant pulmonary part-solid nodules: differentiation via thin-section computed tomography

Cited by 18 publications

References 17 publications

Development, Validation, and Comparison of Image-Based, Clinical Feature-Based and Fusion Artificial Intelligence Diagnostic Models in Differentiating Benign and Malignant Pulmonary Ground-Glass Nodules

Development, Validation, and Comparison of Image-Based, Clinical Feature-Based and Fusion Artificial Intelligence Diagnostic Models in Differentiating Benign and Malignant Pulmonary Ground-Glass Nodules

Dual-layer spectral detector CT (SDCT) can improve the detection of mixed ground-glass lung nodules

Clinical and Computed Tomography Characteristics of Solitary Pulmonary Nodules Caused by Fungi: A Comparative Study

Contact Info

Product

Resources

About