Lung nodules less than 1.5cm: differentiation of pulmonary adenocarcinomas from benign nodules using CT texture analysis

Congress:

ECR 2020

Poster Number:

C-02292

Type:

Scientific Exhibit

Keywords:

Performed at one institution, Diagnostic or prognostic study, Retrospective, Cancer, Computer Applications-Detection, diagnosis, CT, Oncology, Lung, Chest

Authors:

H.-F. Zhu, J. Fu, X.-Y. Meng, X.-L. Mu, C.-B. Liu; Beijing/CN

DOI:

10.26044/ecr2020/C-02292

DOI-Link:

https://dx.doi.org/10.26044/ecr2020/C-02292

Fig. 2: Figure 1 The ROI in the texture analysis was drawn freehand around the...

Fig. 3: Figure 2 The workflow in this study.

Fig. 1: Figure 1 A54y female with partial solid nodules in the left upper lobe.B...

Purpose

It is a challenge for differential diagnosis of benign pulmonary nodules and pulmonary adenocarcinomas, especially for lung nodules less than 1.5cm.Semantic characteristics of pulmonary nodules such as size, attenuation, and margins are often insufficient for characterization（Figure 1）[1,2].In light of this challenge, a suggestion to improve diagnostic accuracy using CT texture analysis was proposed. Texture analysis was a quantitative imaging analysis tool that based on attenuation values of each voxel and their distribution within lesions, which is expected to explore a more detailed quantitative assessment of...

Methods and materials

Patients We retrospectively analyzed patients who underwent chest CT at our institution between August 2017 and June 2019. All aspects of this retrospective study were approved by the institutional review board. Inclusion criteria: (1) All patients underwent chest NECT scanning; (2) Pulmonary nodules with a diameter of longer than 0.6cm and less than 1.5cm;(3)There was no obvious calcification and cavity, and there was no atelectasis and satellite disease around the nodules; (4) With surgical proved pathology; (5) no previous radiotherapy or chemotherapy. Forty-one patients were...

Results

Result Compared with adenocarcinomas, benign nodules had significantly greater strength(p=0.005), contrast(p=0.002), variance(p=0.026) and lower kurtosis(p=0.016) ,emphasis(p=0.035) .A multiple regression model using these features showed excellent AUC=0.864,（95%CI 0.8265-0.8966）sensitivity=0.748,specificity=0.950.

Conclusion

Conclusion CT texture features have potentials to enhance the differentiating performance.

Personal information and conflict of interest

Hai-feng Zhu, M.B. Director ,Department of Radiology, Civil Aviation General Hospital. Chaoyang Road,Gaojing No.1 100123 Beijing, China Phone: + 86-85762244-2349 e-mail : [email protected] - nothing to disclose

References

Beig N, Khorrami M, Alilou M, et al. Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas.Radiology. 2019;290(3):783–792. doi:10.1148/radiol.2018180910 Patz, Edward F, Pinsky, Paul, Gatsonis, Constantine,et al. Overdiagnosis in Low-Dose Computed Tomography Screening for Lung Cancer. Jama Internal Medicine.2013;174(2):269.doi:10.1001/jamainternmed.2013.12738. Dennie C, Thornhill R, Sethi-Virmani V, et al.Role of quantitative computed tomography texture analysis in the differentiation of primary lung cancer and granulomatous nodules.Quant Imaging Med Surg.2016;6(1):6–15. doi: 10.3978/j.issn.2223-4292.2016.02.01. Thawani R, McLane M, Beig N, et al. Radiomics and radiogenomics in lung...