Radiomic analysis of pulmonary ground-glass opacity nodules for distinction of preinvasive lesions, invasive pulmonary adenocarcinoma and minimally invasive adenocarcinoma based on quantitative texture analysis of CT

Objective： To identify the differences among preinvasive lesions, minimally invasive adenocarcinomas （MIAs）and invasive pulmonary adenocarcinomas （IPAs） based on radiomic feature analysis with computed tomography（CT）.Methods： A total of 109 patients with ground-glass opacity lesions （GGOs） in the lungs determined by CTexaminations were enrolled, all of whom had received a pathologic diagnosis. After the manual delineation andsegmentation of the GGOs as regions of interest （ROIs）, the patients were subdivided into three groups based onpathologic analyses： the preinvasive lesions （including atypical adenomatous hyperplasia and adenocarcinoma insitu） subgroup, the MIA subgroup and the IPA subgroup. Next, we obtained the texture features of the GGOs. Thedata analysis was aimed at finding both the differences between each pair of the groups and predictors to distinguishany two pathologic subtypes using logistic regression. Finally, a receiver operating characteristic （ROC） curve wasapplied to accurately evaluate the performances of the regression models.Results： We found that the voxel count feature （P〈0.001） could be used as a predictor for distinguishing IPAsfrom preinvasive lesions. However, the surface area feature （P=0.040） and the extruded surface area feature（P=0.013） could be predictors of IPAs compared with MIAs. In addition, the correlation feature （P=0.046） coulddistinguish preinvasive lesions from MIAs better.Conclusions： Preinvasive lesions, MIAs and IPAs can be discriminated based on texture features within CTimages, although the three diseases could all appear as GGOs on CT images. The diagnoses of these three diseasesare very important for clinical surgery.

Asymptomatic pancreatic lesions: New insights and clinical implications

Despite great efforts in experimental and clinical research, the prognosis of pancreatic cancer (PC) has not changed significantly for decades. Detection of pre-invasive lesions or early-stage PC with small resectable cancers in asymptomatic individuals remains one of the most promising approaches to substantially improve the overall outcome of PC. Therefore, screening programs have been proposed to identify curable lesions especially in individuals with a familial or genetic predisposition for PC. In this regard, Canto et al recently contributed an important article comparing computed tomography, magnetic resonance imaging, and endoscopic ultrasound for the screening of 216 asymptomatic high-risk individuals (HRI). Pancreatic lesions were detected in 92 of 216 asymptomatic HRI (42.6%). The high diagnostic yield in this study raises several questions that need to be answered of which two will be discussed in detail in this commentary: First: which imaging test should be performed? Second and most importantly: what are we doing with incidentally detected pancreatic lesions? Which ones can be observed and which ones need to be resected?