Zhang T, Wang Y, Sun Y, et al. - As for radiologists, classification of non-solid nodules is of great importance, researchers herein examined if an improvement in the classification performance of radiologists in classifying pulmonary non-solid nodules (NSNs) could be achieved with 3D convolutional neural network (CNN). They retrospectively analyzed data of patients with solitary NSNs and diagnosed as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC) in pathological after surgical resection were analyzed retrospectively. This study was performed including 532 patients in their institution: training dataset included 427 cases (144 AIS, 167 MIA, 116 IAC) and validation dataset included 105 cases (36 AIS, 41 MIA and 28 IAC). External validation was performed including 177 patients (60 AIS, 69 MIA and 48 IAC) from another hospital in the testing dataset. CNN led to successful classification of NSNs based on CT images and its classification performance was noted to be superior to radiologists’ model. However, significant improvement in the classification performance of radiologists can be achieved when combined with CNN in classifying NSNs.