CT-based AI could be game changer for radiologists assessing invasive, noninvasive cancers

The study included 365 patients treated at two medical centers from 2016-2019. All patients had SSPNs and pathologically confirmed MIA or IAC. Preoperative CT images were used to select deep learning features. The deep learning signature (DLS) was developed via the least absolute shrinkage and selection operator (LASSO). 

Between the MIA and IAC groups, 18 learning features with non-zero coefficients were enrolled in the signature. Independent predictors of the DLS were used to help develop the deep learning network (DLN). In training, internal validation and external validation, the…