Solid Attenuation Components Attention Deep Learning Model to Predict Micropapillary and Solid Patterns in Lung Adenocarcinomas on Computed Tomography.

BACKGROUND: High-grade adenocarcinoma subtypes (micropapillary and solid) treated with sublobar resection have an unfavorable prognosis compared with those treated with lobectomy. We investigated the potential of incorporating solid attenuation component masks with deep learning in the prediction of high-grade components to optimize surgical strategy preoperatively. METHODS: A total of 502 patients with pathologically confirmed high-grade adenocarcinomas were retrospectively enrolled between 2016 and 2020. The SACs attention DL model was developed to apply solid-attenuation-component-like subregion masks (tumor area ≥ - 190 HU) to guide the DL model for predicting high-grade subtypes. The SACA-DL was assessed using 5-fold cross-validation and external validation in the training and testing sets, respectively. The performance, which was evaluated using the area under the curve (AUC), was compared between SACA-DL and the DL model without SACs attention (DLwoSACs), the prior radiomics model, or the model based on the consolidation/tumor (C/T) diameter ratio. RESULTS: We classified 313 and 189 patients into training and testing cohorts, respectively. The SACA-DL achieved an AUC of 0.91 for the cross-validation, which was significantly superior to those of the DLwoSACs (AUC = 0.88; P = 0.02), prior radiomics model (AUC = 0.85; P = 0.004), and C/T ratio (AUC = 0.84; P = 0.002). An AUC of 0.93 was achieved for external validation in the SACA-DL and was significantly better than those of the DLwoSACs (AUC = 0.89; P = 0.04), prior radiomics model (AUC = 0.85; P < 0.001), and C/T ratio (AUC = 0.85; P < 0.001). CONCLUSIONS: The combination of solid-attenuation-component-like subregion masks with the DL model is a promising approach for the preoperative prediction of high-grade adenocarcinoma subtypes.

CT-Based Radiomic Analysis for Preoperative Prediction of Tumor Invasiveness in Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodule.

It remains a challenge to preoperatively forecast whether lung pure ground-glass nodules (pGGNs) have invasive components. We aimed to construct a radiomic model using tumor characteristics to predict the histologic subtype associated with pGGNs. We retrospectively reviewed clinicopathologic features of pGGNs resected in 338 patients with lung adenocarcinoma between 2011-2016 at a single institution. A radiomic prediction model based on forward sequential selection and logistic regression was constructed to differentiate adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma. The study cohort included 133 (39.4%), 128 (37.9%), and 77 (22.8%) patients with AIS, MIA, and invasive adenocarcinoma (acinar 55.8%, lepidic 33.8%, papillary 10.4%), respectively. The majority (83.7%) underwent sublobar resection. There were no nodal metastases or tumor recurrence during a mean follow-up period of 78 months. Three radiomic features-cluster shade, homogeneity, and run-length variance-were identified as predictors of histologic subtype and were selected to construct a prediction model to classify the AIS/MIA and invasive adenocarcinoma groups. The model achieved accuracy, sensitivity, specificity, and AUC of 70.6%, 75.0%, 70.0%, and 0.7676, respectively. Applying the developed radiomic feature model to predict the histologic subtypes of pGGNs observed on CT scans can help clinically in the treatment selection process.