Objective: Identification of tumor invasiveness of pulmonary adenocarcinomas before surgery is one of the most important guides to surgical planning. Additionally, preoperative diagnosis of lung adenocarcinoma with micropapillary patterns is also critical for clinical decision making. We aimed to evaluate the accuracy of deep learning models on classifying invasiveness degree and attempted to predict the micropapillary pattern in lung adenocarcinoma. Methods: The records of 291 histopathologically confirmed lung adenocarcinoma patients were retrospectively analyzed and consisted of 61 adenocarcinoma in situ, 80 minimally invasive adenocarcinoma, 117 invasive adenocarcinoma, and 33 invasive adenocarcinoma with micropapillary components (> 5%). We constructed two diagnostic models, the Lung-DL model and the Dense model, based on the LeNet and the DenseNet architecture respectively. Results: For distinguishing the nodule invasiveness degree, the area under the curve (AUC) value of the diagnosis with the Lung-DL model is 0.88 and that with the Dense model is 0.86. In the prediction of the micropapillary pattern, overall accuracies of 92% and 72.91% were obtained for the Lung-DL model and the Dense model, respectively. Conclusion: Deep learning was successfully used for the invasiveness classification of pulmonary adenocarcinomas. This is also the first time that deep learning techniques have been used to predict micropapillary patterns. Both tasks can increase efficiency and assist in the creation of precise individualized treatment plans.

Biosurfactant producers are crucial for incremental oil production in microbial enhanced oil recovery (MEOR) processes. The isolation of biosurfactant-producing bacteria from oil reservoirs is important because they are considered suitable for the extreme conditions of the reservoir. In this work, a novel biosurfactant-producing strain Acinetobacter junii BD was isolated from a reservoir to reduce surface tension and emulsify crude oil. The biosurfactants produced by the strain were purified and then identified via electrospray ionization-Fourier transform ion cyclotron resonance mass spectrometry (ESI FT-ICR-MS). The biosurfactants generated by the strain were concluded to be rhamnolipids, the dominant rhamnolipids were C26H48O9, C28H52O9 and C32H58O13. The optimal carbon source and nitrogen source for biomass and biosurfactant production were NaNO3 and soybean oil. The results showed that the content of acid components increased with the progress of crude oil biodegradation. A glass micromodel test demonstrated that the strain significantly increased oil recovery through interfacial tension reduction, wettability alteration and the mobility of microorganisms. In summary, the findings of this study indicate that the newly developed BD strain and its metabolites have great potential in MEOR.