https://www.selleckchem.com/products/PP242.html 04), surgical time (P = 0.01), the number of chest tube drainages (P < 0.01), and the total length of hospital stay (P = 0.03). However, no patients experienced bronchopleural fistula, postoperative pneumonia, or conversion to thoracotomy in either group. Five patients experienced prolonged air leakage in the IF group, and no prolonged air leakage occurred in the CF group. An IF would certainly increase the difficulty of CLM surgery, and thoracoscopic lobectomy using the pulmonary hilum approach is an effective and safe method for CLM patients. An IF would certainly increase the difficulty of CLM surgery, and thoracoscopic lobectomy using the pulmonary hilum approach is an effective and safe method for CLM patients. Computer-aided diagnosis (CAD)-based artificial intelligence (AI) has been shown to be highly accurate for detecting and characterizing colon polyps. However, the application of AI to identify normal colon landmarks and differentiate multiple colon diseases has not yet been established. We aimed to develop a convolutional neural network (CNN)-based algorithm (GUTAID) to recognize different colon lesions and anatomical landmarks. Colonoscopic images were obtained to train and validate the AI classifiers. An independent dataset was collected for verification. The architecture of GUTAID contains two major sub-models the Normal, Polyp, Diverticulum, Cecum and CAncer (NPDCCA) and Narrow-Band Imaging for Adenomatous/Hyperplastic polyps (NBI-AH) models. The development of GUTAID was based on the 16-layer Visual Geometry Group (VGG16) architecture and implemented on Google Cloud Platform. In total, 7838 colonoscopy images were used for developing and validating the AI model. An additional 1273 images were independently applied to verify the GUTAID. The accuracy for GUTAID in detecting various colon lesions/landmarks is 93.3% for polyps, 93.9% for diverticula, 91.7% for cecum, 97.5% for cancer, and 83.5% for adenoma