Several types of cancer can be clinically diagnosed by PET/CT, which can also perform whole-body imaging based on 18F-fluorodeoxyglucose (FDG) uptake. The present study assesses the value of PET/CT for diagnosing of pulmonary metastasis of colorectal cancer. We staged or restaged 256 patients with colorectal cancer by PET/CT. Actual and suspected pulmonary metastases were detected in 37 (male, n=23; female, n=14) patients with primary or recurrent colorectal cancer. Among them, 35 (21 males, 14 females) patients had extant homochronous (n=7) and metachronous (n=28) pulmonary metastasis. The sensitivity and specificity of FDG-PET/CT for pulmonary metastasis were 57.1% and 99.1%, respectively, and the positive and negative predictive values were 90.1% and 93.6%, respectively. The uptake of FDG was affected by the size of the metastatic nodules; uptake was positive and negative in pulmonary metastases with an average size of 14.9mm and 5.75mm, respectively. The limit of positive FDG uptake was reached in pulmonary metastases of about 9mm. Pulmonary metastasis of colorectal cancer can be accurately and conveniently diagnosed by PET/CT, especially when nodules are >9mm.

Analysis of operative data with convolutional neural networks (CNNs) is expected to improve the knowledge and professional skills of surgeons. Identification of objects in videos recorded during surgery can be used for surgical skill assessment and surgical navigation. The objectives of this study were to recognize objects and types of forceps in surgical videos acquired during colorectal surgeries and evaluate detection accuracy. Images (n = 1818) were extracted from 11 surgical videos for model training, and another 500 images were extracted from 6 additional videos for validation. The following 5 types of forceps were selected for annotation: ultrasonic scalpel, grasping, clip, angled (Maryland and right-angled), and spatula. IBM Visual Insights software was used, which incorporates the most popular open-source deep-learning CNN frameworks. In total, 1039/1062 (97.8%) forceps were correctly identified among 500 test images. Calculated recall and precision values were as follows: grasping forceps, 98.1% and 98.0%; ultrasonic scalpel, 99.4% and 93.9%; clip forceps, 96.2% and 92.7%; angled forceps, 94.9% and 100%; and spatula forceps, 98.1% and 94.5%, respectively. Forceps recognition can be achieved with high accuracy using deep-learning models, providing the opportunity to evaluate how forceps are used in various operations.

Peritoneal carcinomatosis (PC) from colorectal cancer has been associated with poor survival but new approaches and postoperative chemotherapy have improved survival. The purpose of this study was to evaluate the clinical utility of imaging in cases of PC from colorectal cancer. This is a retrospective single-institution study which examined 23 patients with colorectal cancer who underwent positron emission tomography (PET), computed tomography (CT) and received a final diagnosis PC in our institute between 2005 and 2010. PET/CT detected PC in 19 of 23 cases (82.6%), whereas CT detected PC in 6 of 20 cases (30%). Four cases of PC were FDG-negative, all with maximal size <10mm, representing smaller tumors. FDG-negative PC was diffuse in 3 cases and nodular in 1. The distributed spotty uptake of FDG-negative PC was harder to detect. Diagnostic detection of PC was only achieved in 3 of 23 cases (13%). In the remaining cases, clinical diagnosis was metastasis to lymph nodes, recurrence, or normal FDG uptake by intestine. PET/CT offers efficient detection of PC and has the potential to improve clinical diagnosis when coupled with an understanding of the pathways of flow for ascitic fluid and peritoneal seeding.