Purpose: To evaluate ability of radiomic (computer-extracted imaging) features to distinguish non-small cell lung cancer adenocarcinomas from granulomas at noncontrast CT. Materials and Methods: For this retrospective study, screening or standard diagnostic noncontrast CT images were collected for 290 patients (mean age, 68 years; range, 18–92 years; 125 men [mean age, 67 years; range, 18–90 years] and 165 women [mean age, 68 years; range, 33–92 years]) from two institutions between 2007 and 2013. Histopathologic analysis was available for one nodule per patient. Corresponding nodule of interest was identified on CT axial images by a radiologist with manually annotation. Nodule shape, wavelet (Gabor), and texture-based (Haralick and Laws energy) features were extracted from intra- and perinodular regions. Features were pruned to train machine learning classifiers with 145 patients. In a test set of 145 patients, classifier results were compared against a convolutional neural network (CNN) and diagnostic readings of two radiologists. Results: Support vector machine classifier with intranodular radiomic features achieved an area under the receiver operating characteristic curve (AUC) of 0.75 on the test set. Combining radiomics of intranodular with perinodular regions improved the AUC to 0.80. On the same test set, CNN resulted in an AUC of 0.76. Radiologist readers achieved AUCs of 0.61 and 0.60, respectively. Conclusion: Radiomic features from intranodular and perinodular regions of nodules can distinguish non-small cell lung cancer adenocarcinomas from benign granulomas at noncontrast CT. Summary Perinodular and intranodular radiomic features corresponding to texture and shape (radiomics) were evaluated to distinguish nonsmall cell lung cancer adenocarcinomas from benign granulomas at noncontrast CT.
Non-availability of recommended test results to treating physicians for patients on OPAT is associated with increased readmissions during OPAT.
Differentiation between benign and malignant nodules is a problem encountered by radiologists when visualizing computed tomography (CT) scans. Adenocarcinomas and granulomas have a characteristic spiculated appearance and may be fluorodeoxyglucose avid, making them difficult to distinguish for human readers. In this retrospective study, we aimed to evaluate whether a combination of radiomic texture and shape features from noncontrast CT scans can enable discrimination between granulomas and adenocarcinomas. Our study is composed of CT scans of 195 patients from two institutions, one cohort for training ([Formula: see text]) and the other ([Formula: see text]) for independent validation. A set of 645 three-dimensional texture and 24 shape features were extracted from CT scans in the training cohort. Feature selection was employed to identify the most informative features using this set. The top ranked features were also assessed in terms of their stability and reproducibility across the training and testing cohorts and between scans of different slice thickness. Three different classifiers were constructed using the top ranked features identified from the training set. These classifiers were then validated on the test set and the best classifier (support vector machine) yielded an area under the receiver operating characteristic curve of 77.8%.
Postesophagectomy anastomotic leak is a common postsurgical complication. The current standard method of detecting leak is esophagram usually late in the postoperative period. Perianastomotic drain amylase level had shown promising results in early detection anastomosis leak. Previous studies have shown that postoperative day 4 amylase level is more specific and sensitive than esophagram. The purpose of this study is to determine if implementing a drain amylase-based screening method for anastomotic leak can reduce length of stay and hospital cost relative to a traditional esophagram-based pathway. The drain amylase protocol we propose uses postoperative day 4 drain amylase level to direct the initiation of PO intake and discharge. We designed a decision analysis tree using TreeAge Pro software to compare the drain amylase-based screening method to the standard of care, the esophagram. We performed a retrospective review of postesophagectomy patients from a tertiary academic medical center (University hospital Cleveland medical center) where amylase level was measured routinely postoperatively. The patients were separated into amylase-based pathway group and the standard of care group based on their postop management. The length of stay, costs, complications, and leak rate of these two groups were used to inform the decision analysis tree. In the base-case analysis, the decision analysis demonstrated that an amylase-based screening method can reduce the hospital stay by one day and reduced costs by ∼$3,000 compared to esophagram group. To take the variability of the data into consideration, we performed a Monte Carlo simulation. The result showed again a median saving of 0.71 days and ∼$2,500 per patient in hospital cost. A ballistic sensitivity analysis was performed to show that the sensitivity of postoperative day 4 amylase level in detecting a leak was the most important factor in the model. We conclude that implementing an amylase-based screening method for anastomotic leak in postesophagectomy patient can significantly reduce hospital cost and length of stay. This study demonstrates a novel protocol to improve postesophagectomy care. Based on this result, we believe a prospective multicenter study is appropriate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.