Objectives: To compare two statistical models, namely logistic regression and artificial neural network (ANN), in prediction of vestibular schwannoma (VS) recurrence.Methods: Seven hundred eighty-nine patients with VS diagnosis completed an online survey. Potential predictors for recurrence were derived from univariate analysis by reaching the cut off P value of .05. Those nine potential predictors were years since treatment, surgeon's specialty, resection amount, and having incomplete eye closure, dry eye, double vision, facial pain, seizure, and voice/swallowing problem as a complication following treatment. Multivariate binary logistic regression model was compared with a four-layer 9-5-10-1 feedforward backpropagation ANN for prediction of recurrence.Results: The overall recurrence rate was 14.5%. Significant predictors of recurrence in the regression model were years since treatment and resection amount (both P < .001). The regression model did not show an acceptable performance (area under the curve [AUC] = 0.64; P = .27). The regression model's sensitivity and specificity were 44% and 69%, respectively and correctly classified 56% of cases. The ANN showed a superior performance compared to the regression model (AUC = 0.79; P = .001) with higher sensitivity (61%) and specificity (81%), and correctly classified 70% of cases.Conclusion: The constructed ANN model was superior to logistic regression in predicting patient-answered VS recurrence in an anonymous survey with higher sensitivity and specificity. Since artificial intelligence tools such as neural networks can have higher predictive abilities compared to logistic regression models, continuous investigation into their utility as complementary clinical tools in predicting certain surgical outcomes is warranted.Mehdi Abouzari and Khodayar Goshtasbi contributed equally to this manuscript.

Conventional x-ray sources for medical imaging utilize bremsstrahlung radiation. These sources generate large bandwidth (BW) x-ray spectra with large fractions of photons that impart a dose, but do not contribute to image production. X-ray sources based on laser-Compton scattering can have inherently small energy BWs and can be tuned to low dose-imparting energies, allowing them to take advantage of atomic K-edge contrast enhancement. This paper investigates the use of gadolinium-based K-edge subtraction imaging in the context of mammography using a laser-Compton source through simulations quantifying contrast and dose in such imaging systems as a function of laser-Compton source parameters. Our simulations indicate that a K-edge subtraction image generated with a 0.5% BW (FWHM) laser-Compton x-ray source can obtain an equal contrast to a bremsstrahlung image with only 3% of the dose.

Tuning the Compton edge energy of a Laser Compton X-ray source is difficult on the experimental time scale for K-edge subtraction (KES) imaging. Scanning KES imaging can overcome this difficulty by utilizing angle-correlated spectra.

The development of compact quasimonoenergetic x-ray radiation sources based on laser Compton scattering (LCS) offers opportunities for novel approaches to medical imaging. However, careful experimental design is required to fully utilize the angle-correlated x-ray spectra produced by LCS sources. Direct simulations of LCS x-ray spectra are computationally expensive and difficult to employ in experimental optimization. In this manuscript, we present a computational method that fully characterizes angle-correlated LCS x-ray spectra at any end point energy within a range defined by three direct simulations. With this approach, subsequent LCS x-ray spectra can be generated with up to 200 times less computational overhead.