ABSTRACT
The study of microstructure evolution in additive manufacturing of metals would be aided by knowing the thermal history. Since temperature measurements beneath the surface are difficult, estimates are obtained from computational thermo-mechanical models calibrated against traces left in the sample revealed after etching, such as the trace of the melt pool boundary. Here we examine the question of how reliable thermal histories computed from a model that reproduces the melt pool trace are. To this end, we perform experiments in which one of two different laser beams moves with constant velocity and power over a substrate of 17-4PH SS or Ti-6Al-4V, with low enough power to avoid generating a keyhole. We find that thermal histories appear to be reliably computed provided that (a) the power density distribution of the laser beam over the substrate is well characterized, and (b) convective heat transport effects are accounted for. Poor control of the laser beam leads to potentially multiple three-dimensional melt pool shapes compatible with the melt pool trace, and therefore to multiple potential thermal histories. Ignoring convective effects leads to results that are inconsistent with experiments, even for the mild melt pools here.
ABSTRACT
Purpose: We applied a deep convolutional neural network model for automatic identification of ellipsoid zone (EZ) in spectral domain optical coherence tomography B-scans of retinitis pigmentosa (RP). Methods: Midline B-scans having visible EZ from 220 patients with RP and 20 normal subjects were manually segmented for inner limiting membrane, inner nuclear layer, EZ, retinal pigment epithelium, and Bruch's membrane. A total of 2.87 million labeled image patches (33 × 33 pixels) extracted from 480 B-scans were used for training a convolutional neural network model implemented in MATLAB. B-scans from a separate group of 80 patients with RP were used for testing the model. A local connected area searching algorithm was developed to process the model output for reconstructing layer boundaries. Correlation and Bland-Altman analyses were conducted to compare EZ width measured by the model to those by manual segmentation. Results: The accuracy of the trained model to identify inner limiting membrane, inner nuclear layer, EZ, retinal pigment epithelium, and Bruch's membrane patches in the test dataset was 98%, 89%, 91%, 94%, and 96%, respectively. The EZ width measured by the model was highly correlated with that by two graders (r = 0.97; P < 0.0001). Bland-Altman analysis revealed a mean EZ width difference of 0.30 mm (coefficient of repeatability = 0.9 mm) between the model and the graders, comparable to the mean difference of 0.34mm (coefficient of repeatability = 0.8 mm) between two graders. Conclusions: The results demonstrated the capability of a deep machine learning-based method for automatic identification of EZ in RP, suggesting that the method can be used to quantify structural deficits in RP for detecting disease progression and for evaluating treatment effect. Translational Relevance: A deep machine learning model has the potential to replace humans for grading spectral domain optical coherence tomography images in RP.
