We introduce Lipschitz-Killing curvature (LKC) regression, a new method to produce $(1-α)$ thresholds for signal detection in random fields that does not require knowledge of the spatial correlation structure. The idea is to fit observed empirical Euler characteristics to the Gaussian kinematic formula via generalized least squares, which quickly and easily provides statistical estimates of the LKCs --- complex topological quantities that can be extremely challenging to compute, both theoretically and numerically. With these estimates, we can then make use of a powerful parametric approximation via Euler characteristics for Gaussian random fields to generate accurate $(1-α)$ thresholds and $p$-values. The main features of our proposed LKC regression method are easy implementation, conceptual simplicity, and facilitated diagnostics, which we demonstrate in a variety of simulations and applications.