Microscopic analysis of biological structures can be significantly enhanced by representing the object of study as a three-dimensional entity. To assist neurobiologists investigate the molecular mechanisms involved in neurite formation requires an adequate visual model or at least some measurable data. Reconstruction helps analysis of biological structures by representing the object of study as a three-dimensional entity. It helps gain insight into the morphological variation observed in each class of neurons and for simulations of neuronal behavior. To perform the reconstruction, biologists today have to rely on time-consuming manual or semi-manual methods which either doesn't exhibit robustness against noise of microscopy images or fail to capture precise dendritic structures, thus necessitating the need of fully-automated reconstruction methods for neuronal structures. In our work, we designed a framework with the goal of enabling automation and yet produce flexible outputs to ensure a high quality reconstruction with minimal user intervention. Our framework is also not bound by varying contrast, size or resolution of data, thus capable of working on data obtained from wide variety of acquisition methods and neuronal structures.