||Multi-scale approaches have been widely used in data-compression, image smoothing, segmentation, object recognition, and in other fields of image processing and computer vision. The notion of scale evolved in the form of scale-space theory where the key idea is to represent and analyze an image at various resolutions. Subsequently, significant research works have been devoted along the direction of formulating “local scale” that allows fine tuning of regional operations in various applications. Several research groups have studied relations between mathematical morphology and scale. Previously, we introduced morphologic approaches toward defining local scale. Recently, we have been studying correlation among local scale, distance transform, and object morphology and combining those with topologic approaches to solve various practical problems, especially, in medical imaging. We have applied multi-scale topo-morphologic approaches to solve some fundamental challenges and to formulate several novel algorithms including – (1) separation of arterial and venous trees in non-contrast in vivo pulmonary CT imaging where arteries and veins are indistinguishable by their intensity values and are fused at various locations and scales, (2) quantification trabecular bone micro-architecture at in vivo resolution regime, and (3) local structure adaptive diffusive image filtering. Problems related to the first application have been solved using a new multi-scale topo-morphologic opening algorithm that iteratively solve opens two fused structures starting at larger scales and progressing toward smaller ones. The notion of manifold-scale has been introduced to design an algorithm that allows classification of trabecular bones on the continuum between perfect plates and perfect rods. Finally, we will briefly describe the notion of tensor scale and discuss its application to image filtering.