The dramatic increase in fragility fractures, due to aging population and pathologies, with the related health and economic burden rise the urge of a cutting-edge perspective to prevent fractures in human bones. Now, an additional wake-up call rises from the outbreak of Covid-19 pandemic: a slowdown in the bone formation processes is hypothesized as a direct outcome of the virus infection, which lead to a reduction in bone mass and strength. If this hypothesis would be confirmed, Covid-19 disease could have an effect on bone architecture deterioration, that may require preventive treatments to avoid long-term bone-related complications. Recent studies address the issue from a multi-scale perspective, elevating the micro-scale phenomena as the key for detecting early damage occurrence. However, several limitations arise specifically to define a quantitative framework to assess the contribution of micro-morphology (in particular lacunae) to fracture initiation and propagation. Moreover, the need for high resolution imaging imposes time-demanding post-processing phases. To address the current time-consuming and computationally expensive manual/semi-automatic segmenting steps, we aim at implementing convolutional neural network to detect the initiation and propagation of micro-scale damages. The expected results should highlight the intimate cross talks between toughening and weakening phenomena at micro-scale as a fundamental aspect for fracture mechanisms elucidation.