High‐resolution mitochondria imaging in combination with image analysis tools have significantly advanced our understanding of cellular function in health and disease. However, most image analysis tools for mitochondrial studies have been designed to work with fluorescently labeled images only. Additionally, efforts to integrate features describing mitochondrial networks with machine learning techniques for the differentiation of cell types have been limited. Herein, we present AutoMitoNetwork software for image‐based assessment of mitochondrial networks in label‐free autofluorescence images using a range of interpretable morphological, intensity, and textural features. To demonstrate its utility, we characterized unstained mitochondrial networks in healthy retinal cells and in retinal cells exposed to two types of treatments: rotenone, which directly inhibited mitochondrial respiration and ATP production, and iodoacetic acid, which had a milder impact on mitochondrial networks via the inhibition of anaerobic glycolysis. For both cases, our multi‐dimensional feature analysis combined with a support vector machine classifier distinguished between healthy cells and those treated with rotenone or iodoacetic acid. Subtle changes in morphological features were measured including increased fragmentation in the treated retinal cells, pointing to an association with metabolic mechanisms. AutoMitoNetwork opens new options for image‐based machine learning in label‐free imaging, diagnostics, and mitochondrial disease drug development.