Mineral image segmentation is widely used in mining, sorting, exploration, composition analysis, and other production works. The burgeoning field of deep learning provides preferred solutions for mineral image segmentation. We present a review of recent literature in this direction, covering the module components, encoder-decoders architecture, representative networks, mineral image datasets, performance metrics, and state-of-the-art models. In the application performance survey, the review contents include mineral type, image type, image resolution, image data quantity, architecture selection, and encoder network construction, as well as summarizes the advantages of deep learning-based mineral image segmentation methods. We conducted small-scale experiments for the current mainstream architectures and visualize the segmentation results for performance comparison. We also investigated the application challenges and bottlenecks of deep learning-based methods, propose several innovative directions, and discuss promising future applications. •Review and analysis of deep learning-based mineral image segmentation.•Survey of mineral image datasets, commonly-used models, and optimization strategies.•Visualization of the segmentation performance of current mainstream models.•Discussion of the application changes and innovations in mineral image segmentation.•Outlook of application potentials of deep learning in mineral production fields.