Dental Panoramic radiography (DPR) image provides a potentially inexpensive source to evaluate bone density change through visual clue analysis on trabecular bone structure. However, dense overlapping of bone structures in DPR image and scarcity of labeled samples make learning of accurate mapping from DPR patches to osteoporosis condition challenging. In this paper, we propose a deep Octuplet Siamese Network (OSN) to learn and fuse discriminative features for osteoporosis condition prediction using multiple DRP patches. By exploring common features, OSN uses patches of eight locations together to train the shared feature extractor. Feature fusion for different location adopts both accumulation and concatenation with fully considering of patches' spatial symmetry. In our dedicated two-stage fine-tuning scheme, an augmented texture analysis dataset is employed to prevent overfitting in transferring weights learned on ImageNet to DPR dataset when using merely 108 samples. Leave-one-out test shows that our proposed OSN outperforms all other state of the art methods in osteoporosis category classification task.