3D MedicalDet-Mamba: A Hybrid Mamba-CNN Network for Medical Object Detection and Localization

3D object detection in medical imaging poses significant challenges due to the high dimensionality and complex spatial relationships of volumetric data. Recent advancements with convolutional neural network (CNN)- and transformer-based approaches have shown promise; however, CNNs struggle with capturing long-range dependencies, while transformers incur high computational and memory costs when handling high-resolution 3D medical images. Mamba-based models offer an efficient alternative by modeling long-range dependencies in a linear manner, reducing complexity while maintaining effective feature representation. This study introduces 3D MedicalDet-Mamba, a novel hybrid framework that integrates the complementary strengths of CNNs and Mamba for precise 3D medical object detection and localization. Specifically, we propose the locality-integrated Mamba (LIM) module, which combines parallel multi-kernel convolutions with Mamba-based blocks to capture both global dependencies and fine-grained local structures, ensuring a more comprehensive feature representation. Additionally, we introduce the inter-scale aggregation Mamba (ISAM) block, a Mamba-based component that leverages hexa-hierarchical 3D slice (HH3S) scanning to aggregate multi-scale voxel-level features. This mechanism enhances the separation of medical objects from complex backgrounds while improving global feature extraction efficiency. Experimental results on public datasets show that 3D MedicalDet-Mamba outperforms state-of-the-art methods in both detection and localization accuracy. Code is available at https://github.com/ssli23/3D-MedicalDet-Mamba.