Search

In this paper, we present the Multi-Center Privacy-Preserving Network (MP-Net), a novel framework designed for secure medical image segmentation in multi-center collaborations. Our methodology offers a new approach to multi-center collaborative learning, capable of reducing the volume of data transmission and enhancing data privacy protection. Unlike federated learning, which requires the transmission of model data between the central server and local servers in each round, our method only necessitates a single transfer of encrypted data. The proposed MP-Net comprises a three-layer model, consisting of encryption, segmentation, and decryption networks. We encrypt the image data into ciphertext using an encryption network and introduce an improved U-Net for image ciphertext segmentation. Finally, the segmentation mask is obtained through a decryption network. This architecture enables ciphertext-based image segmentation through computable image encryption. We evaluate the effectiveness of our approach on three datasets, including two cardiac MRI datasets and a CTPA dataset. Our results demonstrate that the MP-Net can securely utilize data from multiple centers to establish a more robust and information-rich segmentation model.

Osteosarcoma is a devastating malignant neoplasm that seriously threatens human health. After an osteosarcoma resection, the simultaneous treatment of tumor recurrence, postoperative infection, and large bone loss remains a formidable challenge clinically. Herein, a versatile multiscale therapeutic platform (Fs-BP-DOX@PDA) is engineered based on NiTi alloys with versatile properties for near-infrared (NIR)-mediated osteosarcoma synergistic photothermo-chemotherapy, bone regeneration, and bacterial elimination. First, an intriguing method for fabricating groovelike micro-nanostructures (Fs-NiTi) through femtosecond laser direct writing to enhance osseointegration with strong contact guidance is proposed. Then, black phosphorus (BP) nanosheets as gratifying photothermal conversion agents, osteogenetic agents, and a drug delivery platform are decorated on Fs-NiTi to construct multiscale hierarchical structures (Fs-BP). Finally, the polydopamine (PDA) modification is utilized to enhance the photothermal performance, biocompatibility, and chemical stability of doxorubicin (DOX)-loaded Fs-BP and endow NIR/pH-dual-responsive DOX release properties. Fs-BP-DOX@PDA effectively induces tumor cell (Saos-2 and MDA-MB-231) death in vitro, completely eradicates osteosarcoma in mice, and observably promotes bone-regeneration bioactivity. Furthermore, it possesses prominent antibacterial efficiencies toward Staphylococcus aureus(99.2%) and Pseudomonas aeruginosa(99.6%). Overall, this work presents a smart comprehensive fabrication methodology to construct a versatile multiscale therapeutic platform for multimodal osteosarcoma treatment and biomedical tissue engineering.