Cranial defects may result from clinical brain tumor surgery or accidental trauma. The defect skulls require hand-designed skull implants to repair. The edge of the skull implant needs to be accurately matched to the boundary of the skull wound with various defects. For the manual design of cranial implants, it is time-consuming and technically demanding, and the accuracy is low. Therefore, an informer residual attention U-Net (IRA-Unet) for the automatic design of three-dimensional (3D) skull implants was proposed in this paper. Informer was applied from the field of natural language processing to the field of computer vision for attention extraction. Informer attention can extract attention and make the model focus more on the location of the skull defect. Informer attention can also reduce the computation and parameter count from N2 to log(N). Furthermore,the informer residual attention is constructed. The informer attention and the residual are combined and placed in the position of the model close to the output layer. Thus, the model can select and synthesize the global receptive field and local information to improve the model accuracy and speed up the model convergence. In this paper, the open data set of the AutoImplant 2020 was used for training and testing, and the effects of direct and indirect acquisition of skull implants on the results were compared and analyzed in the experimental part. The experimental results show that the performance of the model is robust on the test set of 110 cases fromAutoImplant 2020. The Dice coefficient and Hausdorff distance are 0.940 4 and 3.686 6, respectively. The proposed model reduces the resources required to run the model while maintaining the accuracy of the cranial implant shape, and effectively assists the surgeon in automating the design of efficient cranial repair, thereby improving the quality of the patient’s postoperative recovery.
Prostate cancer is one of the most prevalent malignancies among men worldwide, and its diagnosis relies heavily on accurate analysis of whole slide imaging (WSI) in histopathology. However, manual interpretation is time-consuming and prone to inconsistent accuracy. Existing multiple instance learning (MIL)-based studies can assist diagnosis but still suffer from high computational cost, insufficient exploitation of inter-instance relationships, and neglect of tissue heterogeneity. To address these challenges, this paper proposes a feature distillation multiple instance learning method based on sequence reorganization mamba (FDMIL). The proposed approach leveraged the long-sequence modeling capability of SR-Mamba to capture effective inter-instance dependencies and heterogeneity. Meanwhile, a feature distillation mechanism was introduced to remove redundant representations and reduce computational overhead. Additionally, an auxiliary loss function was designed to mitigate pseudo-bag noise interference. We evaluated FDMIL on the Peking Union Medical College Hospital (PUMCH) prostate cancer WSI dataset and the public Camelyon16 dataset. Experimental results demonstrated that FDMIL achieved significant performance improvements on both datasets, reaching an AUC of 93.9%, ACC of 90.1%, and F1-score of 87.3%, outperforming existing state-of-the-art methods. These results verify the effectiveness and clinical applicability of FDMIL in both institutional and public scenarios.
