FractureNet: A 3D Convolutional Neural Network Based on the Architecture of m-Ary Tree for Fracture Type Identification

Data augmentation for medical imaging: A systematic literature review

Recent advances in Deep Learning have largely benefited from larger and more diverse training sets. However, collecting large datasets for medical imaging is still a challenge due to privacy concerns and labeling costs. Data augmentation makes it possible to greatly expand the amount and variety of data available for training without actually collecting new samples. Data augmentation techniques range from simple yet surprisingly effective transformations such as cropping, padding, and flipping, to complex generative models. Depending on the nature of the input and the visual task, different data augmentation strategies are likely to perform differently. For this reason, it is conceivable that medical imaging requires specific augmentation strategies that generate plausible data samples and enable effective regularization of deep neural networks. Data augmentation can also be used to augment specific classes that are underrepresented in the training set, e.g., to generate artificial lesions. The goal of this systematic literature review is to investigate which data augmentation strategies are used in the medical domain and how they affect the performance of clinical tasks such as classification, segmentation, and lesion detection. To this end, a comprehensive analysis of more than 300 articles published in recent years (2018-2022) was conducted. The results highlight the effectiveness of data augmentation across organs, modalities, tasks, and dataset sizes, and suggest potential avenues for future research.

Convenient design method for customized implants based on bionic vein structure features

Matching implants to bones is crucial for customized orthopedic medicine. Existing methods for designing customized implants predominantly adopt the parameterized deformation method that uses a fragmented representation of semantic parameters. Such a representation cannot provide information integration management and therefore restricts the retrieval of information regarding implant features and the improvement of customized design efficiency. Therefore, this study proposes a rapid design method for customized implants based on bionic vein structure features. First, a bionic vein structure was designed to represent the implant type. Second, the bionic vein structure was represented by a digraph structure with morphological and dimensional features. Finally, the implant model was rapidly built by retrieving the sketch and other modeling operations. Common implants such as the T-shaped plate, L-shaped plate, clover plate, and femoral stem prosthesis were used as explanations or test cases. The experimental work shows that combining the traditional parametric deformation method with bionic vein structure features in our present method is flexible and efficient results, and can improve the efficiency of customized implant design.