A cascading learning method with SegFormer for radiographic measurement of periodontal bone loss.

OBJECTIVE: Marginal alveolar bone loss is one of the key features of periodontitis and can be observed via panoramic radiographs. This study aimed to establish a cascading learning method with deep learning (DL) for precise radiographic bone loss (RBL) measurements at specific tooth positions. MATERIALS AND METHODS: Through the design of two tasks for tooth position recognition and tooth semantic segmentation using the SegFormer model, specific tooth's crown, intrabony portion, and suprabony portion of the roots were obtained. The RBL was subsequently measured by length through these three areas using the principal component analysis (PCA) principal axis. RESULTS: The average intersection over union (IoU) for the tooth position recognition task was 0.8906, with an F1-score of 0.9338. The average IoU for the tooth semantic segmentation task was 0.8465, with an F1-score of 0.9138. When the two tasks were combined, the average IoU was 0.7889, with an F1-score of 0.8674. The correlation coefficient between the RBL prediction results based on the PCA principal axis and the clinicians' measurements exceeded 0.85. Compared to those of the other two methods, the average precision of the predicted RBL was 0.7722, the average sensitivity was 0.7416, and the average F1-score was 0.7444. CONCLUSIONS: The method for predicting RBL using DL and PCA produced promising results, offering rapid and reliable auxiliary information for future periodontal disease diagnosis. CLINICAL RELEVANCE: Precise RBL measurements are important for periodontal diagnosis. The proposed RBL-SF can measure RBL at specific tooth positions and assign the bone loss stage. The ability of the RBL-SF to measure RBL at specific tooth positions can guide clinicians to a certain extent in the accurate diagnosis of periodontitis.

Nonreplicating vaccinia virus vectors expressing the H5 influenza virus hemagglutinin produced in modified Vero cells induce robust protection.

The timely development of safe and effective vaccines against avian influenza virus of the H5N1 subtype will be of the utmost importance in the event of a pandemic. Our aim was first to develop a safe live vaccine which induces both humoral and cell-mediated immune responses against human H5N1 influenza viruses and second, since the supply of embryonated eggs for traditional influenza vaccine production may be endangered in a pandemic, an egg-independent production procedure based on a permanent cell line. In the present article, the generation of a complementing Vero cell line suitable for the production of safe poxviral vaccines is described. This cell line was used to produce a replication-deficient vaccinia virus vector H5N1 live vaccine, dVV-HA5, expressing the hemagglutinin of a virulent clade 1 H5N1 strain. This experimental vaccine was compared with a formalin-inactivated whole-virus vaccine based on the same clade and with different replicating poxvirus-vectored vaccines. Mice were immunized to assess protective immunity after high-dose challenge with the highly virulent A/Vietnam/1203/2004(H5N1) strain. A single dose of the defective live vaccine induced complete protection from lethal homologous virus challenge and also full cross-protection against clade 0 and 2 challenge viruses. Neutralizing antibody levels were comparable to those induced by the inactivated vaccine. Unlike the whole-virus vaccine, the dVV-HA5 vaccine induced substantial amounts of gamma interferon-secreting CD8 T cells. Thus, the nonreplicating recombinant vaccinia virus vectors are promising vaccine candidates that induce a broad immune response and can be produced in an egg-independent and adjuvant-independent manner in a proven vector system.