Background: Dysferlinopathy is caused by mutations in the dysferlin (DYSF) gene. Here, we described the genetic features of a large cohort of Chinese patients with this disease. Methods: Eighty-nine index patients were included in the study. DYSF gene analysis was performed by Sanger sequencing in 41 patients and targeted next generation sequencing (NGS) in 48 patients. Multiplex ligation-dependent probe amplification (MLPA) was performed to detect exon duplication/deletion in patients with only one pathogenic mutation. Results: Among the 89 index patients, 79 patients were demonstrated to carry two disease-causing (73 cases) or possibly disease-causing mutations (6 cases), including 26 patients with homozygous mutations. We identified 105 different mutations, including 59 novel ones. Notably, in 13 patients in whom only one pathogenic mutation was initially found by Sanger sequencing or NGS, 3 were further identified to carry exon deletions by MLPA. The mutations identified in this study appeared to cluster in the N-terminal region. Mutation types included missense mutations (30.06%), nonsense mutations (17.18%), frameshift mutations (30.67%), in-frame deletions (2.45%), intronic mutations (17.79%), and exonic rearrangement (1.84%). No genotype-phenotype correlation was identified. Conclusions: DYSF mutations in Chinese patients clustered in the N-terminal region of the gene. Exonic rearrangements were found in 23% of patients with only one pathogenic mutation identified by Sanger sequencing or NGS. The novel mutations found in this study greatly expanded the mutational spectrum of dysferlinopathy.
29 September 2023 in Biocybernetics and Biomedical Engineering
Domain adaptation in medical image segmentation enables pre-trained models to generalize to new target domains. Given limited annotated data and privacy constraints, Source-Free Active Domain Adaptation (SFADA) methods provide promising solutions by selecting a few target samples for labeling without accessing source samples. However, in a fully source-free setting, existing works have not fully explored how to select these target samples in a class-balanced manner and how to conduct robust model adaptation using both labeled and unlabeled samples. In this study, we discover that boundary samples with source-like semantics but sharp predictive discrepancies are beneficial for SFADA. We define these samples as the most influential points and propose a slice-wise framework using influential points learning to explore them. Specifically, we detect source-like samples to retain source-specific knowledge. For each target sample, an adaptive K-nearest neighbor algorithm based on local density is introduced to construct neighborhoods of source-like samples for knowledge transfer. We then propose a class-balanced Kullback-Leibler divergence for these neighborhoods, calculating it to obtain an influential score ranking. A diverse subset of the highest-ranked target samples (considered influential points) is manually annotated. Furthermore, we design a progressive teacher model to facilitate SFADA for medical image segmentation. Guided by influential points, this model independently generates and utilizes pseudo-labels to mitigate error accumulation. To further suppress noise, curriculum learning is incorporated into the model to progressively leverage reliable supervision signals from pseudo-labels. Experiments on multiple benchmarks demonstrate that our method outperforms state-of-the-art methods even with only 2.5% of the labeling budget.
Blood cell detection is an essential branch of microscopic imaging for disease diagnosis. TE-YOLOF is an effective model for blood cell detection, and was recently found to have an outstanding trade-off between accuracy and model complexity. However, there is a lack of understanding of whether the dilated encoder in TE-YOLOF works well for blood cell detection. To address this issue, we perform a thorough experimental analysis and find the interesting fact that the dilated encoder is not necessary for TE-YOLOF to perform the blood cell detection task. For the purpose of increasing performance on blood cell detection, in this research, we use the attention mechanism to dominate the dilated encoder place in TE-YOLOF and find that the attention mechanism is effective to address this problem. Based upon these findings, we propose a novel approach, named Enhanced Channel Attention Module (ECAM), based on attention mechanism to achieve precision improvement with less growth on model complexity. Furthermore, we examine the proposed ECAM method compared with other tip-top attention mechanisms and find that the proposed attention method is more effective on blood cell detection task. We incorporate the spatial attention mechanism in CBAM with our ECAM to form a new module, which is named Enhanced-CBAM. We propose a new network named Enhanced Channel Attention Network (ENCANet) based upon Enhanced-CBAM to perform blood cell detection on BCCD dataset. This network can increase the accuracy to 90.3 AP while the parameter is only 6.5 M. Our ENCANet is also effective for conducting cross-domain blood cell detection experiments.