No abstract

Unsupervised image registration commonly adopts U-Net style networks to predict dense displacement fields in the full-resolution spatial domain. For high-resolution volumetric image data, this process is however resource-intensive and time-consuming. To tackle this problem, we propose the Fourier-Net, replacing the expansive path in a U-Net style network with a parameter-free model-driven decoder. Specifically, instead of our Fourier-Net learning to output a full-resolution displacement field in the spatial domain, we learn its low-dimensional representation in a band-limited Fourier domain. This representation is then decoded by our devised model-driven decoder (consisting of a zero padding layer and an inverse discrete Fourier transform layer) to the dense, full-resolution displacement field in the spatial domain. These changes allow our unsupervised Fourier-Net to contain fewer parameters and computational operations, resulting in faster inference speeds. Fourier-Net is then evaluated on two public 3D brain datasets against various state-of-the-art approaches. For example, when compared to a recent transformer-based method, named TransMorph, our Fourier-Net, which only uses 2.2% of its parameters and 6.66% of the multiply-add operations, achieves a 0.5% higher Dice score and an 11.48 times faster inference speed. Code is available at https://github.com/xi-jia/Fourier-Net.

No abstract

Purpose: To elucidate mechanisms of thymic epithelial tumor (TET) canceration through characterization of genomic mutations and signal pathway alterations.Methods: Primary tumor and blood samples were collected from 21 patients diagnosed with TETs (thymoma and thymic cancer), 15 of whom were screened by nucleic acid extraction and total exon sequencing. Bioinformatics was used to comprehensively analyze sequencing data for these samples, including differences in tumor mutation burden (TMB) and signaling pathways.Results: We found that the gene with the highest mutation frequency in thymic carcinoma was ZNF429 (36%). In addition, mutations in BAP1 (14%), ABI1 (7%), BCL9L (7%), CHEK2 (7%) were only detected in thymic carcinoma, whereas ZNF721 mutations (7%) were found only in thymoma. Mean TMB values for thymic carcinoma and thymoma groups were 0.722 and 0.663 mutations per megabase (Mb), respectively, differences that were not statistically significant. There were significant differences in enriched pathways for cellular components between tumor metastasis and non-metastatic samples. The ErbB signaling pathway was enriched in both the thymoma group and the intersection group, whereas “pathways in cancer” was found in both the thymoma group and thymic cancer group. In contrast, enrichment of longevity-regulating and MAPK signaling pathways was found only in the thymoma group.Conclusions: We identified multiple differences in somatic genes and pathways, providing insights into differences between thymoma and thymic carcinoma that could aid in designing personalized clinical therapy.