Long-Term Outcomes of High-Risk Medulloblastoma Treatment Background Medulloblastoma is one of the most common malignant brain tumors in children. Despite advancements in treatment, the prognosis for high-risk medulloblastoma patients remains poor. High-risk medulloblastoma typically includes patients with metastatic disease, TP53 mutations, MYC/MY...

Clinical and Biological Heterogeneity in MYC/MYCN-Amplified Medulloblastoma Academic Background Medulloblastoma (MB) is one of the most common malignant brain tumors in children. Despite recent advances in treatment, approximately 30% of patients still die from the disease, and survivors often face long-term treatment-related complications. Amplifi...

Study on Relapse Patterns of Intracranial Ependymoma Background Ependymoma (EPn) is a rare but highly heterogeneous central nervous system tumor, particularly common in children. Despite significant advances in the biology and molecular characteristics of ependymoma in recent years, its relapse patterns remain unclear. The timing and location of re...

Advances in Risk Stratification and Treatment Strategies for Medulloblastoma Background Medulloblastoma is a common malignant brain tumor in children, with significant differences in treatment and prognosis depending on its molecular subtypes. In recent years, advances in molecular biology have revealed that medulloblastoma can be further divided i...

The Oncogenic Role of Dppa4 in Pituitary Neuroendocrine Tumors Academic Background Pituitary Neuroendocrine Tumors (PitNETs) are common intracranial tumors that often exhibit hormone-secreting functions and are a significant cause of hypogonadism and infertility in humans. Although most PitNETs can be controlled through surgery and medication, some...

Learning Meshing from Delaunay Triangulation for 3D Shape Representation Academic Background Surface reconstruction from point clouds is a long-standing problem in computer vision and graphics. Traditional implicit methods, such as Poisson surface reconstruction, compute an implicit function and extract the surface using the Marching Cubes algorith...

Dynamic People Tracking by Service Robots Using Diffusion Models Academic Background Tracking dynamic people in cluttered and crowded human-centered environments is a challenging problem in robotics. Due to intraclass variations such as occlusions, pose deformations, and lighting changes, traditional tracking methods often struggle to accurately id...

Academic Background and Problem Statement Multi-View Stereo (MVS) is a fundamental task in 3D computer vision that aims to recover the 3D geometry of a scene from multiple posed images. This technology has broad applications in robotics, scene understanding, augmented reality, and more. In recent years, learning-based MVS methods have achieved sign...

Academic Background and Problem Statement In recent years, deep neural networks have made significant progress in the field of computer vision, particularly in tasks such as image recognition, object detection, and semantic segmentation. However, even the most advanced deep models struggle when faced with long-tailed distribution data, where the nu...

Academic Background and Problem Statement With the increasing prominence of data privacy issues, Federated Learning (FL) has emerged as a decentralized machine learning paradigm, allowing multiple clients to collaboratively train a global model without sharing data, thereby protecting data privacy. However, existing FL methods typically assume that...