arXiv subjects

Yuchen Pei

Publications and source records attributed to Yuchen Pei.

7 recordsLinked to original sources

arXiv2026

When Fusion Fails: Corruption-Aware Rebalanced Fusion for Multi-Modal Medical Image Segmentation

Multi-modal medical image segmentation leverages complementary diagnostic information, yet fusion can underperform single-modality baselines when spatially aligned inputs differ in quality. Here, "corruption" primarily denotes resolution-induced degradation rather than misalignment or complete modality absence, while synthetic noise is evaluated only as an auxiliary setting. We identify a critical optimization-inference inconsistency: degraded modalities can receive weak training updates yet substantially affect predictions, indicating active interference with fusion. We attribute this failure to resampling-induced feature corruption and optimization bias, where noisy features propagate through skip connections and encourage unreliable modality selection. We therefore propose CoReFuse-Med, a Corruption-aware Rebalanced Fusion framework that suppresses corruption during feature transmission and rebalances modality contributions during high-level fusion. Experiments on EPVS, BraTS, and WMH, including multiple Z-axis slice-retention ratios and an auxiliary noise test, demonstrate improved accuracy and robustness under modality-quality discrepancies. Our code is available at https://github.com/lrever/CoReFuse.

cs.CV↗

arXiv2025

Standardized Evaluation of Automatic Methods for Perivascular Spaces Segmentation in MRI -- MICCAI 2024 Challenge Results

Perivascular spaces (PVS), when abnormally enlarged and visible in magnetic resonance imaging (MRI) structural sequences, are important imaging markers of cerebral small vessel disease and potential indicators of neurodegenerative conditions. Despite their clinical significance, automatic enlarged PVS (EPVS) segmentation remains challenging due to their small size, variable morphology, similarity with other pathological features, and limited annotated datasets. This paper presents the EPVS Challenge organized at MICCAI 2024, which aims to advance the development of automated algorithms for EPVS segmentation across multi-site data. We provided a diverse dataset comprising 100 training, 50 validation, and 50 testing scans collected from multiple international sites (UK, Singapore, and China) with varying MRI protocols and demographics. All annotations followed the STRIVE protocol to ensure standardized ground truth and covered the full brain parenchyma. Seven teams completed the full challenge, implementing various deep learning approaches primarily based on U-Net architectures with innovations in multi-modal processing, ensemble strategies, and transformer-based components. Performance was evaluated using dice similarity coefficient, absolute volume difference, recall, and precision metrics. The winning method employed MedNeXt architecture with a dual 2D/3D strategy for handling varying slice thicknesses. The top solutions showed relatively good performance on test data from seen datasets, but significant degradation of performance was observed on the previously unseen Shanghai cohort, highlighting cross-site generalization challenges due to domain shift. This challenge establishes an important benchmark for EPVS segmentation methods and underscores the need for the continued development of robust algorithms that can generalize in diverse clinical settings.

q-bio.QM↗

arXiv2022

Fetal Brain Tissue Annotation and Segmentation Challenge Results

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

eess.IV↗

arXiv2017

A $q$-Robinson-Schensted-Knuth Algorithm and a $q$-polymer

In [Matveev-Petrov 2016](arXiv:1504.00666) a $q$-deformed Robinson-Schensted-Knuth algorithm ($q$RSK) was introduced. In this article we give reformulations of this algorithm in terms of the Noumi-Yamada description, growth diagrams and local moves. We show that the algorithm is symmetric, namely the output tableaux pairs are swapped in a sense of distribution when the input matrix is transposed. We also formulate a $q$-polymer model based on the $q$RSK, prove the corresponding Burke property, which we use to show a strong law of large numbers for the partition function given stationary boundary conditions and $q$-geometric weights. We use the $q$-local moves to define a generalisation of the $q$RSK taking a Young diagram-shape of array as the input. We write down the joint distribution of partition functions in the space-like direction of the $q$-polymer in $q$-geometric environment, formulate a $q$-version of the multilayer polynuclear growth model ($q$PNG) and write down the joint distribution of the $q$-polymer partition functions at a fixed time.

math.CO↗

arXiv2015

On a quantum causal stochastic double product integral related to Lévy area

We study the family of causal double product integrals \begin{equation*} \prod_{a < x < y < b}\left(1 + i{λ\over 2}(dP_x dQ_y - dQ_x dP_y) + i {μ\over 2}(dP_x dP_y + dQ_x dQ_y)\right) \end{equation*} where $P$ and $Q$ are the mutually noncommuting momentum and position Brownian motions of quantum stochastic calculus. The evaluation is motivated heuristically by approximating the continuous double product by a discrete product in which infinitesimals are replaced by finite increments. The latter is in turn approximated by the second quantisation of a discrete double product of rotation-like operators in different planes due to a result in [Hudson-Pei2015]. The main problem solved in this paper is the explicit evaluation of the continuum limit $W$ of the latter, and showing that $W$ is a unitary operator. The kernel of $W$ is written in terms of Bessel functions, and the evaluation is achieved by working on a lattice path model and enumerating linear extensions of related partial orderings, where the enumeration turns out to be heavily related to Dyck paths and generalisations of Catalan numbers.

math-ph↗

arXiv2013

A symmetry property for q-weighted Robinson-Schensted algorithms and other branching insertion algorithms

In O'Connell-Pei(2013) a q-weighted version of the Robinson-Schensted algorithm was introduced. In this paper we show that this algorithm has a symmetry property analogous to the well known symmetry property of the normal Robinson-Schensted algorithm. The proof uses a generalisation of the growth diagram approach introduced by Fomin(1979,1986,1994,1995). This approach, which uses "growth graphs", can also be applied to a wider class of insertion algorithms which have a branching structure, including some of the other q-weighted versions of the Robinson-Schensted algorithm which have recently been introduced by Borodin-Petrov(2013).

math.CO↗

arXiv2013

A q-weighted version of the Robinson-Schensted algorithm

We introduce a q-weighted version of the Robinson-Schensted (column insertion) algorithm which is closely connected to q-Whittaker functions (or Macdonald polynomials with t=0) and reduces to the usual Robinson-Schensted algorithm when q=0. The q-insertion algorithm is `randomised', or `quantum', in the sense that when inserting a positive integer into a tableau, the output is a distribution of weights on a particular set of tableaux which includes the output which would have been obtained via the usual column insertion algorithm. There is also a notion of recording tableau in this setting. We show that the distribution of weights of the pair of tableaux obtained when one applies the q-insertion algorithm to a random word or permutation takes a particularly simple form and is closely related to q-Whittaker functions. In the case $0\le q<1$, the q-insertion algorithm applied to a random word also provides a new framework for solving the q-TASEP interacting particle system introduced (in the language of q-bosons) by Sasamoto and Wadati (1998) and yields formulas which are equivalent to some of those recently obtained by Borodin and Corwin (2011) via a stochastic evolution on discrete Gelfand-Tsetlin patterns (or semistandard tableaux) which is coupled to the q-TASEP process. We show that the sequence of P-tableaux obtained when one applies the q-insertion algorithm to a random word defines another, quite different, evolution on semistandard tableaux which is also coupled to the q-TASEP process.

math.CO↗