arXiv subjects

Wanying Dou

Publications and source records attributed to Wanying Dou.

4 recordsLinked to original sources

arXiv2026

Zonal-Aware Prostate Cancer Detection and Classification via Hadamard-Fused Mamba-UNet

Accurate clinically significant prostate cancer (csPCa) detection from prostate MRI requires a detailed understanding of the prostate anatomical context. Deep learning approaches have achieved promising results in zonal and lesion segmentation; however, the joint analysis of prostate zonal anatomy and lesion morphology in a unified framework remains relatively underexplored. In this work, we propose ZH-Mamba, a multi-stage zonal-aware csPCa detection framework consisting of two H-Mamba UNets models for prostate zonal segmentation and lesion localization, followed by an anatomy-aware Convolutional Neural Network classifier for csPCa detection. The proposed model leverages a learnable Hadamard Transform-based fusion mechanism to enhance zonal and lesion feature representations without increasing computational complexity. The learned fusion patterns consistently emphasize prostate regions, suggesting that the proposed fusion captures anatomically relevant feature representations. We demonstrate a strong zonal segmentation performance on the PI-CAI dataset, reaching Dice scores of $\textbf{0.95}$, $\textbf{0.85}$, and $\textbf{0.95}$ for whole gland (WG), peripheral zone (PZ), and transition zone (TZ), respectively, providing robust anatomical priors for downstream csPCa detection. Experimental results on an independent internal dataset confirm the generalization capability of the proposed zonal segmentation model. For lesion localization, the H-Mamba UNet achieves a competitive Dice score of $\textbf{0.70}$. Integrating the zonal masks and lesion localization, the proposed ZH-Mamba framework achieves an AUC of $\textbf{0.86}$, Average Precision ($\mathrm{AP}_{\mathrm{Patient}}$) of $\textbf{0.72}$, and F1 score of $\textbf{0.76}$, demonstrating the effectiveness of zonal-aware csPCa detection.

eess.IV↗

arXiv2026

CrossPan: A Comprehensive Benchmark for Cross-Sequence Pancreas MRI Segmentation and Generalization

Automatic pancreas segmentation is fundamental to abdominal MRI analysis, yet deep learning models trained on one MRI sequence often fail catastrophically when applied to another-a challenge that has received little systematic investigation. We introduce CrossPan, a multi-institutional benchmark comprising 1,386 3D scans across three routinely acquired sequences (T1-weighted, T2-weighted, and Out-of-Phase) from eight centers. Our experiments reveal three key findings. First, cross-sequence domain shifts are far more severe than cross-center variability: models achieving Dice scores above 0.85 in-domain collapse to near-zero (<0.02) when transferred across sequences. Second, state-of-the-art domain generalization methods provide negligible benefit under these physics-driven contrast inversions, whereas foundation models like MedSAM2 maintain moderate zero-shot performance through contrast-invariant shape priors. Third, semi-supervised learning offers gains only under stable intensity distributions and becomes unstable on sequences with high intra-organ variability. These results establish cross-sequence generalization-not model architecture or center diversity-as the primary barrier to clinically deployable pancreas MRI segmentation. Dataset and code are available at https://crosspan.netlify.app/.

cs.CV↗

arXiv2025

Rethink Domain Generalization in Heterogeneous Sequence MRI Segmentation

Clinical magnetic-resonance (MR) protocols generate many T1 and T2 sequences whose appearance differs more than the acquisition sites that produce them. Existing domain-generalization benchmarks focus almost on cross-center shifts and overlook this dominant source of variability. Pancreas segmentation remains a major challenge in abdominal imaging: the gland is small, irregularly, surrounded by organs and fat, and often suffers from low T1 contrast. State-of-the-art deep networks that already achieve >90% Dice on the liver or kidneys still miss 20-30% of the pancreas. The organ is also systematically under-represented in public cross-domain benchmarks, despite its clinical importance in early cancer detection, surgery, and diabetes research. To close this gap, we present PancreasDG, a large-scale multi-center 3D MRI pancreas segmentation dataset for investigating domain generalization in medical imaging. The dataset comprises 563 MRI scans from six institutions, spanning both venous phase and out-of-phase sequences, enabling study of both cross-center and cross-sequence variations with pixel-accurate pancreas masks created by a double-blind, two-pass protocol. Through comprehensive analysis, we reveal three insights: (i) limited sampling introduces significant variance that may be mistaken for distribution shifts, (ii) cross-center performance correlates with source domain performance for identical sequences, and (iii) cross-sequence shifts require specialized solutions. We also propose a semi-supervised approach that leverages anatomical invariances, significantly outperforming state-of-the-art domain generalization techniques with 61.63% Dice score improvements and 87.00% on two test centers for cross-sequence segmentation. PancreasDG sets a new benchmark for domain generalization in medical imaging. Dataset, code, and models will be available at https://pancreasdg.netlify.app.

eess.IV↗

arXiv2025

Predicting Risk of Pulmonary Fibrosis Formation in PASC Patients

While the acute phase of the COVID-19 pandemic has subsided, its long-term effects persist through Post-Acute Sequelae of COVID-19 (PASC), commonly known as Long COVID. There remains substantial uncertainty regarding both its duration and optimal management strategies. PASC manifests as a diverse array of persistent or newly emerging symptoms--ranging from fatigue, dyspnea, and neurologic impairments (e.g., brain fog), to cardiovascular, pulmonary, and musculoskeletal abnormalities--that extend beyond the acute infection phase. This heterogeneous presentation poses substantial challenges for clinical assessment, diagnosis, and treatment planning. In this paper, we focus on imaging findings that may suggest fibrotic damage in the lungs, a critical manifestation characterized by scarring of lung tissue, which can potentially affect long-term respiratory function in patients with PASC. This study introduces a novel multi-center chest CT analysis framework that combines deep learning and radiomics for fibrosis prediction. Our approach leverages convolutional neural networks (CNNs) and interpretable feature extraction, achieving 82.2% accuracy and 85.5% AUC in classification tasks. We demonstrate the effectiveness of Grad-CAM visualization and radiomics-based feature analysis in providing clinically relevant insights for PASC-related lung fibrosis prediction. Our findings highlight the potential of deep learning-driven computational methods for early detection and risk assessment of PASC-related lung fibrosis--presented for the first time in the literature.

eess.IV↗