Selected work

Representative Papers

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

Aug 12, 2026

Combinatorial drug screening is hindered by an expansive search space, high costs, and scarce patient samples, while existing approaches rely heavily on molecular profiling and cohort-specific training, limiting their clinical applicability. This work proposes ScreenShot, a hierarchical Transformer-based foundation model pretrained on 40 drug screening datasets, which leverages in-context learning to predict individual patient responses to combination therapies directly from minimal functional assay data—without requiring molecular profiles or task-specific fine-tuning. ScreenShot achieves, for the first time, few-shot prediction of combinatorial drug responses in a zero-fine-tuning, profile-free setting, and integrates a weighted k-means++ active learning strategy to guide experimental design. Evaluated on four independent test sets, ScreenShot outperforms baseline methods in both response prediction accuracy and identification of effective treatments; its active learning strategy attains the hit-detection performance of uniform screening using only one-third of the experimental budget.

0 citationsRead paper

Motion Artifact-Aware Self-Supervised Representation Learning for 3D Brain MRI Motion Artifact Reduction

Aug 10, 2026

This work addresses signal loss, blurring, and geometric distortions in brain MRI caused by patient motion by proposing the SSRL-MAR framework, which achieves motion artifact correction through a three-stage self-supervised learning strategy without requiring paired clean-corrupted data or k-space information. The method first extracts motion representations via 3D patch-based contrastive learning, then constructs a motion artifact synthesis network, and finally leverages the learned degradation model to guide a generator in restoring high-quality images. Notably, it is the first approach to enable motion-aware self-supervised representation learning and image-domain artifact removal without motion labels or paired data, further enhanced by unsupervised domain adaptation for improved generalization. Experiments show that on simulated data, it achieves a PSNR of 23.81 dB and SSIM of 91.55%; on real MR-ART data, domain adaptation yields a 2.0 dB PSNR gain and reduces volumetric errors in key brain structures by over 50%, approaching the performance of supervised methods that rely on paired data.

0 citationsRead paper

Average Cause-Specific Hazard: A Censoring-Invariant Measure of Event Burden Under Competing Risks

Jul 14, 2026

In studies with competing risks, conventional incidence measures are susceptible to censoring mechanisms and often fail to accurately reflect the true burden of events. This work proposes the Average Cause-Specific Hazard (ACSH), a novel incidence metric based on survival weighting that does not rely on assumptions about the censoring distribution. The authors develop a nonparametric estimator for ACSH and a corresponding two-sample comparison procedure. ACSH retains the intuitive interpretability of incidence rates while fully eliminating bias induced by censoring, and enables group comparisons without requiring strong modeling assumptions. Simulation studies demonstrate its favorable finite-sample properties, and its application to the CANVAS trial yields robust and interpretable estimates of between-group differences.

0 citationsRead paper

Value-of-Information Analysis for External Validation of Risk Prediction Models in Multicenter Studies and Systematic Reviews

Jul 02, 2026

This study addresses the challenge of evaluating whether risk prediction models outperform default strategies in external validation settings, where limited sample sizes and unaccounted multicenter heterogeneity often hinder reliable assessment. The authors extend the expected value of perfect information (EVPI) and expected value of partial perfect information (EVPPI) to a multicenter and systematic review framework, introducing novel metrics—EVPIglobal, EVPIcluster_j, EVPIcluster, and EVPPIcluster,prevalence—to distinguish between global and local optimal strategies and to separate observed from unobserved centers, thereby disentangling sources of heterogeneity. Leveraging the MetaNB R package within a Bayesian decision-theoretic and meta-analytic framework, they conduct a value-of-information analysis of the ADNEX model across 36 centers. Results indicate that adopting ADNEX globally requires no additional data (EVPIglobal = 0); eliminating uncertainty about center-specific performance and prevalence could reduce false positives by 1,134 cases annually, with prevalence uncertainty alone accounting for 158 avoidable false positives; and in unobserved centers, there remains a 3% probability that the default strategy is superior.

0 citationsRead paper

MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration

Jun 30, 2026

This work proposes a training-free blind image restoration method for images degraded by a combination of blur, downsampling, noise, and missing pixels. Leveraging implicit neural representations (INRs), the approach introduces a coarse-to-fine multi-scale residual optimization framework augmented with an explicit ℓ₀-type sparse proximal regularization in the high-resolution image domain. This regularization effectively mitigates the spectral bias and artifacts inherent to INRs. By jointly modeling the mixed degradation process and structural image priors, the method achieves consistently superior performance over existing zero-shot techniques such as Deep Image Prior across multiple benchmarks, delivering stable, interpretable, and high-fidelity reconstructions with well-preserved fine details.

0 citationsRead paper

Recent publications

Latest Papers

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

Aug 12, 2026

Combinatorial drug screening is hindered by an expansive search space, high costs, and scarce patient samples, while existing approaches rely heavily on molecular profiling and cohort-specific training, limiting their clinical applicability. This work proposes ScreenShot, a hierarchical Transformer-based foundation model pretrained on 40 drug screening datasets, which leverages in-context learning to predict individual patient responses to combination therapies directly from minimal functional assay data—without requiring molecular profiles or task-specific fine-tuning. ScreenShot achieves, for the first time, few-shot prediction of combinatorial drug responses in a zero-fine-tuning, profile-free setting, and integrates a weighted k-means++ active learning strategy to guide experimental design. Evaluated on four independent test sets, ScreenShot outperforms baseline methods in both response prediction accuracy and identification of effective treatments; its active learning strategy attains the hit-detection performance of uniform screening using only one-third of the experimental budget.

0 citationsRead paper

Motion Artifact-Aware Self-Supervised Representation Learning for 3D Brain MRI Motion Artifact Reduction

Aug 10, 2026

This work addresses signal loss, blurring, and geometric distortions in brain MRI caused by patient motion by proposing the SSRL-MAR framework, which achieves motion artifact correction through a three-stage self-supervised learning strategy without requiring paired clean-corrupted data or k-space information. The method first extracts motion representations via 3D patch-based contrastive learning, then constructs a motion artifact synthesis network, and finally leverages the learned degradation model to guide a generator in restoring high-quality images. Notably, it is the first approach to enable motion-aware self-supervised representation learning and image-domain artifact removal without motion labels or paired data, further enhanced by unsupervised domain adaptation for improved generalization. Experiments show that on simulated data, it achieves a PSNR of 23.81 dB and SSIM of 91.55%; on real MR-ART data, domain adaptation yields a 2.0 dB PSNR gain and reduces volumetric errors in key brain structures by over 50%, approaching the performance of supervised methods that rely on paired data.

0 citationsRead paper

Average Cause-Specific Hazard: A Censoring-Invariant Measure of Event Burden Under Competing Risks

Jul 14, 2026

In studies with competing risks, conventional incidence measures are susceptible to censoring mechanisms and often fail to accurately reflect the true burden of events. This work proposes the Average Cause-Specific Hazard (ACSH), a novel incidence metric based on survival weighting that does not rely on assumptions about the censoring distribution. The authors develop a nonparametric estimator for ACSH and a corresponding two-sample comparison procedure. ACSH retains the intuitive interpretability of incidence rates while fully eliminating bias induced by censoring, and enables group comparisons without requiring strong modeling assumptions. Simulation studies demonstrate its favorable finite-sample properties, and its application to the CANVAS trial yields robust and interpretable estimates of between-group differences.

0 citationsRead paper

Value-of-Information Analysis for External Validation of Risk Prediction Models in Multicenter Studies and Systematic Reviews

Jul 02, 2026

This study addresses the challenge of evaluating whether risk prediction models outperform default strategies in external validation settings, where limited sample sizes and unaccounted multicenter heterogeneity often hinder reliable assessment. The authors extend the expected value of perfect information (EVPI) and expected value of partial perfect information (EVPPI) to a multicenter and systematic review framework, introducing novel metrics—EVPIglobal, EVPIcluster_j, EVPIcluster, and EVPPIcluster,prevalence—to distinguish between global and local optimal strategies and to separate observed from unobserved centers, thereby disentangling sources of heterogeneity. Leveraging the MetaNB R package within a Bayesian decision-theoretic and meta-analytic framework, they conduct a value-of-information analysis of the ADNEX model across 36 centers. Results indicate that adopting ADNEX globally requires no additional data (EVPIglobal = 0); eliminating uncertainty about center-specific performance and prevalence could reduce false positives by 1,134 cases annually, with prevalence uncertainty alone accounting for 158 avoidable false positives; and in unobserved centers, there remains a 3% probability that the default strategy is superior.

0 citationsRead paper

MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration

Jun 30, 2026

This work proposes a training-free blind image restoration method for images degraded by a combination of blur, downsampling, noise, and missing pixels. Leveraging implicit neural representations (INRs), the approach introduces a coarse-to-fine multi-scale residual optimization framework augmented with an explicit ℓ₀-type sparse proximal regularization in the high-resolution image domain. This regularization effectively mitigates the spectral bias and artifacts inherent to INRs. By jointly modeling the mixed degradation process and structural image priors, the method achieves consistently superior performance over existing zero-shot techniques such as Deep Image Prior across multiple benchmarks, delivering stable, interpretable, and high-fidelity reconstructions with well-preserved fine details.

0 citationsRead paper