Shunjie-Fabian Zheng

Mr. Shunjie-Fabian Zheng


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
SZShunjie-Fabian Zheng
Shunjie-Fabian Zheng
HLHyeonjun Lee
Hyeonjun Lee
TKThijs Kooi
Thijs Kooi
ADAli Diba
Ali Diba
Breast cancer remains the most commonly diagnosed malignancy among women in the developed world. Early detection through mammography screening plays a pivotal role in reducing mortality rates. While computer-aided diagnosis (CAD) systems have shown promise in assisting radiologists, existing approaches face critical limitations in clinical deployment - particularly in handling the nuanced interpretation of multi-modal data and feasibility due to the requirement of prior clinical history. This study introduces a novel framework that synergistically combines visual features from 2D mammograms with structured textual descriptors derived from easily accessible clinical metadata and synthesized radiological reports through innovative tokenization modules. Our proposed methods in this study demonstrate that strategic integration of convolutional neural networks (ConvNets) with language representations achieves superior performance to vision transformer-based models while handling high-resolution images and enabling practical deployment across diverse populations. By evaluating it on multi-national cohort screening mammograms, our multi-modal approach achieves superior performance in cancer detection and calcification identification compared to unimodal baselines, with particular improvements. The proposed method establishes a new paradigm for developing clinically viable VLM-based CAD systems that effectively leverage imaging data and contextual patient information through effective fusion mechanisms.

30 October 2025 in arXiv
Verified
Preprint
Open access
PDF file
SZShunjie-Fabian Zheng
Shunjie-Fabian Zheng
HLHyeonjun Lee
Hyeonjun Lee
TKThijs Kooi
Thijs Kooi
ADAli Diba
Ali Diba
Large annotated datasets are essential for training robust Computer-Aided Diagnosis (CAD) models for breast cancer detection or risk prediction. However, acquiring such datasets with fine-detailed annotation is both costly and time-consuming. Vision-Language Models (VLMs), such as CLIP, which are pre-trained on large image-text pairs, offer a promising solution by enhancing robustness and data efficiency in medical imaging tasks. This paper introduces a novel Multi-View Mammography and Language Model for breast cancer classification and risk prediction, trained on a dataset of paired mammogram images and synthetic radiology reports. Our MV-MLM leverages multi-view supervision to learn rich representations from extensive radiology data by employing cross-modal self-supervision across image-text pairs. This includes multiple views and the corresponding pseudo-radiology reports. We propose a novel joint visual-textual learning strategy to enhance generalization and accuracy performance over different data types and tasks to distinguish breast tissues or cancer characteristics(calcification, mass) and utilize these patterns to understand mammography images and predict cancer risk. We evaluated our method on both private and publicly available datasets, demonstrating that the proposed model achieves state-of-the-art performance in three classification tasks: (1) malignancy classification, (2) subtype classification, and (3) image-based cancer risk prediction. Furthermore, the model exhibits strong data efficiency, outperforming existing fully supervised or VLM baselines while trained on synthetic text reports and without the need for actual radiology reports.

3 December 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
SZShunjie-Fabian Zheng
Shunjie-Fabian Zheng
KDKathrin Diegruber
Kathrin Diegruber
DEDavid Esser
David Esser
SVSolveig Vieluf
Solveig Vieluf
CSChristopher Stremmel
Christopher Stremmel
Background: Left ventricular (LV) function and lactate dynamics are major prognostic markers after ST-segment elevation myocardial infarction (STEMI). Early identification of patients at risk for impaired LV function or systemic hypoperfusion may improve outcomes. Machine learning (ML) can enhance predictive accuracy beyond traditional statistical methods, yet most prior studies were limited by small sample sizes and categorical outcomes. Methods: We retrospectively analyzed 2132 consecutive STEMI patients admitted to LMU Hospital (2014–2023). After preprocessing, 1608 patients with complete data were included. Thirty-eight demographic, clinical, procedural, and laboratory variables were used to train Decision Tree, Random Forest, and XGBoost regression models for predicting continuous left ventricular ejection fraction (LVEF) at discharge and lactate levels during hospitalization. Model performance was evaluated using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and mean absolute percentage error (MAPE). Feature importance and Shapley additive explanations (SHAP) were applied for interpretability. Results: Ensemble models outperformed single trees. XGBoost achieved the best performance for LVEF prediction (MSE = 0.008, RMSE = 0.086, MAE = 0.068, R2 = 0.35). Lactate prediction showed moderate accuracy (R2 = 0.42 for admission and 0.47 for peak levels). Key predictors included cardiogenic shock, left anterior descending (LAD) culprit lesions, and peak lactate. Conclusions: ML enables individualized prediction of LV function and lactate dynamics after STEMI using routinely available clinical and laboratory data. Ensemble models, particularly XGBoost, demonstrated consistent and clinically meaningful predictive performance and generalizability, supporting their potential for early, data-driven risk stratification in acute cardiac care.