Citations

Clear

6 citation(s) found for "Han, Wenchao".

The CARE framework for AI dataset documentation in clinical laboratories: a comprehensive checklist and data lineage methodology
Garcia, Christopher A., Reed, Katelyn A. , Lantz, Eric, Day, Patrick L. , Stadler, Brian C, Zarella, Mark D. , Hart, Steven N. , Han, Wenchao, Wahsh, Ezzaddin Al, Novak, Debra, McClintock, David S. , Day, Patrick , Tavolara, Thomas E, Al Wahsh, Ezzaddin, Novak, Debra A, McClintock, David S , Hart, Steven N , Lantz, Eric, Han, Wenchao, Tavolara, Thomas Erol , Wahsh, EzzAddin Al, Novak, Debra A

Mayo Clinic

American Journal of Clinical Pathology | March 7, 2026 | Volume: 165 | Issue: 5 | Pages: No page available

10.1093/ajcp/aqag029 | PMID 42114029 Get It

Abstract Objectives Traditional laboratory regulatory frameworks provide robust guidance for conventional clinical testing but lack requirements for data documentation for artificial intelligence and machine learning (AI/ML) solutions. This gap creates significant risks since AI solutions directly inherit patterns, biases, and limitations from their training data. Here, we describe the development and implementation of a comprehensive data documentation checklist with accompanying data lineage for use within an AI lifecycle framework for clinical laboratories. Methods Building on the previously established Clinical AI Readiness Evaluator (CARE) framework, we developed a comprehensive data checklist and data lineage methodology through a multiphase process, including (1) comprehensive review of existing AI/ML data documentation frameworks, (2) focused meetings with 3 institutional AI operations teams, and (3) 3 rounds of iterative refinement by our multidisciplinary team. The checklist’s effectiveness was then assessed using 3 diverse AI/ML projects moving through the CARE framework. Results The CARE Data Checklist and Data Lineage provide a structured approach to documenting critical aspects of datasets used in AI/ML projects, including data composition, demographics, collection methods, labeling processes, usage constraints, maintenance requirements, and a data readiness assessment. The checklist addresses unique data-centric challenges of AI/ML applications, facilitating transparency, reproducibility, and regulatory compliance. Conclusions The CARE Data Checklist and Data Lineage serve as both a technical guide and a communication tool bridging gaps between technical and clinical stakeholders. By working on these documents early in the AI lifecycle, laboratories can anticipate and address data-related challenges, ultimately saving time, optimizing resources, and improving the reliability of AI-augmented laboratory solutions.
A human-in-the-loop explanation framework for morphologically transparent AI predictions from whole-slide images
Lou, Peiliang , Zhu, Yitan , Kumari, Roopa, Yang, William , Wang, Y. Claire , Guo, Ruifemg, Goode, Ellen, Huang, Yajue, Han, Wenchao, Feng, Tianshu , Wang, Chen, Zhu, Yitan , Chia, Nicholas , Yang, William, Wang, Yan, Novotny, Brenna C. , Winham, Stacey J. , Goode, Ellen L. , Han, Wenchao, Wang, Chen

Mayo Clinic

No container title available | January 30, 2026 | Volume: No volume available | Issue: No issue available | Pages: No page available

10.64898/2026.01.27.701796 Get It

Abstract Deep learning models enable the prediction of clinical endpoints from whole-slide images (WSIs), but many such models function as “black boxes”, lacking transparency about whether and which histomorphological patterns drive their predictions, hindering interpretability and clinical adoption. Here we propose a human-in-the-loop explanation framework, MorphoXAI, which provides both local and global interpretability for deep learning models by incorporating human-expert interpretations. At the global level, it reveals the histomorphological patterns on which the model consistently relies to distinguish between classes of WSIs, as well as the patterns associated with confusion between classes. At the local level, it indicates which of these patterns are used in the prediction of an individual WSI and which regions within the slide correspond to such patterns. We validated our method on a deep learning model trained for ovarian tumor histologic subtype prediction. The results show that our framework generates explanations that accurately reflect the histomorphology underlying the model’s predictions at both global and local levels. For interpretability and clinical utility in diagnostic contexts, human evaluation results showed that our explanations were easy to interpret, rich in diagnostic features, and directly helpful for diagnostic decision-making, thereby enhancing pathologist-AI collaboration. Our work highlights that unifying global and local explanations and grounding them in expert-interpreted morphology enhances the interpretability and verifiability of deep learning models, thereby facilitating the transparent deployment of such models in clinical practice.
Lymphovision: A lymphoma-specialized foundation model for histology-based lymphoma classification and subtyping
Seheult, Jansen N. , Han, Wenchao, Keser, Reyhan Kevser , Sapkota, Nishchal, Kumar, Nilesh, Mwangi, Raphael , Dalland, Joanna , Larson, D. J., Zhang, Chi , Dangott, Bryan, McClintock, David S. , Reed, Katelyn A. , Schwartz, Kaitlin, Bjorheim, Annette, Lee, Jodi, Halvorson, J. Derek, Nowakowski, Grzegorz S. , Ansell, Stephen M. , King, Rebecca, Seheult, Jansen N , Tavolara, Thomas Erol , Kumar, Nilesh, Larson, Daniel, Gibson, Sarah E. , Horna, Pedro , Schwartz, Kaitlin, Lee, Jodi, Halvorson, Joseph, Witzig, Thomas E. , Maurer, Matthew J. , Cerhan, James R. , Hsi, Eric D.

Mayo Clinic

Blood | December 4, 2025 | Volume: 146 | Issue: Supplement 1 | Pages: 117-117

10.1182/blood-2025-117 Get It

Abstract Background: Recent advances in computer vision have given rise to image foundation models (FMs), large-scale neural networks pre-trained on millions of unlabeled histopathology patches, which can learn generalizable representations of tissue morphology. In many cancers, these FMs have predicted genetic mutations and prognoses directly from histology, suggesting that morphology encodes “hidden” molecular information. In lymphoma, this field is nascent but growing.General-purpose histopathology FMs have limited representation of lymphoid morphology. We developed and evaluated LymphoVision, a lymphoma-specialized image foundation model pretrained with self-supervised learning, to extract clinically meaningful features from routine hematoxylin and eosin (H&E) histology. Methods: LymphoVision was pre-trained using knowledge distillation and consistency (DINOv2) on over 37 million multi-resolution patches (5x, 10x, 20x, 40x) sampled using a density-aware strategy from 31,211 H&E whole slide images (WSIs) from 9,155 archival lymphoma and reactive lymphoproliferative cases. To ensure diverse, representative samples, our patch sampling method uses an efficient graph-based clustering algorithm and prioritizes morphologically informative regions by clustering patch embeddings and performing density sampling within each cluster. The pretrained encoder was evaluated using a clustering-constrained attention multiple instance learning (MIL) framework on three diagnostic tasks: (1) cell-of-origin (COO) classification in diffuse large B-cell lymphoma (DLBCL), distinguishing germinal center B-cell (GCB) from non-GCB subtypes based on the Hans immunohistochemistry algorithm; (2) follicular lymphoma (FL) grading, differentiating low-grade (grades 1–2) from high-grade (grade 3); and (3) multiclass lymphoma subtype classification across six categories: DLBCL, FL, marginal zone lymphoma (MZL), mantle cell lymphoma (MCL), classical Hodgkin lymphoma (CHL), and benign/reactive lymphoid conditions. WSI-level labels were derived from pathology reports, and none of the evaluation cases were included in pretraining. Models used a ViT-Giant LymphoVision backbone to generate 20x patch embeddings, followed by MIL using 50% training data and 2-fold cross-validation (25% validation, 25% test). Performance was assessed using area under the receiver operating characteristic curve (AUC), accuracy, recall (sensitivity) and F1 score. Results: For DLBCL COO classification (total n=358 cases), LymphoVision achieved a mean test AUC of 0.93 (range 0.92–0.94), accuracy of 84.5% and F1 of 0.85 across two independent test folds (n=91 per fold, 50% GCB). These results outperformed general-purpose FMs on the same task and cases, including Virchow-v2 (AUC 0.85) and UNI-v2 (AUC 0.88), despite those models being pretrained on 10–100 times more images. For FL grading (total n=660 cases), the test set in each fold included 166 cases (18% grade 3), yielding a mean test AUC of 0.88 (range 0.87–0.90), accuracy of 89.2% and F1 of 0.80. In multiclass lymphoma subtype classification (total n=1,176 cases), the test set included 296 cases per fold. LymphoVision achieved a mean test AUC of 0.98 (range 0.97-0.99), mean test accuracy of 87.1% and mean F1 of 0.84. Class-wise recall was 92.0% for DLBCL (n=112), 88.2% for FL (n=72), 77.2% for MZL (n=29), 70.8% for MCL (n=35), 87.5% for CHL (n=24), and 95.8% for benign/reactive lymphoid conditions (n=24). Conclusion: LymphoVision is a lymphoma-specialized FM trained using self-supervision that achieves high diagnostic accuracy across multiple clinically meaningful tasks using weak supervision and standard H&E images, suggesting the encoder has learned fine-grained lymphoma morphology. Based on historical benchmarks from the 1997 International Lymphoma Study Group classification project, expert hematopathologists achieved diagnostic agreement rates of 55% to 84% using H&E morphology alone for the non-Hodgkin lymphoma (NHL) entities included in our multiclass task. LymphoVision approached or exceeded these benchmarks. These findings underscore the value of our approach using disease-specialized pretraining and intelligent patch sampling for data-efficient histopathology learning. LymphoVision has the potential to augment diagnostics, enable scalable AI-powered classification in real-world workflows, and serve as a foundation for prognostic and theragnostic applications. External validation and multimodal integration are ongoing.
Clinical Validation and Post-Implementation Performance Monitoring of a Neural Network-Assisted Approach for Detecting Chronic Lymphocytic Leukemia Minimal Residual Disease by Flow Cytometry
Seheult, Jansen N. , Otteson, Gregory E., Weybright, Matthew J. , Timm, Michael, Han, Wenchao, Horna, Pedro , Olteanu, Horatiu , Shi, Min , Timm, Michael M, Horna, Pedro , Olteanu, Horatiu , Shi, Min , Seheult, Jansen N , Jevremović, Dragan

Mayo Clinic

Cancers | May 19, 2025 | Volume: 17 | Issue: 10 | Pages: 1688

10.3390/cancers17101688 | PMID 40427185 Get It

Background: Flow cytometric detection of minimal residual disease (MRD) in chronic lymphocytic leukemia (CLL) is complex, time-consuming, and subject to inter-operator variability. Deep neural networks (DNNs) offer potential for standardization and efficiency improvement, but require rigorous validation and monitoring for safe clinical implementation. Methods: We evaluated a DNN-assisted human-in-the-loop approach for CLL MRD detection. Initial validation included method comparison against manual analysis (n = 240), precision studies, and analytical sensitivity verification. Post-implementation monitoring comprised four components: daily electronic quality control, input data drift detection, error analysis, and attribute acceptance sampling. Laboratory efficiency was assessed through a timing study of 161 cases analyzed by five technologists. Results: Method comparison demonstrated 97.5% concordance with manual analysis for qualitative classification (sensitivity 100%, specificity 95%) and excellent correlation for quantitative assessment (r = 0.99, Deming slope = 0.99). Precision studies confirmed high repeatability and within-laboratory precision across multiple operators. Analytical sensitivity was verified at 0.002% MRD. Post-implementation monitoring identified 2.97% of cases (26/874) with input data drift, primarily high-burden CLL and non-CLL neoplasms. Error analysis showed the DNN alone achieved 97% sensitivity compared to human-in-the-loop-reviewed results, with 13 missed cases (1.5%) showing atypical immunophenotypes. Attribute acceptance sampling confirmed 98.8% of reported negative cases were true negatives. The DNN-assisted workflow reduced average analysis time by 60.3% compared to manual analysis (4.2 ± 2.3 vs. 10.5 ± 5.8 min). Conclusions: The implementation of a DNN-assisted approach for CLL MRD detection in a clinical laboratory provides diagnostic performance equivalent to expert manual analysis while substantially reducing analysis time. Comprehensive performance monitoring ensures ongoing safety and effectiveness in routine clinical practice. This approach provides a model for responsible AI integration in clinical laboratories, balancing automation benefits with expert oversight.
Enhancing HER2 testing in breast cancer: predicting fluorescence in situ hybridization (FISH) scores from immunohistochemistry images via deep learning
Macaulay, Daniel O , Han, Wenchao, Zarella, Mark D. , Garcia, Chris, Garcia, Chris A, Tavolara, Thomas E, Macaulay, Daniel O , Tavolara, Thomas Erol

Mayo Clinic

The Journal of Pathology: Clinical Research | March 12, 2025 | Volume: 11 | Issue: 2 | Pages: No page available

10.1002/2056-4538.70024 | PMID 40050230 Get It

AbstractBreast cancer affects millions globally, necessitating precise biomarker testing for effective treatment. HER2 testing is crucial for guiding therapy, particularly with novel antibody‐drug conjugates (ADCs) like trastuzumab deruxtecan, which shows promise for breast cancers with low HER2 expression. Current HER2 testing methods, including immunohistochemistry (IHC) and in situ hybridization (ISH), have limitations. IHC, a semi‐quantitative assay, is prone to interobserver variability. While ISH provides higher precision than IHC, it remains more resource‐intensive in terms of cost and workflow. However, turnaround time is typically faster than that of other advanced molecular methods such as next‐generation sequencing. We adapted the clustering‐constrained‐attention multiple‐instance deep learning model to improve IHC testing and reduce dependence on reflex fluorescence ISH (FISH) tests. Using 5,731 HER2 IHC images, including 592 cases with FISH testing, we trained two models: one for predicting HER2 scores from IHC images and another for predicting FISH scores from equivocal cases. The HER2 IHC score prediction model achieved 91% ± 0.01 overall accuracy and a receiver operating characteristic (ROC) area under the curve (AUC) of 0.98 ± 0.01. The FISH score prediction model had an ROC AUC of 0.84 ± 0.07, with sensitivity at 0.37 ± 0.13 and specificity at 0.96 ± 0.03. External validation on cases from 203 institutions showed similar performance. The HER2 IHC model maintained a 91% ± 0.01 accuracy and an ROC AUC of 0.98 ± 0.01, while the FISH model had an ROC AUC of 0.75 ± 0.03, with sensitivity at 0.28 ± 0.04 and specificity at 0.93 ± 0.01. Our model advances HER2 scoring by reducing subjectivity and variability in current scoring methods. Despite lower accuracy and sensitivity in the FISH prediction model, it may be a beneficial option for settings where reflex FISH testing is unavailable or prohibitive. With high specificity, our model can serve as an effective screening tool, enhancing breast cancer diagnosis and treatment selection.
An AI Model (LORIS) to Predict Immune Checkpoint Blockade Response in Cancer: A Clinical Data Science Perspective
Han, Wenchao, McClintock, David S. , Tavolara, Thomas E, McClintock, David S , Tavolara, Thomas Erol

Mayo Clinic

Clinical Chemistry | November 8, 2024 | Volume: 71 | Issue: 3 | Pages: 345-347

10.1093/clinchem/hvae196 | PMID 39688398 Get It