Zheyi Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zheyi Ji has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Junhan Zhao
Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
2 shared publications - Sen Yang
Department of Radiation Oncology, Stanford University School of Medicine, Stanford, USA
2 shared publications - Xiyue Wang
Department of Biomedical Informatics Harvard Medical School Boston USA
2 shared publications - Chang He
Department of Human Genetics, University of Chicago, Chicago, IL, USA
1 shared publication - Chengyun Dou
Department of Infectious Diseases The First Affiliated Hospital University of South China Hengyang Hunan China
1 shared publication - Chijioke Chukwudi
Division of Cardiac Surgery, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, USA
1 shared publication
Latest Publications
- Open Access
- 29 September 2026
- Published by Wiley in Advanced Science
- p. e78019
A Generalizable Multimodal Model for Treatment‐Stratified Risk and Survival Assessment under Real‐World Constraints: A Multi‐Center Study of Colorectal Cancer
Integrating histopathology, genomic, and clinical phenotypes holds promise for improving prognostic patient stratification, including within treatment‐defined subgroups, in colorectal cancer (CRC). However, ensuring the availability of all modalities in routine clinical practice remains challenging. Comprehensive molecular profiling is often constrained by cost and turnaround time, leaving histopathology as the most consistently available modality across institutions. In addition, variability in staining protocols, scanning devices, patient demographics, and outcome distributions across centers undermines the generalizability of models trained under controlled conditions with complete inputs. To address these challenges, we developed the Domain‐Adaptive Incomplete Multimodal Stratification framework (DAIMS). DAIMS leverages paired histopathology, genomic, and clinical data during training to learn generalizable disease representations and uses histology‐derived surrogate latent representations when auxiliary modalities are unavailable, enabling flexible histology‐only inference. Trained on TCGA samples and validated on two independent European and East Asian cohorts comprising 842 patients, DAIMS consistently outperformed state‐of‐the‐art methods. Adapted DAIMS improved the C‐index by 5.6%–13.9% on F1CRC and 4.1%–9.0% on SURGEN compared with baseline methods. DAIMS improved within‐cohort prognostic discrimination and localized prognostically relevant morphological patterns that remained stable across institutions. Our evaluation showed that DAIMS achieved generalizable survival stratification across disease stages, molecular subgroups, and treatment‐defined patient groups.
- 29 September 2026
- Published by Wiley in Advanced Science
- p. e78019
Open AccessA Generalizable Multimodal Model for Treatment‐Stratified Risk and Survival Assessment under Real‐World Constraints: A Multi‐Center Study of Colorectal Cancer
Integrating histopathology, genomic, and clinical phenotypes holds promise for improving prognostic patient stratification, including within treatment‐defined subgroups, in colorectal cancer (CRC). However, ensuring the availability of all modalities in routine clinical practice remains challenging. Comprehensive molecular profiling is often constrained by cost and turnaround time, leaving histopathology as the most consistently available modality across institutions. In addition, variability in staining protocols, scanning devices, patient demographics, and outcome distributions across centers undermines the generalizability of models trained under controlled conditions with complete inputs. To address these challenges, we developed the Domain‐Adaptive Incomplete Multimodal Stratification framework (DAIMS). DAIMS leverages paired histopathology, genomic, and clinical data during training to learn generalizable disease representations and uses histology‐derived surrogate latent representations when auxiliary modalities are unavailable, enabling flexible histology‐only inference. Trained on TCGA samples and validated on two independent European and East Asian cohorts comprising 842 patients, DAIMS consistently outperformed state‐of‐the‐art methods. Adapted DAIMS improved the C‐index by 5.6%–13.9% on F1CRC and 4.1%–9.0% on SURGEN compared with baseline methods. DAIMS improved within‐cohort prognostic discrimination and localized prognostically relevant morphological patterns that remained stable across institutions. Our evaluation showed that DAIMS achieved generalizable survival stratification across disease stages, molecular subgroups, and treatment‐defined patient groups.
- 5 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (8) , 5862-5874
Counterfactual Bidirectional Co-Attention Transformer for Integrative Histology-Genomic Cancer Risk Stratification
Applying deep learning to predict patient prognostic survival outcomes using histological whole-slide images (WSIs) and genomic data is challenging due to the morphological and transcriptomic heterogeneity present in the tumor microenvironment. Existing deep learning-enabled methods often exhibit learning biases, primarily because the genomic knowledge used to guide directional feature extraction from WSIs may be irrelevant or incomplete. This results in a suboptimal and sometimes myopic understanding of the overall pathological landscape, potentially overlooking crucial histological insights. To tackle these challenges, we propose the CounterFactual Bidirectional Co-Attention Transformer framework. By integrating a bidirectional co-attention layer, our framework fosters effective feature interactions between the genomic and histology modalities and ensures consistent identification of prognostic features from WSIs. Using counterfactual reasoning, our model utilizes causality to model unimodal and multimodal knowledge for cancer risk stratification. This approach directly addresses and reduces bias, enables the exploration of ’what-if' scenarios, and offers a deeper understanding of how different features influence survival outcomes. Our framework, validated across eight diverse cancer benchmark datasets from The Cancer Genome Atlas (TCGA), represents a major improvement over current histology-genomic model learning methods. It shows an average 2.5% improvement in c-index performance over 18 state-of-the-art models in predicting patient prognoses across eight cancer types. Our code is released at https://github.com/BusyJzy599/CFBCT-main.
- 5 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (8) , 5862-5874
Counterfactual Bidirectional Co-Attention Transformer for Integrative Histology-Genomic Cancer Risk Stratification
Applying deep learning to predict patient prognostic survival outcomes using histological whole-slide images (WSIs) and genomic data is challenging due to the morphological and transcriptomic heterogeneity present in the tumor microenvironment. Existing deep learning-enabled methods often exhibit learning biases, primarily because the genomic knowledge used to guide directional feature extraction from WSIs may be irrelevant or incomplete. This results in a suboptimal and sometimes myopic understanding of the overall pathological landscape, potentially overlooking crucial histological insights. To tackle these challenges, we propose the CounterFactual Bidirectional Co-Attention Transformer framework. By integrating a bidirectional co-attention layer, our framework fosters effective feature interactions between the genomic and histology modalities and ensures consistent identification of prognostic features from WSIs. Using counterfactual reasoning, our model utilizes causality to model unimodal and multimodal knowledge for cancer risk stratification. This approach directly addresses and reduces bias, enables the exploration of ’what-if' scenarios, and offers a deeper understanding of how different features influence survival outcomes. Our framework, validated across eight diverse cancer benchmark datasets from The Cancer Genome Atlas (TCGA), represents a major improvement over current histology-genomic model learning methods. It shows an average 2.5% improvement in c-index performance over 18 state-of-the-art models in predicting patient prognoses across eight cancer types. Our code is released at https://github.com/BusyJzy599/CFBCT-main.