WWWei Wu

Wei Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Wei Wu has a total of 84 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Supplementary Tables 1-13 from T-cell Receptor Profiling of Blood to Detect Lung Cancer

    by Maria T. Søgaard, Diane Tseng, Sarah Gibbs, Wei Wu, Lorna G. Nolan, Pamela Y. Yang, Mason Lai, Jianhong Cao, Sudhakar Pipavath, Koshlan Mayer-Blackwell, et al.

    Supplementary Tables 1-13 from T-cell Receptor Profiling of Blood to Detect Lung Cancer

  • Open Access

    Figure S5 from T-cell Receptor Profiling of Blood to Detect Lung Cancer

    by Maria T. Søgaard, Diane Tseng, Sarah Gibbs, Wei Wu, Lorna G. Nolan, Pamela Y. Yang, Mason Lai, Jianhong Cao, Sudhakar Pipavath, Koshlan Mayer-Blackwell, et al.

    Validation of TCR disease status prediction on a CMV cohort

  • Open Access

    Data from T-cell Receptor Profiling of Blood to Detect Lung Cancer

    by Maria T. Søgaard, Diane Tseng, Sarah Gibbs, Wei Wu, Lorna G. Nolan, Pamela Y. Yang, Mason Lai, Jianhong Cao, Sudhakar Pipavath, Koshlan Mayer-Blackwell, et al.

    The blood T-cell receptor (TCR) repertoire broadly reflects current and lifetime immune responses against infectious pathogens and cancer, but the circulating T-cell repertoire remains a largely untapped resource for cancer biomarker studies due to repertoire complexity and limited profiling data. In this study, we investigated the use of blood TCR sequencing for the early detection of lung cancer. We sequenced the leukocyte fraction of peripheral blood from 633 individuals divided into a case–control cohort (n = 511) and a lung cancer screening cohort (n = 122), representing more than 12.6 million unique clonotypes. Based on the TCR repertoires in these individuals, we devised a Tumor Immune Lymphocyte Score (TILS) using either TCR specificity groups (TILS-A) or highly recurrent “public” TCR clonotypes (TILS-B) capable of detecting lung cancer. TILS-A consisted of 125 TCR specificity groups that outperformed the TILS-B classifier of 49 public, TCRβ-Vβ–defined clonotypes for cancer detection. TILS classifiers (TILS-A and TILS-B) provided predictive value after accounting for age, smoking status, and nodule size in the lung cancer screening cohort and improved cancer prediction for individuals with indeterminate lung cancer risk. In the subgroup analysis, TILS-A was associated with lung cancer in both early- and late-stage disease, had improved accuracy when accounting for HLA status, and was validated in an external dataset studying lung cancer initiation. Collectively, these data suggest that profiles of the circulating T-cell response can provide value for lung cancer detection and support its use as a diagnostic tool.

  • Open Access

    Figure S3 from T-cell Receptor Profiling of Blood to Detect Lung Cancer

    by Maria T. Søgaard, Diane Tseng, Sarah Gibbs, Wei Wu, Lorna G. Nolan, Pamela Y. Yang, Mason Lai, Jianhong Cao, Sudhakar Pipavath, Koshlan Mayer-Blackwell, et al.

    TCRβ sequences belonging to both TILS-A and TILS-B classifiers

  • Open Access

    Figure S1 from T-cell Receptor Profiling of Blood to Detect Lung Cancer

    by Maria T. Søgaard, Diane Tseng, Sarah Gibbs, Wei Wu, Lorna G. Nolan, Pamela Y. Yang, Mason Lai, Jianhong Cao, Sudhakar Pipavath, Koshlan Mayer-Blackwell, et al.

  • T-cell Receptor Profiling of Blood to Detect Lung Cancer

    by Maria T. Søgaard, Diane Tseng, Sarah Gibbs, Wei Wu, Lorna G. Nolan, Pamela Y. Yang, Mason Lai, Jianhong Cao, Sudhakar Pipavath, Koshlan Mayer-Blackwell, et al.

    The blood T-cell receptor (TCR) repertoire broadly reflects current and lifetime immune responses against infectious pathogens and cancer, but the circulating T-cell repertoire remains a largely untapped resource for cancer biomarker studies due to repertoire complexity and limited profiling data. In this study, we investigated the use of blood TCR sequencing for the early detection of lung cancer. We sequenced the leukocyte fraction of peripheral blood from 633 individuals divided into a case–control cohort (n = 511) and a lung cancer screening cohort (n = 122), representing more than 12.6 million unique clonotypes. Based on the TCR repertoires in these individuals, we devised a Tumor Immune Lymphocyte Score (TILS) using either TCR specificity groups (TILS-A) or highly recurrent “public” TCR clonotypes (TILS-B) capable of detecting lung cancer. TILS-A consisted of 125 TCR specificity groups that outperformed the TILS-B classifier of 49 public, TCRβ-Vβ–defined clonotypes for cancer detection. TILS classifiers (TILS-A and TILS-B) provided predictive value after accounting for age, smoking status, and nodule size in the lung cancer screening cohort and improved cancer prediction for individuals with indeterminate lung cancer risk. In the subgroup analysis, TILS-A was associated with lung cancer in both early- and late-stage disease, had improved accuracy when accounting for HLA status, and was validated in an external dataset studying lung cancer initiation. Collectively, these data suggest that profiles of the circulating T-cell response can provide value for lung cancer detection and support its use as a diagnostic tool.


  • Top Cited Papers
    Open Access

    Demographic bias of expert-level vision-language foundation models in medical imaging

    by Yuzhe Yang, Yujia Liu, Xin Liu, Avanti Gulhane, Domenico Mastrodicasa, Wei Wu, Edward J. Wang, Dushyant Sahani, Shwetak Patel

    Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. However, it is crucial to ensure that these AI models do not mirror or amplify human biases, disadvantaging historically marginalized groups such as females or Black patients. In this study, we investigate the algorithmic fairness of state-of-the-art vision-language foundation models in chest x-ray diagnosis across five globally sourced datasets. Our findings reveal that compared to board-certified radiologists, these foundation models consistently underdiagnose marginalized groups, with even higher rates seen in intersectional subgroups such as Black female patients. Such biases present over a wide range of pathologies and demographic attributes. Further analysis of the model embedding uncovers its substantial encoding of demographic information. Deploying medical AI systems with biases can intensify preexisting care disparities, posing potential challenges to equitable healthcare access and raising ethical questions about their clinical applications.


  • Open Access

    Validation of a High-Specificity Blood Autoantibody Test to Detect Lung Cancer in Pulmonary Nodules

    by Kathryn J. Long, Gerard A. Silvestri, Michael N. Kammer, Sarah Gibbs, Wei Wu, Monica Johal, Sudhakar Pipavath, Trevor Pitcher, James Jett, Viswam S. Nair


  • Open Access

    Multi-Omic Biomarkers Improve Indeterminate Pulmonary Nodule Malignancy Risk Assessment

    by Kristin J. Lastwika, Wei Wu, Yuzheng Zhang, Ningxin Ma, Mladen Zečević, Sudhakar N. J. Pipavath, Timothy W. Randolph, A. McGarry Houghton, Viswam S. Nair, Paul D. Lampe, et al.

    The clinical management of patients with indeterminate pulmonary nodules is associated with unintended harm to patients and better methods are required to more precisely quantify lung cancer risk in this group. Here, we combine multiple noninvasive approaches to more accurately identify lung cancer in indeterminate pulmonary nodules. We analyzed 94 quantitative radiomic imaging features and 41 qualitative semantic imaging variables with molecular biomarkers from blood derived from an antibody-based microarray platform that determines protein, cancer-specific glycan, and autoantibody–antigen complex content with high sensitivity. From these datasets, we created a PSR (plasma, semantic, radiomic) risk prediction model comprising nine blood-based and imaging biomarkers with an area under the receiver operating curve (AUROC) of 0.964 that when tested in a second, independent cohort yielded an AUROC of 0.846. Incorporating known clinical risk factors (age, gender, and smoking pack years) for lung cancer into the PSR model improved the AUROC to 0.897 in the second cohort and was more accurate than a well-characterized clinical risk prediction model (AUROC = 0.802). Our findings support the use of a multi-omics approach to guide the clinical management of indeterminate pulmonary nodules.


  • Antisynthetase syndrome–related interstitial lung disease (ASyS-ILD): longitudinal imaging findings

    by Wei Wu, Bridget F. Collins, Gregory C. Gardner, Daniel S. Hippe, Lawrence A. Ho, Ganesh Raghu, Sudhakar N. J. Pipavath

    Objectives Interstitial lung disease (ILD) impacts mortality in antisynthetase syndrome (ASyS). Computed tomographic (CT) patterns and evolution in ASyS ILD are not well described. We report longitudinal CT patterns in ASyS-ILD and their impact on survival. Methods This is a monocentric retrospective study of 47 patients with ASyS-ILD. Longitudinal CT patterns and fibrosis severity (severity of radiographic features indicating fibrosis) were analyzed by two radiologists in consensus. The association between imaging features and survival was examined using univariate Cox regression analysis. Results In total, 211 CT scans were analyzed with an average of 4 ± 2 CT scans/patient with a median follow-up of 79 months in 47 patients. Non-fibrotic patterns were present initially in 63.8% (n = 30) of patients, while fibrotic patterns occurred in 36.2% (n = 17). The initial non-fibrotic patterns/abnormalities resolved in 23.3% (n = 7), evolved in 6.7% (n = 2), persisted in 13.3% (n = 4), and progressed in 56.7% (n = 17), while initial fibrotic patterns persisted in 82.4% (n = 14) and progressed in 17.6% (n = 3). Radiographic progression of ILD (progression in CT pattern or increased fibrosis severity) occurred in 53.2% (n = 25) of patients. Advanced age and radiographic progression were associated with decreased survival (all p < 0.05). The presence of ground-glass opacities (GGO) and predominant lower lung distribution of abnormalities on initial CTs were associated with increased survival (all p < 0.05). Conclusion Progression occurred in 56.7% of ASyS-ILD patients presenting with non-fibrotic patterns. Fibrotic patterns tended to persist. Age and radiographic progression were associated with reduced survival while the initial presence of GGO and predominant lower lobe distribution were associated with increased survival. Key Points • In ASyS-ILD, initial non-fibrotic patterns such as OP, cNSIP, or OP-cNSIP tended to progress to fNSIP. • Fibrotic patterns such as fNSIP or UIP in ASyS-ILD tended to persist without pattern changes. • GGO and lower lung predominance on initial CT were associated with better survival while advanced baseline age and radiographic ILD progression during follow-up were associated with decreased survival.