Stephen R. Bowen
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
Research Subjects
Stephen R. Bowen has a total of 207 co-authors. Here are the top co-authors by number of shared publications:
- Paul Eugene Kinahan
Department of Radiology University of Washington Seattle Washington USA
30 shared publications - Jing Zeng
Department of Radiation Oncology, University of Washington School of Medicine, Seattle, Washington
22 shared publications - Daniel Scott Hippe
Clinical Research Division, Fred Hutchinson Cancer Center, Seattle, WA, USA
20 shared publications - Ramesh Rengan
Department of Radiation Oncology, University of Washington School of Medicine, Seattle, USA
16 shared publications - Clemens Grassberger
University of Washington 4 Seattle
15 shared publications - Faisal Yaseen
University of Washington
14 shared publications
Latest Publications
- Open Access
Uncertainty-Aware Multiscale Treatment Response Forecasting in Advanced Non-Small Cell Lung Cancer Using Residual-Variance Conformal Prediction
Voxel-level prediction of treatment response from longitudinal Fluorodexoyglucose (FDG) positron emission tomography / computed tomography (PET/CT) can enable spatially adaptive dose planning in advanced non-small cell lung cancer (NSCLC), but point predictions alone lack the uncertainty quantification needed for safe clinical decision-making. Standard conformal prediction (CP) provides distribution-free coverage but yields spatially uniform intervals and assumes exchangeability—an assumption violated by intra-tumoral spatial correlation. We propose a multiscale CP framework built on a re-optimized VoxelForecast generalized least squares model that explicitly captures voxel-level covariance. Variogram sensitivity analysis identified the Stable model as significantly superior to previouly used Matérn family. The framework combines hierarchical nested leave-one-patient-out calibration, which restores exchangeability for valid voxel-level coverage, with residual-variance CP (VarCP), which learns a heteroscedastic, location-dependent scale to produce adaptive intervals while preserving finite-sample marginal coverage guarantees. On two prospective NSCLC trial cohorts—FLARE-RT (N=25 locally advanced, chemoradio-therapy; 11,100 voxels) and BRIGHT (N=19 metastatic, chemoimmunotherapy; 26,980 voxels)—multiscale feature integration reduced voxel-level prediction error by 35% and 31%, respectively. VarCP maintained nominal coverage while producing 7–18% (FLARE-RT) and 4–8% (BRIGHT) narrower voxel-level intervals than a hierarchically calibrated standard CP baseline (paired Wilcoxon signed-rank, significant at most miscoverage levels), with comparable lesion-level gains (7–18% and 6–10%) via median-based aggregation of voxel residuals. VarCP delivers tighter yet mathematically guaranteed spatial uncertainty maps, supporting both voxel-level dose-adjustment and whole-lesion treatment planning in advanced NSCLC.
Open AccessUncertainty-Aware Multiscale Treatment Response Forecasting in Advanced Non-Small Cell Lung Cancer Using Residual-Variance Conformal Prediction
Voxel-level prediction of treatment response from longitudinal Fluorodexoyglucose (FDG) positron emission tomography / computed tomography (PET/CT) can enable spatially adaptive dose planning in advanced non-small cell lung cancer (NSCLC), but point predictions alone lack the uncertainty quantification needed for safe clinical decision-making. Standard conformal prediction (CP) provides distribution-free coverage but yields spatially uniform intervals and assumes exchangeability—an assumption violated by intra-tumoral spatial correlation. We propose a multiscale CP framework built on a re-optimized VoxelForecast generalized least squares model that explicitly captures voxel-level covariance. Variogram sensitivity analysis identified the Stable model as significantly superior to previouly used Matérn family. The framework combines hierarchical nested leave-one-patient-out calibration, which restores exchangeability for valid voxel-level coverage, with residual-variance CP (VarCP), which learns a heteroscedastic, location-dependent scale to produce adaptive intervals while preserving finite-sample marginal coverage guarantees. On two prospective NSCLC trial cohorts—FLARE-RT (N=25 locally advanced, chemoradio-therapy; 11,100 voxels) and BRIGHT (N=19 metastatic, chemoimmunotherapy; 26,980 voxels)—multiscale feature integration reduced voxel-level prediction error by 35% and 31%, respectively. VarCP maintained nominal coverage while producing 7–18% (FLARE-RT) and 4–8% (BRIGHT) narrower voxel-level intervals than a hierarchically calibrated standard CP baseline (paired Wilcoxon signed-rank, significant at most miscoverage levels), with comparable lesion-level gains (7–18% and 6–10%) via median-based aggregation of voxel residuals. VarCP delivers tighter yet mathematically guaranteed spatial uncertainty maps, supporting both voxel-level dose-adjustment and whole-lesion treatment planning in advanced NSCLC.
- Open Access
- 27 August 2026
- Published by Springer Nature in Research Square
Toward uncertainty-aware clinical decision support for treatment response prediction in metastatic NSCLC: integrating FDG-PET, T-cell repertoire, and cytokines with conformal prediction
Background Variable response to chemoimmunotherapy in metastatic non-small cell lung cancer (mNSCLC), together with the limited discriminative accuracy of PD-L1 tumor proportion score, highlights the need for reliable, uncertainty-aware early response prediction using multimodal biomarkers. We developed and prototyped a multimodal clinical decision support (CDS) framework integrating longitudinal FDG-PET, T-cell receptor (TCR), and cytokine biomarkers with conformal prediction to deliver uncertainty-quantified, patient-level response predictions. Methods Thirty-five patients with mNSCLC receiving first-line carboplatin–pemetrexed–pembrolizumab on the PET-BRIGHT trial (NCT04151940) underwent FDG-PET/CT and blood collection at baseline and week 3. Multimodal biomarkers included FDG-PET metrics (standardized uptake value/total lesion glycolysis), TCR diversity metrics, and inflammatory cytokines. Nested leave-one-out cross-validation with automated feature selection identified a single biomarker per modality. Class-balanced logistic regression was used for classification, with discrimination assessed by the area under the receiver operating characteristic curve (AUROC) and calibration by the Brier score. Conformal prediction (targeting 80% reliability) quantified patient-level uncertainty via prediction sets and singleton rate. Unimodal and multimodal early- and late-fusion models were evaluated using baseline-only and combined baseline plus mid-treatment biomarkers. Models were benchmarked against PD-L1 tumor proportion score, and statistical significance was assessed by permutation testing against an empirical null. Results PD-L1 tumor proportion score, the current clinical standard, discriminated poorly (AUROC 0.58, 95% CI 0.39–0.78). At PreTx, unimodal TCR was the strongest single modality (AUROC 0.80), followed by PET (0.76) and cytokines (0.54). Late fusion of PET and TCR achieved the highest PreTx discrimination (0.85) and increased singleton predictions from 78% to 89%. After incorporating mid-treatment biomarkers, cytokines became the strongest single modality (0.78) while TCR was attenuated (0.66); late fusion of PET and cytokines achieved the highest discrimination overall (0.86). Thirteen of 22 model and timepoint combinations exceeded a permutation null at p < 0.05, and empirical coverage was 78% and 82% against an 80% target. Conclusions A multimodal framework combining longitudinal biomarkers with conformal prediction substantially outperformed the current clinical standard while identifying patients for whom a confident prediction could not be made. A prototype CDS interface demonstrates feasibility for clinical translation. Trial registration ClinicalTrials.gov NCT04151940, registered 26 September 2019.
- 27 August 2026
- Published by Springer Nature in Research Square
Open AccessToward uncertainty-aware clinical decision support for treatment response prediction in metastatic NSCLC: integrating FDG-PET, T-cell repertoire, and cytokines with conformal prediction
Background Variable response to chemoimmunotherapy in metastatic non-small cell lung cancer (mNSCLC), together with the limited discriminative accuracy of PD-L1 tumor proportion score, highlights the need for reliable, uncertainty-aware early response prediction using multimodal biomarkers. We developed and prototyped a multimodal clinical decision support (CDS) framework integrating longitudinal FDG-PET, T-cell receptor (TCR), and cytokine biomarkers with conformal prediction to deliver uncertainty-quantified, patient-level response predictions. Methods Thirty-five patients with mNSCLC receiving first-line carboplatin–pemetrexed–pembrolizumab on the PET-BRIGHT trial (NCT04151940) underwent FDG-PET/CT and blood collection at baseline and week 3. Multimodal biomarkers included FDG-PET metrics (standardized uptake value/total lesion glycolysis), TCR diversity metrics, and inflammatory cytokines. Nested leave-one-out cross-validation with automated feature selection identified a single biomarker per modality. Class-balanced logistic regression was used for classification, with discrimination assessed by the area under the receiver operating characteristic curve (AUROC) and calibration by the Brier score. Conformal prediction (targeting 80% reliability) quantified patient-level uncertainty via prediction sets and singleton rate. Unimodal and multimodal early- and late-fusion models were evaluated using baseline-only and combined baseline plus mid-treatment biomarkers. Models were benchmarked against PD-L1 tumor proportion score, and statistical significance was assessed by permutation testing against an empirical null. Results PD-L1 tumor proportion score, the current clinical standard, discriminated poorly (AUROC 0.58, 95% CI 0.39–0.78). At PreTx, unimodal TCR was the strongest single modality (AUROC 0.80), followed by PET (0.76) and cytokines (0.54). Late fusion of PET and TCR achieved the highest PreTx discrimination (0.85) and increased singleton predictions from 78% to 89%. After incorporating mid-treatment biomarkers, cytokines became the strongest single modality (0.78) while TCR was attenuated (0.66); late fusion of PET and cytokines achieved the highest discrimination overall (0.86). Thirteen of 22 model and timepoint combinations exceeded a permutation null at p < 0.05, and empirical coverage was 78% and 82% against an 80% target. Conclusions A multimodal framework combining longitudinal biomarkers with conformal prediction substantially outperformed the current clinical standard while identifying patients for whom a confident prediction could not be made. A prototype CDS interface demonstrates feasibility for clinical translation. Trial registration ClinicalTrials.gov NCT04151940, registered 26 September 2019.
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table S2 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Predictive variables considered in competing risk analysis for LRP/DM
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S2 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Predictive variables considered in competing risk analysis for LRP/DM
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table S1 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Representativeness of Study Participants
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S1 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Representativeness of Study Participants
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S3 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Kaplan–Meier curves for OS (left column) and PFS (right column), stratified by PET response status (non-responder vs responder), treatment modality (proton vs photon), durvalumab use (durvalumab vs no durvalumab), histology (adenocarcinoma vs squamous cell carcinoma and other), and chemotherapy regimen (carboplatin + paclitaxel vs other).
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S3 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Kaplan–Meier curves for OS (left column) and PFS (right column), stratified by PET response status (non-responder vs responder), treatment modality (proton vs photon), durvalumab use (durvalumab vs no durvalumab), histology (adenocarcinoma vs squamous cell carcinoma and other), and chemotherapy regimen (carboplatin + paclitaxel vs other).
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S2 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Pattern of failures including death, LRP and DM
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S2 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Pattern of failures including death, LRP and DM
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table S7 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Correlation among top features with DM in the cohort of PET non-responders.
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S7 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Correlation among top features with DM in the cohort of PET non-responders.
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table S4 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Univariate Fine-Gray-regression for LRP prediction: predictive variables with p values. All HR for continuous variables reported are based on a 1-standard deviation (SD) increase.
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S4 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
Univariate Fine-Gray-regression for LRP prediction: predictive variables with p values. All HR for continuous variables reported are based on a 1-standard deviation (SD) increase.
- Open Access
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S4 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
(A) Time-Dependent AUC with 95% confidence interval for DM predicted by mid.TLG at 0.5-years intervals across multiple time points. (B) Time-Dependent ROC Curve at 2 Years achieving AUC of 0.655, with no optimal threshold in TLG that maximized the Youden index.
- 14 August 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S4 from Mature Outcomes and Patterns of Failure in the Phase II FLARE-RT Trial of Biological Image-Guided and Risk-Adaptive Chemoradiation for Unresectable NSCLC
(A) Time-Dependent AUC with 95% confidence interval for DM predicted by mid.TLG at 0.5-years intervals across multiple time points. (B) Time-Dependent ROC Curve at 2 Years achieving AUC of 0.655, with no optimal threshold in TLG that maximized the Youden index.