Casey Bales
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
Casey Bales has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
- Milan Radovich
Caris Life Sciences, Irving, Texas
50 shared publications - David Spetzler
Caris Life Sciences, Phoenix, USA
49 shared publications - George W. Sledge
Caris Life Sciences, Phoenix, USA
49 shared publications - Hassan Ghani
Caris Life Sciences, Phoenix, USA
49 shared publications - Jennifer R. Ribeiro
Caris Life Sciences, Phoenix, USA
49 shared publications - Matthew James Oberley
Caris Life Sciences, Phoenix, USA
49 shared publications
Latest Publications
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Figure 6 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
External validation of MI Clarity M3T for late DR in the TAILORx translational cohort. A, Kaplan–Meier analysis of late DR comparing MI Clarity M3T risk groups in all patients. B, Multivariable Cox analysis assessing the independent prognostic value of the MI Clarity M3T risk label, adjusted for clinical covariates. C, Kaplan–Meier analysis of late DR comparing MI Clarity M3T risk groups in arms B and C (ITT). LDR, late distant recurrence.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 6 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
External validation of MI Clarity M3T for late DR in the TAILORx translational cohort. A, Kaplan–Meier analysis of late DR comparing MI Clarity M3T risk groups in all patients. B, Multivariable Cox analysis assessing the independent prognostic value of the MI Clarity M3T risk label, adjusted for clinical covariates. C, Kaplan–Meier analysis of late DR comparing MI Clarity M3T risk groups in arms B and C (ITT). LDR, late distant recurrence.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Figure 4 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Effect of ELT on DR across subgroups in the NSABP B-42 translational cohort.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 4 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Effect of ELT on DR across subgroups in the NSABP B-42 translational cohort.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 6 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Clinicopathologic, and treatment characteristics of patients classified as MI Clarity–High versus Low risk in the NSABP B-42 translational cohort.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 6 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Clinicopathologic, and treatment characteristics of patients classified as MI Clarity–High versus Low risk in the NSABP B-42 translational cohort.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Figure 4 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
External validation of MI Clarity M3T for overall distant recurrence (DR) in the TAILORx translational cohort.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure 4 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
External validation of MI Clarity M3T for overall distant recurrence (DR) in the TAILORx translational cohort.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 11 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Clinicopathologic, and treatment characteristics of patients classified as MI Clarity–High versus Low risk in the TAILORx translational late-DR cohort.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 11 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Clinicopathologic, and treatment characteristics of patients classified as MI Clarity–High versus Low risk in the TAILORx translational late-DR cohort.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Figure 5 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Kaplan–Meier analysis of DR comparing patients treated with ELT vs. placebo in the NSABP B-42 translational cohort. A, All patients. B, Low-risk group. C, High-risk group. High- and low-risk groups are defined by the M3T model.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 5 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Kaplan–Meier analysis of DR comparing patients treated with ELT vs. placebo in the NSABP B-42 translational cohort. A, All patients. B, Low-risk group. C, High-risk group. High- and low-risk groups are defined by the M3T model.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Figure 2 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Kaplan–Meier analysis of DR in the NSABP B-42 translational cohort according to MI Clarity M3T risk groups. A, All patients. B, ELT-treated group. C, Placebo group. High- and low-risk groups are defined by the M3T model.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 2 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Kaplan–Meier analysis of DR in the NSABP B-42 translational cohort according to MI Clarity M3T risk groups. A, All patients. B, ELT-treated group. C, Placebo group. High- and low-risk groups are defined by the M3T model.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 10 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Time-dependent predictive performance of the M3T model for ELT benefit in clinical subgroups with violated proportional hazards (PH) assumption.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 10 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Time-dependent predictive performance of the M3T model for ELT benefit in clinical subgroups with violated proportional hazards (PH) assumption.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 1 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Clinicopathologic and treatment characteristics of patients in the translational cohort versus remaining NSABP B-42 patients.
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 1 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
Clinicopathologic and treatment characteristics of patients in the translational cohort versus remaining NSABP B-42 patients.
- Open Access
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Figure 1 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
A, Overview of the M3T model workflow. The model was developed using the NSABP B-42 translational cohort (N = 2,271) with five-fold cross-validation, integrating H&E image–derived features and selected tabular clinicopathologic features through the M3T (multimodal, multitask transformer). An auxiliary task predicting the lowest BMD T-score enhanced prognostic performance and improved stratification of patients with differential ELT benefit but was not required for model inference. The model outputs a continuous risk score that is dichotomized into low- and high-risk groups. Independent external validation was performed in the TAILORx translational cohort (N = 4,300). Prognostic, predictive, and calibration analyses were conducted to evaluate model performance. B, End-to-end image preprocessing, feature extraction, model training, and output architecture. Tissue regions were detected from H&E-stained WSIs, tiled at 10× magnification, and processed using CTransPath to generate tile-level image embeddings. Tile-level image embeddings and clinicopathologic features were projected into a shared representation space and processed through transformer encoder and decoder modules. During training, an auxiliary task predicting the lowest BMD T-score was incorporated to improve prognostic performance and stratification of patients with differential ELT benefit. The primary task generated a continuous risk score for late DR risk stratification. The dashed box shows the detailed architecture of the transformer encoder (left) and transformer decoder (right).
- 31 July 2026
- Published by American Association for Cancer Research (AACR)
Open AccessFigure 1 from Development and Validation of a Multimodal–Multitask Deep Learning Approach for Estimating Late Distant Recurrence Risk in HR-Positive Early Breast Cancer
A, Overview of the M3T model workflow. The model was developed using the NSABP B-42 translational cohort (N = 2,271) with five-fold cross-validation, integrating H&E image–derived features and selected tabular clinicopathologic features through the M3T (multimodal, multitask transformer). An auxiliary task predicting the lowest BMD T-score enhanced prognostic performance and improved stratification of patients with differential ELT benefit but was not required for model inference. The model outputs a continuous risk score that is dichotomized into low- and high-risk groups. Independent external validation was performed in the TAILORx translational cohort (N = 4,300). Prognostic, predictive, and calibration analyses were conducted to evaluate model performance. B, End-to-end image preprocessing, feature extraction, model training, and output architecture. Tissue regions were detected from H&E-stained WSIs, tiled at 10× magnification, and processed using CTransPath to generate tile-level image embeddings. Tile-level image embeddings and clinicopathologic features were projected into a shared representation space and processed through transformer encoder and decoder modules. During training, an auxiliary task predicting the lowest BMD T-score was incorporated to improve prognostic performance and stratification of patients with differential ELT benefit. The primary task generated a continuous risk score for late DR risk stratification. The dashed box shows the detailed architecture of the transformer encoder (left) and transformer decoder (right).