Abstract 3144: Deep learning-based predictive biomarker for adjuvant chemotherapy in early-stage hormone receptor-positive breast cancer

Abstract Background: The predictive value of adjuvant chemotherapy for early-stage hormone receptor-positive breast cancer has been only validated by a 21-gene expression assay. We hypothesized that deep-learning prediction from HE images, called Lunit-SCOPE, is a potential prognostic and predictive biomarker of adjuvant chemotherapy.Methods: We retrospectively collected HE slides from 1153 de-identified breast cancer patients at the Samsung Medical Center (SMC) in order to develop a deep-learning algorithm called Lunit-SCOPE. The histological parameters from 255 patients, deciphered by Lunit-SCOPE, were trained to predict the recurrence score (RS) using the 21-gene assay from Oncotype DX. We validated the model’s performance using the recurrence survival of 898 patients and The Cancer Genome Atlas (TCGA) cohort, and examined related biological functions through RNA sequence data.Results: The histologic parameter-based RS prediction model predicted the oncotype DX score (R2=0.96) and the recurrence survival analysis on the validation (p<0.01) and TCGA cohort (p<0.01), where the most important variables were the nuclear grade and the mitotic cells in the cancer epithelium. Of the 85 patients classified as the high-risk group, 72 patients who received adjuvant therapy had a significantly better survival (p<0.01). The functions of the top 300 highly correlated genes with a predicted RS were enriched for cell cycle, nuclear division and cell division. Of the 21-genes from the Oncotype DX, the predicted RS had positive correlations with the proliferation category genes and was negatively correlated with the prognostic genes in the estrogen category.Conclusion: An integrative analysis using Lunit-SCOPE predicts a high risk of recurrence and those who would benefit from adjuvant chemotherapy for early-stage hormone-positive breast cancer.

Download Full-text

Deep learning from HE slides predicts the clinical benefit from adjuvant chemotherapy in hormone receptor-positive breast cancer patients

Scientific Reports ◽

10.1038/s41598-021-96855-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Soo Youn Cho ◽

Jeong Hoon Lee ◽

Jai Min Ryu ◽

Jeong Eon Lee ◽

Eun Yoon Cho ◽

...

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Adjuvant Chemotherapy ◽

Cancer Patients ◽

Hormone Receptor ◽

Oncotype Dx ◽

Breast Cancer Patients ◽

Hormone Receptor Positive ◽

Predicted Risk ◽

Positive Breast Cancer

AbstractWe hypothesized that a deep-learning algorithm using HE images might be capable of predicting the benefits of adjuvant chemotherapy in cancer patients. HE slides were retrospectively collected from 1343 de-identified breast cancer patients at the Samsung Medical Center and used to develop the Lunit SCOPE algorithm. Lunit SCOPE was trained to predict the recurrence using the 21-gene assay (Oncotype DX) and histological parameters. The risk prediction model predicted the Oncotype DX score > 25 and the recurrence survival of the prognosis validation cohort and TCGA cohorts. The most important predictive variable was the mitotic cells in the cancer epithelium. Of the 363 patients who did not receive adjuvant therapy, 104 predicted high risk had a significantly lower survival rate. The top-300 genes highly correlated with the predicted risk were enriched for cell cycle, nuclear division, and cell division. From the Oncotype DX genes, the predicted risk was positively correlated with proliferation-associated genes and negatively correlated with prognostic genes from the estrogen category. An integrative analysis using Lunit SCOPE predicted the risk of cancer recurrence and the early-stage hormone receptor-positive breast cancer patients who would benefit from adjuvant chemotherapy.

Download Full-text

Association between estrogen receptor status and Oncotype Dx breast recurrence score.

Journal of Clinical Oncology ◽

10.1200/jco.2021.39.15_suppl.e12519 ◽

2021 ◽

Vol 39 (15_suppl) ◽

pp. e12519-e12519

Author(s):

Noman Ahmed Jang Khan ◽

Mahmoud Abdallah ◽

Todd W. Gress ◽

Mohamed Farouq Alsharedi

Keyword(s):

Breast Cancer ◽

Estrogen Receptor ◽

Adjuvant Chemotherapy ◽

Hormone Receptor ◽

Early Stage ◽

Recurrence Score ◽

Tumor Grade ◽

Oncotype Dx ◽

Hormone Receptor Positive ◽

Positive Breast Cancer

e12519 Background: The 21 gene assay Oncotype Dx Breast Recurrence Score (RS) is currently the standard of care to determine if adjuvant chemotherapy is needed in early stage node negative, hormone receptor positive, HER-2 negative breast cancer. In current American society of clinical oncology (ASCO) guidelines there is little or no benefit of adjuvant chemotherapy in patients older than 50 years whose tumors have Oncotype DX RS <26, and for patients 50 years or less whose tumors have Oncotype DX RS <16. We sought to evaluate the percentage of estrogen receptor (ER) expression as a surrogate measure of determining adjuvant chemotherapy by examining the relationship between ER expression and RS. Methods: We identified 301 patients from years 2015 to 2019 from our cancer registry with early stage hormone receptor positive breast cancer and had oncotype DX testing performed. We divided patients into three groups: Group 1 (ERG1) with ER <10%; Group 2 (ERG2) with ER 10-49%; and Group 3 (ERG3) with ER equal or >50%. We also collected information on tumor size (cm), tumor grade, Nottingham score, and ki-67 percentage. A sub-group analysis was performed for patients < 50 years age (n=30). We compared all continuous variables across ER groups using the Kruskal-Wallis rank test and individual between group comparisons using the Wilcoxon rank sum test. All statistical tests performed utilized a two-tailed p value of <0.05 with the Bonferroni correction for multiple comparisons. Results: Among 301 patients with early stage hormone receptor positive breast cancer, 89.1% were ductal, 7.9% lobular, and 2.9% mixed histology. Median age was 68, 58 and 66 for ERG1, ERG2, and ERG3, respectively (p = 0.41). Median RS was 36 (ERG1), 23 (ERG2), and 16 (ERG3) (p = 0.78 for ERG1 vs. ERG2; p = 0.01 for ERG1 vs. ERG3). As expected, tumor grade, tumor size, and Nottingham score decreased significantly from ERG1 to ERG3. For patients <50 years, median age was 44, 46 and 45 for ERG1, ERG2, and ERG3, respectively (p = 0.75). Median RS was 10 (ERG1), 24 (ERG2) and 18 (ERG3) (p = 0.04 for ERG1 vs. ERG2; p = 0.17 for ERG1 vs. ERG3). Conclusions: We found a significant association between estrogen receptor levels and Oncotype Dx recurrence score (RS) in patients with early stage hormone receptor positive breast cancer patients. Further studies are needed to determine the predictive ability of hormone receptor levels on the outcomes of patients treated for early stage hormone receptor positive breast cancer.

Download Full-text

Author Correction: Deep learning from HE slides predicts the clinical benefit from adjuvant chemotherapy in hormone receptor-positive breast cancer patients

Scientific Reports ◽

10.1038/s41598-021-00546-6 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Soo Youn Cho ◽

Jeong Hoon Lee ◽

Jai Min Ryu ◽

Jeong Eon Lee ◽

Eun Yoon Cho ◽

...

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Adjuvant Chemotherapy ◽

Cancer Patients ◽

Clinical Benefit ◽

Hormone Receptor ◽

Breast Cancer Patients ◽

Hormone Receptor Positive ◽

Positive Breast Cancer

Download Full-text

Endocrine Therapy in Premenopausal Hormone Receptor–Positive Breast Cancer

Journal of Oncology Practice ◽

10.1200/jop.2016.016865 ◽

2016 ◽

Vol 12 (11) ◽

pp. 1148-1156 ◽

Cited By ~ 4

Author(s):

Amye J. Tevaarwerk ◽

Kari B. Wisinski ◽

Ruth M. O’Regan

Keyword(s):

Breast Cancer ◽

Endocrine Therapy ◽

Systemic Therapy ◽

Hormone Receptor ◽

Randomized Trials ◽

Early Stage ◽

Premenopausal Women ◽

Breast Cancers ◽

Hormone Receptor Positive ◽

Positive Breast Cancer

Systemic therapy for premenopausal women with hormone receptor–positive breast cancer has evolved in the last 5 years, but critical questions remain. Recent randomized trials have demonstrated a benefit for the addition of ovarian suppression to endocrine therapy in patients with breast cancers considered to be at high risk for recurrence, whereas those with lower-risk cancers seem to have a favorable outcome with tamoxifen alone. Two large randomized trials have demonstrated a benefit for extending adjuvant tamoxifen beyond 5 years. Currently the choice of systemic therapy is selected empirically but molecular profiling may, in the near future, provide a more conclusive means of selecting an endocrine therapeutic approach for premenopausal patients. Given that a significant subset of hormone receptor–positive cancers are intrinsically resistant to endocrine agents, as well as the finding that inhibiting cyclin-dependent kinases 4 and 6 and mammalian target of rapamycin appears to potentially reverse this resistance in patients with metastatic disease, evaluation of these agents in the early-stage setting is ongoing.

Download Full-text

Use of Biomarkers to Guide Decisions on Adjuvant Systemic Therapy for Women With Early-Stage Invasive Breast Cancer: American Society of Clinical Oncology Clinical Practice Guideline Focused Update

Journal of Clinical Oncology ◽

10.1200/jco.2017.74.0472 ◽

2017 ◽

Vol 35 (24) ◽

pp. 2838-2847 ◽

Cited By ~ 137

Author(s):

Ian Krop ◽

Nofisat Ismaila ◽

Fabrice Andre ◽

Robert C. Bast ◽

William Barlow ◽

...

Keyword(s):

Breast Cancer ◽

Systemic Therapy ◽

Hormone Receptor ◽

Early Stage ◽

Adjuvant Systemic Therapy ◽

Node Negative ◽

Clinical Risk ◽

Hormone Receptor Positive ◽

High Clinical Risk ◽

Positive Breast Cancer

Purpose This focused update addresses the use of MammaPrint (Agendia, Irvine, CA) to guide decisions on the use of adjuvant systemic therapy. Methods ASCO uses a signals approach to facilitate guideline updates. For this focused update, the publication of the phase III randomized MINDACT (Microarray in Node-Negative and 1 to 3 Positive Lymph Node Disease May Avoid Chemotherapy) study to evaluate the MammaPrint assay in 6,693 women with early-stage breast cancer provided a signal. An expert panel reviewed the results of the MINDACT study along with other published literature on the MammaPrint assay to assess for evidence of clinical utility. Recommendations If a patient has hormone receptor–positive, human epidermal growth factor receptor 2 (HER2)–negative, node-negative breast cancer, the MammaPrint assay may be used in those with high clinical risk to inform decisions on withholding adjuvant systemic chemotherapy due to its ability to identify a good-prognosis population with potentially limited chemotherapy benefit. Women in the low clinical risk category did not benefit from chemotherapy regardless of genomic MammaPrint risk group. Therefore, the MammaPrint assay does not have clinical utility in such patients. If a patient has hormone receptor–positive, HER2-negative, node-positive breast cancer, the MammaPrint assay may be used in patients with one to three positive nodes and a high clinical risk to inform decisions on withholding adjuvant systemic chemotherapy. However, such patients should be informed that a benefit from chemotherapy cannot be excluded, particularly in patients with greater than one involved lymph node. The clinician should not use the MammaPrint assay to guide decisions on adjuvant systemic therapy in patients with hormone receptor–positive, HER2-negative, node-positive breast cancer at low clinical risk, nor any patient with HER2-positive or triple-negative breast cancer, because of the lack of definitive data in these populations. Additional information can be found at www.asco.org/breast-cancer-guidelines and www.asco.org/guidelineswiki .

Download Full-text