Abstract PS1-63: A survey of radiation oncologists on contemporary axillary management in post-mastectomy breast cancer patients

e11084 Background: Oncotype DX is a 21-gene assay developed for early stage, hormone receptor positive breast cancer that generates a Recurrence Score which estimates response to chemotherapy and the likelihood of systemic recurrence at 10 years. It differentiates between patients who would benefit from chemotherapy plus hormonal therapy versus hormonal therapy alone. This study’s goal was to determine if the Recurrence Score affected clinical management at our institution and physicians’ accuracy at predicting Recurrence Scores. Methods: A retrospective review was conducted of 116 breast cancer patients treated over a 7 year period. Clinic notes, pathology reports, and additional relevant information were presented to breast surgeons, oncologists, radiation oncologists, and surgical pathologists. Individual physicians estimated recurrence risks and recommended treatment based on those estimates. The Recurrence Score was revealed and changes in therapeutic recommendations were recorded. Results: Treatment recommendations changed in 43% of patients. 29% had a change from chemotherapy followed by hormone therapy to hormone therapy alone due to a low recurrence score, while 14% initially recommended hormonal therapy were changed to chemotherapy plus hormonal therapy due to an intermediate range score. Surgical oncologists accurately predicted Recurrence Scores 52% of the time, medical oncologists 46%, radiation oncologists 45%, and surgical pathologists 15%. A nested mixed model showed that pathologists were statistically significantly worse at predicting recurrence scores than surgical oncologists, medical oncologists, and radiation oncologists. Conclusions: The Oncotype DX assay changes management of breast cancer patients at our institution, frequently downgrading the intensity of systemic therapy. Clinicians were able to accurately estimate recurrence categories about 50% of the time. We recommend the use of Oncotype DX assay along with assessment of clinicopathologic features of an individual’s disease in eligible patients to enhance the selection of appropriate adjuvant therapy.

Download Full-text

Are heart toxicities in breast cancer patients important for radiation oncologists? A practice pattern survey in German speaking countries

BMC Cancer ◽

10.1186/s12885-017-3548-2 ◽

2017 ◽

Vol 17 (1) ◽

Cited By ~ 5

Author(s):

Marciana Nona Duma ◽

Stefan Münch ◽

Markus Oechsner ◽

Stephanie Elisabeth Combs

Keyword(s):

Breast Cancer ◽

Cancer Patients ◽

Practice Pattern ◽

Breast Cancer Patients ◽

Radiation Oncologists ◽

German Speaking

Download Full-text

Clinical feasibility of deep learning-based auto-segmentation of target volumes and organs-at-risk in breast cancer patients after breast-conserving surgery

Radiation Oncology ◽

10.1186/s13014-021-01771-z ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Seung Yeun Chung ◽

Jee Suk Chang ◽

Min Seo Choi ◽

Yongjin Chang ◽

Byong Su Choi ◽

...

Keyword(s):

Breast Cancer ◽

At Risk ◽

Deep Learning ◽

Cancer Patients ◽

Organs At Risk ◽

Breast Conserving Surgery ◽

Dice Similarity Coefficient ◽

Breast Cancer Patients ◽

Dose Volume Histograms ◽

Radiation Oncologists

Abstract Background In breast cancer patients receiving radiotherapy (RT), accurate target delineation and reduction of radiation doses to the nearby normal organs is important. However, manual clinical target volume (CTV) and organs-at-risk (OARs) segmentation for treatment planning increases physicians’ workload and inter-physician variability considerably. In this study, we evaluated the potential benefits of deep learning-based auto-segmented contours by comparing them to manually delineated contours for breast cancer patients. Methods CTVs for bilateral breasts, regional lymph nodes, and OARs (including the heart, lungs, esophagus, spinal cord, and thyroid) were manually delineated on planning computed tomography scans of 111 breast cancer patients who received breast-conserving surgery. Subsequently, a two-stage convolutional neural network algorithm was used. Quantitative metrics, including the Dice similarity coefficient (DSC) and 95% Hausdorff distance, and qualitative scoring by two panels from 10 institutions were used for analysis. Inter-observer variability and delineation time were assessed; furthermore, dose-volume histograms and dosimetric parameters were also analyzed using another set of patient data. Results The correlation between the auto-segmented and manual contours was acceptable for OARs, with a mean DSC higher than 0.80 for all OARs. In addition, the CTVs showed favorable results, with mean DSCs higher than 0.70 for all breast and regional lymph node CTVs. Furthermore, qualitative subjective scoring showed that the results were acceptable for all CTVs and OARs, with a median score of at least 8 (possible range: 0–10) for (1) the differences between manual and auto-segmented contours and (2) the extent to which auto-segmentation would assist physicians in clinical practice. The differences in dosimetric parameters between the auto-segmented and manual contours were minimal. Conclusions The feasibility of deep learning-based auto-segmentation in breast RT planning was demonstrated. Although deep learning-based auto-segmentation cannot be a substitute for radiation oncologists, it is a useful tool with excellent potential in assisting radiation oncologists in the future. Trial registration Retrospectively registered.

Download Full-text