CT Radiomics for Predicting Pathological Complete Response of Axillary Lymph Nodes in Breast Cancer After Neoadjuvant Chemotherapy: A Prospective Study

Author(s): Yan-Ling Li¹;Li-Ze Wang¹;Qing-Lei Shi²;Ying-Jian He¹;Jin-Feng Li¹;Hai-Tao Zhu¹;Tian-Feng Wang³;Xiao-Ting Li¹;Zhao-Qing Fan³;Tao Ouyang³;Ying-Shi Sun¹

Source: https://doi.org/10.1093/oncolo/oyad010

Dr. Maen Hussein's Thoughts

A way to avoid axillary dissection, with more neoadjuvant therapy treatments, this may help avoid unnecessary axillary dissection. Probably needs more validation with larger studies but is a good start. Also, the first related to radiological findings, so welcome input from our FCS Radiologists.

BACKGROUND

The diagnostic effectiveness of traditional imaging techniques is insufficient to assess the response of lymph nodes (LNs) to neoadjuvant chemotherapy (NAC), especially for pathological complete response (pCR). A radiomics model based on computed tomography (CT) could be helpful.

PATIENTS AND METHODS

Prospective consecutive breast cancer patients with positive axillary LNs initially were enrolled, who received NAC prior to surgery. Chest contrast-enhanced thin-slice CT scan was performed both before and after the NAC (recorded as the first and the second CT respectively), and on both of them, the target metastatic axillary LN was identified and demarcated layer by layer. Using pyradiomics-based software that was independently created, radiomics features were retrieved. A pairwise machine learning workflow based on Sklearn (https://scikit-learn.org/) and FeAture Explorer was created to increase diagnostic effectiveness. An effective pairwise auto encoder model was developed by the improvement of data normalization, dimensionality reduction, and features screening scheme as well as the comparison of the prediction effectiveness of the various classifiers,

RESULTS

A total of 138 patients were enrolled, and 77 (58.7%) in the overall group achieved pCR of LN after NAC. Nine radiomics features were finally chosen for modeling. The AUCs of the training group, validation group, and test group were 0.944 (0.919-0.965), 0.962 (0.937-0.985), and 1.000 (1.000-1.000), respectively, and the corresponding accuracies were 0.891, 0.912, and 1.000.

CONCLUSION

The pCR of axillary LNs in breast cancer following NAC can be precisely predicted using thin-sliced enhanced chest CT-based radiomics.

Author Affiliations

¹Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiology, Peking University Cancer Hospital & Institute, Beijing, People’s Republic of China²Chinese University of Hong Kong (Shenzhen) School of Medicine, Shenzhen Research Institute of Big Data, People’s Republic of China ³Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Breast Cancer Center, Peking University Cancer Hospital & Institute, People’s Republic of China

Low-Dose Tamoxifen in Noninvasive Breast Neoplasia: Long-Term Results From an Individual-Participant Data Pooled Analysis

Among 1,545 women included with a median follow-up of 9.4 years in postmenopausal women, breast cancer events occurred in 40 of 335 receiving low-dose tamoxifen versus 93 of 401 controls HR, 0.51, with a 10-year absolute reduction of 11.2%. Among premenopausal women, no significant reduction was observed dose was 5mg daily of 10mg every other day in ductal carcinoma in situ (DCIS) and high-risk pts. Less is as good.

Datopotamab deruxtecan in patients with untreated, advanced triple-negative breast cancer (TROPION-Breast02): a randomised, open-label, international, phase III trial

644 patients who are triple-negative breast cancer (TNBC) not candidates for immunotherapy were randomly assigned to receive Dato-DXd (n = 323) or chemotherapy (n = 321). Median progression-free survival (PFS) was 10.8 months with Dato-DXd and 5.6 months with chemotherapy. Median overall survival (OS) was 23.7 months and 18.7 months with Dato-DXd and chemotherapy, respectively HR 0.79; P = 0.029]. Treatment-related adverse events (TRAEs) of grade ≥3 were reported in 105 (33%) and 89 (29%) patients who received Dato-DXd and chemotherapy, respectively, they were more treatment discontinuation in the chemotherapy arm secondary to treatment related adverse events in 14 (4%) and 23 (7%) patients. There were no treatment-related deaths in either arm. New standard of care? Recall this is on patients not eligible for immunotherapy.

Hypo- Versus Standard Fractionated Locoregional Radiotherapy of Patients With High-Risk Breast Cancer in the Randomized Phase III Trial: The Danish Breast Cancer Group Skagen Trial 1

Less radiation (40Gy vs 50 Gy) was non inferior in preventing locoregional recurrence and distant mets, also lymphedema rates were not worse. Would love feedback from our rad onc, but it seems less is as good.

HER2CLIMB-05: A Phase III Study of Tucatinib Versus Placebo in Combination With Trastuzumab and Pertuzumab as First-Line Maintenance Therapy for HER2+ Metastatic Breast Cancer

Progression-free survival (PFS) was statistically significantly improved with addition of tucatinib versus placebo 24.9 v 16.3 months regardless of the presence/absence of BM or hormone receptor status.

Role of neoadjuvant versus adjuvant chemotherapy, dose density, and treatment schedule in biologically high-risk HR+/HER2- breast cancer: A pooled analysis of the WSG ADAPT-HR+/HER2- and PlanB trials.

1467 pts with RS > 25 and 551 with clinically (neoadjuvant cohort in ADAPT-HR+/HER2-) or pathologically N2, (longer) docetaxel-based CTx showed better distant, invasive disease-free survival in N2-3 pts patients with RS ≤25, OS was also shown in pts with RS>25 anthracycline regimens did not show a significant survival difference in high-risk HR+/HER2 whether used in neoadjuvant or adjuvant setting. So may be no anthracycline for HR+ve pts who are high risk disease.