Machine Learning Approach for the Determination of the Best Cut-Off Points for Ki67 Proliferation Index in Adjuvant and Neo-Adjuvant Therapy Breast Cancer Patients.

BACKGROUND: This study aims to evaluate Ki67 cut-off points for differentiating low and high-risk patients based on survival and recurrence and find the best Ki67 cut-off points in breast cancer patients undergoing adjuvant and neoadjuvant therapy using machine learning methods. PATIENTS AND METHODS: Patients with breast cancer treated at 2 referral hospitals between December 2000 and March 2021 who had invasive breast cancer entered this study. There were 257 patients in the neoadjuvant group and 2139 in the adjuvant group. A decision tree method was used to predict the likelihood of survival and recurrence. The 2-ensemble technique of RUSboost and bagged tree were imposed on the decision tree method to increase the accuracy of the determination. 80 percent of the data was used to train and validate the model, and 20% was used as a test. RESULTS: In adjuvant therapy breast cancer patients with Invasive ductal carcinoma (IDC) and Invasive lobular carcinoma (ILC) the cutoff points for survival were 20 and 10, respectively. For luminal A, luminal B, Her2 neu, and triple-negative adjuvant therapy patients' the cutoff points for survival were 25, 15, 20, and 20, respectively. For neoadjuvant therapy luminal A and luminal B group, survival cutoff points were 25 and 20, respectively. CONCLUSION: Despite variability in measurement and cut-off points, the Ki-67 proliferation index is still helpful in the clinic. Further investigation is needed to determine the best cut-off points for different patients. The sensitivity and specificity of Ki-67 cutoff point prediction models in this study could further prove its significance as a prognostic factor.

DOK7 CpG hypermethylation in blood leukocytes as an epigenetic biomarker for acquired tamoxifen resistant in breast cancer.

BACKGROUND: Breast cancer (BC) is among the most common cause of cancer 10.4% and one of the leading causes of death among 20-50 years old women in the world. Tamoxifen drug is the first line therapy for BC however tamoxifen resistance (TR) has shown in 30-50% of cases that may face BC recurrence. Hence, TR early detection reduces BC recurrence and fatalities. The epigenetic alteration that happens by hypermethylation of tumor suppressor genes and hypomethylation of oncogenes has been suggested to be useful in early cancer or drug resistance diagnosis. METHODS: This is the first study to investigate DOK7 CpG hypermethylation in blood leukocytes of 31 TR (ER+) BC compared to 29 tamoxifen sensitive BC to evaluate DOK7 as a potential TR biomarker. DNA was extracted from blood samples of all participants and MSRE-PCR and real-time PCR were used for quantification of CpG methylation alterations. RESULTS: The means of DOK7 CpG hypermethylation were obtained as 85.03%, 29.1% and 57.34% in TR, TS and normal control respectively. Significant hypermethylation were found among TR vs. TS (p < 0.001), TS vs. normal (p < 0.001) and TR vs. normal controls (p < 0.03). Online databases expression and survival analysis of DOK7 showed increasing expression in TS groups vs. TR groups which have consistency with our methylation alteration results. The sensitivity and specificity of the TR epigenetic test were determined using ROC analysis showed 89.66% and 96.77% respectively and showed that 37.5% above hypermethylation is at risk for TR and breast cancer recurrence. CONCLUSION: There is a significant difference in the methylation ratio of DOK7 between tamoxifen resistant and tamoxifen sensitive groups that may be useful in the early diagnosis of tamoxifen resistance in BC cases and cancer recurrence prevention.

Measurement of peripheral dose to the pelvic region and the associated risk for cancer development after breast intraoperative electron radiation therapy.

This study aimed to measure the received dose to the pelvic region of patients during breast intraoperative electron radiation therapy (IOERT). Furthermore, we compared the findings with those of external beam radiation therapy. Finally, secondary ovarian and uterus cancer risks following breast IOERT were estimated. In the current study, the received dose to the pelvic surface of 18 female patients during breast IOERT boosts were measured by thermoluminescent dosimeter (TLD-100) chips. All patients were treated with 12 Gy given in a single fraction. To estimate the dose to the ovary and uterus of the patients, conversion coefficients for depth from the surface dose were obtained in a Rando phantom. Given the received dose to the pelvic region of the patients, secondary ovarian and uterus cancer risks following breast IOERT were estimated. The received doses to the ovary and uterus surface of the patients were 0.260 ± 0.155 mGy to 31.460 ± 6.020 mGy and 0.485 ± 0.122 mGy to 22.387 ± 15.476 mGy, respectively. Corresponding intra-pelvic (ovary and uterus) regional doses were 0.012 ± 0.007 mGy to 1.479 ± 0.283 mGy and 0.027 ± 0.001 mGy to 1.164 ± 0.805 mGy, respectively. Findings demonstrated that the ratio of the received dose by the pelvic surface to the regional dose during breast IOERT was much less than external beam radiation therapy. The mean of the secondary cancer risks for the ovary in 8 and 10 MeV electron beam energies were 135.722 ± 117.331 × 10-6 and 69.958 ± 28.072 × 10-6, and for the uterus were 17.342 ± 10.583 × 10-6 and 2.971 ± 3.604 × 10-6, respectively. According to our findings, the use of breast IOERT in pregnant patients can be considered as a safe radiotherapeutic technique, because the received dose to the fetus was lower than 50 mGy. Furthermore, IOERT can efficiently reduce the unnecessary dose to the pelvic region and lowers the risk of secondary ovarian and uterus cancer following breast irradiation.