UCLA Department of Radiation Oncology

Background

Cancer is frequently associated with tumor-related anemia, and many chemotherapeutic agents impair hematopoiesis, leading to impaired quality of life for affected patients. The use of erythropoiesis-stimulating agents has come under scrutiny after prospective clinical trials using recombinant erythropoietin to correct anemia reported increased incidence of thromboembolic events and cancer-related deaths. Furthermore, previous preclinical reports indicated expansion of the pool of breast cancer-initiating cells when erythropoietin was combined with ionizing radiation.

Methods

Using four established breast cancer cell lines, we test the effects of recombinant human erythropoietin and the number of breast cancer-initiating cells in vitro and in vivo and study if recombinant human erythropoietin promotes the phenotype conversion of non-tumorigenic breast cancer cells into breast cancer-initiating cells. In a prospective study, we evaluate whether elevated endogenous serum erythropoietin levels correlate with increased numbers of tumor-initiating cells in a cohort of breast cancer patients who were scheduled to undergo radiation treatment.

Results

Our results indicate that recombinant erythropoietin increased the number of tumor-initiating cells in established breast cancer lines in vitro. Irradiation of breast cancer xenografts caused a phenotype conversion of non-stem breast cancer cells into induced breast cancer-initiating cells. This effect coincided with re-expression of the pluripotency factors c-Myc, Sox2, and Oct4 and was enhanced by recombinant erythropoietin. Hemoglobin levels were inversely correlated with serum erythropoietin levels, and the latter were correlated with disease stage. However, tumor sections revealed a negative correlation between serum erythropoietin levels and the number of ALDH1A3-positive cells, a marker for breast cancer-initiating cells.

Conclusions

We conclude that physiologically slow-rising serum erythropoietin levels in response to tumor-related or chemotherapy-induced anemia, as opposed to large doses of recombinant erythropoietin, do not increase the pool of breast cancer-initiating cells.

Background and purpose

Currently, there is no robust indicator within the Cone-Beam Computed Tomography (CBCT) DICOM headers as to which anatomical region is present on the scan. This can be a predicament to CBCT-based algorithms trained on specific body regions, such as auto-segmentation and radiomics tools used in the radiotherapy workflow. We propose an anatomical region labeling (ARL) algorithm to classify CBCT scans into four distinct regions: head & neck, thoracic-abdominal, pelvis, and extremity.

Materials and methods

Algorithm training and testing was performed on 3,802 CBCT scans from 596 patients treated at our radiotherapy center. The ARL model, which consists of a convolutional neural network, makes use of a single CBCT coronal slice to output a probability of occurrence for each of the four classes. ARL was evaluated on the test dataset composed of 1,090 scans and compared to a support vector machine (SVM) model. ARL was also used to label CBCT treatment scans for 22 consecutive days as part of a proof-of-concept implementation. A validation study was performed on the first 100 unique patient scans to evaluate the functionality of the tool in the clinical setting.

Results

ARL achieved an overall accuracy of 99.2% on the test dataset, outperforming the SVM (91.5% accuracy). Our validation study has shown strong agreement between the human annotations and ARL predictions, with accuracies of 99.0% for all four regions.

Conclusion

The high classification accuracy demonstrated by ARL suggests that it may be employed as a pre-processing step for site-specific, CBCT-based radiotherapy tools.