In Journal of pathology informatics ; h5-index 23.0
Neoadjuvant chemo-radiotherapy (nCRT) followed by surgical resection is the standard treatment strategy in patients with locally advanced rectal cancer (RC). The pathological effect of nCRT is assessed by determining the tumor regression grade (TRG) of the resected tumor. Various methods exist for assessing TRG and all are performed manually by the pathologist with an accompanying risk of interobserver variation. Automated digital image analysis could be a more objective and reproducible approach to evaluate TRG. This study aimed at developing a digital method to assess TRG in RC following nCRT, and correlate the results to the currently used Mandard method. A deep learning-based semi-automatic Epithelium-Tumor area Percentage (ETP) algorithm enabling quantification of tumor regression by determining the percentage of residual tumor epithelium out of the total tumor area was developed. The ETP was quantified in 50 cases treated with nCRT and 25 cases with no prior nCRT served as controls. Median ETP was 39.25% in untreated compared with 6.64% in patients who received nCRT (P < .001). The ETP of the resected tumors treated with nCRT increased along with increasing Mandard grade (P < .001). As new treatment strategies in RC are emerging, performing an accurate and reproducible evaluation of TRG is important in the assessment of treatment response and prognosis. TRG is often used as an outcome point in clinical trials. The ETP algorithm is capable of performing a precise and objective value of tumor regression.
Jepsen Dea Natalie Munch, Høeg Henrik, Thagaard Jeppe, Walbech Julie Sparholt, Gögenur Ismail, Fiehn Anne-Marie Kanstrup
2022
Deep learning, Digital pathology, Neoadjuvant treatment, Rectal cancer, Tumor regression grade
