Abstract
Patients with locally advanced rectal cancer (LARC) who achieve a pathologic complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) typically have a good prognosis. An early and accurate prediction of the treatment response, i.e., whether a patient achieves pCR, could significantly help doctors make tailored plans for LARC patients. This study proposes a pipeline of pCR prediction using a combination of deep learning and radiomics analysis. Taking into consideration missing pre-nCRT magnetic resonance imaging (MRI), as well as aiming to improve the efficiency for clinical application, the pipeline only included a post-nCRT T2-weighted (T2-w) MRI. Unlike other studies that attempted to carefully find the region of interest (ROI) using a pre-nCRT MRI as a reference, we placed the ROI on a “suspicious region”, which is a continuous area that has a high possibility to contain a tumor or fibrosis as assessed by radiologists. A deep segmentation network, termed the two-stage rectum-aware U-Net (tsraU-Net), is designed to segment the ROI to substitute for a time-consuming manual delineation. This is followed by a radiomics analysis model based on the ROI to extract the hidden information and predict the pCR status. The data from a total of 275 patients were collected from two hospitals and partitioned into four datasets: Seg-T (N = 88) for training the tsraUNet, Rad-T (N = 107) for building the radiomics model, In-V (N = 46) for internal validation, and Ex-V (N = 34) for external validation. The proposed method achieved an area under the curve (AUC) of 0.829 (95% confidence interval [CI]: 0.821, 0.837) on In-V and 0.815 (95% CI, 0.801, 0.830) on Ex-V. The performance of the method was considerable and stable in two validation sets, indicating that the well-designed pipeline has the potential to be used in real clinical procedures.
Highlights
Colorectal cancer is currently still the third most common cancer and the second most fatal cancer in the world [1]
This study proposes a pipeline of pathologic complete response (pCR) prediction using a combination of deep learning and radiomics analysis
The aim of this study is to explore a pipeline that only uses the information from a single post-neoadjuvant chemoradiotherapy (nCRT) T2 magnetic resonance imaging (MRI) combined with a new method to provide a fast and reliable region of interest (ROI)
Summary
Colorectal cancer is currently still the third most common cancer and the second most fatal cancer in the world [1]. For patients with locally advanced rectal cancer (LARC), neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision (TME) has been the standard clinical treatment [4,5,6]. The pathological response of LARC patients after nCRT treatment has demonstrated obvious heterogeneity [8]. It has been reported that approximately 20% of patients, defined as pathologic complete response (pCR) patients, contain no residual surviving tumor cells after nCRT and surgery [9, 10]. These patients have a favorable long-term prognosis with superb local control and disease-free survival [11]. A prediction method before surgery would greatly assist doctors in evaluating the treatment effects of nCRT and construct a tailored plan for each patient
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have