Multiparametric MRI and Whole Slide Image-Based Pretreatment Prediction of Pathological Response to Neoadjuvant Chemoradiotherapy in Rectal Cancer: A Multicenter Radiopathomic Study
Background The aim of this work is to combine radiological and pathological information of tumor to develop a signature for pretreatment prediction of discrepancies of pathological response at several centers and restage patients with locally advanced rectal cancer (LARC) for individualized treatmen...
Saved in:
Published in | Annals of surgical oncology Vol. 27; no. 11; pp. 4296 - 4306 |
---|---|
Main Authors | , , , , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Cham
Springer International Publishing
01.10.2020
Springer Nature B.V |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Background
The aim of this work is to combine radiological and pathological information of tumor to develop a signature for pretreatment prediction of discrepancies of pathological response at several centers and restage patients with locally advanced rectal cancer (LARC) for individualized treatment planning.
Patients and Methods
A total of 981 consecutive patients with evaluation of response according to tumor regression grade (TRG) who received nCRT were retrospectively recruited from four hospitals (primary cohort and external validation cohort 1–3); both pretreatment multiparametric MRI (mp-MRI) and whole slide image (WSI) of biopsy specimens were available for each patient. Quantitative image features were extracted from mp-MRI and WSI and used to construct a radiopathomics signature (RPS) powered by an artificial-intelligence model. Models based on mp-MRI or WSI alone were also constructed for comparison.
Results
The RPS showed overall accuracy of 79.66–87.66% in validation cohorts. The areas under the curve of RPS at specific response grades were 0.98 (TRG0), 0.93 (≤ TRG1), and 0.84 (≤ TRG2). RPS at each grade of pathological response revealed significant improvement compared with both signatures constructed without combining multiscale tumor information (
P
< 0.01). Moreover, RPS showed relevance to distinct probabilities of overall survival and disease-free survival in patients with LARC who underwent nCRT (
P
< 0.05).
Conclusions
The results of this study suggest that radiopathomics, combining both radiological information of the whole tumor and pathological information of local lesions from biopsy, could potentially predict discrepancies of pathological response prior to nCRT for better treatment planning. |
---|---|
ISSN: | 1068-9265 1534-4681 |
DOI: | 10.1245/s10434-020-08659-4 |