Detailed localization of the rectal wall after chemoradiation on standard-of-care post-chemoradiation (CRT) MRIs could enable more targeted follow-up interventions, but it is a challenging and laborious task for radiologists. This may be because the primary tumor site (i.e. primary" wall) and the remaining adjacent" wall areas depict visually overlapping intensity characteristics as a result of chemoradiation-induced noise and treatment effects. In this study, we present initial results for developing and optimizing fully convolutional networks (FCNs) to automatically segment the rectal wall on post-CRT MRIs. Our cohort comprised 50 post-CRT, T2-weighted MRIs from rectal cancer patients with expert annotations of the entire length of the rectal wall (with separate indications for extent of primary wall as well as adjacent wall). The FCN framework was designed to provide a pixel-wise segmentation of the rectal wall while utilizing the original T2w intensity images, and was tested on 20% of the cohort that was held-out from training. Our results showed that (a) the best-performing FCN for segmenting primary wall areas utilized a training set comprising primary wall sections alone (median DSC = 0.71), while (b) optimal segmentations of adjacent wall areas were achieved by an FCN trained on both primary and adjacent wall sections (median DSC = 0.68). Notably, the primary wall FCN performed poorly when applied to adjacent wall and vice versa; perhaps indicating that fundamental physiological differences exist between these wall areas that must be accounted for within automated CN segmentation approaches. FCNs may hence have to be optimized on a region-specific basis to obtain detailed, accurate delineations of the entire rectal wall on post-CRT T2w MRI, towards more targeted excision surgery and adjuvant therapy.
KEYWORDS: Magnetic resonance imaging, Tumors, Cancer, CRTs, Feature extraction, In vivo imaging, Medical research, Feature selection, Tissues, Lung cancer
A major clinical challenge in rectal cancer currently is non-invasive identification of tumor regression to standard- of-care neoadjuvant chemoradiation (CRT). Multi-parametric MRI is routinely acquired after CRT, but expert radiologists find it highly challenging to assess the degree of tumor regression on both T2-weighted (T2w) and Gadolinium contrast-enhanced (CE) MRI; resulting in poor agreement with gold-standard pathologic evaluation. In this study, we present initial results for integrating quantitative image appearance (radiomic) features from post-CRT T2w and CE MRI towards in vivo assessment of pathologic rectal tumor response to chemoradiation. 29 rectal cancer patients with post-CRT multi-parametric 3 T MRI (with T2w, initial and delayed CE phases) were included in this study. Through spatial co-registration, the treated region of the rectal wall was identified and annotated on T2w and all CE phases (as well as correcting for motion artifacts in CE MRI). 165 radiomic features (including Haralick, Gabor, Laws, Sobel/Kirsch) were separately extracted from each of T2w and 2 CE phases; within the entire rectal wall. The top 2 response-associated radiomic features for each of (a) T2w, (b) 2 CE phases, (c) combined T2w+CE phases were identified via feature selection and evaluated in a leave- one-patient-out cross validation setting. Integrating T2w and CE radiomic features was found to be markedly more accurate (AUC=0.93) for assessing post-CRT pathologic tumor stage, compared to T2w radiomic features (AUC=0.80) and CE radiomic features (AUC=0.63) individually. Top-ranked features captured heterogeneity of gradient responses on T2w MRI and macro-scale Gabor wavelet responses of contrast enhancement on CE MRI. Combining radiomic features from post-CRT T2w and CE MRI may hence enable more comprehensive evaluation of response to neoadjuvant therapy in rectal cancers, which can be used to better guide follow-up interventions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.