Precise segmentation of rectal cancer tumors on routine MRI is critical for accurate clinical staging and downstream computational analyses. While deep learning-based segmentation algorithms have shown much promise in automating the otherwise tedious, subjective, and costly process of manual segmentation, they require significant amounts of manually annotated data for training. To address these limitations of deep learning-based segmentation models, we present a novel deep learning framework that incorporates human-in-the-loop (HITL) refinement to automatically delineate rectal tumors on multi-plane pre-treatment MR imaging. When evaluated on multiple holdout validation cohorts including a clinical trial dataset, the post-HITL segmentation model significantly outperformed the pre-HITL model with median dice similarity coefficient of 0.763 and Hausdorff distance of 28.4mm in comparison to 0.601 and 31.8mm, respectively. HITL refinement learning also significantly accelerated the manual annotation process by 20 minutes. HITL learning represents a feasible, effective, and efficient solution to semi-automated tumor segmentation on routine rectal cancer MRI scans.
Radiomic analysis has shown significant potential for predicting treatment response to neoadjuvant therapy in rectal cancers via routine MRI, though primarily based off a single acquisition plane or single region of interest. To exploit intuitive clinical and biological aspects of tumor extent on MRI, we present a novel multi-plane, multi-region radiomics framework to more comprehensively characterize and interrogate treatment response on MRI. Our framework was evaluated on a cohort of 71 T2-weighted axial and coronal MRIs from patients diagnosed with rectal cancer and who underwent chemoradiation. 2D radiomic features were extracted from three regions of interest (tumor, fat proximal to tumor, and perirectal fat) across axial and coronal planes, with a two-stage feature selection scheme designed to identify descriptors associated with pathologic complete response. When evaluated via a quadratic discriminant analysis classifier, our multi-plane, multi-region radiomics model outperformed single-plane or single-region feature sets with an area under the ROC curve (AUC) of 0.80 ± 0.03 in discovery and AUC=0.65 in hold-out validation. Uniquely, the optimal feature set comprised descriptors from across multiple planes (axial, coronal) as well as multiple regions (tumor, proximal fat, perirectal fat). Our multi-plane, multi-region radiomics framework may thus enable more comprehensive phenotyping of treatment response on MRI, potentially finding application for improved personalization of therapeutic and surgical interventions in rectal cancers.
With increasing promise of radiomics and deep learning approaches in capturing subtle patterns associated with disease response on routine MRI, there is an opportunity to more closely combine components from both approaches within a single architecture. We present a novel approach to integrating multi-scale, multi-oriented wavelet networks (WN) into a convolutional neural network (CNN) architecture, termed a deep hybrid convolutional wavelet network (DHCWN). The proposed model comprises the wavelet neurons (wavelons) that use the shift and scale parameters of a mother wavelet function as its building units. Whereas the activation functions in a typical CNN are fixed and monotonic (e.g. ReLU), the activation functions of the proposed DHCWN are wavelet functions that are flexible and significantly more stable during optimization. The proposed DHCWN was evaluated using a multi-institutional cohort of 153 pre-treatment rectal cancer MRI scans to predict pathologic response to neoadjuvant chemoradiation. When compared to typical CNN and a multilayer wavelet perceptron (DWN-MLP) 2D and 3D architectures, our novel DHCWN yielded significantly better performance in predicting pathologic complete response (achieving a maximum accuracy of 91.23% and a maximum AUC of 0.79), across multi-institutional discovery and hold-out validation cohorts. Interpretability evaluation of all three architectures via Grad-CAM and Shapley visualizations revealed DHCWNs best captured complex texture patterns within tumor regions on MRI as associated with pathologic complete response classification. The proposed DHCWN thus offers a significantly more extensible, interpretable, and integrated solution for characterizing predictive signatures via routine imaging data.
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.