Shape and Flow Sensing in Arterial Image Guidance From UV Exposed Optical Fibers Based on Spatio-Temporal Networks.

OBJECTIVE: Minimally invasive revascularization procedures such as percutaneous transluminal angioplasty seek to treat occlusions in peripheral arteries. However their ability to treat long occlusions are hampered by difficulties to monitor the location of intravascular devices such as guidewires using fluoroscopy which requires continuous radiation, and lack the capacity to measure physiological characteristics such as laminar blood flow close to occlusions. Fiber optic technologies provide means of tracking by measuring fibers under strain, however they are limited to known geometrical models and are not used to measure external variations. METHODS: We present a navigation framework based on optical frequency domain reflectometry (OFDR) using fully-distributed optical sensor gratings enhanced with ultraviolet exposure to track the three-dimensional shape and surrounding blood flow of intra-vascular guidewires. To process the strain information provided by the continuous gratings, a dual-branch model learning spatio-temporal features allows to predict the output measures based on scattered wavelength distributions. The first network determines the 3D shape appearance of the guidewire using the input backscattered wavelength shift data in combination with prior segmentations, while a second network (graph temporal convolution network) produces estimates of vascular flow velocities using ground-truth 4D-flow MRI acquisitions. RESULTS: Experiments performed on synthetic and animal models, as well as in a preliminary human trial shows the capability of the model to generate accurate 3D shape tracking and blood flow velocities differences below 2 cm/s, thus providing realistic physiologic and anatomical properties for intravascular techniques. CONCLUSION AND SIGNIFICANCE: The study demonstrates the feasibility of using the device clinically, and could be integrated within revascularization workflows for treating occlusions in arteries, since the navigation framework involves minimal manual intervention.

Prediction of post transarterial chemoembolization MR images of hepatocellular carcinoma using spatio-temporal graph convolutional networks.

Magnetic resonance imaging (MRI) plays a critical role in the planning and monitoring of hepatocellular carcinomas (HCC) treated with locoregional therapies, in order to assess disease progression or recurrence. Dynamic contrast-enhanced (DCE)-MRI sequences offer temporal data on tumor enhancement characteristics which has strong prognostic value. Yet, predicting follow-up DCE-MR images from which tumor enhancement and viability can be measured, before treatment of HCC actually begins, remains an unsolved problem given the complexity of spatial and temporal information. We propose an approach to predict future DCE-MRI examinations following transarterial chemoembolization (TACE) by learning the spatio-temporal features related to HCC response from pre-TACE images. A novel Spatial-Temporal Discriminant Graph Neural Network (STDGNN) based on graph convolutional networks is presented. First, embeddings of viable, equivocal and non-viable HCCs are separated within a joint low-dimensional latent space, which is created using a discriminant neural network representing tumor-specific features. Spatial tumoral features from independent MRI volumes are then extracted with a structural branch, while dynamic features are extracted from the multi-phase sequence with a separate temporal branch. The model extracts spatio-temporal features by a joint minimization of the network branches. At testing, a pre-TACE diagnostic DCE-MRI is embedded on the discriminant spatio-temporal latent space, which is then translated to the follow-up domain space, thus allowing to predict the post-TACE DCE-MRI describing HCC treatment response. A dataset of 366 HCC's from liver cancer patients was used to train and test the model using DCE-MRI examinations with associated pathological outcomes, with the spatio-temporal framework yielding 93.5% classification accuracy in response identification, and generating follow-up images yielding insignificant differences in perfusion parameters compared to ground-truth post-TACE examinations.

Prediction of inter-fractional radiotherapy dose plans with domain translation in spatiotemporal embeddings.

External beam radiation therapy fractions have become extremely complex and tedious procedures to plan, due to stringent requirements of delivering the highest radiation dose to the tumor while maximally avoiding organs at risk. However, due to anatomic and/or biological changes between fractions, dose re-optimization may be needed. Re-optimization is a time-consuming task which is typically triggered based on subjective visual assessment by an experienced physician. To address limitations in this process, we introduce a predictive framework which learns the evolution of tumor anatomy as well as inter-fractional dose delivery variations for head and neck cancers. First, joint low-dimensional discriminant embeddings maximizing the separation between responsive and non-responsive groups to external beam radiotherapy plans are constructed from deep neural networks in order to capture patient-specific dose modulations with respect to anatomical variations. Then, latent representations are fed to a domain-level adversarial network to translate observed anatomical changes into dosimetric variations, which aims to enforce local semantic consistency in the overall translation. Dose distribution trajectories are represented in a group-average piecewise-geodesic setting to handle anatomical variations during therapy, using a quadratic optimization to perform curve regression. At test time, an annotated baseline CT is projected onto the latent space and translated to dose domain, from which a spatiotemporal regression model is constructed using parallel transport trajectories defined from closest samples. This allows to predict dosimetry changes during the course of treatment. The model was trained on 337 cases and tested on 50 separate patients using sequential CT and associated dosimetry data, with the probabilistic framework yielding a Dice score of 92% and an overall dose difference of 1.2 Gy in organs at risk and tumor volume over the course of multi-day treatment course, with a 5% reduction in delivered fraction segments.