Surface Of Interest Research Articles

Abstract 17865: Machine Learning With Multimodal Pre Ablation Imaging for Predicting Recurrence in Atrial Fibrillation Patients

Purpose: Catheter ablation is a popular treatment option for atrial fibrillation (AF), but AF recurrence is common. Currently, no marker exists to reliably predict the risk or location of recurrence (AF+). In this work, a multimodal imaging approach was employed to identify surface of interest (SOI) associated with recurrence using pre-ablation MRI and CT scans. Hypothesis: Shape of the left atrium (LA) plays a critical role in AF recurrence. The difference between AF+ and AF- may be identified on pre-ablation scan and may find potential sites for additional pre-emptive ablation. Method: Two representative template scans were selected from each group and all patients were registered to these respective templates to develop an atlas for each group. The two atlases were then co-registered, and the difference areas were obtained using a t-test with 500 permutations. The SOI was identified as the area that showed statistically significant (p <0.05) differences between the AF+ and AF-. The process was repeated 5 times to obtain most frequent SOI. Since no ground truth for SOI exists, we used a multimodal imaging approach to construct atlases on CT and MRI; the corresponding SOIs were compared. Results: 102 CT (51 AF+) and 160 MRI (79 AF+) scans collected from Cleveland Clinic and Vanderbilt University were randomly sampled 5 times. At each iteration 20 patients from AF+ and AF- patients were randomly chosen and employed to create atlases for generating SOIs. The dice sore of MRI and CT derived SOI were 0.75± 0.08 and 0.82±0.05, respectively. The SOI region was below the LA appendage and left inferior pulmonary vein on both CT and MRI. The ratio of significant region to LA volume were [9%-18%] and [8%-19%] for CT and MRI, respectively indicating a good agreement between two SOIs. Conclusion: We identified SOI associated with AF+ from CT and MRI and found correlation between them at sites expected to be near the vein of Marshall, an area increasingly targeted for recurrent AF after prior ablation.

Abstract 18852: Machine Learning to Predict Atrial Fibrillation Recurrence Using Pulmonary Vein Morphology

Introduction: Predicting risk of recurrence and sites of recurrence after atrial fibrillation (AF) ablation help direct ablation strategies. While the left atrium (LA) has been implicated as a possible site of AF recurrence leading to ablation directed toward LA substrates, reconnection of pulmonary veins (PVs) has been observed as a mechanism of recurrence on repeat ablations. Hypothesis: Regions of statistical shape differences between AF recurrence (AF+) and non-recurrence patients (AF-) within the PV on a CT scan might be associated with sites of recurrence, that features extracted from these regions may be better predictors of AF recurrence. Methods: A Hierarchical Atlas construction method for PV branching shape analysis was developed. Patients with the median volume of LA plus PV in each cohort were selected as the templates. All CT scans in each cohort were registered to the cohort’s template. Then, each branch was individually registered to the branch’s template and resulting control points applied to the LA and other PV branches to maintain connectivity. This process was repeated with 6 iterations to better adjust branching. Two separate atlases of AF+ and AF- were constructed. The areas of significant shape differences on the PV, surfaces of interest (SOIs), between the two groups were obtained via a General Linear Model based t-test on the atlases. Normal and curvature-based features were extracted from SOI regions. A Gradient Boosting classifier was trained based on these features. Cross-validation and atlas construction involved 104 cases. 50 cases served as a holdout set. Results: The classifier trained on SOI features on CT scans achieved AUCs of 0.76 (cross-validation) and 0.74 (holdout set). SOIs include sites within the left superior PV and the right PV carina. Conclusions: This finding appears to suggest that SOI regions on PVs tend to be associated with recurrence and hence may be candidate sites for additional ablation for preventing recurrence of AF.

Abstract 14084: Computationally Identified Shape Differences In The Left Atrium On Pre-ablation Ct Scans Appear To Be Associated With Recurrence Of Atrial Fibrillation

Introduction: Catheter-based ablation is an increasingly utilized management strategy for atrial fibrillation (AF); however, a major problem is AF recurrence post-ablation. There is increasing interest in the use of advanced image analysis to better understand differences in left atrial (LA) shape that may be associated with a higher recurrence risk and potential sites of recurrence. Hypothesis: Factors which lead to the post-ablation recurrence prompt LA differential remodeling. The significant shape difference regions among AF recurrence (AF+) and AF non-recurrence (AF-) patients can be identified from pre-ablation CT scans. Those regions could potentially represent future sites of recurrence and hence could be targets for ablation. Methods: This study included pre-ablation CT-scans of 51 AF+ and 51 AF- patients. Two separate atlases were created by registering Left atrial CT volumes of AF+ and AF- patients to their representative templates (T+ and T- respectively). The atlases were co-registered to a common canonical frame of reference (T-) and a non-parametric General Linear Model (GLM) based t-test with 500 permutations was used to identify the regions (Surface of interest (SOI)) that are statistically significant (p-value<0.1) between the two classes. To reduce sensitivity in the template selection, we constructed an ensemble SOI based on SOIs obtained from 10 different templates and made the frequency map of overlap SOIs. Results: The registration accuracy in the final common frame in terms of average Dice similarity coefficient was in the range of 0.85-0.94 over the 10 SOI constructions. The frequency map revealed the maximum overlap of SOIs in an area where left pulmonary veins enter the left atrium. This could potentially represent a new target for ablation. Conclusions: An ensemble atlas-based shape differentiation method revealed SOI regions that are structurally associated with recurrence and might potentially represent targets for ablation.

A new machine learning approach for predicting likelihood of recurrence following ablation for atrial fibrillation from CT

ObjectiveTo investigate left atrial shape differences on CT scans of atrial fibrillation (AF) patients with (AF+) versus without (AF−) post-ablation recurrence and whether these shape differences predict AF recurrence.MethodsThis retrospective study included 68 AF patients who had pre-catheter ablation cardiac CT scans with contrast. AF recurrence was defined at 1 year, excluding a 3-month post-ablation blanking period. After creating atlases of atrial models from segmented AF+ and AF− CT images, an atlas-based implicit shape differentiation method was used to identify surface of interest (SOI). After registering the SOI to each patient model, statistics of the deformation on the SOI were used to create shape descriptors. The performance in predicting AF recurrence using shape features at and outside the SOI and eight clinical factors (age, sex, left atrial volume, left ventricular ejection fraction, body mass index, sinus rhythm, and AF type [persistent vs paroxysmal], catheter-ablation type [Cryoablation vs Irrigated RF]) were compared using 100 runs of fivefold cross validation.ResultsDifferences in atrial shape were found surrounding the pulmonary vein ostia and the base of the left atrial appendage. In the prediction of AF recurrence, the area under the receiver-operating characteristics curve (AUC) was 0.67 for shape features from the SOI, 0.58 for shape features outside the SOI, 0.71 for the clinical parameters, and 0.78 combining shape and clinical features.ConclusionDifferences in left atrial shape were identified between AF recurrent and non-recurrent patients using pre-procedure CT scans. New radiomic features corresponding to the differences in shape were found to predict post-ablation AF recurrence.

Computer extracted shape features of prostate capsule from MRI to predict biochemical recurrence of prostate cancer post-treatment.

e16579 Background: Pre-treatment identification of biochemical recurrence (BCR) from MRI may enable the use of aggressive neo-adjuvant therapies for prostate cancer patients to improve prognosis. BCR is often associated with aggressive cancer growth and/or extra prostatic extension resulting in an irregular bulge and focal capsular retraction. This may induce differences in the shape of the prostate capsule between BCR positive (BCR+) and BCR negative (BCR-) patients as observed on MRI. In this work, we show that computer extracted shape features of the prostate capsule on MRI can identify patients that are at a risk of BCR post-treatment Methods: In a single centre IRB approved study, from a registry of 874 patients, availability of complete image datasets (T1w, T2w and ADC map); no treatment for PCa before MRI; presence of clinically localised PCa; availability of Gleason score; and data available for post-treatment PSA and follow-up for at least 3 years in patients without BCR were used as inclusion criteria to select 80 patients. The prostate capsule was manually segmented on T2w MRI by an experienced radiologist. Two atlases A+ and A- were created for BCR+ and BCR- patients respectively with similar Gleason score (6 to 9), similar numbers in each cohort (25 each) and similar tumor stage (T2 to T3). A t-test based analysis corrected for multiple comparison revealed statistically significant prostate shape differences between A+ and A- in surface of interest (SOI). Curvature features (magnitude and surface normal orientations) were extracted from SOI of the two cohorts. A random forest classifier was trained using the 50 training images (from A+ and A-) and validated using a hold-out validation set of 30 patients. Results: The inter-quartile range, variance, skewness and kurtosis of curvature magnitude and normal orientations were found to be predictive of BCR. The RF classifier trained using these features could predict BCR with an accuracy of 78% and an AUC of 0.71 in the validation set. Conclusions: Curvature magnitude and orientation features of the prostate capsule from the SOI may be predictive of BCR. In future a multi centre independent datasets will be used to validate the findings.