Search

Purpose: Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. Methods: We implement an open-source interactive-machine-learning software application that facilitates corrective-annotation for deep-learning generated contours on X-ray CT images. A trained-physician contoured 933 hearts using our software by delineating the first image, starting model training, and then correcting the model predictions for all subsequent images. These corrections were added into the training data, which was used for continuously training the assisting model. From the 933 hearts, the same physician also contoured the first 10 and last 10 in Eclipse (Varian) to enable comparison in terms of accuracy and duration. Results: We find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods. After 923 images had been delineated, hearts took 2 min and 2 s to delineate on average, which includes time to evaluate the initial model prediction and assign the needed corrections, compared to 7 min and 1 s when delineating manually. Conclusions: Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows.

Purpose: Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. Methods: We implement an open-source interactive-machine-learning software application that facilitates corrective-annotation for deep-learning generated contours on X-ray CT images. A trained-physician contoured 933 hearts using our software by delineating the first image, starting model training, and then correcting the model predictions for all subsequent images. These corrections were added into the training data, which was used for continuously training the assisting model. From the 933 hearts, the same physician also contoured the first 10 and last 10 in Eclipse (Varian) to enable comparison in terms of accuracy and duration. Results: We find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods. After 923 images had been delineated, hearts took 2 min and 2 s to delineate on average, which includes time to evaluate the initial model prediction and assign the needed corrections, compared to 7 min and 1 s when delineating manually. Conclusions: Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows.

Organ-at-risk contouring is still a bottleneck in radiotherapy, with many deep learning methods falling short of promised results when evaluated on clinical data. We investigate the accuracy and time-savings resulting from the use of an interactive-machine-learning method for an organ-at-risk contouring task. We compare the method to the Eclipse contouring software and find strong agreement with manual delineations, with a dice score of 0.95. The annotations created using corrective-annotation also take less time to create as more images are annotated, resulting in substantial time savings compared to manual methods, with hearts that take 2 minutes and 2 seconds to delineate on average, after 923 images have been delineated, compared to 7 minutes and 1 seconds when delineating manually. Our experiment demonstrates that interactive-machine-learning with corrective-annotation provides a fast and accessible way for non computer-scientists to train deep-learning models to segment their own structures of interest as part of routine clinical workflows. Source code is available at \href{https://github.com/Abe404/RootPainter3D}{this HTTPS URL}.

Purpose: There are primarily two techniques for affixing the scleral buckle (SB) to the sclera in the repair of rhegmatogenous retinal detachment (RRD): scleral tunnels or scleral sutures. Methods: This retrospective study examined all patients with primary RRD who were treated with primary SB or SB combined with vitrectomy from January 1, 2015 through December 31, 2015 across six sites. Two cohorts were examined: SB affixed using scleral sutures versus scleral tunnels. Pre- and postoperative variables were evaluated including visual acuity, anatomic success, and postoperative strabismus. Results: The mean preoperative logMAR VA for the belt loop cohort was 1.05 ±" role="presentation">± 1.06 (Snellen 20/224) and for the scleral suture cohort was 1.03 ±" role="presentation">± 1.04 (Snellen 20/214, p = 0.846). The respective mean postoperative logMAR VAs were 0.45 ±" role="presentation">± 0.55 (Snellen 20/56) and 0.46 ±" role="presentation">± 0.59 (Snellen 20/58, p = 0.574). The single surgery success rate for the tunnel cohort was 87.3% versus 88.6% for the suture cohort (p = 0.601). Three patients (1.0%) in the scleral tunnel cohort developed postoperative strabismus, but only one patient (0.1%) in the suture cohort (p = 0.04, multivariate p = 0.76). All cases of strabismus occurred in eyes that underwent SB combined with PPV (p = 0.02). There were no differences in vision, anatomic success, or strabismus between scleral tunnels versus scleral sutures in eyes that underwent primary SB. Conclusion: Scleral tunnels and scleral sutures had similar postoperative outcomes. Combined PPV/SB in eyes with scleral tunnels might be a risk for strabismus post retinal detachment surgery.