VASCULAR AND INTERVENTIONAL RADIOLOGYP ercutaneous cryoablation (PCA) is an increasingly utilized treatment option for stage I renal cell carcinoma (RCC). The American Urologic Association included ablation in its treatment guidelines for stage I RCC in 2009, albeit with cautionary references to increased risk for local recurrence compared with surgery (1). The National Comprehensive Cancer Network added ablation to its own guidelines in 2018 (2). These recommendations were based on meta-analyses of mostly small retrospective studies (3,4). Notwithstanding the lack of definitive evidence, patients with small renal masses are increasingly referred for ablation. The impetus behind the increasing utilization of PCA is mainly due to the changing epidemiologic landscape of RCC.The expected number of RCC in the United States in 2019 is 74 000, with an increasing lifetime risk currently standing at 1.7%, and comprising 4.2% of all cancers (5). Furthermore, the proportion of patients diagnosed with stage I RCC continues to increase (currently 65%-75%) as well ( 6). This migration toward lower clinical stage is partly due to increase in incidental detection (utilization of crosssectional imaging) and recognized risk factors, mainly obesity and smoking (7). These trends are emulated by European statistics on the epidemiology of RCC (8). The growth in (both relative and absolute) numbers of patients with RCC diagnosed at stage I is making nephron-sparing surgery (the current standard of care) and ablation increasingly important. Despite the mounting number of published studies supporting the use of ablation for small renal masses, most have limitations that include small number of patients, lack of histologic proof, retrospective design, and/ or short follow-up time.

BackgroundNystagmus identification and interpretation is challenging for non-experts who lack specific training in neuro-ophthalmology or neuro-otology. This challenge is magnified when the task is performed via telemedicine. Deep learning models have not been heavily studied in video-based eye movement detection.MethodsWe developed, trained, and validated a deep-learning system (aEYE) to classify video recordings as normal or bearing at least two consecutive beats of nystagmus. The videos were retrospectively collected from a subset of the monocular (right eye) video-oculography (VOG) recording used in the Acute Video-oculography for Vertigo in Emergency Rooms for Rapid Triage (AVERT) clinical trial (#NCT02483429). Our model was derived from a preliminary dataset representing about 10% of the total AVERT videos (n = 435). The videos were trimmed into 10-sec clips sampled at 60 Hz with a resolution of 240 × 320 pixels. We then created 8 variations of the videos by altering the sampling rates (i.e., 30 Hz and 15 Hz) and image resolution (i.e., 60 × 80 pixels and 15 × 20 pixels). The dataset was labeled as “nystagmus” or “no nystagmus” by one expert provider. We then used a filtered image-based motion classification approach to develop aEYE. The model's performance at detecting nystagmus was calculated by using the area under the receiver-operating characteristic curve (AUROC), sensitivity, specificity, and accuracy.ResultsAn ensemble between the ResNet-soft voting and the VGG-hard voting models had the best performing metrics. The AUROC, sensitivity, specificity, and accuracy were 0.86, 88.4, 74.2, and 82.7%, respectively. Our validated folds had an average AUROC, sensitivity, specificity, and accuracy of 0.86, 80.3, 80.9, and 80.4%, respectively. Models created from the compressed videos decreased in accuracy as image sampling rate decreased from 60 Hz to 15 Hz. There was only minimal change in the accuracy of nystagmus detection when decreasing image resolution and keeping sampling rate constant.ConclusionDeep learning is useful in detecting nystagmus in 60 Hz video recordings as well as videos with lower image resolutions and sampling rates, making it a potentially useful tool to aid future automated eye-movement enabled neurologic diagnosis.

No abstract

No abstract

No abstract