Various vision-threatening eye diseases including age-related macular degeneration (AMD) and central serous chorioretinopathy(CSCR) are caused due to the dysfunctions manifested in the highly vascular choroid layer of the posterior segment of the eye.In the current clinical practice, screening choroidal structural changes is widely based on optical coherence tomography (OCT)images. Accordingly, to assist clinicians, several automated choroidal biomarker detection methods using OCT images aredeveloped. However, the performance of these algorithms is largely constrained by the quality of the OCT scan. Consequently,determining the quality of choroidal features in OCT scans is significant in building standardized quantification tools and henceconstitutes our main objective. This study includes a dataset of 1593 good and 2581 bad quality Spectralis OCT images gradedby an expert. Noting the efficacy of deep-learning (DL) in medical image analysis, we propose to train three state-of-the-artDL models: ResNet18, EfficientNet-B0 and EfficientNet-B3 to detect the quality of OCT images. The choice of these modelswas inspired by their ability to preserve the salient features across all the layers without information loss. To evaluate theattention of DL models on the choroid, we introduced color transparency maps (CTMs) based on GradCAM explanations.Further, we proposed two subjective grading scores: overall choroid coverage (OCC) and choroid coverage in the visibleregion(CCVR) based on CTMs to objectively correlate visual explanations vis-à-vis DL model attentions. We observed that theaverage accuracy and F-scores for the three DL models are greater than 96%. Further, the OCC and CCVR scores achievedfor the three DL models under consideration substantiate that they mostly focus on the choroid layer in making the decision. Inparticular, of the three DL models, EfficientNet-B3 is in close agreement with the clinician’s inference. The proposed DL-basedframework demonstrated high detection accuracy as well as attention on the choroid layer, where EfficientNet-B3 reportedsuperior performance. Our work assumes significance in bench-marking the automated choroid biomarker detection tools andfacilitating high-throughput screening. Further, the methods proposed in this work can be adopted for evaluating the attentionof DL-based approaches developed for other region-specific quality assessment tasks.

Various vision-threatening eye diseases including age-related macular degeneration (AMD) and central serous chorioretinopathy (CSCR) are caused due to the dysfunctions manifested in the highly vascular choroid layer of the posterior segment of the eye. In the current clinical practice, screening choroidal structural changes is widely based on optical coherence tomography (OCT) images. Accordingly, to assist clinicians, several automated choroidal biomarker detection methods using OCT images are developed. However, the performance of these algorithms is largely constrained by the quality of the OCT scan. Consequently, determining the quality of choroidal features in OCT scans is significant in building standardized quantification tools and hence constitutes our main objective. This study includes a dataset of 1593 good and 2581 bad quality Spectralis OCT images graded by an expert. Noting the efficacy of deep-learning (DL) in medical image analysis, we propose to train three state-of-the-art DL models: ResNet18, EfficientNet-B0 and EfficientNet-B3 to detect the quality of OCT images. The choice of these models was inspired by their ability to preserve the salient features across all the layers without information loss. To evaluate the attention of DL models on the choroid, we introduced color transparency maps (CTMs) based on GradCAM explanations. Further, we proposed two subjective grading scores: overall choroid coverage (OCC) and choroid coverage in the visible region(CCVR) based on CTMs to objectively correlate visual explanations vis-à-vis DL model attentions. We observed that the average accuracy and F-scores for the three DL models are greater than 96%. Further, the OCC and CCVR scores achieved for the three DL models under consideration substantiate that they mostly focus on the choroid layer in making the decision. In particular, of the three DL models, EfficientNet-B3 is in close agreement with the clinician’s inference. The proposed DL-based framework demonstrated high detection accuracy as well as attention on the choroid layer, where EfficientNet-B3 reported superior performance. Our work assumes significance in bench-marking the automated choroid biomarker detection tools and facilitating high-throughput screening. Further, the methods proposed in this work can be adopted for evaluating the attention of DL-based approaches developed for other region-specific quality assessment tasks.

Category: Ankle; Midfoot/Forefoot Introduction/Purpose: High BMI is a known risk factor for development of CAI and intraarticular pathology, but few studies have examined BMI's impact of the outcomes of lateral ligament reconstruction. The open Brostrom-Gould reconstruction, an anatomic repair, is the gold standard for repair of the lateral ligamentous complex. We aim to evaluation the impact of BMI on patient reported outcomes after open Brostrom-Gould repair. Methods: A total of 201 patients who underwent open Brostrom-Gould Repair were identified using CPT code. Patients undergoing repair for acute ligamentous injury were excluded. A completed telephonic survey was required for inclusion yielding 92 patients. The telephone survey included: PROMIS Physical Function (PF), Pain Interference (PI), and Depression domains(D) and the Foot and Ankle Ability Measure (FAAM). Medical records were examined for patient characteristics, operative variables, and complications. Patients were grouped by BMI <30 and BMI >30. Results: A total of 28 males (30%) and 61 females (69%) were including in this study. The average time at completion of survey was 4.1 years (standard deviation of 2.8). The median age was 44 with an interquartile range (IQR) of 20, while the median BMI was 31.5 with an IQR of 13.4. Obese patients had significantly worse PROMIS PF (Median 44.5 IQR 7.4 vs median 48 IQR 16.5) and FAAM Activity of Daily Living subscale scores (Median 61.6 IQR 30.0 vs. median 82.7 IQR.36). Patients' FAAM self-reported overall level of function was significantly lower in obese patients (Median 70.0 IQR 20.0 vs median 85 IQR 29). The BMI groups did not vary by other PROMIS domains or FAAM subscales. Conclusion: At intermediate term follow-up, Obese patients report significantly worse physical function after open Bostrom- Gould repair compared to non-obese patients. Surgeons should be aware of this when prognosticating the outcomes of anatomic ankle reconstruction.