CatStep: Automated Cataract Surgical Phase Classification and Boundary Segmentation Leveraging Inflated 3D-Convolutional Neural Network Architectures and BigCat.

Objective: Accurate identification of surgical phases during cataract surgery is essential for improving surgical feedback and performance analysis. Time spent in each surgical phase is an indicator of performance, and segmenting out specific phases for further analysis can simplify providing both qualitative and quantitative feedback on surgical maneuvers. Study Design: Retrospective surgical video analysis. Subjects: One hundred ninety cataract surgical videos from the BigCat dataset (comprising nearly 4 million frames, each labeled with 1 of 11 nonoverlapping surgical phases). Methods: Four machine learning architectures were developed for segmentation of surgical phases. Models were trained using cataract surgical videos from the BigCat dataset. Main Outcome Measures: Models were evaluated using metrics applied to frame-by-frame output and, uniquely in this work, metrics applied to phase output. Results: The final model, CatStep, a combination of a temporally sensitive model (Inflated 3D Densenet) and a spatially sensitive model (Densenet169), achieved an F1-score of 0.91 and area under the receiver operating characteristic curve of 0.95. Phase-level metrics showed considerable boundary segmentation performance with a median absolute error of phase start and end time of just 0.3 seconds and 0.1 seconds, respectively, a segmental F1-score @70 of 0.94, an oversegmentation score of 0.89, and a segmental edit score of 0.92. Conclusion: This study demonstrates the feasibility of high-performance automated surgical phase identification for cataract surgery and highlights the potential for improved surgical feedback and performance analysis. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery.

Cataract surgery remains the only definitive treatment for visually significant cataracts, which are a major cause of preventable blindness worldwide. Successful performance of cataract surgery relies on stable dilation of the pupil. Automated pupil segmentation from surgical videos can assist surgeons in detecting risk factors for pupillary instability prior to the development of surgical complications. However, surgical illumination variations, surgical instrument obstruction, and lens material hydration during cataract surgery can limit pupil segmentation accuracy. To address these problems, we propose a novel method named adaptive wavelet tensor feature extraction (AWTFE). AWTFE is designed to enhance the accuracy of deep learning-powered pupil recognition systems. First, we represent the correlations among spatial information, color channels, and wavelet subbands by constructing a third-order tensor. We then utilize higher-order singular value decomposition to eliminate redundant information adaptively and estimate pupil feature information. We evaluated the proposed method by conducting experiments with state-of-the-art deep learning segmentation models on our BigCat dataset consisting of 5,700 annotated intraoperative images from 190 cataract surgeries and a public CaDIS dataset. The experimental results reveal that the AWTFE method effectively identifies features relevant to the pupil region and improved the overall performance of segmentation models by up to 2.26% (BigCat) and 3.31% (CaDIS). Incorporation of the AWTFE method led to statistically significant improvements in segmentation performance (P < 1.29 × 10-10 for each model) and yielded the highest-performing model overall (Dice coefficients of 94.74% and 96.71% for the BigCat and CaDIS datasets, respectively). In performance comparisons, the AWTFE consistently outperformed other feature extraction methods in enhancing model performance. In addition, the proposed AWTFE method significantly improved pupil recognition performance by up to 2.87% in particularly challenging phases of cataract surgery.

Comparison of Machine and Human Expert Evaluation of Capsulorrhexis Creation Performance Through Analysis of Surgical Video Recordings.

Purpose: Achieving competency in cataract surgery is an essential component of ophthalmology residency training. Video-based analysis of surgery can change training through its objective, reliable, and timely assessment of resident performance. Methods: Using the Image Labeler application in MATLAB, the capsulorrhexis step of 208 surgical videos, recorded at the University of Michigan, was annotated for subjective and objective analysis. Two expert surgeons graded the creation of the capsulorrhexis based on the International Council of Ophthalmology's Ophthalmology Surgical Competency Assessment Rubric:Phacoemulsification (ICO-OSCAR:phaco) rating scale and a custom rubric (eccentricity, roundness, size, centration) that focuses on the objective aspects of this step. The annotated rhexis frames were run through an automated analysis to obtain objective scores for these components. The subjective scores were compared using both intra and inter-rater analyses to assess the consistency of a human-graded scale. The subjective and objective scores were compared using intraclass correlation methods to determine relative agreement. Results: All rhexes were graded as 4/5 or 5/5 by both raters for both items 4 and 5 of the ICO-OSCAR:phaco rating scale. Only roundness scores were statistically different between the subjective graders (mean difference = -0.149, p-value = 0.0023). Subjective scores were highly correlated for all components (>0.6). Correlations between objective and subjective scores were low (0.09 to 0.39). Conclusion: Video-based analysis of cataract surgery presents significant opportunities, including the ability to asynchronously evaluate performance and provide longitudinal assessment. Subjective scoring between two raters was moderately correlated for each component.

Evaluation of Methods for Detection and Semantic Segmentation of the Anterior Capsulotomy in Cataract Surgery Video.

Background: The capsulorhexis is one of the most important and challenging maneuvers in cataract surgery. Automated analysis of the anterior capsulotomy could aid surgical training through the provision of objective feedback and guidance to trainees. Purpose: To develop and evaluate a deep learning-based system for the automated identification and semantic segmentation of the anterior capsulotomy in cataract surgery video. Methods: In this study, we established a BigCat-Capsulotomy dataset comprising 1556 video frames extracted from 190 recorded cataract surgery videos for developing and validating the capsulotomy recognition system. The proposed system involves three primary stages: video preprocessing, capsulotomy video frame classification, and capsulotomy segmentation. To thoroughly evaluate its efficacy, we examined the performance of a total of eight deep learning-based classification models and eleven segmentation models, assessing both accuracy and time consumption. Furthermore, we delved into the factors influencing system performance by deploying it across various surgical phases. Results: The ResNet-152 model employed in the classification step of the proposed capsulotomy recognition system attained strong performance with an overall Dice coefficient of 92.21%. Similarly, the UNet model with the DenseNet-169 backbone emerged as the most effective segmentation model among those investigated, achieving an overall Dice coefficient of 92.12%. Moreover, the time consumption of the system was low at 103.37 milliseconds per frame, facilitating its application in real-time scenarios. Phase-wise analysis indicated that the Phacoemulsification phase (nuclear disassembly) was the most challenging to segment (Dice coefficient of 86.02%). Conclusion: The experimental results showed that the proposed system is highly effective in intraoperative capsulotomy recognition during cataract surgery and demonstrates both high accuracy and real-time capabilities. This system holds significant potential for applications in surgical performance analysis, education, and intraoperative guidance systems.

Severe Spontaneous Tilt of Scleral-Fixated Intraocular Lenses.

PURPOSE: To report and evaluate a multicenter series of 18 cases of severe, spontaneous IOL tilt involving the flanged intrascleral haptic fixation technique (FISHF). DESIGN: Clinical study with historical controls. METHODS: We report a cross-sectional study of 46 FISHF cases using the CT Lucia 602 IOL at a single academic center over a period of 24 weeks to determine the incidence of severe rotisserie-style rotational tilt. These rates were then compared with the same time-frame the prior year to help determine if this is a new phenomenon. Additional cases of severe tilt were solicited from another 4 academic centers. RESULTS: Among 46 FISHF cases at a single center, 5 developed severe tilt. No clear pattern in surgical technique, ocular history, or ocular anatomy was evident in these cases compared with controls, although the involved IOLs clustered within a narrow diopter range, indicative of a batch effect. In the same 24-week interval the year before, 33 FISHF cases were performed, none of which exhibited severe rotational tilt. In our multicenter dataset, 18 cases of tilt were identified. Surgeons included fellow and early-career physicians as well as surgeons with multiple years of experience with the Yamane technique. A variety of surgical approaches for FISHF were represented. In at least 8 of the cases, haptic rotation and/or dehiscence at the optic-haptic junction were documented. CONCLUSIONS: The identification of haptic rotation and dehiscence intraoperatively in several cases may reflect a new stability issue involving the optic-haptic junction.

Tensor-based Feature Extraction for Pupil Recognition in Cataract Surgery.

Cataract surgery remains the definitive treatment for cataracts, which are a major cause of preventable blindness worldwide. Adequate and stable dilation of the pupil are necessary for the successful performance of cataract surgery. Pupillary instability is a known risk factor for cataract surgery complications, and the accurate segmentation of the pupil from surgical video streams can enable the analysis of intraoperative pupil changes in cataract surgery. However, pupil segmentation performance can suffer due to variations in surgical illumination, obscuration of the pupil with surgical instruments, and hydration of the lens material intraoperatively. To overcome these challenges, we present a novel method called tensor-based pupil feature extraction (TPFE) to improve the accuracy of pupil recognition systems. We analyzed the efficacy of this approach with experiments performed on a dataset of 4,560 intraoperative annotated images from 190 cataract surgeries in human patients. Our results indicate that TPFE can identify features relevant to pupil segmentation and that pupil segmentation with state-of-the-art deep learning models can be significantly improved with the TPFE method.

Trainee Perspectives of Private Equity's Impact on Ophthalmology.

Objective The accelerated involvement of private equity (PE) in ophthalmology has many potential implications for the future of the field. The aim of this study was to evaluate trainee perspectives on PE's impact on ophthalmology. Methods An electronic survey was sent to trainees via an online ophthalmology research newsletter. The survey assessed for career goals and perspectives on the involvement of PE and its impact across a variety of attributes. Results A total of 41 United States-based respondents responded to the survey, 68% were medical students and 32% were residents or fellows. Seventy-eight percent of respondents reported they would not consider working for a PE-owned practice. There was a negative perceived impact of PE for physician autonomy, long-term physician income, career advancement, and quality of care. There was a positive perceived impact for the number of physician extenders, more referral sources, financial support, bargaining with insurance companies, starting physician salary, and administrative burden. All respondents agreed (76% strongly agree, 24% somewhat agree) that education about practice options and ownership structures is important to include in residency program education, with preferred modalities of small group discussions and on-site learning. Conclusions Trainees broadly perceive PE to negatively impact the practice of ophthalmology. While there were attributes perceived to be positively impacted by PE, these were not felt to be as important as those which may be negatively affected. New modalities for education about practice ownership options are necessary, and small group discussions and on-site learning may be of the highest yield for trainees.

Opioid Prescribing Patterns for Ulcerative Keratitis.

PURPOSE: The purpose of this study was to characterize rates of opioid prescription for different ulcerative keratitis types. METHODS: This cohort study included patients diagnosed with ulcerative keratitis according to the University of Michigan electronic health record data between September 1, 2014 and December 22, 2020. Ulcerative keratitis was categorized by etiologic type (bacterial, fungal, viral, acanthamoeba, inflammatory, polymicrobial, or unspecified) using rule-based data classification that accounted for billing diagnosis code, antimicrobial or antiinflammatory medications prescribed, laboratory results, and manual chart review. Opioid prescriptions were converted to morphine milligram equivalent and summed over 90 days from diagnosis. Opioid prescription rate and amount were compared between ulcerative keratitis types. RESULTS: Of 3322 patients with ulcerative keratitis, 173 (5.2%) were prescribed at least 1 opioid for pain management within 90 days of diagnosis. More patients with acanthamoeba (32.4%), fungal (21.1%), and polymicrobial (25.0%) keratitis were treated with opioids compared with bacterial (6.7%), unspecified (2.9%), or viral (1.8%) keratitis (all Bonferroni adjusted P < 0.05). For the 173 patients who were prescribed opioids, a total of 353 prescriptions were given within 90 days of diagnosis, with half given within the first week after diagnosis. The quantity of opioid prescribed within 90 days from diagnosis was not significantly different between ulcerative keratitis types (P = 0.6559). Morphine milligram equivalent units prescribed ranged from 97.5 for acanthamoeba keratitis to 112.5 for fungal keratitis. CONCLUSIONS: The type of ulcerative keratitis may influence the opioid prescription rate. Providers can better serve patients needing opioids for pain management through improved characterization of pain and development of more tailored pain management regimens.

Analysis of Cataract Surgery Instrument Identification Performance of Convolutional and Recurrent Neural Network Ensembles Leveraging BigCat.

Purpose: To develop a method for accurate automated real-time identification of instruments in cataract surgery videos. Methods: Cataract surgery videos were collected at University of Michigan's Kellogg Eye Center between 2020 and 2021. Videos were annotated for the presence of instruments to aid in the development, validation, and testing of machine learning (ML) models for multiclass, multilabel instrument identification. Results: A new cataract surgery database, BigCat, was assembled, containing 190 videos with over 3.9 million annotated frames, the largest reported cataract surgery annotation database to date. Using a dense convolutional neural network (CNN) and a recursive averaging method, we were able to achieve a test F1 score of 0.9528 and test area under the receiver operator characteristic curve of 0.9985 for surgical instrument identification. These prove to be state-of-the-art results compared to previous works, while also only using a fraction of the model parameters of the previous architectures. Conclusions: Accurate automated surgical instrument identification is possible with lightweight CNNs and large datasets. Increasingly complex model architecture is not necessary to retain a well-performing model. Recurrent neural network architectures add additional complexity to a model and are unnecessary to attain state-of-the-art performance. Translational Relevance: Instrument identification in the operative field can be used for further applications such as evaluating surgical trainee skill level and developing early warning detection systems for use during surgery.

Outcomes of Penetrating Keratoplasty After Open Globe Injury.

PURPOSE: The purpose of this study was to investigate the clinical features, surgical outcomes, and prognostic factors of penetrating keratoplasty (PKP) after open globe injury (OGI). METHODS: A retrospective review of all patients treated for OGI between January 2000 and July 2017 was conducted. Demographic, preoperative, perioperative, and postoperative data were collected for those who underwent PKP after OGI. The predictive value of each preoperative variable on graft failure was assessed using univariate and multivariable Cox proportional hazards models, and the predictive value of variables on post-PKP visual outcome was assessed using both univariate and multivariable logistic regression models. All eyes that underwent PKP after OGI were included unless they had less than 365 days of follow-up. RESULTS: Forty-six eyes that underwent PKP met inclusion criteria. The median age was 46 years (interquartile range = 23.00-61.25), median follow-up was 78.5 months (interquartile range = 38.63-122.02), and 37 of 46 subjects (80.4%) were male. The observed 1- and 5-year graft survival estimates were 80.4% and 41.7%, respectively. Factors statistically associated with graft failure in multivariable analyses were rejection episode, hazard ratio (HR) = 3.29; retinal detachment (RD), HR = 3.47; and endophthalmitis, HR = 6.27. Fifteen of 42 eyes (35.7%) regained ambulatory vision (20/200 or better). The strongest predictors of vision worse than 20/200 at the last follow-up were RD, odds ratio (OR) = 43.88; graft rejection, OR = 12.42; and injury outside the workplace, OR = 25.05. CONCLUSIONS: Despite a high graft survival at 1 year, most of the patients did not regain ambulatory vision. Graft rejection, RD, and endophthalmitis were risk factors for graft failure. These factors should be considered when counseling patients regarding PKP after OGI.

Association of Limiting Opioid Prescriptions With Use of Opioids After Corneal Surgery.

Importance: Opioids, which carry a high risk for addiction and overdose, are commonly prescribed after corneal surgery. Data are lacking describing opioid prescribing practices and opioid needs by patients after ophthalmic surgery. Objectives: To quantify opioid use and to assess the association of decreasing the number of opioid tablets prescribed after corneal surgery with postsurgical use. Design, Setting, and Participants: This prospective cohort study investigated opioid use after corneal surgery using direct interviews of 2 adult patient cohorts separated by an updated opioid prescribing guideline. The first cohort survey assessed the quantity of opioid tablets used after surgery. The cornea division of a tertiary care academic medical center reviewed the use needs and decreased the number of tablets prescribed after routine cases. Simultaneously, a statewide opioid monitoring program began that provided patients with opioid information. A second unique cohort received a more detailed survey to assess use, opioid disposal, and pain control. Data for the first cohort were collected from December 1, 2017, through January 19, 2018; for the second cohort, from June 1 to September 15, 2018. Data were analyzed from October 24, 2018, through September 24, 2019. Exposure: Corneal surgery. Main Outcomes and Measures: Differences in use of opioid tablets used by both patient cohorts, assessed using the 2-sample t test. Results: Of 112 eligible, contacted patients, 82 consented to participate (42 men [51%]; mean [SD] age, 42.5 [17.8] years) and were included in the analysis; 38 of 42 participated in the first cohort and 44 of 70 participated in the second cohort. Of those receiving opioid prescriptions, the first cohort was prescribed significantly more tablets than the second cohort (mean [SD], 18.8 [4.2] vs 6.6 [3.1]; difference, 12.2 [95% CI, 10.4-14.0]; P < .001). The first cohort used significantly more tablets than the second cohort (mean [SD], 8.3 [7.0] vs 4.0 [3.2]; difference, 4.3 [95% CI, 1.4-7.2]; P = .005) and had significantly more leftover tablets (mean [SD], 10.3 [6.9] vs 2.9 [2.7]; difference, 7.5 [95% CI, 4.7-10.2]; P < .001). In the detailed survey for the second cohort, 19 of 27 patients reported pain control as adequate (70% [95% CI, 50%-86%]); 6 of 27, as more than needed (22% [95% CI, 9%-42%]). Twenty of 28 participants (71% [95% CI, 55%-88%]) had leftover tablets; 17 of these (85% [95% CI, 62%-97%]) did not dispose of leftovers, and 3 (15% [95% CI, 3%-38%]) threw away or flushed leftovers. Conclusions and Relevance: After an assessment of opioid needs, physicians prescribed fewer opioid pills. However, patients who underwent cornea surgery and received fewer tablets continued to have adequate pain control and used even fewer tablets compared with the initial cohort. Patients with unused opioid tablets did not dispose of them properly.

Recipient Factors Associated With Graft Detachment of a Subsequent Eye in Sequential Descemet Membrane Endothelial Keratoplasty.

PURPOSE: To evaluate the recipient factors associated with graft detachment in the subsequent eye of patients who underwent sequential Descemet membrane endothelial keratoplasty (DMEK). METHODS: A retrospective, consecutive case series with 158 eyes of 79 patients who underwent DMEK surgeries in both eyes between October 2013 and April 2019 for treatment of Fuchs endothelial dystrophy. The main outcome measure was the presence of graft detachment (any amount of detachment) at postoperative 1 week in the subsequent eye. Preoperative, intraoperative, and postoperative factors were evaluated for association with graft detachment. RESULTS: Of 79 patients (158 eyes) with a mean follow-up of 11.7 ± 8.4 months, 18 patients (36 eyes) developed graft detachment in both eyes 1 week postoperatively. The risk of detachment in the subsequent eye was increased when the first eye had any amount of detachment [odds ratio = 2.8; 95% confidence interval (CI) = 1.1-7.3; P = 0.037]. When the first eye had a clinically significant detachment (>30% detached), the risk of detachment occurring in the subsequent eye was greater (odds ratio = 15.7; 95% CI = 1.8-134.5; P = 0.012). This risk of graft detachment in the subsequent eye increased 33% for every 5% increase in the detachment percentage in the first eye (odds ratio = 1.3; 95% CI = 1.1-1.6; P = 0.008). CONCLUSIONS: The presence of graft detachment after DMEK increases the risk of graft detachment in subsequent DMEK in the contralateral eye. Modification in perioperative care and surgical technique in the contralateral eye, such as a larger gas bubble, use of SF6 20%, and combining cataract surgery, may be needed when graft detachment occurs after DMEK in the first eye.

Lacrimal gland uptake of (67)Ga-gallium citrate correlates with biopsy results in patients with suspected sarcoidosis.

PURPOSE: To investigate whether lacrimal gland uptake on (67)Ga-gallium citrate scintigraphy correlates with histopathologic evidence of sarcoidosis. METHODS: A retrospective, pilot study of 31 patients with suspected sarcoidosis who underwent gallium scintigraphy and lacrimal gland biopsy. Lacrimal gland gallium uptake was assessed by subjective visual scoring (SVS) and lacrimal uptake ratio (LUR). RESULTS: Eleven (36%) patients had lacrimal gland biopsies containing noncaseating granulomas. A statistically significant correlation was found between lacrimal gland gallium uptake and biopsy positivity using SVS (p = 0.03) or LUR (p = 0.01). Using SVS, biopsy positivity rate increased from 0 to 50% in patients with mild to intense uptake. Using LUR, biopsy positivity rate increased linearly as the ratio increased from 13% (LUR < 4) to 100% (LUR > 8). CONCLUSIONS: Lacrimal biopsy positivity rate significantly correlated with gallium uptake on scintigraphy. Both SVS and LUR methods appear to correlate with histologic results and may potentially aid in patient selection for biopsy.

Corneal autograft and allograft in a 10-month-old premature boy with acquired bilateral corneal opacities.

PURPOSE: To report a case in which corneal autograft and allograft were performed in a 10.5-month-old, ex 24-week, premature boy with bilateral corneal opacities from infectious keratitis. METHODS: Case report based upon chart review. RESULTS: At 3 years, the corneal autograft is clear without vascular ingrowth. After transplantation, the clarity of the autograft improved markedly and unexpectedly from its pretransplantation appearance. The child fixes and follows and has central steady maintained fixation at near with a spectacle correction of +11.00 diopters. The allografted cornea is opaque with 360 degrees of vascular ingrowth. This eye is phthisical with no response to light. CONCLUSIONS: In circumstances in which a viable cornea is available from the patient's worse prognosis eye, a corneal autograft is a potential treatment option.

Capsular tension ring in the management of occult lens zonular dehiscence in infantile glaucoma.

The authors present a case of bilateral zonular dehiscence in a boy with infantile glaucoma who had developed cataracts. The zonular dehiscence was noted at the beginning of cataract surgery. The cataracts were removed and capsular tension rings and intraocular lenses were safely inserted and remained well centered.

Use of whole-body FDG PET-CT to aid in the diagnosis of occult sarcoidosis.

PURPOSE: To report a case where combined whole-body Fluorine-18 fluorodeoxyglucose (FDG) PET-CT scanning was used to aid in the diagnosis of a patient with occult sarcoidosis. DESIGN: Case report. METHODS: FDG PET-CT scanning was performed in a patient who presented with persistent bilateral panuveitis after cataract surgery and had undergone an extensive negative workup. RESULTS: FDG PET-CT scanning demonstrated extensive mediastinal adenopathy. Biopsy showed a non-caseating granuloma with associated giant cell formation consistent with a diagnosis of sarcoidosis. CONCLUSIONS: FDG PET-CT scanning generates tomographic scans with excellent sensitivity, spatial resolution, and anatomical landmark identification and may be useful in the workup of idiopathic uveitis.