Reproducibility of Quantitative Double-Echo Steady-State T2 Mapping of Knee Cartilage.

BACKGROUND: Cartilage T2 can detect joints at risk of developing osteoarthritis. The quantitative double-echo steady state (qDESS) sequence is attractive for knee cartilage T2 mapping because of its acquisition time of under 5 minutes. Understanding the reproducibility errors associated with qDESS T2 is essential to profiling the technical performance of this biomarker. PURPOSE: To examine the combined acquisition and segmentation reproducibility of knee cartilage qDESS T2 using two different regional analysis schemes: 1) manual segmentation of subregions loaded during common activities and 2) automatic subregional segmentation. STUDY TYPE: Prospective. SUBJECTS: 11 uninjured participants (age: 28 ± 3 years; 8 (73%) female). FIELD STRENGTH/SEQUENCE: 3-T, qDESS. ASSESSMENT: Test-retest T2 maps were acquired twice on the same day and with a 1-week interval between scans. For each acquisition, average cartilage T2 was calculated in four manually segmented regions encompassing tibiofemoral contact areas during common activities and 12 automatically segmented regions from the deep-learning open-source framework for musculoskeletal MRI analysis (DOSMA) encompassing medial and lateral anterior, central, and posterior tibiofemoral regions. Test-retest T2 values from matching regions were used to evaluate reproducibility. STATISTICAL TESTS: Coefficients of variation (%CV), root-mean-square-average-CV (%RMSA-CV), and intraclass correlation coefficients (ICCs) assessed test-retest T2 reproducibility. The median of test-retest standard deviations was used for T2 precision. Bland-Altman (BA) analyses examined test-retest biases. The smallest detectable difference (SDD) was defined as the BA limit of agreement of largest magnitude. Significance was accepted for P < 0.05. RESULTS: All cartilage regions across both segmentation schemes demonstrated intraday and interday qDESS T2 CVs and RMSA-CVs of ≤5%. T2 ICC values >0.75 were observed in the majority of regions but were more variable in interday tibial comparisons. Test-retest T2 precision was <1.3 msec. The T2 SDD was 3.8 msec. DATA CONCLUSION: Excellent CV and RMSA-CV reproducibility may suggest that qDESS T2 increases or decreases >5% (3.8 msec) could represent changes to cartilage composition. TECHNICAL EFFICACY: Stage 2.

Noise2Recon: Enabling SNR-robust MRI reconstruction with semi-supervised and self-supervised learning.

PURPOSE: To develop a method for building MRI reconstruction neural networks robust to changes in signal-to-noise ratio (SNR) and trainable with a limited number of fully sampled scans. METHODS: We propose Noise2Recon, a consistency training method for SNR-robust accelerated MRI reconstruction that can use both fully sampled (labeled) and undersampled (unlabeled) scans. Noise2Recon uses unlabeled data by enforcing consistency between model reconstructions of undersampled scans and their noise-augmented counterparts. Noise2Recon was compared to compressed sensing and both supervised and self-supervised deep learning baselines. Experiments were conducted using retrospectively accelerated data from the mridata three-dimensional fast-spin-echo knee and two-dimensional fastMRI brain datasets. All methods were evaluated in label-limited settings and among out-of-distribution (OOD) shifts, including changes in SNR, acceleration factors, and datasets. An extensive ablation study was conducted to characterize the sensitivity of Noise2Recon to hyperparameter choices. RESULTS: In label-limited settings, Noise2Recon achieved better structural similarity, peak signal-to-noise ratio, and normalized-RMS error than all baselines and matched performance of supervised models, which were trained with 14 × $$ 14\times $$ more fully sampled scans. Noise2Recon outperformed all baselines, including state-of-the-art fine-tuning and augmentation techniques, among low-SNR scans and when generalizing to OOD acceleration factors. Augmentation extent and loss weighting hyperparameters had negligible impact on Noise2Recon compared to supervised methods, which may indicate increased training stability. CONCLUSION: Noise2Recon is a label-efficient reconstruction method that is robust to distribution shifts, such as changes in SNR, acceleration factors, and others, with limited or no fully sampled training data.

Generalizability of Deep Learning Segmentation Algorithms for Automated Assessment of Cartilage Morphology and MRI Relaxometry.

BACKGROUND: Deep learning (DL)-based automatic segmentation models can expedite manual segmentation yet require resource-intensive fine-tuning before deployment on new datasets. The generalizability of DL methods to new datasets without fine-tuning is not well characterized. PURPOSE: Evaluate the generalizability of DL-based models by deploying pretrained models on independent datasets varying by MR scanner, acquisition parameters, and subject population. STUDY TYPE: Retrospective based on prospectively acquired data. POPULATION: Overall test dataset: 59 subjects (26 females); Study 1: 5 healthy subjects (zero females), Study 2: 8 healthy subjects (eight females), Study 3: 10 subjects with osteoarthritis (eight females), Study 4: 36 subjects with various knee pathology (10 females). FIELD STRENGTH/SEQUENCE: A 3-T, quantitative double-echo steady state (qDESS). ASSESSMENT: Four annotators manually segmented knee cartilage. Each reader segmented one of four qDESS datasets in the test dataset. Two DL models, one trained on qDESS data and another on Osteoarthritis Initiative (OAI)-DESS data, were assessed. Manual and automatic segmentations were compared by quantifying variations in segmentation accuracy, volume, and T2 relaxation times for superficial and deep cartilage. STATISTICAL TESTS: Dice similarity coefficient (DSC) for segmentation accuracy. Lin's concordance correlation coefficient (CCC), Wilcoxon rank-sum tests, root-mean-squared error-coefficient-of-variation to quantify manual vs. automatic T2 and volume variations. Bland-Altman plots for manual vs. automatic T2 agreement. A P value < 0.05 was considered statistically significant. RESULTS: DSCs for the qDESS-trained model, 0.79-0.93, were higher than those for the OAI-DESS-trained model, 0.59-0.79. T2 and volume CCCs for the qDESS-trained model, 0.75-0.98 and 0.47-0.95, were higher than respective CCCs for the OAI-DESS-trained model, 0.35-0.90 and 0.13-0.84. Bland-Altman 95% limits of agreement for superficial and deep cartilage T2 were lower for the qDESS-trained model, ±2.4 msec and ±4.0 msec, than the OAI-DESS-trained model, ±4.4 msec and ±5.2 msec. DATA CONCLUSION: The qDESS-trained model may generalize well to independent qDESS datasets regardless of MR scanner, acquisition parameters, and subject population. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

[Formula: see text] Field inhomogeneity correction for qDESS [Formula: see text] mapping: application to rapid bilateral knee imaging.

PURPOSE: [Formula: see text] mapping is a powerful tool for studying osteoarthritis (OA) changes and bilateral imaging may be useful in investigating the role of between-knee asymmetry in OA onset and progression. The quantitative double-echo in steady-state (qDESS) can provide fast simultaneous bilateral knee [Formula: see text] and high-resolution morphometry for cartilage and meniscus. The qDESS uses an analytical signal model to compute [Formula: see text] relaxometry maps, which require knowledge of the flip angle (FA). In the presence of [Formula: see text] inhomogeneities, inconsistencies between the nominal and actual FA can affect the accuracy of [Formula: see text] measurements. We propose a pixel-wise [Formula: see text] correction method for qDESS [Formula: see text] mapping exploiting an auxiliary [Formula: see text] map to compute the actual FA used in the model. METHODS: The technique was validated in a phantom and in vivo with simultaneous bilateral knee imaging. [Formula: see text] measurements of femoral cartilage (FC) of both knees of six healthy participants were repeated longitudinally to investigate the association between [Formula: see text] variation and [Formula: see text]. RESULTS: The results showed that applying the [Formula: see text] correction mitigated [Formula: see text] variations that were driven by [Formula: see text] inhomogeneities. Specifically, [Formula: see text] left-right symmetry increased following the [Formula: see text] correction ([Formula: see text] = 0.74 > [Formula: see text] = 0.69). Without the [Formula: see text] correction, [Formula: see text] values showed a linear dependence with [Formula: see text]. The linear coefficient decreased using the [Formula: see text] correction (from 24.3 ± 1.6 ms to 4.1 ± 1.8) and the correlation was not statistically significant after the application of the Bonferroni correction (p value > 0.01). CONCLUSION: The study showed that [Formula: see text] correction could mitigate variations driven by the sensitivity of the qDESS [Formula: see text] mapping method to [Formula: see text], therefore, increasing the sensitivity to detect real biological changes. The proposed method may improve the robustness of bilateral qDESS [Formula: see text] mapping, allowing for an accurate and more efficient evaluation of OA pathways and pathophysiology through longitudinal and cross-sectional studies.

Effects of the Competitive Season and Off-Season on Knee Articular Cartilage in Collegiate Basketball Players Using Quantitative MRI: A Multicenter Study.

BACKGROUND: Injuries to the articular cartilage in the knee are common in jumping athletes, particularly high-level basketball players. Unfortunately, these are often diagnosed at a late stage of the disease process, after tissue loss has already occurred. PURPOSE/HYPOTHESIS: To evaluate longitudinal changes in knee articular cartilage and knee function in National Collegiate Athletic Association (NCAA) basketball players and their evolution over the competitive season and off-season. STUDY TYPE: Longitudinal, multisite cohort study. POPULATION: Thirty-two NCAA Division 1 athletes: 22 basketball players and 10 swimmers. FIELD STRENGTH/SEQUENCE: Bilateral magnetic resonance imaging (MRI) using a combined T1ρ and T2 magnetization-prepared angle-modulated portioned k-space spoiled gradient-echo snapshots (MAPSS) sequence at 3T. ASSESSMENT: We calculated T2 and T1ρ relaxation times to compare compositional cartilage changes between three timepoints: preseason 1, postseason 1, and preseason 2. Knee Osteoarthritis Outcome Scores (KOOS) were used to assess knee health. STATISTICAL TESTS: One-way variance model hypothesis test, general linear model, and chi-squared test. RESULTS: In the femoral articular cartilage of all athletes, we saw a global decrease in T2 and T1ρ relaxation times during the competitive season (all P < 0.05) and an increase in T2 and T1ρ relaxation times during the off-season (all P < 0.05). In the basketball players' femoral cartilage, the anterior and central compartments respectively had the highest T2 and T1ρ relaxation times following the competitive season and off-season. The basketball players had significantly lower KOOS measures in every domain compared with the swimmers: Pain (P < 0.05), Symptoms (P < 0.05), Function in Daily Living (P < 0.05), Function in Sport/Recreation (P < 0.05), and Quality of Life (P < 0.05). CONCLUSION: Our results indicate that T2 and T1ρ MRI can detect significant seasonal changes in the articular cartilage of basketball players and that there are regional differences in the articular cartilage that are indicative of basketball-specific stress on the femoral cartilage. This study demonstrates the potential of quantitative MRI to monitor global and regional cartilage health in athletes at risk of developing cartilage problems. LEVEL OF EVIDENCE: 2 Technical Efficacy Stage: 2.

Rapid volumetric gagCEST imaging of knee articular cartilage at 3 T: evaluation of improved dynamic range and an osteoarthritic population.

Chemical exchange saturation transfer of glycosaminoglycans, gagCEST, is a quantitative MR technique that has potential for assessing cartilage proteoglycan content at field strengths of 7 T and higher. However, its utility at 3 T remains unclear. The objective of this work was to implement a rapid volumetric gagCEST sequence with higher gagCEST asymmetry at 3 T to evaluate its sensitivity to osteoarthritic changes in knee articular cartilage and in comparison with T2 and T1ρ measures. We hypothesize that gagCEST asymmetry at 3 T decreases with increasing severity of osteoarthritis (OA). Forty-two human volunteers, including 10 healthy subjects and 32 subjects with medial OA, were included in the study. Knee Injury and Osteoarthritis Outcome Scores (KOOS) were assessed for all subjects, and Kellgren-Lawrence grading was performed for OA volunteers. Healthy subjects were scanned consecutively at 3 T to assess the repeatability of the volumetric gagCEST sequence at 3 T. For healthy and OA subjects, gagCEST asymmetry and T2 and T1ρ relaxation times were calculated for the femoral articular cartilage to assess sensitivity to OA severity. Volumetric gagCEST imaging had higher gagCEST asymmetry than single-slice acquisitions (p = 0.015). The average scan-rescan coefficient of variation was 6.8%. There were no significant differences in average gagCEST asymmetry between younger and older healthy controls (p = 0.655) or between healthy controls and OA subjects (p = 0.310). T2 and T1ρ relaxation times were elevated in OA subjects (p < 0.001 for both) compared with healthy controls and both were moderately correlated with total KOOS scores (rho = -0.181 and rho = -0.332 respectively). The gagCEST technique developed here, with volumetric scan times under 10 min and high gagCEST asymmetry at 3 T, did not vary significantly between healthy subjects and those with mild-moderate OA. This further supports a limited utility for gagCEST imaging at 3 T for assessment of early changes in cartilage composition in OA.

Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers.

BACKGROUND: Super-resolution is an emerging method for enhancing MRI resolution; however, its impact on image quality is still unknown. PURPOSE: To evaluate MRI super-resolution using quantitative and qualitative metrics of cartilage morphometry, osteophyte detection, and global image blurring. STUDY TYPE: Retrospective. POPULATION: In all, 176 MRI studies of subjects at varying stages of osteoarthritis. FIELD STRENGTH/SEQUENCE: Original-resolution 3D double-echo steady-state (DESS) and DESS with 3× thicker slices retrospectively enhanced using super-resolution and tricubic interpolation (TCI) at 3T. ASSESSMENT: A quantitative comparison of femoral cartilage morphometry was performed for the original-resolution DESS, the super-resolution, and the TCI scans in 17 subjects. A reader study by three musculoskeletal radiologists assessed cartilage image quality, overall image sharpness, and osteophytes incidence in all three sets of scans. A referenceless blurring metric evaluated blurring in all three image dimensions for the three sets of scans. STATISTICAL TESTS: Mann-Whitney U-tests compared Dice coefficients (DC) of segmentation accuracy for the DESS, super-resolution, and TCI images, along with the image quality readings and blurring metrics. Sensitivity, specificity, and diagnostic odds ratio (DOR) with 95% confidence intervals compared osteophyte detection for the super-resolution and TCI images, with the original-resolution as a reference. RESULTS: DC for the original-resolution (90.2 ± 1.7%) and super-resolution (89.6 ± 2.0%) were significantly higher (P < 0.001) than TCI (86.3 ± 5.6%). Segmentation overlap of super-resolution with the original-resolution (DC = 97.6 ± 0.7%) was significantly higher (P < 0.0001) than TCI overlap (DC = 95.0 ± 1.1%). Cartilage image quality for sharpness and contrast levels, and the through-plane quantitative blur factor for super-resolution images, was significantly (P < 0.001) better than TCI. Super-resolution osteophyte detection sensitivity of 80% (76-82%), specificity of 93% (92-94%), and DOR of 32 (22-46) was significantly higher (P < 0.001) than TCI sensitivity of 73% (69-76%), specificity of 90% (89-91%), and DOR of 17 (13-22). DATA CONCLUSION: Super-resolution appears to consistently outperform naïve interpolation and may improve image quality without biasing quantitative biomarkers. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:768-779.

The impact of non-urothelial variant histology on oncological outcomes following radical cystectomy.

OBJECTIVES: To determine if the presence of non-urothelial variant histology (NUVH) is associated with a poorer prognosis following radical cystectomy (RC) compared to pure urothelial carcinoma (PUC). PATIENTS AND METHODS: A prospectively maintained database of all patients undergoing RC at a high-volume regional tertiary bladder cancer service between January 2010 and January 2017 was retrospectively analysed looking for patients with NUVH. Multivariate Cox proportional hazards regression analysis was used to determine disease recurrence, overall survival and bladder cancer-specific survival, as well as lymph node positivity. Association of tumour stage was determined using chi-squared analysis. RESULTS: In total, 430 patients underwent RC of which 73 (17%) had NUVH and 357 (83%) had PUC. The median (range) follow-up was 45.0 (8.5-100.2) months. The presence of NUVH was associated with both increased overall (hazard ratio [HR] 1.86, 95% confidence interval [CI] 1.21-2.85) and bladder cancer-specific mortality (HR 1.81, 95% CI 1.91-3.01), as well as disease recurrence (HR 1.71, 95% CI 1.06-2.75) in multivariate analysis. Squamous cell variant was also associated with increased overall mortality (HR 1.91, 95% CI 1.16-3.13), cancer-specific mortality (HR 2.03, 95% CI 1.21-3.42) and disease recurrence (HR 2.08, 95% CI 1.23-3.52), although this was not seen in other variant subtypes. Lymph node positivity was not associated with NUVH in multivariate analysis (HR 1.28, 95% CI 0.59-2.75), but NUVH was associated with advanced tumour stage on chi-squared analysis (P < 0.001). CONCLUSION: Our results showed a risk of shorter survival in NUVH compared to PUC. This suggests NUVH as an independent predictor of worse outcomes. As a result, patients with NUVH should be counselled preoperatively that overall and disease-specific outcomes are worse postoperatively and about the possible need for adjuvant treatment.

Lower Extremity Revascularization Using Optical Coherence Tomography-Guided Directional Atherectomy: Final Results of the EValuatIon of the PantheriS OptIcal COherence Tomography ImagiNg Atherectomy System for Use in the Peripheral Vasculature (VISION) Study.

PURPOSE: To evaluate the safety and efficacy of a novel optical coherence tomography (OCT)-guided atherectomy catheter in treating patients with symptomatic femoropopliteal disease. METHODS: The VISION trial ( ClinicalTrials.gov identifier NCT01937351) was a single-arm, multicenter, global investigational device exemption study enrolling 158 subjects (mean age 67.2±10.5 years; 87 men) across 20 participating sites. In this cohort, 198 lesions were treated with an average length of 53±40 mm using the Pantheris catheter alone or Pantheris + adjunctive therapy. The primary safety endpoint was the composite of major adverse events (MAEs) through 6 months (objective performance goal 43.2%). Technical success (primary efficacy outcome) was defined as the percent of target lesions with a residual diameter stenosis ≤50% after treatment with the Pantheris device alone (objective performance goal 87.0%). Procedural success was defined as reduction in stenosis to ≤30% after Pantheris ± adjunctive therapy. Tissue specimens retrieved from each treated lesion were histologically analyzed to evaluate the accuracy and precision of OCT image guidance. RESULTS: The primary efficacy outcome was achieved in 192 (97.0%) of the 198 lesions treated with the Pantheris catheter. Across all lesions, mean diameter stenosis was reduced from 78.7%±15.1% at baseline to 30.3%±11.8% after Pantheris alone (p<0.001) and to 22.4%±9.9% after Pantheris ± adjunctive therapy (p<0.001). Of the 198 target lesions, 104 (52.5%) were treated with the Pantheris alone, 84 (42.4%) were treated with Pantheris + adjunctive angioplasty, and 10 (5.1%) with Pantheris + angioplasty + stenting. The composite MAE outcome through 6 months occurred in 25 (16.6%) of 151 subjects. There were no clinically significant perforations, 1 (0.5%) catheter-related dissection, 4 (2%) embolic events, and a 6.4% clinically driven target lesion revascularization rate at 6 months. The 40-lesion chronic total occlusion (CTO) subset (mean lesion length 82±38 mm) achieved a similar significant reduction in stenosis to 35.5%±13.6% after Pantheris alone (p<0.001). Histological analysis of atherectomy specimens confirmed <1% adventitia in 82.1% of the samples, highlighting the precision of OCT guidance. Characterization of the OCT-guided lesions revealed evidence of an underestimation of disease burden when using fluoroscopy. CONCLUSION: OCT-guided atherectomy for femoropopliteal disease is safe and effective. Additionally, the precision afforded by OCT guidance leads to greater removal of plaque during atherectomy while sparing the adventitia.

Diagnostic imaging capabilities of the Ocelot -Optical Coherence Tomography System, ex-vivo evaluation and clinical relevance.

BACKGROUND: Optical coherence tomography (OCT) is a high-resolution sub-surface imaging modality using near-infrared light to provide accurate and high contrast intra-vascular images. This enables accurate assessment of diseased arteries before and after intravascular intervention. This study was designed to corroborate diagnostic imaging equivalence between the Ocelot and the Dragonfly OCT systems with regards to the intravascular features that are most important in clinical management of patients with atherosclerotic vascular disease. These intravascular features were then corroborated in vivo during treatment of peripheral arterial disease (PAD) pathology using the Ocelot catheter. METHODS: In order to compare the diagnostic information obtained by Ocelot (Avinger Inc., Redwood City, CA) and Dragonfly (St. Jude Medical, Minneapolis, MN) OCT systems, we utilized ex-vivo preparations of arterial segments. Ocelot and Dragonfly catheters were inserted into identical cadaveric femoral peripheral arteries for image acquisition and interpretation. Three independent physician interpreters assessed the images to establish accuracy and sensitivity of the diagnostic information. Histologic evaluation of the corresponding arterial segments provided the gold standard for image interpretation. In vivo clinical images were obtained during therapeutic interventions that included crossing of peripheral chronic total occlusions (CTOs) using the Ocelot catheter. RESULTS: Strong concordance was demonstrated when matching image characteristics between both OCT systems and histology. The Dragonfly and Ocelot system's vessel features were interpreted with high sensitivity (91.1-100%) and specificity (86.7-100%). Inter-observer concordance was documented with excellent correlation across all vessel features. The clinical benefit that the Ocelot OCT system provided was demonstrated by comparable procedural images acquired at the point of therapy. CONCLUSIONS: The study demonstrates equivalence of image acquisition and consistent physician interpretation of images acquired by the Ocelot and the Dragonfly OCT systems in-spite of distinct image processing algorithms and catheter configurations. This represents a dramatic shift away from both fluoroscopic imaging and diagnostic-only OCT imaging during peripheral arterial intervention towards therapeutic devices that incorporate real time diagnostic OCT imaging. In the clinical practice, these diagnostic capabilities have translated to best-in-class safety and efficacy for CTO crossing using the Ocelot catheter.

Intraocular Bioadhesives in Vitreoretinal Surgeries: A Systematic Review.

BACKGROUND: Bioadhesion is the ability of materials to adhere to biological surfaces. Bioadhesives are substances which induce or promote bioadhesion. The internal application of bioadhesives is gaining popularity in recent years and is being increasingly utilized in vitreoretinal surgeries. The aim of this review is to discuss the various bioadhesives and their applications in vitreoretinal surgeries. METHODS: PubMed, Google Scholar, ePub and Cochrane library database were used for literature selection. Keywords such as vitreoretinal surgery, bioadhesives, intraocular bioadhesives, glue, fibrin glue, cyanoacrylate glue and transforming growth factor were used individually and in differing combinations to perform a comprehensive systematic literature search. RESULTS: A total of 47 papers were retrieved and included in this review. Cyanoacrylate glue was the first bioadhesive to be utilized for vitreoretinal surgery in human eyes in 1976. The most common indications for the use of bioadhesives were in optic disc pit maculopathy, macular holes and rhegmatogenous retinal detachments. CONCLUSION: The use of intraocular bioadhesives in vitreoretinal surgery represents a significant and evolving area of interest within ophthalmic research. While the pioneering use of cyanoacrylate glue, fibrin glue and transforming growth factor beta demonstrated the possible use of intraocular adhesives, fibrin glue is the most widely used intraocular bioadhesive in vitreoretinal surgery.

Ten-year results of scleral-fixated intraocular lens implantation: outcomes of ab externo scleral fixation with 10-0 polypropylene suture.

PURPOSE: To describe long-term visual and anatomical outcomes of sutured scleral-fixated intraocular lens (SF IOL) implantation. SETTING: Tertiary eyecare hospital in India. DESIGN: Retrospective interventional noncomparative study. METHODS: Postoperative change in corrected distance visual acuity (CDVA) and occurrence of complications were assessed from the patient medical records. Long-term SF IOL survival rates and factors affecting the occurrence of postoperative IOL-related complications were assessed. Patients with postoperative follow-up less than 10 years or incomplete medical records were excluded. RESULTS: 64 eyes of 53 patients were included. Follow-up duration was 11.4 ± 1.2 years. Mean preoperative CDVA was 0.71 ± 0.43 logMAR (Snellen equivalent: 6/30), and mean CDVA at the final visit was 0.52 ± 0.49 logMAR (Snellen equivalent: 6/18) (P < .01). 48% cases had CDVA of 6/12 or better at the last follow-up. 58% cases had coexistent ocular pathology affecting the final visual outcome. IOL and suture-related complications were the commonest and included IOL decentration (17% cases), IOL drop (14%), and suture exposure (6%). The probability of IOL survival (postoperative period without IOL-related complications) was 90.6% at 8 years and 81.2% at 10 years (Kaplan-Meier analysis). Occurrence of postoperative IOL-related complications was unaffected by patient sex, age, indication for surgery (trauma or other), previous intraocular surgery, or technique of scleral fixation (2-point or 4-point) (multivariate regression analysis). CONCLUSIONS: Although sutured SF IOL implantation is viable with favorable long-term visual outcomes, there is a risk of postoperative IOL-related complications. Occurrence of postoperative IOL-related complications is unaffected by patient and ocular factors.

Prospector Heads: Generalized Feature Attribution for Large Models & Data.

Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.

Bacillary layer detachment as an inflammatory biomarker in toxoplasmosis retinochoroiditis: serial evolution on optical coherence tomography.

We describe the clinical course and serial evolution of bacillary layer detachment (BALAD) on optical coherence tomography (OCT) in toxoplasmosis retinochoroiditis and its importance as an inflammatory biomarker. Colour fundus photography and swept-source OCT of the BALAD were done at the time of presentation and subsequently at 1 week, 2 weeks, 4 weeks and at 11 weeks. Treatment involved oral trimethoprim (160 mg) + sulphamethoxazole (800 mg) two times per day, started at presentation for 2 months. Oral prednisolone was started after 1 week at a dose of 50 mg a day and tapered weekly over the next 5 weeks. The BALAD initially increased after starting treatment with trimethoprim-sulphamethoxazole and regressed within 1 week after initiation of oral prednisolone. Best corrected visual acuity improved to 20/40 from 20/160 at presentation (Snellen equivalent). This suggests that BALAD is an indicator of an acute inflammatory event and the accumulated fluid is secondary to retinal and choroidal inflammation.

Fovea sparing internal limiting membrane peeling for idiopathic macular holes-Report of unfavourable outcomes of a surgical technique.

PURPOSE: To describe the outcomes of fovea-sparing internal limiting membrane peeling for idiopathic macular holes. METHOD: This was a prospective, interventional case series in patients with idiopathic macular holes. Patients underwent fovea-sparing internal limiting membrane (ILM) peeling with the help of a finesse loop. The primary outcome measure was successful anatomical closure. Secondary outcome measures were postoperative improvement in best corrected visual acuity (BCVA) or any surgical complications. RESULTS: The study included 22 eyes of 22 patients (median age of 61 (IQR 58 to 66) years). The median basal diameter of the holes was 1054 (IQR 961.5 to 1278) microns, while the median minimal linear diameter was 697 (IQR 461.5 to 786) microns. Successful anatomic closure was achieved in nine cases out of 22 (40.9%). BCVA improved from 20/125 preoperatively to 20/80 at the end of the follow-up. There was no difference in baseline parameters between eyes with closure, versus eyes with an open hole. One eye had an iatrogenic break in an attempt to reinitiate peeling and create a fovea-sparing flap. One of the eyes had an ERM formation at end of 3 months. CONCLUSION: Our outcomes of fovea-sparing ILM peeling in idiopathic macular holes were unfavourable. The residual ILM could be causing tangential traction resulting in non-closure.

Improving Data-Efficiency and Robustness of Medical Imaging Segmentation Using Inpainting-Based Self-Supervised Learning.

We systematically evaluate the training methodology and efficacy of two inpainting-based pretext tasks of context prediction and context restoration for medical image segmentation using self-supervised learning (SSL). Multiple versions of self-supervised U-Net models were trained to segment MRI and CT datasets, each using a different combination of design choices and pretext tasks to determine the effect of these design choices on segmentation performance. The optimal design choices were used to train SSL models that were then compared with baseline supervised models for computing clinically-relevant metrics in label-limited scenarios. We observed that SSL pretraining with context restoration using 32 × 32 patches and Poission-disc sampling, transferring only the pretrained encoder weights, and fine-tuning immediately with an initial learning rate of 1 × 10-3 provided the most benefit over supervised learning for MRI and CT tissue segmentation accuracy (p < 0.001). For both datasets and most label-limited scenarios, scaling the size of unlabeled pretraining data resulted in improved segmentation performance. SSL models pretrained with this amount of data outperformed baseline supervised models in the computation of clinically-relevant metrics, especially when the performance of supervised learning was low. Our results demonstrate that SSL pretraining using inpainting-based pretext tasks can help increase the robustness of models in label-limited scenarios and reduce worst-case errors that occur with supervised learning.

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach.

Current risk scores using clinical risk factors for predicting ischemic heart disease (IHD) events-the leading cause of global mortality-have known limitations and may be improved by imaging biomarkers. While body composition (BC) imaging biomarkers derived from abdominopelvic computed tomography (CT) correlate with IHD risk, they are impractical to measure manually. Here, in a retrospective cohort of 8139 contrast-enhanced abdominopelvic CT examinations undergoing up to 5 years of follow-up, we developed multimodal opportunistic risk assessment models for IHD by automatically extracting BC features from abdominal CT images and integrating these with features from each patient's electronic medical record (EMR). Our predictive methods match and, in some cases, outperform clinical risk scores currently used in IHD risk assessment. We provide clinical interpretability of our model using a new method of determining tissue-level contributions from CT along with weightings of EMR features contributing to IHD risk. We conclude that such a multimodal approach, which automatically integrates BC biomarkers and EMR data, can enhance IHD risk assessment and aid primary prevention efforts for IHD. To further promote research, we release the Opportunistic L3 Ischemic heart disease (OL3I) dataset, the first public multimodal dataset for opportunistic CT prediction of IHD.

Towards Automatic Cartilage Quantification in Clinical Trials - Continuing from the 2019 IWOAI Knee Segmentation Challenge.

Objective: To evaluate whether the deep learning (DL) segmentation methods from the six teams that participated in the IWOAI 2019 Knee Cartilage Segmentation Challenge are appropriate for quantifying cartilage loss in longitudinal clinical trials. Design: We included 556 subjects from the Osteoarthritis Initiative study with manually read cartilage volume scores for the baseline and 1-year visits. The teams used their methods originally trained for the IWOAI 2019 challenge to segment the 1130 knee MRIs. These scans were anonymized and the teams were blinded to any subject or visit identifiers. Two teams also submitted updated methods. The resulting 9,040 segmentations are available online.The segmentations included tibial, femoral, and patellar compartments. In post-processing, we extracted medial and lateral tibial compartments and geometrically defined central medial and lateral femoral sub-compartments. The primary study outcome was the sensitivity to measure cartilage loss as defined by the standardized response mean (SRM). Results: For the tibial compartments, several of the DL segmentation methods had SRMs similar to the gold standard manual method. The highest DL SRM was for the lateral tibial compartment at 0.38 (the gold standard had 0.34). For the femoral compartments, the gold standard had higher SRMs than the automatic methods at 0.31/0.30 for medial/lateral compartments. Conclusion: The lower SRMs for the DL methods in the femoral compartments at 0.2 were possibly due to the simple sub-compartment extraction done during post-processing. The study demonstrated that state-of-the-art DL segmentation methods may be used in standardized longitudinal single-scanner clinical trials for well-defined cartilage compartments.

Ocular Aberrations in Eyes with Primary Congenital Glaucoma.

PURPOSE: To highlight the magnitude of ocular higher order aberrations (HOA) and lower order aberrations (LOA), including component contributions from corneal and internal planes in Primary Congenital Glaucoma (PCG) patients. METHODS: Consecutive treated PCG patients co-operative for ocular examination and aberrometry, were enrolled over two years for this cross-sectional, comparative, single-center, unmasked study. Best-corrected visual acuity, refraction, IOP, wavefront aberrometry and topography (iTrace) were performed and results were compared with unaffected fellow eyes of unilateral glaucoma patients as well as age and sex-matched controls with no ocular anomalies other than treatable refractive error. RESULTS: Both eyes of 32 consecutive PCG patients (17 unilateral, 15 bilateral) and 39 controls were enrolled. The median LogMAR corrected distance visual acuity of PCG eyes was 0.68 (IQR: 0.2-1.8). Total ocular (Root mean square (RMS) 1.7 µm vs 0.3 µm, p = 0.014), corneal (RMS 1.1 µm vs 0.3 µm, p = 0.004) and internal (RMS 1.1 µm vs 0.2 µm, p = 0.013) aberrations, as well as HOAs and LOAs at each plane, were significantly higher in PCG eyes than in controls. Component HOAs from corneal and internal planes were positively correlated with each other (p < 0.001; rs: 0.7). Total aberrations were greater in the affected eyes of PCG compared to the rest. The predominant subtype of HOAs in PCG was coma and trefoil. PCG with corneal opacity/Haab's striae had significantly higher astigmatism than the affected eyes with clear corneae at the corneal plane (p = 0.02). The aberrations were not statistically associated with the corneal diameter or refractive error in PCG eyes. CONCLUSIONS: Significantly greater aberrations (Total, HOAs and LOAs, at corneal as well as an internal plane) were seen among eyes affected with PCG. Though the exact impact of these aberrations on the final visual outcome is difficult to determine, these could play a pertinent role in compromising visual function, thus impacting the management of visual rehabilitation in these patients.

Clinical presentation and treatment outcomes of an algorithmic approach to uveal effusion syndrome.

Purpose: To describe the clinical features and treatment outcomes in spontaneous uveal effusion syndrome (UES). Methods: A 10-year retrospective chart review of UES patients from a tertiary eye center was carried out. Optical coherence tomography (OCT), fundus fluorescein angiography, and ultrasound biomicroscopy (UBM) scans were performed. UES was managed based on presenting best-corrected visual acuity (BCVA), symptoms, and fundus findings. Patients with secondary causes of uveal effusion were excluded. Results: Twenty-five eyes of 16 patients were included. Of the 16 patients, 14 (88%) were male and 9 (56%) had bilateral disease. Fifteen of 25 affected eyes had nanophthalmos (axial length (AL) <20.5 mm) and 6 had hyperopia with AL >20.5 mm. The presenting mean distance BCVA was 0.74 ± 0.64 logMAR (mean Snellen: 20/100). Eleven eyes had exudative retinal detachment, and 4 also had exudative choroidal detachment (CD). Choroidal thickness (CT) was increased in 11 eyes on B-scan ultrasonography, and the mean CT was 1.74 ± 0.38 mm. Sub-retinal fluid (SRF) and retinal folds were the most common OCT findings. UBM findings included shallow angles, peripheral CD, and supra-ciliary effusion. A combination of local and systemic corticosteroids was used to successfully treat 12 eyes, 6 needed surgery, and 7 were observed. Partial sclerectomy with anterior chamber maintainer-assisted SRF drainage was the favored surgery. The median period of follow-up was 6.5 months (0.1-76 months), and the mean distance BCVA at the last follow-up was 0.58 ± 0.42 logMAR (mean Snellen: 20/80). Conclusion: UES can be suitably managed both medically and surgically based on clinical presentation.