Anomaly Detection for Medical Images Using Heterogeneous Auto-Encoder.

Anomaly detection is an important task for medical image analysis, which can alleviate the reliance of supervised methods on large labelled datasets. Most existing methods use a pixel-wise self-reconstruction framework for anomaly detection. However, there are two challenges of these studies: 1) they tend to overfit learning an identity mapping between the input and output, which leads to failure in detecting abnormal samples; 2) the reconstruction considers the pixel-wise differences which may lead to an undesirable result. To mitigate the above problems, we propose a novel heterogeneous Auto-Encoder (Hetero-AE) for medical anomaly detection. Our model utilizes a convolutional neural network (CNN) as the encoder and a hybrid CNN-Transformer network as the decoder. The heterogeneous structure enables the model to learn the intrinsic information of normal data and enlarge the difference on abnormal samples. To fully exploit the effectiveness of Transformer in the hybrid network, a multi-scale sparse Transformer block is proposed to trade off modelling long-range feature dependencies and high computational costs. Moreover, the multi-stage feature comparison is introduced to reduce the noise of pixel-wise comparison. Extensive experiments on four public datasets (i.e., retinal OCT, chest X-ray, brain MRI, and COVID-19) verify the effectiveness of our method on different imaging modalities for anomaly detection. Additionally, our method can accurately detect tumors in brain MRI and lesions in retinal OCT with interpretable heatmaps to locate lesion areas, assisting clinicians in diagnosing abnormalities efficiently.

PatchCL-AE: Anomaly detection for medical images using patch-wise contrastive learning-based auto-encoder.

Anomaly detection is an important yet challenging task in medical image analysis. Most anomaly detection methods are based on reconstruction, but the performance of reconstruction-based methods is limited due to over-reliance on pixel-level losses. To address the limitation, we propose a patch-wise contrastive learning-based auto-encoder for medical anomaly detection. The key contribution is the patch-wise contrastive learning loss that provides supervision on local semantics to enforce semantic consistency between corresponding input-output patches. Contrastive learning pulls corresponding patch pairs closer while pushing non-corresponding ones apart between input and output, enabling the model to learn local normal features better and improve discriminability on anomalous regions. Additionally, we design an anomaly score based on local semantic discrepancies to pinpoint abnormalities by comparing feature difference rather than pixel variations. Extensive experiments on three public datasets (i.e., brain MRI, retinal OCT, and chest X-ray) achieve state-of-the-art performance, with our method achieving over 99% AUC on retinal and brain images. Both the contrastive patch-wise supervision and patch-discrepancy score provide targeted advancements to overcome the weaknesses in existing approaches.

Adaptive enhancement of cataractous retinal images for contrast standardization.

Cataract affects the quality of fundus images, especially the contrast, due to lens opacity. In this paper, we propose a scheme to enhance different cataractous retinal images to the same contrast as normal images, which can automatically choose the suitable enhancement model based on cataract grading. A multi-level cataract dataset is constructed via the degradation model with quantified contrast. Then, an adaptive enhancement strategy is introduced to choose among three enhancement networks based on a blurriness classifier. The blurriness grading loss is proposed in the enhancement models to further constrain the contrast of the enhanced images. During test, the well-trained blurriness classifier can assist in the selection of enhancement networks with specific enhancement ability. Our method performs the best on the synthetic paired data on PSNR, SSIM, and FSIM and has the best PIQE and FID on 406 clinical fundus images. There is a 7.78% improvement for our method compared with the second on the introduced [Formula: see text] score without over-enhancement according to [Formula: see text], which demonstrates that the proper enhancement by our method is close to the high-quality images. The visual evaluation on multiple clinical datasets also shows the applicability of our method for different blurriness. The proposed method can benefit clinical diagnosis and improve the performance of computer-aided algorithms such as vessel tracking and vessel segmentation.

Cost-utility analysis of commonly used anti-glaucoma interventions for mild-to-moderate primary open-angle glaucoma patients in rural and urban China.

OBJECTIVE: An increasing number of studies have explored the clinical effects of antiglaucoma surgical procedures; however, economic evidence was scarce. We aimed to compare the cost-effectiveness between maximal medical treatment (MMT) and commonly used surgical procedures (trabeculectomy, Ahmed glaucoma valve implantation, gonioscopy-assisted transluminal trabeculotomy and ab interno canaloplasty). DESIGN AND SETTING: A Markov model study. PARTICIPANTS: A hypothetical cohort of 100 000 patients with mild-to-moderate primary open-angle glaucoma (POAG). OUTCOMES: Data were obtained from public sources. The main outcomes were incremental cost-utility ratios (ICURs) using quality-adjusted life-years (QALYs). Sensitivity analyses were conducted to verify the robustness and sensitivity of base-case results. MAIN RESULTS: Both cumulative costs and QALYs gained from surgical procedures (US$6045-US$13 598, 3.33-6.05 QALYs) were higher than those from MMT (US$3117-US$6458, 3.14-5.66 QALYs). Compared with MMT, all surgical procedures satisfied the cost-effectiveness threshold (lower than US$30 501 and US$41 568 per QALY gained in rural and urban settings, respectively). During the 5-year period, trabeculectomy produced the lowest ICUR (US$21 462 and US$15 242 per QALY gained in rural and urban settings, respectively). During the 10-year-follow-up, trabeculectomy still produced the lowest ICUR (US$13 379 per QALY gained) in urban setting; however, gonioscopy-assisted transluminal trabeculotomy (US$19 619 per QALY gained) and ab interno canaloplasty (US$18 003 per QALY gained) produced lower ICURs than trabeculectomy (US$19 675 per QALY gained) in rural areas. Base-case results were most sensitive to the utilities and costs of initial treatment and maintenance. CONCLUSIONS: The long-term cost-effectiveness of commonly used surgical procedures could be better than the short-term cost-effectiveness for mild-to-moderate POAG patients in China. Health economic studies, supported by more rigorous structured real-world data, are needed to assess their everyday cost-effectiveness.

A fundus image classification framework for learning with noisy labels.

Fundus images are widely used in the screening and diagnosis of eye diseases. Current classification algorithms for computer-aided diagnosis in fundus images rely on large amounts of data with reliable labels. However, the appearance of noisy labels degrades the performance of data-dependent algorithms, such as supervised deep learning. A noisy label learning framework suitable for the multiclass classification of fundus diseases is presented in this paper, which combines data cleansing (DC), adaptive negative learning (ANL), and sharpness-aware minimization (SAM) modules. Firstly, the DC module filters the noisy labels in the training dataset based on the prediction confidence. Then, the ANL module modifies the loss function by choosing complementary labels, which are neither the given labels nor the labels with the highest confidence. Moreover, for better generalization, the SAM module is applied by simultaneously optimizing the loss and its sharpness. Extensive experiments on both private and public datasets show that our method greatly promotes the performance for classification of multiple fundus diseases with noisy labels.

Implementing a digital comprehensive myopia prevention and control strategy for children and adolescents in China: a cost-effectiveness analysis.

Background: Children and adolescents' myopia is a major public problem. Although the clinical effect of various interventions has been extensively studied, there is a lack of national-level and integral assessments to simultaneously quantify the economics and effectiveness of comprehensive myopia prevention and control programs. We aimed to compare the cost-effectiveness between traditional myopia prevention and control strategy, digital comprehensive myopia prevention and control strategy and school-based myopia screening program in China. Methods: A Markov model was used to compare the cost-utility and cost-effectiveness among school-based myopia screening, traditional myopia prevention and control strategy, and digital comprehensive myopia prevention and control strategy among 6 to 18-year-old rural and urban schoolchildren. Parameters were collected from published sources. The primary outcomes were quality-adjusted life-year, disability-adjusted life-year, incremental cost-utility ratio, and incremental cost-effectiveness ratio. Extensive sensitivity analyses were performed to test the robustness and sensitivity of base-case analysis. Findings: Compared with school-based myopia screening strategy, after implementing digital comprehensive myopia prevention and control strategy, the prevalence of myopia among 18-year-old students in rural and urban areas was reduced by 3.79% and 3.48%, respectively. The incremental cost-utility ratio per quality-adjusted life-year gained with the digital myopia management plan ($11,301 for rural setting, and $10,707 for urban setting) was less than 3 times the per capita gross domestic product in rural settings ($30,501) and less than 1 time the per capita gross domestic product in urban settings ($13,856). In cost-effectiveness analysis, the incremental cost-effectiveness ratio produced by digital comprehensive myopia management strategy ($37,446 and $41,814 per disability-adjusted life-year averted in rural and urban settings) slightly exceeded the cost-effectiveness threshold. When assuming perfect compliance, full coverage of outdoor activities and spectacles satisfied the cost-effectiveness threshold, and full coverage of outdoor activities produced the lowest cost ($321 for rural settings and $808 for urban settings). Interpretations: Health economic evidence confirmed the cost-effectiveness of promoting digital comprehensive myopia prevention and control strategies for schoolchildren at the national level. Sufficient evidence provides an economic and public health reference for further action by governments, policy-makers and other myopia-endemic countries. Funding: National Natural Science Foundation of China, NSFC (82171051), Beijing Natural Science Foundation (JQ20029), Capital Health Research and Development of Special (2020-2-1081), National Natural Science Foundation of China, NSFC (82071000), National Natural Science Foundation of China, NSFC (8197030562).

External validation of a deep learning detection system for glaucomatous optic neuropathy: a real-world multicentre study.

OBJECTIVES: To conduct an external validation of an automated artificial intelligence (AI) diagnostic system using fundus photographs from a real-life multicentre cohort. METHODS: We designed external validation in multiple scenarios, consisting of 3049 images from Qilu Hospital of Shandong University in China (QHSDU, validation dataset 1), 7495 images from three other hospitals in China (validation dataset 2), and 516 images from high myopia (HM) population of QHSDU (validation dataset 3). The corresponding sensitivity, specificity and accuracy of this AI diagnostic system to identify glaucomatous optic neuropathy (GON) were calculated. RESULTS: In validation datasets 1 and 2, the algorithm yielded accuracy of 93.18% and 91.40%, area under the receiver operating curves (AUC) of 95.17% and 96.64%, and significantly higher sensitivity of 91.75% and 91.41%, respectively, compared to manual graders. On the subsets complicated with retinal comorbidities, such as diabetic retinopathy or age-related macular degeneration, in validation datasets 1 and 2, the algorithm achieved accuracy of 87.54% and 93.81%, and AUC of 97.02% and 97.46%, respectively. In validation dataset 3, the algorithm achieved comparable accuracy of 81.98% and AUC of 87.49%, with a sensitivity of 83.61% and specificity of 81.76% on GON recognition specifically in the HM population. CONCLUSIONS: With acceptable generalization capability across varying levels of image quality, different clinical centres, or certain retinal comorbidities, such as HM, the automatic AI diagnostic system had the potential to provide expert-level glaucoma detection.

Ab interno canaloplasty versus gonioscopy-assisted transluminal trabeculotomy in open-angle glaucoma: a randomised controlled trial.

OBJECTIVE: To compare the efficacy and safety of ab interno canaloplasty (ABiC) with gonioscopy-assisted transluminal trabeculotomy (GATT) in patients with open-angle glaucoma (OAG). METHOD: This randomised clinical trial recruited eyes with OAG and no previous incisional ocular surgery, among which 38 were randomised to ABiC and 39 to GATT. Follow-ups were performed at 1, 3, 6 and 12 months postoperatively. The primary outcome measures were intraocular pressure (IOP) and use of glaucoma medication at 12 months postoperatively. The secondary outcome measure was complete surgical success (not requiring glaucoma surgery, IOP ≤21 mm Hg and non-use of glaucoma medications). RESULTS: Both groups had similar demographic and ocular characteristics. A total of 71 of the 77 subjects (92.2%) completed 12-month follow-up. At 12 months, mean IOP was 19.0±5.2 mm Hg in the ABiC group and 16.0±3.1 mm Hg in the GATT group (p=0.003). Overall, 57.2% of ABiC patients and 77.8% of GATT patients were medication free (p=0.06). The number of glaucoma medications was 0.9±1.3 in the ABiC group and 0.6±1.2 in the GATT group (p=0.27). The 12-month cumulative rate of complete surgical success was 56% in the ABiC group and 75% in the GATT group (p=0.09). Three eyes in the ABiC group and one eye in the GATT group required additional glaucoma surgery. Hyphema (87% vs 47%) and supraciliary effusion (92% vs 71%) were noted more often in the GATT group than in the ABiC group. CONCLUSIONS: The preliminary result showed that GATT had an advantage over ABiC in IOP reduction for OAG patients, accompanied by favourable safety at 12-month postoperatively. TRIAL REGISTRATION NUMBER: ChiCTR1800016933.

Deep ensemble learning for accurate retinal vessel segmentation.

Significant progress has been made in deep learning-based retinal vessel segmentation in recent years. However, the current methods suffer from low performance and the robust of the models is not that good. Our work introduces an novel framework for retinal vessel segmentation based on deep ensemble learning. The results of benchmarking comparisons indicate that our model outperforms the existing ones on multiple datasets, demonstrating that our models are more effective, superior, and robust for the retinal vessel segmentation. It evinces the capability of our model to capture the discriminative feature representations through introducing the ensemble strategy to integrate different base deep learning models like pyramid vision Transformer and FCN-Transformer. We expect our proposed method can benefit and accelerate the development of accurate retinal vessel segmentation in this field.

A deep network using coarse clinical prior for myopic maculopathy grading.

Pathological Myopia (PM) is a globally prevalent eye disease which is one of the main causes of blindness. In the long-term clinical observation, myopic maculopathy is a main criterion to diagnose PM severity. The grading of myopic maculopathy can provide a severity and progression prediction of PM to perform treatment and prevent myopia blindness in time. In this paper, we propose a feature fusion framework to utilize tessellated fundus and the brightest region in fundus images as prior knowledge. The proposed framework consists of prior knowledge extraction module and feature fusion module. Prior knowledge extraction module uses traditional image processing methods to extract the prior knowledge to indicate coarse lesion positions in fundus images. Furthermore, the prior, tessellated fundus and the brightest region in fundus images, are integrated into deep learning network as global and local constrains respectively by feature fusion module. In addition, rank loss is designed to increase the continuity of classification score. We collect a private color fundus dataset from Beijing TongRen Hospital containing 714 clinical images. The dataset contains all 5 grades of myopic maculopathy which are labeled by experienced ophthalmologists. Our framework achieves 0.8921 five-grade accuracy on our private dataset. Pathological Myopia (PALM) dataset is used for comparison with other related algorithms. Our framework is trained with 400 images and achieves an AUC of 0.9981 for two-class grading. The results show that our framework can achieve a good performance for myopic maculopathy grading.

Economic evaluation of combined population-based screening for multiple blindness-causing eye diseases in China: a cost-effectiveness analysis.

BACKGROUND: More than 90% of vision impairment is avoidable. However, in China, a routine screening programme is currently unavailable in primary health care. With the dearth of economic evidence on screening programmes for multiple blindness-causing eye diseases, delivery options, and screening frequencies, we aimed to evaluate the costs and benefits of a population-based screening programme for multiple eye diseases in China. METHODS: We developed a decision-analytic Markov model for a cohort of individuals aged 50 years and older with a total of 30 1-year cycles. We calculated the cost-effectiveness and cost-utility of screening programmes for multiple major blindness-causing eye diseases in China, including age-related macular degeneration, glaucoma, diabetic retinopathy, cataracts, and pathological myopia, from a societal perspective (including direct and indirect costs). We analysed rural and urban settings separately by different screening delivery options (non-telemedicine [ie, face-to-face] screening, artificial intelligence [AI] telemedicine screening, and non-AI telemedicine screening) and frequencies. We calculated incremental cost-utility ratios (ICURs) using quality-adjusted life-years and incremental cost-effectiveness ratios (ICERs) in terms of the cost per blindness year avoided. One-way deterministic and simulated probabilistic sensitivity analyses were used to assess the robustness of the main outcomes. FINDINGS: Compared with no screening, non-telemedicine combined screening of multiple eye diseases satisfied the criterion for a highly cost-effective health intervention, with an ICUR of US$2494 (95% CI 1130 to 2716) and an ICER of $12 487 (8773 to 18 791) in rural settings. In urban areas, the ICUR was $624 (395 to 907), and the ICER was $7251 (4238 to 13 501). Non-AI telemedicine screening could result in fewer costs and greater gains in health benefits (ICUR $2326 [1064 to 2538] and ICER $11 766 [8200 to 18 000] in rural settings; ICUR $581 [368 to 864] and ICER $6920 [3926 to 13 231] in urban settings). AI telemedicine screening dominated no screening in rural settings, and in urban settings the ICUR was $244 (-315 to 1073) and the ICER was $2567 (-4111 to 15 389). Sensitivity analyses showed all results to be robust. By further comparison, annual AI telemedicine screening was the most cost-effective strategy in both rural and urban areas. INTERPRETATION: Combined screening of multiple eye diseases is cost-effective in both rural and urban China. AI coupled with teleophthalmology presents an opportunity to promote equity in eye health. FUNDING: National Natural Science Foundation of China.

Non-invasive intracranial pressure estimation using ultrasonographic measurement of area of optic nerve subarachnoid space.

OBJECTIVE: To verify whether the area of the ONSAS (ONSASA) obtained by transorbital ultrasonography can be used to accurately evaluate the intracranial pressure (ICP). METHODS: The recorded indexes included the optic nerve diameter, the optic nerve sheath diameter (ONSD), the width of both sides of the ONSAS (ONSASW) at 3 mm from the optic nerve head and the entire ONSASA outlined between 3 and 7 mm. After exploring and comparing five models to describe the relationship between body mass index (BMI), mean arterial blood pressure (MABP), ONSASA and ICP, the best model was determined. RESULTS: In all, 90 patients with neurological diseases undergoing continuous invasive ICP monitoring were included in the study. In the training group, the correlation coefficient for the association between the ICP and ONSASA (Pearson's correlation r=0.953) was higher than that for the association of the ICP with the ONSD (r=0.672; p<0.0001) and ONSASW at 3 mm behind the globe (r=0.691; p<0.0001). In the training group, the weighting function for prediction of the ICP was as follows: non-invasive ICP=2.050×ONSASA-0.051×BMI +0.036*MABP-5.837. With 20 mm Hg as the cut-off point for a high or low ICP, the sensitivity and specificity of ONSASA predicting ICP was 1.00 and 0.92. Receiver operator curve analysis revealed that the calculated cut-off value for predicting elevated ICP was 19.96 (area under curve= 0.960, 95% CI 0.865 to 1.00). CONCLUSION: Measurement of the ONSASA using ultrasonography can serve as a practical method for rapid and non-invasive quantification for evaluating ICP through an accurate mathematical formula with the BMI and MABP considered as contributing parameters. TRIAL REGISTRATION NUMBER: The study was registered in the Chinese Clinical Trial Registry (Study no ChiCTR2100045274).

Identification of the Optimal Model for the Prediction of Diabetic Retinopathy in Chinese Rural Population: Handan Eye Study.

Background: To identify an optimal model for diabetic retinopathy (DR) prediction in Chinese rural population by establishing and comparing different algorithms based on the data from Handan Eye Study (HES). Methods: Five algorithms, including multivariable logistic regression (MLR), classification and regression trees (C&RT), support vector machine (SVM), random forests (RF), and gradient boosting machine (GBM), were used to establish DR prediction models with HES data. The performance of the models was assessed based on the adjusted area under the ROC curve (AUROC), sensitivity, specificity, and accuracy. Results: The data on 4752 subjects were used to build the DR prediction model, and among them, 198 patients were diagnosed with DR. The age of the included subjects ranged from 30 to 85 years old, with an average age of 50.9 years (SD = 3.04). The kappa coefficient of the diagnosis between the two ophthalmologists was 0.857. The MLR model revealed that blood glucose, systolic blood pressure, and body mass index were independently associated with the development of DR. The AUROC obtained by GBM (0.952), RF (0.949), and MLR (0.936) was similar and statistically larger than that of CART (0.682) and SVM (0.765). Conclusions: The MLR model exhibited excellent prediction performance and visible equation and thus was the optimal model for DR prediction. Therefore, the MLR model may have the potential to serve as a complementary screening tool for the early detection of DR, especially in remote and underserved areas.

Cost-effectiveness and cost-utility of traditional and telemedicine combined population-based age-related macular degeneration and diabetic retinopathy screening in rural and urban China.

Background: To assess the cost-effectiveness and cost-utility of a population-level traditional and telemedicine combined age-related macular degeneration (AMD) and diabetic retinopathy (DR) screening program in rural and urban China. Methods: Decision-analytic Markov models were conducted to evaluate the costs and benefits of traditional and telemedicine combined AMD and DR screening from a societal perspective. A cohort of all participants aged 50 years old and above was followed through a total of 30 1-year Markov cycles. Separate analyses were performed for rural and urban settings. Relevant parameters such as the prevalence of AMD and DR, transition probability, compliance with screening and treatment, screening sensitivity, specificity, utility, and mortality were collected from published studies specific to China, other Asian counties' studies, or unpublished data sources such as the National Committee for the Prevention of Blindness. Costs of screening, full examination, and treatment come from the real medical environments and unified pricing of Beijing Municipal Medical Insurance Bureau. Primary outcomes were incremental cost-utility ratios (ICURs) using quality-adjusted life-years (QALYs) and incremental cost-effectiveness ratios (ICERs) using years of blindness avoided. One-way deterministic and simulated probabilistic sensitivity analyses were conducted to reflect uncertainty. Findings: Under the status quo, the total expected medical costs for a 50-year-old patient with AMD or DR were $869·59 and $1,514·18 in rural and urban settings, respectively. Both traditional and telemedicine screening were highly cost-effective. In rural settings, ICURs were $191 (95% confidence interval [CI]: $66 to $239) and $199 (95% CI: $-12 to $217), and ICERs were $2,436 (95% CI: $1,089 to $3,254) and $2,441 (95% CI: $1,452 to $3,900) for traditional and telemedicine screening separately. Even more surprising, both screening strategies dominated no screening in urban settings. Our results were insensitive and robust to extensive sensitivity analyses. Among all acceptable screening intervals (from 1 to 5 years), annual screening could not only produce biggest benefits but also keep ICERs less than three times and one time the per capita gross domestic product (GDP) in rural and urban settings separately. When compared with traditional screening, ICERs of telescreening were less than three times the per capita GDP in rural settings ($2,559 to $8,809) and less than one time the per capita GDP in urban settings (less than $5,564), annual telescreening produced the biggest benefits, it could avert 119 and 270 years of blindness in rural and urban areas separately when 100,000 people were screened. Interpretation: We performed decision-analytic Markov models for combined AMD and DR screening in rural and urban China, and the results showed that population-level combined screening for AMD and DR is likely to be highly cost-effective in both rural and urban China for people over 50 years old. Optimal screening may have an interval of every year based on teleophthalmology platforms. In the future, China should pay more attention to chronic eye diseases and the government should establish a sound chronic disease management system and make every patient enjoy equal medical services. Funding: National Natural Science Foundation of China, NSFC (82171051); the Major Innovation Platform of Public Health & Disease Control and Prevention, Renmin University of China and Beijing Nova program (Z191100001119072).

Prevalence of cataract and cataract surgery in urban and rural Chinese populations over 50 years old: a systematic review and Meta-analysis.

AIM: To summarize the data of epidemiological studies on cataract prevalence over 50 years old in urban and rural areas of China from 2000 to 2020, and to analyze the prevalence of cataract and operation rate in China. METHODS: By searching PubMed, EMBASE, Web of Science, Wanfang Data and CNKI, Chinese and English literatures on the prevalence of cataract in China were retrieved, and the relevant characteristic data were extracted. Then, Stata v15SE software was used for Meta-analysis and heterogeneity test. According to the results of heterogeneity, the corresponding effect models were selected to combine the extracted data. RESULTS: A total of 20 studies were included in this study, with a total of 111 434 cases. Meta-analysis showed heterogeneity. According to the random effect model, the overall prevalence of cataract in Chinese people over 50 years old was 27.45%, that in rural was 28.79%, and that in urban was 26.66%. The overall coverage rate of cataract surgery was 9.19%. CONCLUSION: The prevalence of cataract is high in China, and there is still room for improvement in surgical coverage, so it is very important to promote cataract screening and prevention.

Torin 1 alleviates impairment of TFEB-mediated lysosomal biogenesis and autophagy in TGFBI (p.G623_H626del)-linked Thiel-Behnke corneal dystrophy.

Thiel-Behnke corneal dystrophy (TBCD) is an epithelial-stromal TGFBI dystrophy caused by mutations in the TGFBI (transforming growth factor beta induced) gene, though the underlying mechanisms and pathogenesis of TBCD are still obscure. The study identifies a novel mutation in the TGFBI gene (p.Gly623_His626del) in a TBCD pedigree. Characteristics of the typical vacuole formation, irregular corneal epithelial thickening and thinning, deposition of eosinophilic substances beneath the epithelium, and involvement of the anterior stroma were observed in this pedigree via transmission electron microscopy (TEM) and histological staining. Tgfbi-p.Gly623_Tyr626del mouse models of TBCD were subsequently generated via CRISPR/Cas9 technology, and the above characteristics were further verified via TEM and histological staining. Lysosomal dysfunction and downregulation of differential expression protein CTSD (cathepsin D) were observed using LysoTracker Green DND-26 and proteomic analysis, respectively. Hence, lysosomal dysfunction probably leads to autophagic flux obstruction in TBCD; this was supported by enhanced LC3-II and SQSTM1 levels and decreased CTSD. TFEB (transcription factor EB) was prominently decreased in TBCD corneal fibroblasts and administration of ATP-competitive MTOR inhibitor torin 1 reversed this decline, resulting in the degradation of accumulated mut-TGFBI (mutant TGFBI protein) via the ameliorative lysosomal function and autophagic flux owing to elevated TFEB activity as measured by western blot, confocal microscopy, and flow cytometry. Transfected HEK 293 cells overexpressing human full-length WT-TGFBI and mut-TGFBI were generated to further verify the results obtained in human corneal fibroblasts. Amelioration of lysosome dysfunction may therefore have therapeutic efficacy in the treatment of TBCD.Abbreviations AS-OCT: anterior segment optical coherence tomography; ATP: adenosine triphosphate; Cas9: CRISPR-associated protein 9; CLEAR: coordinated lysosomal expression and regulation; CRISPR: clustered regularly interspaced short palindromic repeats; CTSB: cathepsin B; CTSD: cathepsin D; CTSF: cathepsin F; CTSL: cathepsin L; DNA: deoxyribonucleic acid; ECM: extracellular matrix; Fas1: fasciclin 1; FC: flow cytometry; GAPDH: glyceraldeyde-3-phosphate dehydrogenase; GCD2: granular corneal dystrophy type 2; HE: hematoxylin and eosin; LAMP2: lysosomal-associated membrane protein; MT: mutation type; MTOR: mechanistic target of rapamycin kinase; MTORC1: MTOR complex 1; mut-TGFBI: mutant TGFBI protein; SD: standard deviation; TBCD: Thiel-Behnke corneal dystrophy; TEM: transmission electron microscopy; TFEB: transcription factor EB; TGFBI: transforming growth factor beta induced; WT: wild type.