Manual Assessment Method Research Articles

AI-based lumbar central canal stenosis classification on sagittal MR images is comparable to experienced radiologists using axial images

Abstract Objectives The assessment of lumbar central canal stenosis (LCCS) is crucial for diagnosing and planning treatment for patients with low back pain and neurogenic pain. However, manual assessment methods are time-consuming, variable, and require axial MRIs. The aim of this study is to develop and validate an AI-based model that automatically classifies LCCS using sagittal T2-weighted MRIs. Methods A pre-existing 3D AI algorithm was utilized to segment the spinal canal and intervertebral discs (IVDs), enabling quantitative measurements at each IVD level. Four musculoskeletal radiologists graded 683 IVD levels from 186 LCCS patients using the 4-class Lee grading system. A second consensus reading was conducted by readers 1 and 2, which, along with automatic measurements, formed the training dataset for a multiclass (grade 0–3) and binary (grade 0–1 vs. 2–3) random forest classifier with tenfold cross-validation. Results The multiclass model achieved a Cohen’s weighted kappa of 0.86 (95% CI: 0.82–0.90), comparable to readers 3 and 4 with 0.85 (95% CI: 0.80–0.89) and 0.73 (95% CI: 0.68–0.79) respectively. The binary model demonstrated an AUC of 0.98 (95% CI: 0.97–0.99), sensitivity of 93% (95% CI: 91–96%), and specificity of 91% (95% CI: 87–95%). In comparison, readers 3 and 4 achieved a specificity of 98 and 99% and sensitivity of 74 and 54%, respectively. Conclusion Both the multiclass and binary models, while only using sagittal MR images, perform on par with experienced radiologists who also had access to axial sequences. This underscores the potential of this novel algorithm in enhancing diagnostic accuracy and efficiency in medical imaging. Key Points QuestionHow can the classification of lumbar central canal stenosis (LCCS) be made more efficient? FindingsMulticlass and binary AI models, using only sagittal MR images, performed on par with experienced radiologists who also had access to axial sequences. Clinical relevanceOur AI algorithm accurately classifies LCCS from sagittal MRI, matching experienced radiologists. This study offers a promising tool for automated LCCS assessment from sagittal T2 MRI, potentially reducing the reliance on additional axial imaging.

Research on Applying Deep Learning to Visual–Motor Integration Assessment Systems in Pediatric Rehabilitation Medicine

In pediatric rehabilitation medicine, manual assessment methods for visual–motor integration result in inconsistent scoring standards. To address these issues, incorporating artificial intelligence (AI) technology is a feasible approach that can reduce time and improve accuracy. Existing research on visual–motor integration scoring has proposed a framework based on convolutional neural networks (CNNs) for the Beery–Buktenica developmental test of visual–motor integration. However, as the number of training questions increases, the accuracy of this framework significantly decreases. This paper proposes a new architecture to reduce the number of features, channels, and overall model complexity. The architectureoptimizes input features by concatenating question numbers with answer features and selecting appropriate channel ratios and optimizes the output vector by designing the task as a multi-class classification. This paper also proposes a model named improved DenseNet. After experimentation, DenseNet201 was identified as the most suitable pre-trained model for this task and was used as the backbone architecture for improved DenseNet. Additionally, new fully connected layers were added for feature extraction and classification, allowing for specialized feature learning. The architecture can provide reasons for unscored results based on prediction results and decoding rules, offering directions for children’s training. The final experimental results show that the proposed new architecture improves the accuracy of scoring 6 question graphics by 12.8% and 12 question graphics by 20.14% compared to the most relevant literature. The accuracy of the proposed new architecture surpasses the model frameworks of the most relevant literature, demonstrating the effectiveness of this approach in improving scoring accuracy and stability.

Hybrid knowledge and data driven approach for prioritizing sewer sediment cleaning

The efficient assessment of sewer sediment condition is important for municipalities to formulate prioritization strategies for cleaning initiatives. However, manual assessment methods are plagued by inherent subjective and inaccuracy. To address these deficiencies, this paper introduces a hybrid approach integrating both knowledge-based principles and data-driven techniques for Sewer Sediment Cleaning Priority Assessment (SSCPA). The proposed approach exhibits a notable level of assessment accuracy, achieving macro-average precision, recall, and F1-score metrics of 87.9%, 88.0%, and 88.0%, respectively. These findings underscore the efficacy of SSCPA as a valuable tool for evaluating sewer sediment conditions, thereby enhancing the decision-making process for cleaning prioritization efforts. Future research should incorporate the probability of failure as a pivotal factor and explore the temporal dynamics of sewer sediment for more comprehensive insight.

Effectiveness of E-Rapor Implementation: Literature Review

Implementing E-Rapor (Electronic Report) in education has become an exciting research topic that has captured the attention of numerous researchers. Based on the findings of a literature review, E-Rapor aims to bring benefits and positive impacts to the field of education, promoting its growth in the current digital era. However, researchers have also noted several limitations in using the E-Rapor-based information system, including difficulties in its application for information processing, competence planning, and data management. This research seeks to analyze gaps in the learning outcomes achieved by students when the E-Report application system is implemented compared to traditional or manual assessment methods. The data collection method employed in this study is a literature review, which involves gathering secondary data from various reputable sources. As for the research instrument used, the researchers have formulated five research questions that serve as valuable guides throughout the data collection process. The results of the discussion show that E-Reports are useful for regularly assessing student abilities by educators and school employees, allowing quick intervention when necessary, and increasing overall educational efficiency. Due to this, the author recommends further research to understand the impact of using E-Reports on learning outcomes and educational management to be comprehensive.

Exam Assessor Tool: An Automated System for Efficient Answer Sheet Evaluation

With Education 4.0 and four quadrant approach number of innovations have gone into academics for efficient, experiential, and outcome-based education however assessment schemes are still very much dependent on manual assessment methods which are time-consuming and cumbersome. The grading system can sometimes be irrational, with diversified schemes for the same course and can also be biased. Covid 19 pandemic caused a global economic avalanche like we’ve never experienced in our lifetime. Many countries have implemented control measures such as blockades and curfews. The education system in this chaos saw a silver lining with academics shifting to online mode, with paradigm shift in teaching, assessment techniques too need to evolve. Work done is an effort to ease the process of assessment, a machine learning assisted model is developed that automates subjective answer evaluation in the education sector. Our project involved several crucial steps, including grayscale conversion, Natural Language Processing (NLP) for data cleansing, data splitting, and training an artificial neural network (ANN) to predict scores based on extracted features. ANN-based system grades subjective responses without human intervention, reducing the workload of teachers and professors. Model constructed an ANN architecture with three layers using Rectified Linear Activation Unit (ReLU) and Sigmoid activation functions. Trained model was incorporated into a user-friendly web application using the Streamlit library. Model design gives a major boost in grading efficiency and accuracy while providing valuable feedback to students. Research surveys were conducted, and a dataset was constructed for training and testing the model. study yielded an accuracy of 83.14% after employing techniques such as text cleaning, preprocessing, and feature extraction.

Intelligent Evaluation of Chinese Hard-Pen Calligraphy Using a Siamese Transformer Network

The essence of Chinese calligraphy inheritance resides in calligraphy education. However, it encounters challenges such as a scarcity of calligraphy instructors, time-consuming and inefficient manual assessment methods, and inconsistent evaluation criteria. In response to these challenges, this paper introduces a deep learning-based automatic calligraphy evaluation model. Initially, hard-pen handwriting samples from 100 volunteers were collected and preprocessed to create a dataset consisting of 4800 samples, along with the corresponding label files for hard-pen calligraphy evaluation. Subsequently, YOLOv5 was utilized for region detection and character recognition on the evaluation samples to obtain the corresponding standard samples. Lastly, a Siamese metric model, with VGG16 as the primary feature extraction submodule, was developed for hard-pen calligraphy evaluation. To improve feature extraction and propagation, a transformer structure was introduced to extract global information from both the evaluated and standard samples, thereby optimizing the evaluation results. Experimental results demonstrate that the proposed model achieves a precision of 0.75, recall of 0.833, and mAP of 0.990 on the hard-pen calligraphy evaluation dataset, effectively realizing automatic calligraphy evaluation. This model presents a novel approach for intelligently assessing hard-pen calligraphy.

Defect Severity Assessment Model for Sewer Pipeline Based on Automated Pipe Calibration

To address the low-efficiency issue of the manual assessment method for sewer pipe defects, we propose a defect severity assessment model based on automated pipe calibration (DSA-APC), which can provide automated and quantitative assessments. First, the cross-section feature is extracted by automated pipe calibration. A pipe cross-section feature extraction algorithm based on restricted Hough gradient transform (RHGT) is proposed. Then, a fine-defect feature extraction method based on edge detection is proposed to extract the features of pipe defects more finely. Finally, according to the assessment standards of the sewer pipe defect, a defect severity assessment table is constructed, and the area ratio of the defect feature and cross-section feature is used to evaluate the severity. Experiments are carried out on the Songbai data set and Level-sewer10 data set. The average absolute deviation of the DSA-APC model is 2.008%, and the average accuracy is 86.73%. The experimental results show that the DSA-APC model can correctly evaluate the severity level of sewer pipe defects, which has a good practical application value.

Large-scale validation study of an improved semiautonomous urine cytology assessment tool: AutoParis-X.

Adopting a computational approach for the assessment of urine cytology specimens has the potential to improve the efficiency, accuracy, and reliability of bladder cancer screening, which has heretofore relied on semisubjective manual assessment methods. As rigorous, quantitative criteria and guidelines have been introduced for improving screening practices (e.g., The Paris System for Reporting Urinary Cytology), algorithms to emulate semiautonomous diagnostic decision-making have lagged behind, in part because of the complex and nuanced nature of urine cytology reporting. In this study, the authors report on the development and large-scale validation ofa deep-learning tool, AutoParis-X, whichcan facilitate rapid, semiautonomous examination of urine cytology specimens. The results of this large-scale, retrospective validation study indicate that AutoParis-X can accurately determine urothelial cell atypia and aggregate a wide variety of cell-related and cluster-related information across a slide to yield an atypia burden score, which correlates closely with overall specimen atypia and is predictive of Paris system diagnostic categories. Importantly, this approach accounts for challenges associated with the assessment of overlapping cell cluster borders, which improve the ability to predict specimen atypia and accurately estimate the nuclear-to-cytoplasm ratio for cells in these clusters. The authors developed a publicly available, open-source, interactive web application that features a simple, easy-to-use display for examining urine cytology whole-slide images and determining the level of atypia in specific cells, flagging the most abnormal cells for pathologist review. The accuracy of AutoParis-X (and other semiautomated digital pathology systems) indicates that these technologies are approaching clinical readiness and necessitates full evaluation of these algorithms in head-to-head clinical trials.

AUTOMATED COUNTING OF SQUAMOUS EPITHELIAL CELLS IN LIQUID-BASED CYTOLOGY SAMPLES

Cytologic screening is only effective with adequate material. The Bethesda System (TBS), an international system for standardizing the results of cervical cytology, establishes criteria for adequacy. According to the TBS, a sample prepared by liquid-based cytology (LBC) can be classified as adequate if it contains not less than 5,000 squamous epithelial cells. There are methods of manual assessment of the cellularity of cytological samples. However, the uniformity of cellular material distribution of LBC samples makes possible the application of automatic tools for assessing the adequacy of the material based on the cellularity criterion. This paper compares the results of digital LBC samples adequacy assessment using the automated artificial neural network method Vision Cyto Pap and the manual assessment method. Analysis of the results of counting squamous epithelial cells in 506 LBC samples showed a significant correlation (r = 0.93) between the automated and manual method. The high diagnostic parameters (sensitivity = 93.8 % and specificity = 99.2 %) of the automated Vision Cyto Pap method allow to conclude that the algorithms of such a tool can be used to determine the adequacy of the cytological material by the number of squamous epithelium cells with sufficient reliability.

A deep learning approach for dental implant planning in cone-beam computed tomography images

BackgroundThe aim of this study was to evaluate the success of the artificial intelligence (AI) system in implant planning using three-dimensional cone-beam computed tomography (CBCT) images.MethodsSeventy-five CBCT images were included in this study. In these images, bone height and thickness in 508 regions where implants were required were measured by a human observer with manual assessment method using InvivoDental 6.0 (Anatomage Inc. San Jose, CA, USA). Also, canals/sinuses/fossae associated with alveolar bones and missing tooth regions were detected. Following, all evaluations were repeated using the deep convolutional neural network (Diagnocat, Inc., San Francisco, USA) The jaws were separated as mandible/maxilla and each jaw was grouped as anterior/premolar/molar teeth region. The data obtained from manual assessment and AI methods were compared using Bland–Altman analysis and Wilcoxon signed rank test.ResultsIn the bone height measurements, there were no statistically significant differences between AI and manual measurements in the premolar region of mandible and the premolar and molar regions of the maxilla (p > 0.05). In the bone thickness measurements, there were statistically significant differences between AI and manual measurements in all regions of maxilla and mandible (p < 0.001). Also, the percentage of right detection was 72.2% for canals, 66.4% for sinuses/fossae and 95.3% for missing tooth regions.ConclusionsDevelopment of AI systems and their using in future for implant planning will both facilitate the work of physicians and will be a support mechanism in implantology practice to physicians.

The identification of fire potentials in oil mining area on Minas Sumatera Operations-Indonesia by manual assessment method

The petroleum industry both mining and crude oil processing has a high level of fire risk. This can be caused by the hydrocarbons from the content of mining products, crude oil content to the fuel which is contained in the area around processing. Where, if there is a fire in the surround area can cause a terrible explosion in the oil tank or pool fire. To identify the potential fires, a manual assessment method can be carried out by: making clusters and grouping of production activities, risk matrix table of industrial activities, field observations, identification of hazard materials, analyzes and actions in accordance with the standard operating procedures applied in the company. From the results of observations on the oil and gas industry in Sumatra – Operation Indonesia, generally the identification of potential fires is good, there are several factors that must be taken so the zero accidents in the oil industry can be fully satisfied.

Adherence to disease-specific drug treatment among patients with pulmonary arterial hypertension or chronic thromboembolic pulmonary hypertension.

BackgroundPulmonary arterial hypertension (PAH) and chronic thromboembolic pulmonary hypertension (CTEPH) require lifelong treatment. The aim of the present study was to investigate adherence to disease-specific treatment in patients with PAH or CTEPH.MethodsThe study comprised an adult population diagnosed with PAH (n=384) or CTEPH (n=187) alive in 2016–2017. The study utilised three registries: the Swedish PAH registry, the National Board of Health and Welfare, and Statistics Sweden. Withdrawals from pharmacies of disease-specific oral treatments were studied. Adherence was assessed as: 1) Number of days covered defined as the difference between the total number of daily dosages dispensed and the total number of days covered; and 2) Manual assessment by two persons that independently reviewed each patient's prescription fill history to detect anomalies or patterns of deteriorating or improving adherence over time.ResultsThe mean age was 61±16 years, 61% were female and mean time since diagnosis was 4.6 years. Adherence was 62% using the Number of days covered method and 66% by the Manual assessment method. Drug-specific adherence varied from 91% for riociguat to 60% for sildenafil. Good adherence was associated with shorter time since diagnosis in patients with PAH and with lower number of concomitant other chronic treatments in patients with CTEPH. Age, sex, socioeconomic status or number of pulmonary hypertension (PH) treatments were not associated with adherence.ConclusionAdherence to oral disease-specific treatment was 60–66% and associated with time since diagnosis and number of concomitant chronic treatments. Sex, age or socioeconomic factors did not affect adherence.

Comparison Of Waist And Hip Circumference Measures From 3-dimensional Technology And Manual Measurements

Three-dimensional (3D) scanning technology is becoming increasingly popular to obtain quick anthropometric and body composition measurements and may be a practical alternative to manual assessment methods. PURPOSE: To compare waist and hip circumferences measured from a 3D scan to manual measurements in healthy adults. METHODS: Data was collected on 66 healthy male (n=22) and female (n=44) young adults (Mean ± SD: Age: 20.6 ± 1.1 yrs, BMI: 22.6 ± 2.0 kg/m2). Manual measurement of the waist was assessed at the narrowest part of the trunk; hip circumference was measured at the widest region of the buttocks. Circumferences were measured twice by the same researcher and averaged. Measurements corresponding to the same waist and hip regions assessed manually were automatically determined by the 3D scanner software. Paired-samples t-tests were utilized to determine differences between methods for the total sample and each sex. Manual measurements were used as the criterion to evaluate prediction error (standard error of the estimate [SEE]). RESULTS: For the total sample, the 3D scan significantly underestimated waist (Mean difference (3D - manual) [MD]: MD: 6.3 ± 2.2 cm; p<0.001) and hip (MD: 2.8 ± 2.3 cm; p<0.001) circumferences compared to manual assessments. For the men, the 3D scanner significantly underestimated waist (MD: 6.6 ± 2.1 cm; p<0.001) and hip (MD: 2.2 ± 1.9 cm; p<0.001) circumferences. The same trend was seen for women for the waist (MD: 6.1 ± 2.2 cm; p<0.001) and hips (MD: 3.0 ± 2.5 cm; p<0.001). Prediction error of hip circumference was greater for women (SEE=2.42 cm) compared to men (SEE=1.94 cm); waist circumference error was similar for women (SEE=2.14 cm) and men (SEE =2.05 cm). CONCLUSIONS: 3D technology may underestimate waist and hip circumference estimates compared to manual techniques in normal weight adults. However, 3D technology may be useful to provide quick anthropometric measurements.

Clinical assessment of reactive balance control in acquired brain injury: A comparison of manual and cable release-from-lean assessment methods.

Perturbation-evoked stepping reactions are infrequently assessed directly in clinical settings even though stepping reactions in response to a sudden loss-of-balance perturbation ultimately determine whether a fall occurs. Individuals with acquired brain injury (ABI) due to stroke who are ambulatory and awaiting hospital discharge have been found to exhibit delayed stepping reactions but are typically discharged without assessment of perturbation-evoked stepping. Tests that specifically target the capacity to perform perturbation-evoked stepping reactions are important to identify those at risk for falls and to direct intervention strategies. The aim of this study was to evaluate agreement and reliability of two assessment methods used to assess rapid stepping reactions, specifically in individuals with ABI due to stroke or other causes. A secondary aim was to compare perturbation-triggered biomechanics of the two assessment methods. Thirty-five participants who were less than 4months post-ABI were evaluated in an inpatient unit at the Toronto Rehabilitation Institute. Stepping reactions were assessed using manual release-from-lean and cable release-from-lean perturbation-based assessment methods. There was moderate agreement between the assessment scores resulting from the two assessment methods (κ=0.55) and substantial test-retest reliability (κ's>0.61) for both assessment methods. There was no evidence that the assessment score was affected by assessment method, test-retest, or assessment order. However, the cable release from lean resulted in a more rapid release of the lean support force (2ms vs. 125ms) and earlier foot-off times (340ms vs. 401ms) compared with the manual release from lean. Delays in foot-off time associated with the manual release-from-lean perturbation raise concerns that the manual assessment method may not provide a perturbation that is sufficiently challenging to reveal a patient's balance-recovery capacity and associated fall risk. However, the manual assessment requires no equipment and the assessment score may provide a useful indication of gross reactive balance control.

A Deep Automated Skeletal Bone Age Assessment Model with Heterogeneous Features Learning.

Skeletal bone age assessment is a widely used standard procedure in both disease detection and growth prediction for children in endocrinology. Conventional manual assessment methods mainly rely on personal experience in observing X-ray images of left hand and wrist to calculate bone age, which show some intrinsic limitations from low efficiency to unstable accuracy. To address these problems, some automated methods based on image processing or machine learning have been proposed, while their performances are not satisfying enough yet in assessment accuracy. Motivated by the remarkable success of deep learning (DL) techniques in the fields of image classification and speech recognition, we develop a deep automated skeletal bone age assessment model based on convolutional neural networks (CNNs) and support vector regression (SVR) using multiple kernel learning (MKL) algorithm to process heterogeneous features in this paper. This deep framework has been constructed, not only exploring the X-ray images of hand and twist but also some other heterogeneous information like race and gender. The experiment results prove its better performance with higher bone age assessment accuracy on two different data sets compared with the state of the art, indicating that the fused heterogeneous features provide a better description of the degree of bones' maturation.

A microfluidic device for motility and osmolality analysis of zebrafish sperm.

A microfluidic chip is described that facilitates research and quality control analysis of zebrafish spermwhich, due to its miniscule (i.e., 2-5 μl) sample volume and short duration of motility (i.e., <1min), present a challenge for traditional manual assessment methods. A micromixer molded in polydimethylsiloxane (PDMS) bonded to a glass substrate was used to activate sperm samples by mixing with water, initiated by the user depressing a transfer pipette connected to the chip. Sample flow in the microfluidic viewing chamber was able to be halted within 1s, allowing for rapid analysis of the sample using established computer-assisted sperm analysis (CASA) methods. Zebrafish sperm cell activation was consistent with manual hand mixing and yielded higher values of motility at earlier time points, as well as more subtle time-dependent trends in motility, than those processed by hand. Sperm activation curves, which indicate sample quality by evaluating percentage and duration of motility at various solution osmolalities, were generated with on-chip microfabricated gold floor electrodes interrogated by impedance spectroscopy. The magnitude of admittance was linearly proportional to osmolality and was not affected by the presence of sperm cells in the vicinity of the electrodes. This device represents a pivotal step in streamlining methods for consistent, rapid assessment of sperm quality for aquatic species. The capability to rapidly activate sperm and consistently measure motility with CASA using the microfluidic device described herein will help improve the reproducibility of studies on sperm and assist development of germplasm repositories.

Empirical research on the utility of a preparation manual for a disaster medical response drill.

PurposeIt is difficult for emergency physicians to plan and execute a disaster medical response drill while conducting their daily work activities. Readily available drill preparation manuals are therefore essential, alongside assessment methods to ensure quality. Here, we propose email text analysis as a manual assessment method, and investigate its validity.MethodsThe preparation status of two similar large-scale disaster medical response drills were compared. All email texts exchanged during the preparation stage were analyzed, and frequently appearing words (quality element) and word counts (quantity element) were compared between Drill 1, which was organized without a manual, and Drill 2, organized with a manual.ResultsWord frequency analysis revealed that the key components of the manual (visualization of necessary work, preparation of documents in a certain format, and clarification of aims of the drill) contributed to the effectiveness of the preparation process for Drill 2. Furthermore, work volume during the preparation for Drill 2 was decreased by 41.9% from that during the preparation for Drill 1.ConclusionPreparation of a high-quality manual is crucial so that emergency physicians can plan and execute a disaster medical response drill. Email text analysis can serve as an objective method assessing the quality of manuals.

Software‐supported evaluation of gastric motility in MRI: A feasibility study

The aim of this study was to evaluate the feasibility of dedicated motility assessment software for quantitative evaluation of basic gastric motility and to validate it using manual measurements. Ten patients (5 males/5 females, mean 41 years) out of a previous series of small bowel MR-enterography examinations with well visible stomachs were included in this Institutional Reviews Board approved, retrospective study. MRI (1.5-T, Siemens Sonata) was performed after standardised oral preparation (3% aqueous mannitol over 1 h). Coronal 2DtrueFISP (TR 283.8/TE 1.89/FOV400/10 mm slice) motility acquisitions covering the entire abdomen were performed in apnoea. For each patient, image analysis for assessment of gastric motility was performed both manually and using the dedicated software either the proximal (n = 5) or in the distal (n = 5) gastric corpus. The main quantitative endpoints (amplitude, frequency) describing gastric motility were compared using (paired) Student's t-Test. All motility curves qualitatively matched each other (10/10). No significant differences (P > 0.05) were found for amplitudes (mean: 18.17 mm manual; 17.78 mm software), contraction frequencies (5.1/min; 4.7/min) and mean lumen diameters (34.12 mm; 33.13 mm), respectively. Mean duration for a single measurement was significantly (P < 0.001) lower with the software (6.40 min manual technique; 1.40 min software assisted). The software proves to be feasible for fast and accurate measurement of basic gastric motility parameters providing comparable data in comparison to manual assessment methods. It might help to reduce the time needed for assessment of relevant characteristics of gastric motility.

Validity of a New Computer-Aided Diagnosis Imaging Program to Quantify Nuclear Cataract from Slit-lamp Photographs

To validate a new computer-aided diagnosis (CAD) imaging program for the assessment of nuclear lens opacity. Slit-lamp lens photographs from the Singapore Malay Eye Study (SiMES) were graded using both the CAD imaging program and manual assessment method by a trained grader using the Wisconsin Cataract Grading System. Cataract was separately assessed clinically during the study using Lens Opacities Classification System III (LOCS III). The repeatability of CAD and Wisconsin grading methods were assessed using 160 paired images. The agreement between the CAD and Wisconsin grading methods, and the correlations of CAD with Wisconsin and LOCS III were assessed using the SiMES sample (5547 eyes from 2951 subjects). In assessing the repeatability, the coefficient of variation (CoV) was 8.10% (95% confidence interval [CI], 7.21-8.99), and the intraclass correlation coefficient (ICC) was 0.96 (95% CI, 0.93-0.96) for the CAD method. There was high agreement between the CAD and Wisconsin methods, with a mean difference (CAD minus Wisconsin) of -0.02 (95% limit of agreement, -0.91 and 0.87) and an ICC of 0.81 (95% CI, 0.80-0.82). CAD parameters were also significantly correlated with LOCS III grading (all P < 0.001). This new CAD imaging program assesses nuclear lens opacity with results comparable to the manual grading using the Wisconsin System. This study shows that an automated, precise, and quantitative assessment of nuclear cataract is possible.