Automatic Quality Evaluation Research Articles

AI upscaling Supporting Image Alignment in Photogrammetric Reconstruction

Abstract. This research aims to investigate and analyze the contribution provided by preventive image processing using AI in the SfM data acquisition process. Specifically, the objective is to observe qualities and defects of "AI upscaling" integrated into the normal workflow of digital restitution, with the hypothesis that greater sharpness and resolution can lead to better alignments and better model generations. Other similar experiments have been carried out previously on the AI intervention in the photos to improve the alignments, but a generic procedure and with untrained public AI has not yet been experimented. In the first phase of the research, the most suitable AI upscaling method for the purpose is selected, processing example images and comparing them with the original and various settings of the AI parameters to maintain likeness. In the second phase, the procedure efficiency was evaluated in several ways: through the automatic evaluation of Agisoft Metashape's Image Quality, by directly comparing the resulting model with the standard digital reconstruction of the same objects, comparing with a model produced with the native AI upscaling of the return program, and finally comparing with a high-level survey without defects. This test was repeated for four case studies specifically diversified by several factors, including subject scale, level of detail, lighting, color, blur, and type of camera used. Clear improvements emerge in all cases of AI upscaling, even reaching successful reconstructions that would not have started with the canonical method. It can therefore be stated that this preventive upscaling procedure is decisive in cases of low quality or damaged datasets, while in cases of already qualitatively sufficient photos it can be a useful support for increasing the level of detail.

An automatic method for accurate signal-to-noise ratio estimation and baseline correction of Raman spectra of environmental microplastics

In this study, we introduced a k-iterative double sliding-window (DSW^k) method for the estimation of spectral noise, signal-to-noise ratio (SNR), and baseline correction. The performance was evaluated using simulated spectra and compared against other commonly employed methods. Convergent evaluation determined that a k value of 20 strikes an optimal balance between convergence and computational intensity. The DSW^k method demonstrated outstanding performance across different spectral types (flat baseline, baseline with elevation, baseline with fluctuation, baseline with elevation and fluctuation) coupled with SNR values from 10 to 1000, achieving results that ranged from 1.01 to 1.08 times of the reference value in estimating spectral noise. It also showed that the estimated SNR values are 0.89 to 0.93 times of the reference value, demonstrating a 74.5 % − 131.7 % improvement over the conventional method in spectra with elevated and/or fluctuating baselines. Additionally, the DSW^k method proved effective in correcting baselines and identifying polymers in environmental samples of polyethylene (PE), polypropylene (PP), and polystyrene (PS), despite the limitation of reducing the peak height in spectra with low SNR. This method offers the potential to enhance the automatic and accurate evaluation of spectral quality and could assist in the development of guidelines for more rapid parameter adjustments in Raman measurements.

An Image Quality Evaluation and Masking Algorithm Based On Pretrained Deep Neural Networks

With the growing amount of astronomical data, there is an increasing need for automated data processing pipelines, which can extract scientific information from observation data without human interventions. A critical aspect of these pipelines is the image quality evaluation and masking algorithm, which evaluate image qualities based on various factors such as cloud coverage, sky brightness, scattering light from the optical system, point-spread-function size and shape, and read-out noise. Occasionally, the algorithm requires masking of areas severely affected by noise. However, the algorithm often necessitates significant human interventions, reducing data processing efficiency. In this study, we present a deep-learning-based image quality evaluation algorithm that uses an autoencoder to learn features of high quality astronomical images. The trained autoencoder enables automatic evaluation of image quality and masking of noise affected areas. We have evaluated the performance of our algorithm using two test cases: images with point spread functions of varying full width half magnitude, and images with complex backgrounds. In the first scenario, our algorithm could effectively identify variations of the point spread functions, which can provide valuable reference information for photometry. In the second scenario, our method could successfully mask regions affected by complex regions, which could significantly increase the photometry accuracy. Our algorithm can be employed to automatically evaluate image quality obtained by different sky surveying projects, further increasing the speed and robustness of data processing pipelines.

Automated Quality Evaluation Index for Arterial Spin Labeling Derived Cerebral Blood Flow Maps.

Arterial spin labeling (ASL) derived cerebral blood flow (CBF) maps are prone to artifacts and noise that can degrade image quality. To develop an automated and objective quality evaluation index (QEI) for ASL CBF maps. Retrospective. Data from N = 221 adults, including patients with Alzheimer's disease (AD), Parkinson's disease, and traumatic brain injury. Pulsed or pseudocontinuous ASL acquired at 3 T using non-background suppressed 2D gradient-echo echoplanar imaging or background suppressed 3D spiral spin-echo readouts. The QEI was developed using N = 101 2D CBF maps rated as unacceptable, poor, average, or excellent by two neuroradiologists and validated by 1) leave-one-out cross validation, 2) assessing if CBF reproducibility in N = 53 cognitively normal adults correlates inversely with QEI, 3) if iterative discarding of low QEI data improves the Cohen's d effect size for CBF differences between preclinical AD (N = 27) and controls (N = 53), 4) comparing the QEI with manual ratings for N = 50 3D CBF maps, and 5) comparing the QEI with another automated quality metric. Inter-rater reliability and manual vs. automated QEI were quantified using Pearson's correlation. P < 0.05 was considered significant. The correlation between QEI and manual ratings (R = 0.83, CI: 0.76-0.88) was similar (P = 0.56) to inter-rater correlation (R = 0.81, CI: 0.73-0.87) for the 2D data. CBF reproducibility correlated negatively (R = -0.74, CI: -0.84 to -0.59) with QEI. The effect size comparing patients and controls improved (R = 0.72, CI: 0.59-0.82) as low QEI data was discarded iteratively. The correlation between QEI and manual ratings (R = 0.86, CI: 0.77-0.92) of 3D ASL was similar (P = 0.09) to inter-rater correlation (R = 0.78, CI: 0.64-0.87). The QEI correlated (R = 0.87, CI: 0.77-0.92) significantly better with manual ratings than did an existing approach (R = 0.54, CI: 0.30-0.72). Automated QEI performed similarly to manual ratings and can provide scalable ASL quality control. 2 TECHNICAL EFFICACY: Stage 1.

Automatic image quality evaluation in digital radiography using for-processing and for-presentation images.

To investigate the impact of digital image post-processing algorithms on various image quality (IQ) metrics of radiographic images under different exposure conditions. A custom-made phantom constructed according to the instructions given in the IAEA Human Health Series No.39 publication was used, along with the respective software that automatically calculates various IQ metrics. Images with various exposure parameters were acquired with a digital radiography unit, which for each acquisition produces two images: one for-processing (raw) and one for-presentation (clinical). Various examination protocols were used, which incorporate diverse post-processing algorithms. The IQ metrics' values (IQ-scores) obtained were analyzed to investigate the effects of increasing incident air kerma (IAK) on the image receptor, tube potential (kVp), additional filtration, and examination protocol on image quality, and the differences between image type (raw or clinical). The IQ-scores were consistent for repeated identical exposures for both raw and clinical images. The effect that changes in exposure parameters and examination protocol had on IQ-scores were different depending on the IQ metric and image type. The expected positive effect that increasing IAK and decreasing tube potential should have on IQ was clearly exhibited in two IQ metrics only, the signal difference-to-noise-ratio (SDNR) and the detectability index (d'), for both image types. No effect of additional filtration on any of the IQ metrics was detected on images of either type. An interesting finding of the study was that for all different image acquisition selections the d' scores were larger in raw images, whereas the other IQ metrics were larger in clinical images for most of the cases. Since IQ-scores of raw and their respective clinical images may be largely different, the same type of image should be consistently used for monitoring IQ constancy and when results from different X-ray systems are compared.

Toward a Model to Evaluate Machine-Processing Quality in Scientific Documentation and Its Impact on Information Retrieval

The lack of quality in scientific documents affects how documents can be retrieved depending on a user query. Existing search tools for scientific documentation usually retrieve a vast number of documents, of which only a small fraction proves relevant to the user’s query. However, these documents do not always appear at the top of the retrieval process output. This is mainly due to the substantial volume of continuously generated information, which complicates the search and access not properly considering all metadata and content. Regarding document content, the way in which the author structures it and the way the user formulates the query can lead to linguistic differences, potentially resulting in issues of ambiguity between the vocabulary employed by authors and users. In this context, our research aims to address the challenge of evaluating the machine-processing quality of scientific documentation and measure its influence on the processes of indexing and information retrieval. To achieve this objective, we propose a set of indicators and metrics for the construction of the evaluation model. This set of quality indicators have been grouped into three main areas based on the principles of Open Science: accessibility, content, and reproducibility. In this sense, quality is defined as the value that determines whether a document meets the requirements to be retrieved successfully. To prioritize the different indicators, a hierarchical analysis process (AHP) has been carried out with the participation of three referees, obtaining as a result a set of nine weighted indicators. Furthermore, a method to implement the quality model has been designed to support the automatic evaluation of quality and perform the indexing and retrieval process. The impact of quality in the retrieval process has been validated through a case study comprising 120 scientific documents from the field of the computer science discipline and 25 queries, obtaining as a result 21% high, 39% low, and 40% moderate quality.

Automatic detection and pixel-level quantification of surface microcracks in ceramics grinding: An exploration with Mask R-CNN and TransUNet

Microcrack damage on the grinding surfaces of engineering ceramics is inevitably incurred. To accurately evaluate the microcrack damage, an automatic detection and pixel-level quantification model based on the joint Mask R-CNN and TransUNet is developed. In addition, a joint training strategy is employed and the model is trained effectively on the image dataset of microcrack damage derived from the Si3N4 grinding, as captured by SEM. The Mask R-CNN demonstrates reliable automatic detection of microcracks, achieving an Average Precision of AP50 = 0.989 and AP75 = 0.864. Meanwhile, the TransUNet achieves fine segmentation of microcracks with complex characteristics, with an F1 score of 0.914 and an IoU value of 0.785. A skeleton-based quantification model of microcrack size is proposed, which delivers comprehensive and precise measurements of area, length, and notably, the width. The proposed quantification model provides a technical reference for the automatic evaluation of grinding surface quality.

Automated quality evaluation for laser cutting in lithium metal battery production using an instance segmentation convolutional neural network

Separating lithium metal foil into individual anodes is a critical process step in all-solid-state battery production. With the use of nanosecond-pulsed laser cutting, a characteristic quality-decisive cut edge geometry is formed depending on the chosen parameter set. This cut edge can be characterized by micrometer-scale imaging techniques such as confocal laser scanning microscopy. Currently, experimental determination of suitable process parameters is time-consuming and biased by the human measurement approach, while no methods for automated quality assurance are known. This study presents a deep-learning computer vision approach for geometry characterization of lithium foil laser cut edges. The convolutional neural network architecture Mask R-CNN was implemented and applied for categorizing confocal laser scanning microscopy images showing defective and successful cuts, achieving a classification precision of more than 95%. The algorithm was trained for automatic pixel-wise segmentation of the quality-relevant melt superelevation along the cut edge, reaching segmentation accuracies of up to 88%. Influence of the training data set size on the classification and segmentation accuracies was assessed confirming the algorithm’s industrial application potential due to the low number of 246 or fewer original images required. The segmentation masks were combined with topography data of cut edges to obtain quantitative metrics for the quality evaluation of lithium metal electrodes. The presented computer vision pipeline enables the integration of an automated image evaluation for quality inspection of lithium foil laser cutting, promoting industrial production of all-solid-state batteries with lithium metal anode.

Low-dose CT image quality evaluation method based on radiomics and deep residual network with attention mechanism

Low-dose computed tomography (CT) produces less radiation but may degrade image quality. Research on automatic evaluation and classification of low-dose CT image quality is necessary, which is helpful to clinicians. A low-dose CT image quality evaluation method is proposed based on radiomics and deep learning. After pre-training on the ImageNet dataset, the trained deep learning model is then transferred to the target dataset of low-dose CT image. Region of interest is obtained through a deep residual network with attention mechanism. Pyradiomics is used to extract radiomics features of ROI, and T-test and LASSO algorithm are used for feature screening. Finally, support vector machine, random forest and logistic regression models are adopted to classify and predict the quality of low-dose CT image based on the selected radiomics features. Experimental results show that the trained deep residual network model with attention module can achieve 92% recognition accuracy of region of interest, and the evaluation accuracy of the three machine learning models achieve 86.6% (support vector machine), 84.5% (random forest) and 61.7% (logistic regression), respectively. Transfer learning can effectively reduce the required number of samples for the training of deep learning model and avoid overfitting. After the introduction of attention module in deep residual network model, accuracy rises faster, and the final accuracy is slightly higher than that of deep residual network model without attention module, but the improvement is slightly lower than expected. Radiomics features of region of interest reflect the quality differences of low-dose CT images which can be employed for the quality evaluation of low-dose CT image.

An AI-based algorithm for the automatic evaluation of image quality in canine thoracic radiographs

The aim of this study was to develop and test an artificial intelligence (AI)-based algorithm for detecting common technical errors in canine thoracic radiography. The algorithm was trained using a database of thoracic radiographs from three veterinary clinics in Italy, which were evaluated for image quality by three experienced veterinary diagnostic imagers. The algorithm was designed to classify the images as correct or having one or more of the following errors: rotation, underexposure, overexposure, incorrect limb positioning, incorrect neck positioning, blurriness, cut-off, or the presence of foreign objects, or medical devices. The algorithm was able to correctly identify errors in thoracic radiographs with an overall accuracy of 81.5% in latero-lateral and 75.7% in sagittal images. The most accurately identified errors were limb mispositioning and underexposure both in latero-lateral and sagittal images. The accuracy of the developed model in the classification of technically correct radiographs was fair in latero-lateral and good in sagittal images. The authors conclude that their AI-based algorithm is a promising tool for improving the accuracy of radiographic interpretation by identifying technical errors in canine thoracic radiographs.

A Very Large Cardiac Channel Data Database (VLCD) Used to Evaluate Global Image Coherence (GIC) as an In Vivo Image Quality Metric.

Ultrasound image quality is of utmost importance for a clinician to reach a correct diagnosis. Conventionally, image quality is evaluated using metrics to determine the contrast and resolution. These metrics require localization of specific regions and targets in the image such as a region of interest (ROI), a background region, and/or a point scatterer. Such objects can all be difficult to identify in in-vivo images, especially for automatic evaluation of image quality in large amounts of data. Using a matrix array probe, we have recorded a Very Large cardiac Channel data Database (VLCD) to evaluate coherence as an in vivo image quality metric. The VLCD consists of 33280 individual image frames from 538 recordings of 106 patients. We also introduce a global image coherence (GIC), an in vivo image quality metric that does not require any identified ROI since it is defined as an average coherence value calculated from all the data pixels used to form the image, below a preselected range. The GIC is shown to be a quantitative metric for in vivo image quality when applied to the VLCD. We demonstrate, on a subset of the dataset, that the GIC correlates well with the conventional metrics contrast ratio (CR) and the generalized contrast-to-noise ratio (gCNR) with R = 0.74 ( ) and R = 0.62 ( ), respectively. There exist multiple methods to estimate the coherence of the received signal across the ultrasound array. We further show that all coherence measures investigated in this study are highly correlated ( 0.9 and ) when applied to the VLCD. Thus, even though there are differences in the implementation of coherence measures, all quantify the similarity of the signal across the array and can be averaged into a GIC to evaluate image quality automatically and quantitatively.

Clinical Usability-Oriented Automatic Contour Quality Evaluation for Deep Learning Auto-Segmentation

Various auto-segmentations, including deep learning auto-segmentation (DLAS), are being increasingly adopted in radiotherapy. A common method to evaluate quality of auto-segmented contours uses thresholds of various quantitative metrics (e.g., dice similarity coefficient (DSC), mean distance to agreement (MDA), etc.) that are often averaged over all contour slices. This method fails to detect contour errors on individual slices, thus, does not reflect the current clinical practice (slice-by-slice evaluation) and the clinical usability (e.g., expected contour editing time). In addition, the use of multi-metrics is generally not easy to interpret. This work aims to develop a novel contour quality classification (CQC) model to evaluate auto-segmented contours based on their clinical applicability. The CQC method was designed to classify a contour on a slice into acceptable, minor edit or major edit category, based on the expected editing effort/time. Organ-specific supervised ensemble tree classification models were trained to relate the slice-based quality category with the combination of seven commonly used calculatable quantitative metrics (i.e., DSC, MDA, Hausdorff 95% distance, surface DSC, added path length (APL), slice area and relative APL). The proposed method was demonstrated by training CQC models using DLAS contours of five abdominal organs (i.e., pancreas, duodenum, stomach, and small and large bowels) from 50 MRI sets and evaluating on 20 MRI and 9 CT testing sets. These test datasets were labelled by six individual observers and the consensus labels were generated through majority vote method. The model performance was evaluated using accuracy (acc), and risk rate (RR, the percentage of unacceptable slices mislabeled as acceptable) and compared with inter-observer variation and baseline threshold-based method. Compared to the majority vote labels, the obtained CQC models achieved a mean accuracy of 95.8% ([94.5%-99.1%]) and 94.3% ([90.6%-96.9%]), and the mean RR of 0.8% ([0.3%-1.3%]) and 0.7% ([0%-1.1%]) for the MRI and CT testing sets, respectively. The CQC performance was comparable to the inter-observer variation and significantly higher than those from the threshold-based method with single or multiple metrics. The execution time on a typical abdominal dataset (e.g., 70 slices) took less than 3 seconds. Table 1 CQC models performance for different organs CONCLUSION: The proposed CQC model can classify the quality of a contour slice with high accuracy. This slice-based single-output evaluation method better reflects the current clinical practice and may be used to evaluate/compare performance of DLAS on any image modality, facilitating its clinical implementation and quality assurance.

A similarity calculation model of road network and its application in map generalization quality evaluation

ABSTRACT As an important part of maps, road networks have always been the focus of research in map generalization. However, the fully automated quality evaluation of road network generalization has not been implemented. This paper proposes a framework of Sample-Map database to evaluate road network generalization quality using spatial similarity measures. The similarity calculation model considers spatial distribution, topological relations, and distance relations of road networks. A Sample-Maps database is created as an evaluation set for different road network types. The method is tested on multi-scale maps from Shenzhen, China, and validated by psychological cognition experiments and professional cartographers’ judgment.

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images.

The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle. Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset. The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices. Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.

An automatic quality evaluation procedure for third-party daily rainfall observations and its application over Australia

Third-party rainfall observations could provide an improvement of the current official observation network for rainfall monitoring. Although third-party weather stations can provide large quantities of near-real-time rainfall observations at fine temporal and spatial resolutions, the quality of these data is susceptible due to variations in quality control applied and there is a need to provide greater confidence in them. In this study, we develop an automatic quality evaluation procedure for daily rainfall observations collected from third-party stations in near real time. Australian Gridded Climate Data (AGCD) and radar Rainfields data have been identified as two reliable data sources that can be used for assessing third-party observations in Australia. To achieve better model interpretability and scalability, these reference data sources are used to provide separate tests rather than a complex single test on a third-party data point. Based on the assumption that the error of a data source follows a Gaussian distribution after a log-sinh transformation, each test issues a p-value-based confidence score as a measure of quality and the confidence of the third-party data observation. The maximum of confidence scores from individual tests is used to merge these tests into a single result which provides overall assessment. We validate our method with synthetic datasets based on high-quality rainfall observations from 100 Bureau of Meteorology (BoM) of Australia stations across Australia and apply it to evaluate real third-party rainfall observations owned by the Department of Primary Industries and regional development (DPIRD) of Western Australia. Our method works well with the synthetic datasets and can detect 76.7% erroneous data while keeping the false alarm rate as low as 1.7%. We also discuss the possibility of using other reference datasets, such as numerical weather prediction data and satellite rainfall data.

MiniatureVQNet: A Light-Weight Deep Neural Network for Non-Intrusive Evaluation of VoIP Speech Quality

In IP audio systems, audio quality is degraded by environmental noise, poor network quality, and encoding–decoding algorithms. Therefore, there is a need for a continuous automatic quality evaluation of the transmitted audio. Speech quality monitoring in VoIP systems enables autonomous system adaptation. Furthermore, there are diverse IP audio transmitters and receivers, from high-performance computers and mobile phones to low-memory and low-computing-capacity embedded systems. This paper proposes MiniatureVQNet, a single-ended speech quality evaluation method for VoIP audio applications based on a lightweight deep neural network (DNN) model. The proposed model can predict the audio quality independent of the source of degradation, whether noise or network, and is light enough to run in embedded systems. Two variations of the proposed MiniatureVQNet model were evaluated: a MiniatureVQNet model trained on a dataset that contains environmental noise only, referred to as MiniatureVQNet–Noise, and a second model trained on both noise and network distortions, referred to as MiniatureVQNet–Noise–Network. The proposed MiniatureVQNet model outperforms the traditional P.563 method in terms of accuracy on all tested network conditions and environmental noise parameters. The mean squared error (MSE) of the models compared to the PESQ score for ITU-T P.563, MiniatureVQNet-Noise, and MiniatureVQNet–Noise–Network was 2.19, 0.34, and 0.21, respectively. The performance of both the MiniatureVQNet–Noise–Network and MiniatureVQNet-Noise model depends on the noise type for an SNR greater than 0 dB and less than 10 dB. In addition, training on a noise–network-distorted speech dataset improves the model prediction accuracy in all VoIP environment distortions compared to training the model on a noise-only dataset.

Evaluating Airfoil Mesh Quality with Transformer

Mesh quality is a major factor affecting the structure of computational fluid dynamics (CFD) calculations. Traditional mesh quality evaluation is based on the geometric factors of the mesh cells and does not effectively take into account the defects caused by the integrity of the mesh. Ensuring the generated meshes are of sufficient quality for numerical simulation requires considerable intervention by CFD professionals. In this paper, a Transformer-based network for automatic mesh quality evaluation (Gridformer), which translates the mesh quality evaluation into an image classification problem, is proposed. By comparing different mesh features, we selected the three features that highly influence mesh quality, providing reliability and interpretability for feature extraction work. To validate the effectiveness of Gridformer, we conduct experiments on the NACA-Market dataset. The experimental results demonstrate that Gridformer can automatically identify mesh integrity quality defects and has advantages in computational efficiency and prediction accuracy compared to widely used neural networks. Furthermore, a complete workflow for automatic generation of high-quality meshes based on Gridformer was established to facilitate automated mesh generation. This workflow can produce a high-quality mesh with a low-quality mesh input through automatic evaluation and optimization cycles. The preliminary implementation of automated mesh generation proves the versatility of Gridformer.

Tunicate swarm-based grey wolf algorithm for fetal heart chamber segmentation and classification: a heuristic-based optimal feature selection concept

Ultrasound image quality management and assessment are an important stage in clinical diagnosis. This operation is often carried out manually, which has several issues, including reliance on the operator’s experience, lengthy labor, and considerable intra-observer variance. As a result, automatic quality evaluation of Ultrasound images is particularly desirable in medical applications. This research work plans to perform the fetal heart chamber segmentation and classification using the novel intelligent technology named as hybrid optimization algorithm Tunicate Swarm-based Grey Wolf Algorithm (TS-GWA). Initially, the US fetal images data is collected and data undergoes the preprocessing using the total variation technique. From the preprocessed images, the optimal features are extracted using the TF-IDF approach. Then, Segmentation is processed on optimally selected features using Spatially Regularized Discriminative Correlation Filters (SRDCF) method. In the final step, the classification of fetal images is done using the Modified Long Short-Term Memory (MLSTM) Network. The fitness function behind the optimal feature selection as well as the hidden neuron optimization of MLSTM is the maximization of PSNR and minimization of MSE. The PSNR value is improved from 3.1 to 9.8 in the proposed method and accuracy of the proposed classification algorithm is improved from 1.9 to 12.13 compared to other existing techniques. The generalization ability and the adaptability of proposed TS-GWA method are described by conducting the various performance analysis. Extensive performance result shows that proposed intelligent techniques performs better than the existing segmentation methods.

A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of "good", "borderline", or "poor" quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance "good" quality photographs (AUC = 0.93 (95% CI, 0.91-0.95), accuracy = 91.4% (95% CI, 90.0-92.9%), sensitivity = 93.8% (95% CI, 92.5-95.2%), specificity = 75.9% (95% CI, 69.7-82.1%) and "poor" quality photographs (AUC = 1.00 (95% CI, 0.99-1.00), accuracy = 99.1% (95% CI, 98.6-99.6%), sensitivity = 81.5% (95% CI, 70.6-93.8%), specificity = 99.7% (95% CI, 99.6-100.0%). "Borderline" quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88-0.93), accuracy = 90.6% (95% CI, 89.1-92.2%), sensitivity = 65.4% (95% CI, 56.6-72.9%), specificity = 93.4% (95% CI, 92.1-94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1-92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH.

OUTLINE OF A DIDACTIC FRAMEWORK FOR COMBINED DATA LITERACY AND MACHINE TRANSLATION LITERACY TEACHING

This paper outlines a didactic framework for combined data literacy and machine translation (MT) literacy teaching for translation and specialised communication students. The framework is being developed in the context of the DataLitMT project, a publicly funded project at the Institute of Translation and Multilingual Communication at TH Köln – University of Applied Sciences, Germany, which develops didactic resources for teaching data literacy in its translation-specific form of MT literacy to students of BA and MA programmes in translation and specialised communication studies. After discussing the high relevance of machine trans-lation literacy and data literacy in professional translation contexts, the paper introduces the DataLitMT project and discusses a framework of professional MT literacy and an MT-oriented data literacy framework, which form the two theoretical pillars of the project. Also, the interface between MT literacy and data literacy will be illustrated by showing how specific (sub)dimensions of data literacy can be mapped to relevant (sub)dimensions of professional MT literacy. Finally, the paper presents some preliminary didactic resources of the DataLitMT project – concerned with social biases in MT, with MT training data preparation and with automatic MT quality evaluation – and discusses how these resources can be used to teach specific (sub)dimensions of data literacy and professional MT literacy to students in the fields of translation/specialised communication studies. Keywords: data literacy, professional machine translation literacy, neural machine translation, translation didactics, DataLitMT