Segmented Images Research Articles

DAH-Unet: A modified UNet for Semantic Segmentation of MRI images for brain tumour detection

Using sophisticated image processing techniques on brain MR images for medical image segmentation significantly improves the ability to detect tumors. It takes a lot of time and requires a doctor's training and experience to manually segment a brain tumor. To address this issue, we proposed a modification in Unet architecture called DAH-Unet that combines residual blocks, a rebuilt atrous spatial pyramid pooling (ASPP), and depth-wise convolutions. Also, a hybrid loss function which is explicitly aware of the boundaries is another thing we suggested. Experiments were conducted on two publicly available dataset and proved better in some metrics as compare to existing semantic segmentation models.

Semantic Segmentation Based on Geometric Calibration Using AI and AR in Health Care

In the medical field, medical imaging is essential for precise diagnosis, treatment planning, and condition monitoring. The goal of this work is to improve the field of healthcare imaging by investigating the complementary applications of augmented reality (AR) and artificial intelligence (AI) in semantic segmentation. More precise identification and delineation of anatomical structures and abnormalities in medical images is made possible by AI-driven semantic segmentation, opening the door to more precise diagnosis and treatment plans. Modern AI algorithms are employed in the suggested methodology to perform semantic segmentation in a variety of medical imaging modalities, including ultrasound, CT, and MRI scans. The detection of anomalies such as tumours, irregularities in organs, and neurological disorders is made easier by these algorithms. The foundation for integrating augmented reality technologies into the healthcare ecosystem is provided by the segmented medical images. AR enhances the interaction and visualization of segmented medical data in the context of healthcare. Real-time augmented reality overlays help surgeons by improving surgical navigation and precision. Additionally, AR apps help with medical education by offering professionals and students alike an immersive learning environment. AR provides interactive visualizations to help patients understand their medical conditions when they are going for therapy and rehabilitation. The difficulties in integrating these technologies in the healthcare industry are discussed in this paper, with a focus on the significance of data privacy, regulatory compliance, and easy integration with current healthcare systems. The successful deployment of AI technologies necessitates interdisciplinary collaboration among AI developers, healthcare professionals, and AR specialists to ensure compliance with ethical, legal, and clinical standards mandated in the healthcare domain. The proposed Segmentation mask is redefined with geometric calibration and used with U-Net for image segmentation. The segmentation is experimented on Cityscapes and PASCAL VOC 2012 datasets. The experimental results show that proposed semantic segmentation based on geometric calibration yields more accuracy than its counterparts.

A method for measuring hairline length and discriminating hairline recession grades based on the BiSeNet model

Abstract Hair plays an important role in a person’s appearance. According to a survey by the World Health Organization, approximately 70% of adults have scalp and hair problems. Doctors currently make hairline recession diagnoses based on hair loss criteria, but this approach is subjective. This paper proposes a novel method for objectively assessing hairline recession grades. First, the Bilateral Segmentation Network model is utilized to obtain a facial segmentation image. Second, this paper utilizes the connected components method to improve the facial segmentation results. Next, the labeling key points method is used to extract part of the features of the eyebrow and facial region and calculate the related values. Finally, the judgment of hairline length and hairline recession grade is realized by combining these features with camera calibration. In this paper, front-face images of 50 volunteers were collected for hairline recession grade determination. The judgment results of expert doctors on hairline length and hairline recession grade were compared with the judgment results of this method. The results showed a 1.3 cm difference in the average length of the hairline and about 80% similarity in hairline recession grade judgments. In conclusion, using machine vision methods to measure the height of the hairline provides objective and repeatable results.

Automatic screening of retinal lesions for detecting diabetic retinopathy using adaptive multiscale MobileNet with abnormality segmentation from public dataset

ABSTRACT Owing to the epidemic growth of diabetes, ophthalmologists need to examine the huge fundus images for diagnosing the disease of Diabetic Retinopathy (DR). Without proper knowledge, people are too lethargic to detect the DR. Therefore, the early diagnosis system is requisite for treating ailments in the medical industry. Therefore, a novel deep model-based DR detection structure is recommended to fix the aforementioned difficulties. The developed deep model-based diabetic retinopathy detection process is performed adaptively. The DR detection process is imitated by garnering the images from benchmark sources. The gathered images are further preceded by the abnormality segmentation phase. Here, the Residual TransUNet with Enhanced loss function is used to employ the abnormality segmentation, and the loss function in this structure may be helpful to lessen the error in the segmentation procedure. Further, the segmented images are passed to the final phase of retinopathy detection. At this phase, the detection is carried out through the Adaptive Multiscale MobileNet. The variables in the AMMNet are optimized by the Adaptive Puzzle Optimization to obtain better detection performance. Finally, the effectiveness of the offered approach is confirmed by the experimentation procedure over various performance indices.

Medical Image, Analysis and Visualization using Image Processing

This project presents an automated approach for detecting brain tumor using Magnetic Resonance Imaging (MRI) and image processing techniques. Traditional methods rely on human inspection, which can be error-prone and time consuming. Our framework consists of several modules: acquiring MRI images, preprocessing to enhance image quality (including noise reduction and edge detection), and segmenting the tumor using the Watershed algorithm. We extract texture features from the segmented images using the Gray Level Co-occurrence Matrix (GLCM), focusing on metrics like energy, contrast, correlation, and homogeneity. Finally, we classify the MRI images as normal or abnormal using a Multilayer Perceptron (MLP) model. This automated detection process improves the efficiency of tumor identification, providing insights into the size, shape, and position of the tumor while alleviating the workload of radiologists.

Stereo slit-scanning tomography of the anterior segment of the human eye

We demonstrate a new tomographic imaging device for 2D cross-sectional and 3D volumetric images of the anterior eye segment. The optical system combines optical sectioning with a stereoscopic camera setup to determine the true spatial location of the ocular structures. Moreover, we propose a calibration procedure to estimate the triangulation function that links the stereo camera pixel indices with the eye-referenced 3D spatial coordinates. The proposed instrument will image the entire anterior chamber and contiguous structures, including the corneal limbus, sclera and eyelids. Furthermore, the system can obtain corneal topography. Finally, we studied the repeatability of the instrument and its agreement with a commercial Scheimpflug imaging tomographer in a group of healthy subjects.

Segmentation uncertainty of vegetated porous media propagates during X-ray CT image-based analysis

Abstract Background and Aims Phase segmentation is a crucial step in X-ray computed tomography (CT) for image-based analysis (CT-IBA) to derive soil and root information. How segmentation uncertainty (SU) affects CT-IBA of vegetated soil has never been explored. Methods We proposed a new framework enabled by machine learning to measure SU and its propagation from the first to the second-order parameters derived from CT-IBA. Vegetated glass beads of varying moisture contents and plant species were CT scanned. Segmented images were used to determine volumetric fractions and morphological properties of each phase for determining the absolute permeability (K). Results Although the root phase is susceptible to SU, its influence on CT-IBA is minimal when the root content is low. However, its SU was magnified when the water phase is present. The grain phase has a lower SU susceptibility, but due to its large volumetric content, the IBA can be affected significantly. Fine roots were found to exhibit higher SU than coarse roots, indicating that root architecture has an effect on the segmentation of the root phase, and thus higher-order properties like K. Conclusion Segmentation of the grain phase is sensitive to SU. A small SU will lead to a remarkably erroneous estimation of pore morphological properties and K. To reduce SU, we suggest reducing the water content to a discontinuous state of a cohesionless vegetated porous media specimen before sending it for CT scanning and IBA. However, caution should be taken when fine roots were dried and experienced excessive shrinkage.

UCapsNet: A Two-Stage Deep Learning Model Using U-Net and Capsule Network for Breast Cancer Segmentation and Classification in Ultrasound Imaging.

Background/Objectives: Breast cancer remains one of the biggest health challenges for women worldwide, and early detection can be truly lifesaving. Although ultrasound imaging is commonly used to detect tumors, the images are not always of sufficient quality, and, thus, traditional U-Net models often miss the finer details needed for accurate detection. This outcome can result in lower accuracy, making early and precise diagnosis more difficult. Methods: This study presents an enhanced U-Net model integrated with a Capsule Network (called UCapsNet) to overcome the limitations of conventional techniques. Our approach improves segmentation by leveraging higher filter counts and skip connections, while the capsule network enhances classification by preserving spatial hierarchies through dynamic routing. The proposed UCapsNet model operates in two stages: first, it segments tumor regions using an enhanced U-Net, followed by a classification of the segmented images with the capsule network. Results: We have tested our model against well-known pre-trained models, including VGG-19, DenseNet, MobileNet, ResNet-50, and Xception. By properly addressing the limitations found in previous studies and using a capsule network trained on the Breast Ultrasound Image (BUSI) dataset, our model resulted in top-achieving impressive precision, recall, and accuracy rates of 98.12%, 99.52%, and 99.22%, respectively. Conclusions: By combining the U-Net's powerful segmentation capabilities with the capsule network's high classification accuracy, UCapsNet boosts diagnostic precision and addresses key weaknesses in existing methods. The findings demonstrate that the proposed model is not only more effective in detecting tumors but also more reliable for practical applications in clinical settings.

A Computer Aided System for Reservoir Rock Classification

This study is mainly aimed to know the reservoir rocks among core specimens that are obtained during the stage of drilling of exploration oil and gas wells by the processing of the image digitally using a Computer-Aided System. This computerized method has been conducted using two programming languages; Python and Matlab. The Python program is used to segment rock images and classify the extracted features, whereas the MATLAB language has been used to extract intensity features from segmented images. The database used in this project has been collected from two sources, one of them from the Sarier formation (the biggest Libyan oil field) while the second source was from the internet. The images used in this study are sedimentary rocks images, which include sandstone, limestone, and dolomite. As a result, this study has reached that the system, which was used here is capable of classifying rocks and can be used to classify oil rocks or any other type of rocks. Also, it can be used near the well due to certain conditions such as the absence of experts due to the lack of enough database, the study has only introduced the preliminary results as proof of the concept.

Gastrointestinal tract disease detection via deep learning based structural and statistical features optimized hexa-classification model.

Gastrointestinal tract (GIT) diseases impact the entire digestive system, spanning from the mouth to the anus. Wireless Capsule Endoscopy (WCE) stands out as an effective analytic instrument for Gastrointestinal tract diseases. Nevertheless, accurately identifying various lesion features, such as irregular sizes, shapes, colors, and textures, remains challenging in this field. Several computer vision algorithms have been introduced to tackle these challenges, but many relied on handcrafted features, resulting in inaccuracies in various instances. In this work, a novel Deep SS-Hexa model is proposed which is a combination two different deep learning structures for extracting two different features from the WCE images to detect various GIT ailment. The gathered images are denoised by weighted median filter to remove the noisy distortions and augment the images for enhancing the training data. The structural and statistical (SS) feature extraction process is sectioned into two phases for the analysis of distinct regions of gastrointestinal. In the first stage, statistical features of the image are retrieved using MobileNet with the support of SiLU activation function to retrieve the relevant features. In the second phase, the segmented intestine images are transformed into structural features to learn the local information. These SS features are parallelly fused for selecting the best relevant features with walrus optimization algorithm. Finally, Deep belief network (DBN) is used classified the GIT diseases into hexa classes namely normal, ulcer, pylorus, cecum, esophagitis and polyps on the basis of the selected features. The proposed Deep SS-Hexa model attains an overall average accuracy of 99.16% in GIT disease detection based on KVASIR and KID datasets. The proposed Deep SS-Hexa model achieves high level of accuracy with minimal computational cost in the recognition of GIT illness. The proposed Deep SS-Hexa Model progresses the overall accuracy range of 0.04%, 0.80% better than GastroVision, Genetic algorithm based on KVASIR dataset and 0.60%, 1.21% better than Modified U-Net, WCENet based on KID dataset respectively.

Intelligent rehabilitation assistant: Application of deep learning methods in sports injury recovery

In recent years, sports injury rehabilitation has developed into a specialized field that has forced the combination of an orthopedic surgeon, sports physiotherapist, and sports physician. Determining the appropriate time for an injured athlete to resume practice or competition is regarded as sports rehabilitation. Discovering the best solutions to avoid injuries, maximize recovery, and enhance performance is crucial for sports activities. The study introduced an intelligent rehabilitation assistant (IRA) that leverages advanced deep learning (DL) methods to enhance sports injury recovery. In this study, the IRA incorporates redefined prairie dog optimized bidirectional long-short-term memory (RPDO-Bi-LSTM) to enhance accuracy, predicting sports injury recovery. The study collected data on the state of rehabilitation, physiological parameters, and general health using wearable sensors and movement patterns. The data was preprocessed using a median filter to remove noise from sensor data. Region-based segmentation using segmented images from preprocessed data. Convolutional neural networks (CNN) using extracted features from obtained data. The IRA provides personalized recovery plans and real-time feedback. The framework consists of the components, suggested models to create quality scores for motions, measurements to quantify motion performance, and scoring of performance measurement elements into numerical quality scores. The proposed method is implemented using Python software. RPDO-Bi-LSTM presentation is evaluated by various metrics, such as accuracy 94.2% recall 98.2%, precision 96.5%, and specificity 95.2%, f1 score 95.6%, he planned technique attained good performance and improved the accuracy of sports injury recovery.

OrganoLabeler: A Quick and Accurate Annotation Tool for Organoid Images.

Organoids are self-assembled 3D cellular structures that resemble organs structurally and functionally, providing in vitro platforms for molecular and therapeutic studies. Generation of organoids from human cells often requires long and costly procedures with arguably low efficiency. Prediction and selection of cellular aggregates that result in healthy and functional organoids can be achieved by using artificial intelligence-based tools. Transforming images of 3D cellular constructs into digitally processable data sets for training deep learning models requires labeling of morphological boundaries, which often is performed manually. Here, we report an application named OrganoLabeler, which can create large image-based data sets in a consistent, reliable, fast, and user-friendly manner. OrganoLabeler can create segmented versions of images with combinations of contrast adjusting, K-means clustering, CLAHE, binary, and Otsu thresholding methods. We created embryoid body and brain organoid data sets, of which segmented images were manually created by human researchers and compared with OrganoLabeler. Validation is performed by training U-Net models, which are deep learning models specialized in image segmentation. U-Net models, which are trained with images segmented by OrganoLabeler, achieved similar or better segmentation accuracies than the ones trained with manually labeled reference images. OrganoLabeler can replace manual labeling, providing faster and more accurate results for organoid research free of charge.

Automated pericardium segmentation and epicardial adipose tissue quantification from computed tomography images

Background and ObjectiveEpicardial Adipose Tissue (EAT) is regarded as an independent risk factor for cardiovascular disease, and an increase in its volume is closely associated with disorders such as coronary artery atherosclerosis. Traditional manual and semi-automatic methods for EAT segmentation rely on subjective judgment, resulting in uncertainty and unreliability, which limits their application in clinical practice. Therefore, this study aims to develop a fully automatic segmentation and quantification method to improve the accuracy of EAT assessment. MethodsA Boundary-Enhanced Multi-scale U-Net network with a Convolutional Transformer (BMT-UNet) is developed to segment the pericardium. The BMT-UNet comprises Boundary-Enhanced (BE) modules, Multi-Scale (MS) modules, and a Convolutional Transformer (ConvT) module. The MS and BE modules in the encoding part are designed to capture detailed boundary features and accurately delineate the pericardium boundary by combining multi-scale features with morphological operations, leveraging their complementarity. The ConvT module integrates global contextual information, thereby enhancing overall segmentation accuracy and addressing the issue of internal holes in the segmented pericardial images. The volume of EAT is automatically quantified using standard fat thresholds with a range of −190 to −30 HU. ResultsFor a Coronary Computed Tomography Angiography (CCTA) dataset which contained 50 patients, the Dice coefficient and Hausdorff distance for the proposed method of pericardial and EAT segmentation are 98.3% ± 0.2%, 5.7±0.8 mm, and 93.9% ± 1.7%, 2.1 ± 0.3 mm, respectively. The linear regression coefficient between the EAT volume segmented and the actual volume is 0.982, and the Pearson correlation coefficient is 0.99. Bland-Altman analysis further confirmed the high consistency between the automated and manual methods. These results demonstrate a significant improvement over existing methods, particularly in terms of segmentation precision and reliability, which are critical for clinical application. ConclusionsThis work develops an automated method for quantifying EAT in Computed Tomography (CT) images, and the results agreed closely with expert evaluations. Code is available at: https://github.com/wy-9903/BMT-UNet.

Cattle identification based on multiple feature decision layer fusion

In farming scenarios, cattle identification has become a key issue for the development of precision farming. In precision livestock farming, single-feature recognition methods are prone to misjudgment in complex scenarios involving multiple cattle obscuring each other during drinking and feeding. This paper proposes a decision-level identification method based on the multi-feature fusion of cattle faces, muzzle patterns, and ear tags. The method utilizes the SOLO algorithm to segment images and employs the FaceNet and PP-OCRv4 networks to extract features for the cattle’s faces, muzzle patterns, and ear tags. These features are compared with the Ground truth, from which the Top 3 features are extracted. The corresponding cattle IDs of these features are then processed using One-Hot encoding to serve as the final input for the decision layer, and various ensemble strategies are used to optimize the model. The results show that using the multimodal decision fusion method makes the recognition accuracy reach 95.74%, 1.4% higher than the traditional optimal unimodal recognition accuracy. The verification rate reaches 94.72%, 10.65% higher than the traditional optimal unimodal recognition verification rate. The research results demonstrate that the multi-feature fusion recognition method has significant advantages in drinking and feeding farm environments, providing an efficient and reliable solution for precise identification and management of cattle in farms and significantly improving recognition accuracy and stability.

Tumor growth and vascular redistribution contributes to the dosimetric preferential effect of microbeam radiotherapy: a Monte Carlo study

The radiobiological mechanisms behind the favorable response of tissues to microbeam radiation therapy (MRT) are not fully described yet. Among other factors, the differential action to tumor and normal tissue vasculature is considered to contribute to MRT efficacy. This computational study evaluates the relevance of tumor growth stage and associated vascular redistribution to this effect. A multiscale approach was employed with two simulation softwares: TOPAS and CompuCell3D. Segmentation images of the angioarchitecture of a non-bearing tumor mouse brain were used. The tumor vasculature at different tumor growth stages was obtained by simulating the tumor proliferation and spatial vascular redistribution. The radiation-induced damage to vascular cells and consequent change in oxygen perfusion were simulated for normal and tumor tissues. The multiscale model showed that oxygen perfusion to tissues and vessels decreased as a function of the tumor proliferation stage, and with the decrease in uniformity of the vasculature spatial distribution in the tumor tissue. This led to an increase in the fraction of hypoxic (up to 60%) and necrotic (10%) tumor cells at advanced tumor stages, whereas normal tissues remained normoxic. These results showed that tumor stage and spatial vascular distribution contribute to the preferential effect of MRT in tumors.

Deep learning-based image analysis with RTFormer network for measuring 2D crystal size distribution during cooling crystallization of β form L-glutamic acid

In this paper, a deep learning-based image analysis method is proposed for in-situ measurement of two-dimensional (2D) crystal size distribution during the cooling crystallization process of β form L-glutamic acid (β-LGA). Firstly, an image quality assessment strategy is presented for in-situ snapshotted crystal images to distinguish different crystallization stages, followed by image enhancement for the snapshotted images in each stage to facilitate analysis. Then, an edge-guided network based on the RTFormer network is developed to acquire precise crystal image segmentation and boundary location, thus improving the identification accuracy on crystal image boundary and its internal body. The network performance is further enhanced by using hyperparameter optimization and a class balance strategy. Subsequently, another identification strategy is developed to distinguish agglomerated and overlapped crystal images, so as to acquire more individual crystals for statistical measurement. Finally, the 2D size of each crystal is calculated based on the major axis and maximum inscribed circle of its segmented image. Experiments on measuring the 2D size distributions of crystal populations during β-LGA crystallization process are performed to verify the accuracy and efficiency of the proposed measurement method.

Contrast-enhanced ultrasound imaging following transperineal laser ablation for lower urinary tract symptoms

ObjectivesTo describe the shape and volume of ablations created by TPLA using multiple fiber configurations. Furthermore, to measure the change in the ablation zone and prostate volume over time, and to assess inter-patient ablation volume variability. MethodsData from a prospective, single center, interventional pilot study including 20 patients is used. All subjects underwent TPLA using the EchoLaser® system, using two to four fibers, depending on prostate size and shape. Contrast-enhanced ultrasound (CEUS) was performed post-treatment and at 1 and 12 months. The prostate and ablation zone volumes were calculated on segmented CEUS imaging. ResultsThe ablation zones were clearly identified on CEUS as non-perfused areas. Depending on fiber configuration, their shape varied from an ellipsoid to a clover profile. Ablation volumes varied from 0.9 (0.6 – 2.2)cm3 using a single fiber and 1800J to 8.7 (3.9 – 19.0)cm3 (median, range) using two fibers and 7200J energy per lobe at one month. At 12 months the majority of the ablation zones showed a volume reduction. Median prostate volume decreased from 78 (37 – 145)cm3 at baseline to 46 (27 – 124)cm3 at 12 months (p=0.0002). There was a relation between prostate volume reduction and Qmax (slope = 0.18) and IPSS (slope = -0.18) improvement. ConclusionsThis study described ablation zone shape and measured the ablation volume following TPLA by various fiber configurations using CEUS, and compared these to functional outcomes. Prostate volume reduced significantly during follow-up. Segmentation showed substantial inter-patient ablation volume variation, which limits treatment predictability and thus accuracy.

Segmented Hash-Based Privacy-Preserving Image Retrieval Scheme in Cloud-Assisted IoT

Segmented Hash-Based Privacy-Preserving Image Retrieval Scheme in Cloud-Assisted IoT

Detecting New Erosions in Rheumatoid Arthritis over One Year — Radiography and High-Resolution Computed Tomography of Finger Joints

Objective: To compare the number of new erosions in two metacarpophalangeal (MCP) joints over one year assessed by high-resolution peripheral quantitative computed tomography (HR-pQCT) and conventional radiography (CR). Furthermore, to estimate the diagnostic accuracy of erosive progression by CR with HR-pQCT as the reference standard.Methods: Paired sets of image data were available from patients with RA (n=310), who underwent HR-pQCT and CR, including the 2nd and 3rd MCP joints only of the dominant hand at baseline and at the one-year follow-up. Erosion number was determined using HR-pQCT and CR. Erosive volume was estimated from segmented HR-pQCT images, and erosion scores were obtained by the Sharp/van der Heijde method from CR. Erosive progression was defined as an increase in total erosion number or a study-specified increase in total erosive volume or total erosion score.Results: At baseline, 250 erosions were identified by CR compared to 1864 erosions by HR-pQCT. After one year, 3 new erosions were detected by CR compared to 66 new erosions by HR-pQCT. Erosive progression was identified in 40 patients using HR-pQCT and in 3 patients using CR. With HR-pQCT as reference, CR had a sensitivity of 2.5% (95% CI: 0.1–13.2%) and a specificity of 99.3% (95% CI: 97.3–99.9%) for detecting erosive progression.Conclusion: HR-pQCT identified more than 20 times the number of new erosions, and more than 10 times as many patients with erosive progression than CR. HR-pQCT is a sensitive tool for monitoring new erosions and erosive progression over one year in RA.

An artificial intelligence mechanism for detecting cystic lesions on CBCT images using deep learning.

The present study aimed to provide and evaluate the efficiency of an artificial intelligence mechanism for detecting cystic lesions on cone beam computed tomography (CBCT) scans. The CBCT image dataset consisted of 150 samples, including 50 cases without lesions, 50 dentigerous cysts (DC), and 50 periapical cysts (PC) based on both radiographic and histopathological diagnosis. The dataset was divided into a development set with 70 % of samples for training and validation and a final test set with the other 30 % of samples. Four images were obtained for each case, including panoramic, manually segmented panoramic, axial, and manually segmented axial images. A deep convolutional neural network (CNN) architecture was used for automatic lesion detection and diagnosing the type of cystic lesion. To increase the number of image samples and avoid overfitting, a data augmentation procedure was applied. Recall, precision, F1-score, and average precision (AP) values were measured for lesion detection performance, and sensitivity, specificity, and accuracy indicators from the confusion matrix were calculated for the lesion classification performance of the CNN model. Mean average precision, recall, and F1-score for the detection of DCs and PCs were respectively, 0.87, 0.92, and 0.89 before data augmentation, and 0.93, 0.95, and 0.93, after the augmentation process. For the classification of DCs with data augmentation, sensitivity, specificity, accuracy, and AUC values were 96.4 %, 99.5 %, 97.3 %, and 0.98, respectively, and for PCs with augmentation, these values were 89.6 %, 98.9 %, 98.1 %, and 0.94, respectively. Lastly, for no lesion samples, sensitivity, specificity, accuracy, and AUC values were 100 %, 99.1 %, 99.4 %, and 0.99, respectively, by application of data augmentation. Our developed deep learning-based CNN algorithm showed high accuracy, sensitivity, and precision values (more than 90 %) for detecting and classifying dentigerous and periapical cysts on CBCT images using data augmentation.