Segmented Images Research Articles

Reliability of quantitative magnetic susceptibility imaging metrics for cerebral cortex and major subcortical structures.

Susceptibility estimates derived from quantitative susceptibility mapping (QSM) images for the cerebral cortex and major subcortical structures are variably reported in brain magnetic resonance imaging (MRI) studies, as average of all ( ), absolute ( ), or positive- ( ) and negative-only ( ) susceptibility values using a region of interest (ROI) approach. This pilot study presents a reliability analysis of currently used ROI-QSM metrics and an alternative ROI-based approach to obtain voxel-weighted ROI-QSM metrics ( and ). Ten healthy subjects underwent repeated (test-retest) 3-dimensional multi-echo gradient-echo (3DMEGE) 3 Tesla MRI measurements. Complex-valued 3DMEGE images were acquired and reconstructed with slice thicknesses of 1 and 2mm (3DMEGE1, 3DMEGE2) along with 3DT1-weighted isometric (voxel 1 mm3) images for independent registration and ROI segmentation. Agreement, consistency, and reproducibility of ROI-QSM metrics were assessed through Bland-Altman analysis, intraclass correlation coefficient, and interscan and intersubject coefficient of variation (CoV). All ROI-QSM metrics exhibited good to excellent consistency and test-retest agreement with no proportional bias. Interscan CoV was higher for in comparison to the other metrics where it was below 15%, in both 3DMEGE1 and 3DMEGE2 datasets. Intersubject CoV for and exceeded 50% in all ROIs. Among the evaluated ROI-QSM metrics, and estimates were less reliable, whereas separating positive and negative values (using ) improved the reproducibility within, and the comparability between, subjects, even when reducing the slice thickness. These preliminary findings may offer valuable insights toward standardizing ROI-QSM metrics across different patient cohorts and imaging settings in future clinical MRI studies.

Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are vision related complications prominently found in diabetic patients. The early identification of DR/DME grades facilitates the devising of an appropriate treatment plan, which ultimately prevents the probability of visual impairment in more than 90% of diabetic patients. Thereby, an automatic DR/DME grade detection approach is proposed in this work by utilizing image processing. In this work, the retinal fundus image provided as input is pre-processed using Discrete Wavelet Transform (DWT) with the aim of enhancing its visual quality. The precise detection of DR/DME is supported further with the application of suitable Artificial Neural Network (ANN) based segmentation technique. The segmented images are subsequently subjected to feature extraction using Adaptive Gabor Filter (AGF) and the feature selection using Random Forest (RF) technique. The former has excellent retinal vein recognition capability, while the latter has exceptional generalization capability. The RF approach also assists with the improvement of classification accuracy of Deep Convolutional Neural Network (CNN) classifier. Moreover, Chicken Swarm Algorithm (CSA) is used for further enhancing the classifier performance by optimizing the weights of both convolution and fully connected layer. The entire approach is validated for its accuracy in determination of grades of DR/DME using MATLAB software. The proposed DR/DME grade detection approach displays an excellent accuracy of 97.91%.

Dementia diagnosis in young adults: a machine learning and optimization approach

AbstractIndividuals who are younger and have dementia often start experiencing its symptoms before they turn 65, with cases even documented in people as young as their thirties. Researchers strive for accurate dementia diagnosis to slow or halt its progression. This paper presents a novel Enhanced Dementia Detection and Classification Model (EDCM) comprised of four modules: data acquisition, preprocessing, hyperparameter optimization, and feature extraction/classification. Notably, the model uses texture information from segmented brain images for improved feature extraction, leading to significant gains in both binary and multi-class classification. This is achieved by selecting optimal features via a Gray Wolf Optimization (GWO)-driven enhancement model. Results demonstrate substantial accuracy improvements after optimization. For instance, using an Extra Tree Classifier for "normal" cases, the model achieves 85% accuracy before optimization. However, with GWO-optimized features and hyperparameters, the accuracy jumps to 97%.

Foreign object detection in urban rail transit based on deep differentiation segmentation neural network

With the increasing scale of urban rail transit, foreign object intrusion has become a significant operational safety hazard in urban rail transit. Although the laser-based automatic foreign object detection system has advantages such as long-distance detection and insensitivity to light changes, it has drawbacks such as large blind spots and low visualization. In response to the problems existing in laser detection systems, we proposed a novel video-based deep differentiation segmentation neural network for foreign object detection. Firstly, the foreign object detection is transformed into a binary classification problem, and the foreign object is determined as the image's foreground using image segmentation principles. Secondly, build a deep segmentation network based on deep convolution. Finally, perform morphological operations and threshold judgment on the foreground segmentation image to filter out the final detection results. To improve the detection effect, we reduced the impact of airflow disturbance by sampling and calculating the average background image. At the same time, the channel attention model and spatial attention model are added to the deep differentiation neural network. Collecting real data on subway platforms for experiments shows that the proposed method has a detection accuracy of 95.8 %, which is superior to traditional detection methods and recent image segmentation neural networks.

Inversion of Cotton Soil and Plant Analytical Development Based on Unmanned Aerial Vehicle Multispectral Imagery and Mixed Pixel Decomposition

In order to improve the accuracy of multispectral image inversion of soil and plant analytical development (SPAD) of the cotton canopy, image segmentation methods were utilized to remove the background interference, such as soil and shadow in UAV multispectral images. UAV multispectral images of cotton bud stage canopies at three different heights (30 m, 50 m, and 80 m) were acquired. Four methods, namely vegetation index thresholding (VIT), supervised classification by support vector machine (SVM), spectral mixture analysis (SMA), and multiple endmember spectral mixture analysis (MESMA), were used to segment cotton, soil, and shadows in the multispectral images of cotton. The segmented UAV multispectral images were used to extract the spectral information of the cotton canopy, and eight vegetation indices were calculated to construct the dataset. Partial least squares regression (PLSR), Random forest (FR), and support vector regression (SVR) algorithms were used to construct the inversion model of cotton SPAD. This study analyzed the effects of different image segmentation methods on the extraction accuracy of spectral information and the accuracy of SPAD modeling in the cotton canopy. The results showed that (1) The accuracy of spectral information extraction can be improved by removing background interference such as soil and shadows using four image segmentation methods. The correlation between the vegetation indices calculated from MESMA segmented images and the SPAD of the cotton canopy was improved the most; (2) At three different flight altitudes, the vegetation indices calculated by the MESMA segmentation method were used as the input variable, and the SVR model had the best accuracy in the inversion of cotton SPAD, with R2 of 0.810, 0.778, and 0.697, respectively; (3) At a flight altitude of 80 m, the R2 of the SVR models constructed using vegetation indices calculated from images segmented by VIT, SVM, SMA, and MESMA methods were improved by 2.2%, 5.8%, 13.7%, and 17.9%, respectively, compared to the original images. Therefore, the MESMA mixed pixel decomposition method can effectively remove soil and shadows in multispectral images, especially to provide a reference for improving the inversion accuracy of crop physiological parameters in low-resolution images with more mixed pixels.

VerFormer: Vertebrae-Aware Transformer for Automatic Spine Segmentation from CT Images.

The accurate and efficient segmentation of the spine is important in the diagnosis and treatment of spine malfunctions and fractures. However, it is still challenging because of large inter-vertebra variations in shape and cross-image localization of the spine. In previous methods, convolutional neural networks (CNNs) have been widely applied as a vision backbone to tackle this task. However, these methods are challenged in utilizing the global contextual information across the whole image for accurate spine segmentation because of the inherent locality of the convolution operation. Compared with CNNs, the Vision Transformer (ViT) has been proposed as another vision backbone with a high capacity to capture global contextual information. However, when the ViT is employed for spine segmentation, it treats all input tokens equally, including vertebrae-related tokens and non-vertebrae-related tokens. Additionally, it lacks the capability to locate regions of interest, thus lowering the accuracy of spine segmentation. To address this limitation, we propose a novel Vertebrae-aware Vision Transformer (VerFormer) for automatic spine segmentation from CT images. Our VerFormer is designed by incorporating a novel Vertebrae-aware Global (VG) block into the ViT backbone. In the VG block, the vertebrae-related global contextual information is extracted by a Vertebrae-aware Global Query (VGQ) module. Then, this information is incorporated into query tokens to highlight vertebrae-related tokens in the multi-head self-attention module. Thus, this VG block can leverage global contextual information to effectively and efficiently locate spines across the whole input, thus improving the segmentation accuracy of VerFormer. Driven by this design, the VerFormer demonstrates a solid capacity to capture more discriminative dependencies and vertebrae-related context in automatic spine segmentation. The experimental results on two spine CT segmentation tasks demonstrate the effectiveness of our VG block and the superiority of our VerFormer in spine segmentation. Compared with other popular CNN- or ViT-based segmentation models, our VerFormer shows superior segmentation accuracy and generalization.

Artificial Intelligence-Based Estimation of Fetal Head Circumference With Biparietal and Occipitofrontal Diameters Using Two-Dimensional Ultrasound Images

Abstract One of the most essential biometrics for measuring fetal growth during prenatal ultrasound exams is the head circumference (HC). However, manual measurement of this biometric by doctors often needs substantial experience. Manual measurement of fetal head circumference during prenatal ultrasound exams requires significant expertise, posing limitations in accuracy and consistency, which can impact clinical decision-making and fetal health assessments. We developed a state-of-the-art image processing algorithm that utilizes biometry and segmented images and employed a fast ellipse fitting method to measure the HC, head orientation (angle) along with biparietal (BPD), and occipitofrontal (OFD) diameter automatically. Our approach offers automation and precision in measuring fetal biometrics, surpassing the limitations of manual measurement by ensuring consistent and accurate assessments, thus enhancing clinical efficiency and facilitating timely interventions for optimal fetal health management. Additionally, to the best of our knowledge, this is the first work that adopts a segmented image from any model or technique and provides significant fetal parameters during ultrasonography in a single shot. The suggested technique is lightweight, real-time, and easily integrate with any segmentation model or technique. We have used three well-known segmentation models for demonstration and compared their performance using dice scores as an evaluation parameter. Among the three, HRNet shows the best results with an average dice score of 0.96; due to the high dice score, we have chosen HRNet over the other two models and proceeded further and implemented our novel algorithm on that to predict the required fetal key measurements. The findings of this study benefit prenatal care by enhancing the accuracy and efficiency of fetal biometric measurements, thereby facilitating improved clinical decision-making and optimizing fetal health assessments.

Biomechanical changes of oblique lumbar interbody fusion with different fixation techniques in degenerative spondylolisthesis lumbar spine: a finite element analysis

ObjectiveThere is a dearth of comprehensive research on the stability of the spinal biomechanical structure when combining Oblique Lumbar Interbody Fusion (OLIF) with internal fixation methods. Hence, we have devised this experiment to meticulously examine and analyze the biomechanical changes that arise from combining OLIF surgery with different internal fixation techniques in patients diagnosed with degenerative lumbar spondylolisthesis.MethodsSeven validated finite element models were reconstructed based on computed tomography scan images of the L3-L5 segment. These models included the intact model, a stand-alone (S-A) OLIF model, a lateral screw rod (LSR) OLIF model, a bilateral pedicle screw (BPS) OLIF model, an unilateral pedicle screw (UPS) OLIF model, a bilateral CBT (BCBT) OLIF model, and an unilateral CBT(UCBT) OLIF model. The range of motion (ROM), as well as stress levels in the cage, L4 lower endplate, L5 upper endplate, and fixation constructs were assessed across these different model configurations.ResultsS-A model had the highest average ROM of six motion modes, followed by LSR, UPS, UCBT, BPS and BCBT. The BCBT model had a relatively lower cage stress than the others. The maximum peak von Mises stress of the fixation constructs was found in the LSR model. The maximum peak von Mises stress of L4 lower endplate was found in the S-A model. The peak von Mises stress on the L4 lower endplate of the rest surgical models showed no significant difference. The maximum peak von Mises stress of the L5 upper endplate was found in the S-A model. The minimum peak von Mises stress of the L5 upper endplate was found in the BCBT model. No significant difference was found for the peak von Mises stress of the L5 upper endplate among LSR, BPS, UPS and UCBT models.ConclusionAmong the six different fixation techniques, BCBT exhibited superior biomechanical stability and minimal stress on the cage-endplate interface. It was followed by BPS, UCBT, UPS, and LSR in terms of effectiveness. Conversely, S-A OLIF demonstrated the least stability and resulted in increased stress on both the cage and endplates. Combining OLIF with BCBT fixation technique enhanced biomechanical stability compared to BPS and presented as a less invasive alternative treatment for patients with degenerative lumbar spondylolisthesis.

ViT-MAENB7: An innovative breast cancer diagnosis model from 3D mammograms using advanced segmentation and classification process

Tumors are an important health concern in modern times. Breast cancer is one of the most prevalent causes of death for women. Breast cancer is rapidly becoming the leading cause of mortality among women globally. Early detection of breast cancer allows patients to obtain appropriate therapy, increasing their probability of survival. The adoption of 3-Dimensional (3D) mammography for the medical identification of abnormalities in the breast reduced the number of deaths dramatically. Classification and accurate detection of lumps in the breast in 3D mammography is especially difficult due to factors such as inadequate contrast and normal fluctuations in tissue density. Several Computer-Aided Diagnosis (CAD) solutions are under development to help radiologists accurately classify abnormalities in the breast. In this paper, a breast cancer diagnosis model is implemented to detect breast cancer in cancer patients to prevent death rates. The 3D mammogram images are gathered from the internet. Then, the gathered images are given to the preprocessing phase. The preprocessing is done using a median filter and image scaling method. The purpose of the preprocessing phase is to enhance the quality of the images and remove any noise or artifacts that may interfere with the detection of abnormalities. The median filter helps to smooth out any irregularities in the images, while the image scaling method adjusts the size and resolution of the images for better analysis. Once the preprocessing is complete, the preprocessed image is given to the segmentation phase. The segmentation phase is crucial in medical image analysis as it helps to identify and separate different structures within the image, such as organs or tumors. This process involves dividing the preprocessed image into meaningful regions or segments based on intensity, color, texture, or other features. The segmentation process is done using Adaptive Thresholding with Region Growing Fusion Model (AT-RGFM)”. This model combines the advantages of both thresholding and region-growing techniques to accurately identify and delineate specific structures within the image. By utilizing AT-RGFM, the segmentation phase can effectively differentiate between different parts of the image, allowing for more precise analysis and diagnosis. It plays a vital role in the medical image analysis process, providing crucial insights for healthcare professionals. Here, the Modified Garter Snake Optimization Algorithm (MGSOA) is used to optimize the parameters. It helps to optimize parameters for accurately identifying and delineating specific structures within medical images and also helps healthcare professionals in providing more precise analysis and diagnosis, ultimately playing a vital role in the medical image analysis process. MGSOA enhances the segmentation phase by effectively differentiating between different parts of the image, leading to more accurate results. Then, the segmented image is fed into the detection phase. The tumor detection is performed by the Vision Transformer-based Multiscale Adaptive EfficientNetB7 (ViT-MAENB7) model. This model utilizes a combination of advanced algorithms and deep learning techniques to accurately identify and locate tumors within the segmented medical image. By incorporating a multiscale adaptive approach, the ViT-MAENB7 model can analyze the image at various levels of detail, improving the overall accuracy of tumor detection. This crucial step in the medical image analysis process allows healthcare professionals to make more informed decisions regarding patient treatment and care. Here, the created MGSOA algorithm is used to optimize the parameters for enhancing the performance of the model. The suggested breast cancer diagnosis performance is compared to conventional cancer diagnosis models and it showed high accuracy. The accuracy of the developed MGSOA-ViT-MAENB7 is 96.6 %, and others model like RNN, LSTM, EffNet, and ViT-MAENet given the accuracy to be 90.31 %, 92.79 %, 94.46 % and 94.75 %. The developed model's ability to analyze images at multiple scales, combined with the optimization provided by the MGSOA algorithm, results in a highly accurate and efficient system for detecting tumors in medical images. This cutting-edge technology not only improves the accuracy of diagnosis but also helps healthcare professionals tailor treatment plans to individual patients, ultimately leading to better outcomes. By outperforming traditional cancer diagnosis models, the proposed model is revolutionizing the field of medical imaging and setting a new standard for precision and effectiveness in healthcare.

INTEGRATING DUAL FUNDUS IMAGE DEEP FEATURE POOLING BASED ON CUP AND DISC SEGMENTATION FOR EFFICIENT GLAUCOMA DETECTION FRAMEWORK INDULGING HEURISTIC CONCEPT

The permanent damage occurring to the optical nerve, which transmits the visualized images to the brain leading to permanent vision loss, is called glaucoma. The detection and diagnosis of glaucoma at the beginning stage are essential to prevent permanent damage caused to vision as there are no initial symptoms to detect the onset of the damage, and there is no cure while the damage progresses to its extreme stage. Many models utilizing deep learning technology have been executed to identify the presence of glaucoma using digital Fundus Images (FI). However, these methods need specialized hardware and are computationally complicated as there is not much-labeled data available, leading to generalization issues in these models. Therefore, the development of a deep learning-oriented model for Glaucoma Detection (GD) using the dual feature pooling of cup and disc segmentation features with the aid of the FI is the main motive behind this work. At first, the digital FI is congregated from standardized online data sources. Then the gathered images are considered for the image segmentation procedure. The disc is segmented from the input image with the aid of the Transformer based Adaptive ResUNet++ (TA-ResUNet++) framework. The segmented disc image is now provided to hybrid convolution networks (HCN) for extracting the disc-oriented features. At the same time, the cup is segmented from the gathered input image using the executed TA-ResUnet++. Following this, the cup features are extracted using the same HCN model. The obtained features regarding the disc and the cup are concatenated in order to generate a single pool of glaucoma features. Then these features are inputted into the implemented bidirectional long short-term memory with multi-head attention (Bi-LSTM-MHA) mechanism to detect the presence of glaucoma in people. The segmentation and detection outcomes are made better by optimizing the parameters in the TA-ResUNet++ and Bi-LSTM-MHA models with the aid of hybrid sewing training with the Chameleon swarm optimization algorithm (HST-CSA). The experimental analysis is done to analyze the effective performance of the developed GD model. Jaccard analysis performed for the developed HST-CSOA-TA-ResUNet++-based disc segmentation gained better performance as 18.29% than MobileNet, 14.11% efficient than ResNet, 12.79% superior to Bi-LSTM and 5.43% higher than Bi-LSTM-MHA while considering best as the statistical measure.

A Whole-Spine Radiography Study to Reduce Patient Exposure Dose and Artifacts Using the EOS Imaging System.

Whole-spine radiography can be accomplished through two methods: (1) segmented imaging employing X-ray tube angulation and detectors, or (2) the Euronext Paris Advanced Orthopedic Solutions (EOS) 2D Imaging system that can capture the entire spine in a single image using X-ray tubes and detectors oriented at a 90-degree angle. This study aimed to establish optimal EOS examination parameters based on patient morphotype and scan speed to reduce patient radiation exposure, repeat examinations, heat stress on equipment, and X-ray tube cooling time. X-ray exposure conditions involved adjustments of scan speed ranging from two to four steps, contingent upon the patient's morphotype ('S', small body; 'M', medium body; and 'L', large body. Patient dose measurements were conducted 20 times for each set of conditions. When transitioning from an 'S' to an 'M' morphotype at a constant scan speed, the entrance skin dose (ESD) exhibited an increase of approximately 41.25 ± 4.57%. A similar change from an 'M' to an 'L' morphotype resulted in an ESD increase of roughly 59.56 ± 24.00%. A transition from an 'S' to an 'L' morphotype at the same scan speed manifested an ESD elevation of approximately 124.21 ± 26.96%. This study underscores significant variations in radiation dose, ranging from 40% to 50%, when altering morphotype while maintaining a consistent scan speed.

A Novel Classification Approach for Retinal Disease Using Improved Gannet Optimization‐Based Capsule DenseNet

ABSTRACTAn unusual condition of the eye called diabetic retinopathy affects the human retina and is brought on by the blood's constant rise in insulin levels. Loss of vision is the result. Diabetic retinopathy can be improved by receiving an early diagnosis to prevent further damage. A cost‐effective method of accumulating medical treatments is through appropriate DR screening. In this work, deep learning framework is introduced for the accurate classification of retinal diseases. The proposed method processes retinal fundus images obtained from databases, addressing noise and artifacts through an improved median filter (ImMF). It leverages the UNet++ model for precise segmentation of the disease‐affected regions. UNet++ enhances feature extraction through cross‐stage connections, improving segmentation results. The segmented images are then fed as input to the improved gannet optimization‐based capsule DenseNet (IG‐CDNet) for retinal disease classification. The hybrid capsule DenseNet (CDNet) classifies disease and is optimized using the improved gannet optimization algorithm to boost classification accuracy. Finally, the accuracy and dice score values achieved are 0.9917 and 0.9652 on the APTOS‐2019 dataset.

Deep Learning-driven Automatic Nuclei Segmentation of Label-free Live Cell Chromatin-sensitive Partial Wave Spectroscopic Microscopy Imaging.

Chromatin-sensitive Partial Wave Spectroscopic (csPWS) microscopy offers a non-invasive glimpse into the mass density distribution of cellular structures at the nanoscale, leveraging the spectroscopic information. Such capability allows us to analyze the chromatin structure and organization and the global transcriptional state of the cell nuclei for the study of its role in carcinogenesis. Accurate segmentation of the nuclei in csPWS microscopy images is an essential step in isolating them for further analysis. However, manual segmentation is error-prone, biased, time-consuming, and laborious, resulting in disrupted nuclear boundaries with partial or over-segmentation. Here, we present an innovative deep-learning-driven approach to automate the accurate nuclei segmentation of label-free live cell csPWS microscopy imaging data. Our approach, csPWS-seg, harnesses the Convolutional Neural Networks-based U-Net model with an attention mechanism to automate the accurate cell nuclei segmentation of csPWS microscopy images. We leveraged the structural, physical, and biological differences between the cytoplasm, nucleus, and nuclear periphery to construct three distinct csPWS feature images for nucleus segmentation. Using these images of HCT116 cells, csPWS-seg achieved superior performance with a median Intersection over Union (IoU) of 0.80 and a Dice Similarity Coefficient (DSC) score of 0.88. The csPWS-seg overcame the segmentation performance over the baseline U-Net model and another attention-based model, SE-U-Net, marking a significant improvement in segmentation accuracy. Further, we analyzed the performance of our proposed model with four loss functions: binary cross-entropy loss, focal loss, dice loss, and Jaccard loss. The csPWS-seg with focal loss provided the best results compared to other loss functions. The automatic and accurate nuclei segmentation offered by the csPWS-seg not only automates, accelerates, and streamlines csPWS data analysis but also enhances the reliability of subsequent chromatin analysis research, paving the way for more accurate diagnostics, treatment, and understanding of cellular mechanisms for carcinogenesis.

Extent and Topography of Subretinal Drusenoid Deposits Associate With Rod-Mediated Vision in Aging and AMD: ALSTAR2 Baseline.

In AMD, rod-mediated dark adaptation (RMDA) at 5° eccentricity is slower in eyes with subretinal drusenoid deposits (SDDs) than in eyes without. Here we quantified SDD burden using supervised deep learning for comparison to vision and photoreceptor topography. In persons ≥60 years from the Alabama Study on Early Age-Related Macular Degeneration 2, normal, early AMD, and intermediate AMD eyes were classified by the AREDS nine-step system. A convolutional neural network was trained on 55°-wide near-infrared reflectance images for SDD segmentation. Trained graders annotated ground truth (SDD yes/no). Predicted and true datasets agreed (Dice coefficient, 0.92). Inference was manually proofread using optical coherence tomography. The mean SDD area (mm2) was compared among diagnostic groups (linear regression) and to vision (age-adjusted Spearman correlations). Fundus autofluorescence images were used to mask large vessels in SDD maps. In 428 eyes of 428 persons (normal, 218; early AMD, 120; intermediate AMD, 90), the mean SDD area differed by AMD severity (P < 0.0001): 0.16 ± 0.87 (normal), 2.48 ± 11.23 (early AMD), 11.97 ± 13.33 (intermediate AMD). Greater SDD area was associated with worse RMDA (r = 0.27; P < 0.0001), mesopic (r = -0.13; P = 0.02) and scotopic sensitivity (r = -0.17; P < 0.001). SDD topography peaked at 5° superior, extended beyond the Early Treatment of Diabetic Retinopathy Study grid and optic nerve, then decreased. SDD area is associated with degraded rod-mediated vision. RMDA 5° (superior retina) probes where SDD is maximal, closer to the foveal center than the rod peak at 3 to 6 mm (10.4°-20.8°) superior and the further eccentric peak of rod:cone ratio. Topographic data imply that factors in addition to rod density influence SDD formation.

Active contour model with improved second-order differential driven term

Driven terms in active contour models (ACMs) play a significant role in edge identification and image segmentation. However, in many existing ACMs, the driven terms are iteratively updated, resulting in slower segmentation speed because the image segmentation time increases with the iteration number. To address this problem, an ACM based on an improved second-order differential driven term (ISDDT) is presented, which can extract the edge information of images. The improved second-order differential driven term is computed only once before the iterations. Therefore, the computational complexity of our presented ACM is reduced, leading to a faster image segmentation speed. In addition, an improved regularization method with mean filtering is presented to improve the robustness of our ISDDT model. As an application, a target contour tracking method is developed based on our ISDDT model. Experimental results show that our ISDDT model segments images with inhomogeneous intensities well. The image segmentation speed of our proposed model has obvious advantages.

An innovative approach for PCO morphology segmentation using a novel MOT-SF technique

Polycystic ovary syndrome (PCOS) is an endocrine disorder affecting women of reproductive age characterized by the presence of multiple follicles in the ovaries that are detectable via ultrasound imaging. Early diagnosis of PCOS morphology can be challenging due to low resolution and increased speckle noise, making it difficult to identify smaller follicle boundaries. This article introduces a novel methodology, multiscale gradient-weighted oriented Otsu thresholding with sum of product fusion (MOT-SF), to address these challenges. The MOT-SF technique precisely recognizes smaller region boundaries even at lower resolutions by employing a pyramidal structure for image computation at multiple scales. Otsu's thresholding is used to segment the image, optimizing the threshold by minimizing the interclass variance at each stage. Incorporating gradient weights (λ) within classes enhances smaller boundary regions and reduces noise. Additionally, the MOT-SF method integrates a sum of product fusion strategies, combining segmented images from various scales to produce a final image that preserves both small and large PCOS structures while mitigating noise. The experimental results show that MOT-SF outperforms traditional methods such as Otsu’s thresholding and Chan-Vese models, as well as deep learning approaches such as R-CNN, in terms of computational efficiency and robustness to variations in ultrasound image quality. The MOT-SF methodology achieves an accuracy of nearly 85% and a precision of 94%, highlighting its potential to improve the detection and characterization of follicles in ultrasound images and advancing diagnostic tools in reproductive health.Graphical

System and method to diagnose conjunctivitis in the eye of a user

This Proposed work explores how machine learning can be used to diagnose conjunctivitis, a common eye ailment. The main goal of the study is to capture eye images using camera-based systems, perform image pre-processing, and employ image segmentation techniques, particularly the UNet++ and U-net models. Additionally, the study involves extracting features from the relevant areas within the segmented images and using Convolutional Neural Networks for classification. All this is carried out using TensorFlow, a well-known machine-learning platform. The research involves thorough training and assessment of both the UNet and U-net++ segmentation models. A comprehensive analysis is conducted, focusing on their accuracy and performance. The study goes further to evaluate these models using both the UBIRIS dataset and a custom dataset created for this specific research. The experimental results emphasize a substantial improvement in the quality of segmentation achieved by the U-net++ model, the model achieved an overall accuracy of 97.07. Furthermore, the UNet++ architecture displays better accuracy in comparison to the traditional U-net model. These outcomes highlight the potential of U-net++ as a valuable advancement in the field of machine learning-based conjunctivitis diagnosis.

Rethinking masked image modelling for medical image representation

Masked Image Modelling (MIM), a form of self-supervised learning, has garnered significant success in computer vision by improving image representations using unannotated data. Traditional MIMs typically employ a strategy of random sampling across the image. However, this random masking technique may not be ideally suited for medical imaging, which possesses distinct characteristics divergent from natural images. In medical imaging, particularly in pathology, disease-related features are often exceedingly sparse and localized, while the remaining regions appear normal and undifferentiated. Additionally, medical images frequently accompany reports, directly pinpointing pathological changes’ location. Inspired by this, we propose Masked medical Image Modelling (MedIM), a novel approach, to our knowledge, the first research that employs radiological reports to guide the masking and restore the informative areas of images, encouraging the network to explore the stronger semantic representations from medical images. We introduce two mutual comprehensive masking strategies, knowledge-driven masking (KDM), and sentence-driven masking (SDM). KDM uses Medical Subject Headings (MeSH) words unique to radiology reports to identify symptom clues mapped to MeSH words (e.g., cardiac, edema, vascular, pulmonary) and guide the mask generation. Recognizing that radiological reports often comprise several sentences detailing varied findings, SDM integrates sentence-level information to identify key regions for masking. MedIM reconstructs images informed by this masking from the KDM and SDM modules, promoting a comprehensive and enriched medical image representation. Our extensive experiments on seven downstream tasks covering multi-label/class image classification, pneumothorax segmentation, and medical image–report analysis, demonstrate that MedIM with report-guided masking achieves competitive performance. Our method substantially outperforms ImageNet pre-training, MIM-based pre-training, and medical image–report pre-training counterparts. Codes are available at https://github.com/YtongXie/MedIM.

A novel hybrid methodology integrating pixel- and object-based techniques for mapping land use and land cover from high-resolution satellite data

ABSTRACT The classification of very high-resolution satellite imagery remains a focal point in remote sensing, attracting increased attention across diverse scientific disciplines. Various classification methods, including pixel- and object-based techniques, have been proposed, and their performances and limitations have been discussed in the literature. This paper presents a hybrid method that combines the strengths of pixel- and object-based methods in image classification to minimize errors associated with the segmentation process, particularly under-segmentation errors in object-based image analysis. The core concept behind the method lies in categorizing segmented image objects as either homogeneous or heterogeneous based on their class probability. In this process, the estimated possibilities from the object-based classification model are considered, and segments are designated as homogeneous or heterogeneous using a user-defined threshold. The object-based classification model determines the class labels for homogeneous image objects, while the heterogeneous ones, containing pixels representing different land cover classes, are classified using the pixel-based model. The performance of hybrid classification models, created by varying thresholds, is analysed using high-resolution WorldView-3 and WorldView-2 imagery and compared with pixel- and object-based classification results. For the implementation of image classification methods, Canonical Correlation Forest (CCF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) were employed. The findings indicated that employing the suggested hybrid strategy with a threshold value selected within a specific range (e.g. between 60% and 80%) and employing a robust classification algorithm that provides class probabilities (e.g. CCF) results in a statistically significant improvement in overall accuracy compared to pixel and object-based methods, with gains of 5% and 4%, respectively. Visual analysis of the produced thematic maps revealed that the proposed method minimizes the salt-and-pepper effect associated with pixel-based classification while mitigating segmentation problems arising from object-based classification.

A comparison between 3D printed models and standard 2D planning in the use of metal block augments in revision knee arthroplasty.

The study focused on the ability to predict the need and size of femoral and tibial augmentation using standard two-dimensional (2D) templates and models created with three-dimensional (3D) printing in surgical planning. This observational cohort study included 28 consecutive patients (22 females, 6 males; mean age: 71±7.3 years; range, 54 to 82 years) with periprosthetic joint infection recruited between March 2021 and September 2023 undergoing revision total knee arthroplasty revision (TKA). Standard planning was made using calibrated X-ray images. The 3D planning started with computed tomography scans to generate a 3D template of the distal femur and proximal tibia. The model was exported to a 3D printer to produce a patient-specific phantom. The surgery was then simulated on the 3D phantom using revision knee arthroplasty instrumentation to evaluate the appropriate augmentation to use until a correct alignment was obtained. Three-dimensional planning predicted the need for femoral and tibial augments in 22 (78.6%) cases at both the tibial and femoral components, while 2D planning correctly predicted the need for augmentation in 17 (60.7%) for the tibial side and 18 (64.3%) for the femoral side. The Cohen's kappa demonstrated a significant agreement between the 3D planning for the femoral metal block and the intraoperative requirement (kappa=0.553), whereas 2D planning showed only nonsignificant poor agreement (kappa=0.083). In contrast, the agreement between 2D or 3D preoperative planning for tibial augment and the intraoperative requirement was nonsignificant (kappa=0.130 and kappa=0.158, respectively). On the femoral side, 2D planning showed only a fair nonsignificant correlation (r=0.35, p=0.069), whereas 3D planning exhibited substantial agreement with the actual thickness of the implanted augment (r=0.65, p<0.001). On the tibial side, 3D and 2D planning showed substantial agreement with the actual size of implanted augments (3D planning, r=0.73, p<0.001; 2D planning, r=0.69, p<0.001). Prediction based on 3D computed tomography segmentation showed significant agreement with the intraoperative need for augmentations in revision TKA. The results suggest that planning with 3D printed models represents a stronger aid in this kind of surgery rather than standard 2D planning, providing greater accuracy in the prediction of the required augmentation in revision TKA.