Segmented Images Research Articles

Adapting SAM2 Model from Natural Images for Tooth Segmentation in Dental Panoramic X-Ray Images

Dental panoramic X-ray imaging, due to its high cost-effectiveness and low radiation dose, has become a widely used diagnostic tool in dentistry. Accurate tooth segmentation is crucial for lesion analysis and treatment planning, helping dentists to quickly and precisely assess the condition of teeth. However, dental X-ray images often suffer from noise, low contrast, and overlapping anatomical structures, coupled with limited available datasets, leading traditional deep learning models to experience overfitting, which affects generalization ability. In addition, high-precision deep models typically require significant computational resources for inference, making deployment in real-world applications challenging. To address these challenges, this paper proposes a tooth segmentation method based on the pre-trained SAM2 model. We employ adapter modules to fine-tune the SAM2 model and introduce ScConv modules and gated attention mechanisms to enhance the model’s semantic understanding and multi-scale feature extraction capabilities for medical images. In terms of efficiency, we utilize knowledge distillation, using the fine-tuned SAM2 model as the teacher model for distilling knowledge to a smaller model named LightUNet. Experimental results on the UFBA-UESC dataset show that, in terms of performance, our model significantly outperforms the traditional UNet model in multiple metrics such as IoU, effectively improving segmentation accuracy and model robustness, particularly with limited sample datasets. In terms of efficiency, LightUNet achieves comparable performance to UNet, but with only 1.6% of its parameters and 24.0% of the inference time, demonstrating its feasibility for deployment on edge devices.

Image analysis-based identification of high risk ER-positive, HER2-negative breast cancers

BackgroundBreast cancer subtypes Luminal A and Luminal B are classified by the expression of PAM50 genes and may benefit from different treatment strategies. Machine learning models based on H&E images may contain features associated with subtype, allowing early identification of tumors with higher risk of recurrence.MethodsH&E images (n = 630 ER+/HER2-breast cancers) were pixel-level segmented into epithelium and stroma. Convolutional neural network and multiple instance learning were used to extract image features from original and segmented images. Patient-level classification models were trained to discriminate Luminal A versus B image features in tenfold cross-validation, with or without grade adjustment. The best-performing visual classifier was incorporated into envisioned diagnostic protocols as an alternative to genomic testing (PAM50). The protocols were then compared in time-to-recurrence models.ResultsAmong ER+/HER2-tumors, the image-based protocol differentiated recurrence times with a hazard ratio (HR) of 2.81 (95% CI: 1.73–4.56), which was similar to the HR for PAM50 (2.66, 95% CI: 1.65–4.28). Grade adjustment did not improve subtype prediction accuracy, but did help balance sensitivity and specificity. Among high grade participants, sensitivity and specificity (0.734 and 0.474, respectively) became more similar (0.732 and 0.624, respectively) in grade-adjusted models. The original and epithelium-specific images had similar performance and highest accuracy, followed by stroma or binarized images showing only the epithelial-stromal interface.ConclusionsGiven low rates of genomic testing uptake nationally, image-based methods may help identify ER+/HER2-patients who could benefit from testing.

A Robust Malaria Cell Detection Framework Using Adaptive and Atrous Convolution-Based Recurrent Mobilenetv2 with Trans-MobileUNet + + -Based Abnormality Segmentation.

The highly contagious malaria disease is spread by the female Anopheles mosquito. This disease results in a patient's death or incapacity to move their muscles, if it is not appropriately identified in the early stages. A Rapid Diagnostic Test (RDT) is a frequently used approach to find malaria cells in red blood cells. However, it might not be able to identify infections with small amounts of samples. In the microscopic detection model, blood stains are placed under a microscope for diagnosing malaria. But accurate diagnosis is hard in this method, particularly in developing nations where the disease is most common. The microscopic detection processes are expensive and time-consuming due to the usage of microscopes. The quality of the blood smears and the availability of a qualified specialist, who is skilled in recognizing the disease, impact the accuracy of malaria detection results. The traditional deep learning-based malaria identification models need more processing power. Therefore, a deep learning-based adaptive method is designed to detect malaria cells through the medical image. Hence, the images are gathered from the standard sites and then fed to the segmentation process. Here, the abnormality segmentation is carried out with the help of a developed Trans-MobileUNet + + (T-MUnet + +) network. Trans-MobileUNet + + captures global context, so it is well-suited for segmentation tasks. The segmented image is applied to the adaptive detection phase where the Adaptive and Atrous Convolution-based Recurrent MobilenetV2 (AA-CRMV2) model is designed for the effective recognition of malaria cells. The efficiency of the designed approach is elevated by optimizing the parameters from the AA-CRMV2 network with the help of the Updated Random Parameter-based Fennec Fox Optimization (URP-FFO) algorithm. Several experimental analyses are evaluated in the implemented model over classical techniques to display their effectualness rate.

Development of an Open-Source Dataset of Flat-Mounted Images for the Murine Oxygen-Induced Retinopathy Model of Ischemic Retinopathy.

To describe an open-source dataset of flat-mounted retinal images and vessel segmentations from mice subject to the oxygen-induced retinopathy (OIR) model. Flat-mounted retinal images from mice killed at postnatal days 12 (P12), P17, and P25 used in prior OIR studies were compiled. Mice subjected to normoxic conditions were killed at P12, P17, and P25, and their retinas were flat-mounted for imaging. Major blood vessels from the OIR images were manually segmented by four graders (JSC, HKR, KBL, JM), with cross-validation performed to ensure similar grading. Overall, 1170 images were included in this dataset. Of these images, 111 were of normoxic mice retina, and 1048 were mice subject to OIR. The majority of images from OIR mice were obtained at P17. The 50 images obtained from an external dataset, OIRSeg, did not have age labels. All images were manually segmented and used in the training or testing of a previously published deep learning algorithm. This is the first open-source dataset of original and segmented flat-mounted retinal images. The dataset has potential applications for expanding the development of generalizable and larger-scale artificial intelligence and analyses for OIR. This dataset is published online and publicly available at dx.doi.org/10.6084/m9.figshare.23690973. This open access dataset serves as a source of raw data for future research involving big data and artificial intelligence research concerning oxygen-induced retinopathy.

Nonlinear associations between street-level greenery quantity and quality, physical activity, and sedentary behaviour in Chinese middle-aged and older adults: A socioeconomic equity perspective

Despite studies investigating the relationships among greenery, physical activity, and sedentary behaviour, it remains unclear whether such associations are nonlinear. Scant attention has also been paid to the role of greenery from a socioeconomic equity perspective. Thus, we assessed possible nonlinear associations between street-level greenery, physical activity, and sedentary behaviour in middle-aged and older adults. We also examined whether and how street-level greenery may increase socioeconomic equity in physical activity and sedentary behaviour. Data on physical activity and sedentary behaviour were obtained from the WHO Study on Global Ageing and Adult Health in Shanghai, China. The quantity and quality of street-level greenery were assessed using segmented street-view images based on deep learning methods. The results of fitting gradient-boosting decision trees showed that street-level greenery quantity was positively related to physical activity. We observed a steep increase in physical activity at low greenery quantity and flattening out at higher quantity. Street-level greenery quality was negatively related to sedentary behaviour. While sedentary behaviour did not change significantly at low greenery quality, the decrease became steep at higher quality. The greenery association was stronger for low incomers and those in deprived neighbourhoods.

Ground-Based Cloud Image Segmentation Method Based on Improved U-Net

Cloud image segmentation is a technique that divides images captured by meteorological satellites or ground-based observations into different regions or categories. By extracting the distribution, shape, and dynamic features of clouds, it provides precise data support for the meteorological and environmental fields, significantly influencing photovoltaic (PV) power generation forecasting, astronomical telescope observatory site selection, and weather forecasting. A ground-based cloud image segmentation model based on an improved U-Net is proposed, which adopts an overall encoder–decoder structure. In the encoder phase, this paper constructs a dilated convolution–atrous spatial pyramid pooling (ASPP)–dilated convolution structure to enhance early cloud feature extraction. Dilated convolution is a novel type of convolution that expands the receptive field by inserting holes into standard convolution, thereby capturing a larger range of contextual information. ASPP maintains high resolution while paying attention to both local details and global structures of the image. In the decoder stage, the bicubic interpolation method is used for up-sampling to restore the feature map resolution and improve the clarity of the segmented image. The bicubic interpolation method refers to the use of cubic polynomial functions to interpolate the pixel values of the input image. In addition, this paper designs a novel skip connection layer structure between the encoder and decoder, composed of a depthwise separable path (DS path) and an improved channel spatial attention module (Im-CSAM) connected in sequence. The DS path combines depthwise separable convolutions and residual structures to facilitate information exchange between high-level and low-level features. The Im-CSAM is a modular attention mechanism that focuses on important cloud features in spatial and channel dimensions to enhance segmentation accuracy. Experiments show that compared to the traditional U-Net, the accuracy, precision, and MIoU of this model improved by 2.2%, 4.1%, and 5.0%, respectively, in the SWINySEG dataset, and by 3.2%, 3.6%, and 5.8%, respectively, in the TCDD dataset, proving that the improved method has a better generalization ability and segmentation performance.

An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detection

Safety is crucial in the railway industry because railways transport millions of passengers and employees daily, making it paramount to prevent injuries and fatalities. In order to guarantee passenger safety, computer vision, unmanned aerial vehicles (UAV), and artificial intelligence will be essential tools in the near future for routinely evaluating the railway environment. An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detection (UAV-RSOD) comprises high-resolution images captured by UAVs over various obstacles within railroad scenes, enabling automatic railroad extraction and obstacle detection. The dataset includes 315 raw images, along with 630 labeled and 630 masked images for railroad semantic segmentation. The dataset consists of 315 original images captured by the UAV for object detection and obstacle detection. To increase dataset diversity for training purposes, we applied data augmentation techniques, which expanded the dataset to 2002 augmented and annotated images for obstacle detection cover six different classes of obstacles on railroad lines. Additionally, we provide the original 315 images along with a script for augmentation, allowing users to generate their own augmented data as needed, offering a more sustainable and customizable option. Each image in the dataset is accurately annotated with bounding boxes and labeled under six categories, including person, boulder, barrel, branch, jerry can, and iron rod. This comprehensive classification and detailed annotation make the dataset an essential tool for researchers and developers working on computer vision applications in the railroad domain.

Hybrid improved fuzzy C-means and watershed segmentation to classify Alzheimer’s using deep learning

Brain damage and deficits in interactions among brain cells are the primary causes of dementia and Alzheimer’s disease (AD). Despite ongoing research, no effective medications have yet been developed for these conditions. Therefore, early detection is crucial for managing the progression of these disorders. In this study, we introduce a novel tool for detecting AD using non invasive medical tests, such as magnetic resonance imaging (MRI). Our method employs fuzzy C-means clustering to identify features that enhance image accuracy. The standard fuzzy C-means algorithm has been augmented with fuzzy components to improve clustering performance. This enhanced approach optimizes segmentation by extracting image information and utilizing a sliding window to calculate center coordinates and establish a stable group matrix. These critical features are subsequently integrated with a two-phase watershed segmentation process. The resulting segmented images are then used to train an optimal convolutional neural network (CNN) for AD classification. Our methodology demonstrated a 98.20% accuracy rate in the detection and classification of segmented MRI brain images, highlighting its efficacy in identifying disease types.

Uni-to-Multi Modal Knowledge Distillation for Bidirectional LiDAR-Camera Semantic Segmentation.

Combining LiDAR points and images for robust semantic segmentation has shown great potential. However, the heterogeneity between the two modalities (e.g. the density, the field of view) poses challenges in establishing a bijective mapping between each point and pixel. This modality alignment problem introduces new challenges in network design and data processing for cross-modal methods. Specifically, 1) points that are projected outside the image planes; 2) the complexity of maintaining geometric consistency limits the deployment of many data augmentation techniques. To address these challenges, we propose a cross-modal knowledge imputation and transition approach. First, we introduce a bidirectional feature fusion strategy that imputes missing image features and performs cross-modal fusion simultaneously. This allows us to generate reliable predictions even when images are missing. Second, we propose a Uni-to-Multi modal Knowledge Distillation (U2MKD) framework, leveraging the transfer of informative features from a single-modality teacher to a cross-modality student. This overcomes the issues of augmentation misalignment and enables us to train the student effectively. Extensive experiments on the nuScenes, Waymo, and SemanticKITTI datasets demonstrate the effectiveness of our approach. Notably, our method achieves an 8.3 mIoU gain over the LiDAR-only baseline on the nuScenes validation set and achieves state-of-the-art performance on the three datasets.

Machine Learning for Automated Oil Palm Fruit Grading: The Role of Fuzzy C-Means Segmentation and Textural Features

Oil palm fruit, a high-demand and economically valuable crop, faces grading challenges in Malaysia due to labour-intensive methods, resulting in unharvested ripe fruits and yield losses. Extensive research has been conducted on outdoor palm fruit classifiers, but most high-accuracy research in this field relies heavily on large image datasets. This creates a trade-off between employing more sophisticated deep-learning approaches that require extensive data and utilising traditional techniques that have lower data requirements. Therefore, the aim is to propose an outdoor image-based fresh fruit bunch (FFB) classification system, emphasising pre-processing technique and feature extraction techniques suitable for limited datasets. To achieve this, the FFB was localised within the original images using the YOLOv4-Tiny algorithm. Subsequently, a salient segmentation method utilising superpixel-based Fast Fuzzy C-means (FFCM) clustering is employed to remove the background from the images. Next, colour moment and opposite colour local binary pattern (OCLBP) features are extracted from the segmented images to capture important information for classification. Finally, the extracted features are fed into a Multilayer Perceptron (MLP) classifier, which enables the system to predict five classes: damaged, empty, unripe, ripe, and overripe. The developed system demonstrated a commendable performance in accurately classifying fruit bunches, achieving an accuracy of 93.68%. In conclusion, the proposed system effectively addresses the issue of unripe fruit harvesting and contributes to the advancement of state-of-the-art methods in classifying outdoor FFB images.

Conceptual Validation of High-Precision Fish Feeding Behavior Recognition Using Semantic Segmentation and Real-Time Temporal Variance Analysis for Aquaculture

Aquaculture plays an important role in the global economy. However, unscientific feeding methods often lead to problems such as feed waste and water pollution. This study aims to address this issue by accurately recognizing fish feeding behaviors to provide automatic bait casting machines with scientific feeding strategies, thereby reducing farming costs. We propose a fish feeding behavior recognition method based on semantic segmentation, which overcomes the limitations of existing methods in dealing with complex backgrounds, water splash interference, fish target overlapping, and real-time performance. In this method, we first accurately segment fish targets in the images using a semantic segmentation model. Then, these segmented images are input into our proposed fish feeding behavior recognition model. By analyzing the aggregation characteristics during the feeding process, we can identify fish feeding behaviors. Experiments show that the proposed method has excellent robustness and real-time performance, and it performs well in the case of complex water background and occlusion of fish targets. We provide the aquaculture industry with an efficient and reliable method for recognizing fish feeding behavior, offering new scientific support for intelligent aquaculture and delivering powerful solutions to improve aquaculture management and production efficiency. Although the algorithm proposed in this study has shown good performance in fish feeding behavior recognition, it requires certain lighting conditions and fish density, which may affect its adaptability in different environments. Future research could explore integrating multimodal data, such as sound information, to assist in judgment, thereby enhancing the robustness of the model and promoting the development of intelligent aquaculture.

An optimal deep learning approach for breast cancer detection and classification with pre-trained CNN-based feature learning mechanism

Breast cancer (BC) is the most dominant kind of cancer, which grows continuously and serves as the second highest cause of death for women worldwide. Early BC prediction helps decrease the BC mortality rate and improve treatment plans. Ultrasound is a popular and widely used imaging technique to detect BC at an earlier stage. Segmenting and classifying the tumors from ultrasound images is difficult. This paper proposes an optimal deep learning (DL)-based BC detection system with effective pre-trained transfer learning models-based segmentation and feature learning mechanisms. The proposed system comprises five phases: preprocessing, segmentation, feature learning, selection, and classification. Initially, the ultrasound images are collected from the breast ultrasound images (BUSI) dataset, and the preprocessing operations, such as noise removal using the Wiener filter and contrast enhancement using histogram equalization, are performed on the collected data to improve the dataset quality. Then, the segmentation of cancer-affected regions from the preprocessed data is done using a dilated convolution-based U-shaped network (DCUNet). The features are extracted or learned from the segmented images using spatial and channel attention including densely connected convolutional network-121 (SCADN-121). Afterwards, the system applies an enhanced cuckoo search optimization (ECSO) algorithm to select the features from the extracted feature set optimally. Finally, the ECSO-tuned long short-term memory (ECSO-LSTM) was utilized to classify BC into ‘3’ classes, such as normal, benign, and malignant. The experimental outcomes proved that the proposed system attains 99.86% accuracy for BC classification, which is superior to the existing state-of-the-art methods.

An intelligent model of pulmonary emphysema detection using adaptive image segmentation and multi-dilated densenet with attention mechanism

Pulmonary emphysema is a significant factor in lung cancer and Chronic Obstructive Pulmonary Disease (COPD). Traditional pulmonary emphysema detection models may have difficulty in accurately detecting and diagnosing the severity of the disease. So, this work developed a novel pulmonary emphysema detection system with the help of deep learning frameworks. Originally, the significant images are accumulated from the benchmark sources, and fed into the Adaptive Trans-DenseUnet (ATDUnet)-based segmentation model. The ATDUnet model is highly effective in accurately segmenting pulmonary emphysema from the gathered images. Moreover, to enhance the segmentation process, the parameters are tuned in the ATDUnet using the Statistical Solution of the Osprey Optimization Algorithm (SSOOA). Subsequently, the segmented image is given to the pulmonary emphysema classification phase, where the Multi-Dilated DenseNet with Attention Mechanism (MDDNet-AM) is employed. By incorporating an attention mechanism, MDDNet-AM can focus on important features within the image for improved accuracy and efficiency in diagnosis. Finally, the developed model offered the pulmonary emphysema classified outcome. Then, the outcome of the developed model is compared against conventional pulmonary emphysema detection methods, and given the accuracy to be 93.10. Therefore, the result proved that the use of developed advanced technology in pulmonary emphysema detection has shown promising results in the field of respiratory health.

Self-supervised learning on dual-sequence magnetic resonance imaging for automatic segmentation of nasopharyngeal carcinoma

Automating the segmentation of nasopharyngeal carcinoma (NPC) is crucial for therapeutic procedures but presents challenges given the hurdles in amassing extensively annotated datasets. Although previous studies have applied self-supervised learning to capitalize on unlabeled data to improve segmentation performance, these methods often overlooked the benefits of dual-sequence magnetic resonance imaging (MRI). In the present study, we incorporated self-supervised learning with a saliency transformation module using unlabeled dual-sequence MRI for accurate NPC segmentation. 44 labeled and 72 unlabeled patients were collected to develop and evaluate our network. Impressively, our network achieved a mean Dice similarity coefficient (DSC) of 0.77, which is consistent with a previous study that relied on a training set of 4,100 annotated cases. The results further revealed that our approach required minimal adjustments, primarily < 20% tweak in the DSC, to meet clinical standards. By enhancing the automatic segmentation of NPC, our method alleviates the annotation burden on oncologists, curbs subjectivity, and ensures reliable NPC delineation.

Accuracy of an nnUNet neural network for the automatic segmentation of intracranial aneurysms, their parent vessels and major cerebral arteries from magnetic resonance imaging-Time of flight (MRI-TOF).

To develop a new machine-learning algorithm for fully automatic identification of cerebral arteries and intracranial aneurysms (IAs) based on a manually segmented magnetic resonance imaging with time-of-flight sequences (MRITOF) dataset. In this retrospective single-center study, 62 MRI-TOF scans of a total of 73 untreated unruptured IAs were manually color-labelled in 21 classes. A nnUNet architecture was trained on MRI-TOF images. The performance of the automatic segmentation was compared with the manual segmentation using Dice Similarity Coefficient (DSC), Centerline Dice (ClDice) and 95th percentile Hausdorff Distance (HD95). Sensitivity was computed for aneurysm detection. Across all 21 classes, the median DSC was 0.86 [95CI: 0.81, 0.89], the median ClDice 0.91 [0.85, 0.94] and the median HD95 was 2.9 [1.0, 14.9] mm. Sensitivity of the model for aneurysms detection was 0.8. For this class specifically, a median DSC of 0.88 [0.13, 0.92], median ClDice of 0.89 [0.06, 1.0] and median HD95 of 1.8 [0.58, 81] mm was achieved. The volume of the labelled anatomical structure was the most relevant determinant of accuracy in this model. Median time to predict was 130.6 [60.9, 284.1] seconds. The nnUNet MRI-TOF based algorithm provided a fast and adequate automatic extraction of unruptured intracranial aneurysms, their parent vessels and the most relevant cerebral arteries. Future steps involve the expansion of the training set with the inclusion of more MRI-TOF studies with and without IAs and its incorporation in 3D imaging viewers and treatment prediction. IA = Intracranial Aneurysm; MRI-TOF＝ Magnetic Resonance Imaging - Time of Flight; DSC = Dice-Sørenson Coefficient; ClDice = Centerline Dice; HD95 = 95th Percentile Hausdorff Distance.

Computer-aided diagnosis of early-stage Retinopathy of Prematurity in neonatal fundus images using artificial intelligence

Retinopathy of Prematurity (ROP) is a retinal disorder affecting preterm babies, which can lead to permanent blindness without treatment. Early-stage ROP diagnosis is vital in providing optimal therapy for the neonates. The proposed study predicts early-stage ROP from neonatal fundus images using Machine Learning (ML) classifiers and Convolutional Neural Networks (CNN) based pre-trained networks. The characteristic demarcation lines and ridges in early stage ROP are segmented utilising a novel Swin U-Net. 2000 Scale Invariant Feature Transform (SIFT) descriptors were extracted from the segmented ridges and are dimensionally reduced to 50 features using Principal Component Analysis (PCA). Seven ROP-specific features, including six Gray Level Co-occurrence Matrix (GLCM) and ridge length features, are extracted from the segmented image and are fused with the PCA reduced 50 SIFT features. Finally, three ML classifiers, such as Support Vector Machine (SVM), Random Forest (RF), andk- Nearest Neighbor (k-NN), are used to classify the 50 features to predict the early-stage ROP from Normal images. On the other hand, the raw retinal images are classified directly into normal and early-stage ROP using six pre-trained classifiers, namely ResNet50, ShuffleNet V2, EfficientNet, MobileNet, VGG16, and DarkNet19. It is seen that the ResNet50 network outperformed all other networks in predicting early-stage ROP with 89.5% accuracy, 87.5% sensitivity, 91.5% specificity, 91.1% precision, 88% NPV and an Area Under the Curve (AUC) of 0.92. Swin U-Net Convolutional Neural Networks (CNN) segmented the ridges and demarcation lines with an accuracy of 89.7% with 80.5% precision, 92.6% recall, 75.76% IoU, and 0.86 as the Dice coefficient. The SVM classifier using the 57 features from the segmented images achieved a classification accuracy of 88.75%, sensitivity of 90%, specificity of 87.5%, and an AUC of 0.91. The system can be utilised as a point-of-care diagnostic tool for ROP diagnosis of neonates in remote areas.

Drivable path detection for a mobile robot with differential drive using a deep Learning based segmentation method for indoor navigation

The integration of artificial intelligence into the field of robotics enables robots to perform their tasks more meaningfully. In particular, deep-learning methods contribute significantly to robots becoming intelligent cybernetic systems. The effective use of deep-learning mobile cyber-physical systems has enabled mobile robots to become more intelligent. This effective use of deep learning can also help mobile robots determine a safe path. The drivable pathfinding problem involves a mobile robot finding the path to a target in a challenging environment with obstacles. In this paper, a semantic-segmentation-based drivable path detection method is presented for use in the indoor navigation of mobile robots. The proposed method uses a perspective transformation strategy based on transforming high-accuracy segmented images into real-world space. This transformation enables the motion space to be divided into grids, based on the image perceived in a real-world space. A grid-based RRT* navigation strategy was developed that uses images divided into grids to enable the mobile robot to avoid obstacles and meet the optimal path requirements. Smoothing was performed to improve the path planning of the grid-based RRT* and avoid unnecessary turning angles of the mobile robot. Thus, the mobile robot could reach the target in an optimum manner in the drivable area determined by segmentation. Deeplabv3+ and ResNet50 backbone architecture with superior segmentation ability are proposed for accurate determination of drivable path. Gaussian filter was used to reduce the noise caused by segmentation. In addition, multi-otsu thresholding was used to improve the masked images in multiple classes. The segmentation model and backbone architecture were compared in terms of their performance using different methods. DeepLabv3+ and ResNet50 backbone architectures outperformed the other compared methods by 0.21%–4.18% on many metrics. In addition, a mobile robot design is presented to test the proposed drivable path determination method. This design validates the proposed method by using different scenarios in an indoor environment.

Fine-tuning pre-trained networks with emphasis on image segmentation: A multi-network approach for enhanced breast cancer detection

Accurate classification of mammography images into normal and cancerous categories is critical for the early detection of breast cancer. This study utilizes transfer learning and deep learning models to extract and diversify features from a combined dataset consisting of the Mini Digital Database for Screening Mammography (DDSM, containing 7808 images) and the Mammographic Image Analysis Society (MIAS) dataset (containing 322 images). The preprocessing steps involve image cropping, removal of artifacts, and enhancement of contrast using Contrast-Limited Adaptive Histogram Equalization (CLAHE). Data augmentation techniques, including the application of median and Gaussian blur, were used to improve the robustness of the models. Three pre-trained networks—Residual Networks with 50 layers (ResNet-50), Visual Geometry Group Network with 19 layers (VGG-19), and Residual Networks with 152 layers Version 2 (ResNet-152V2)—were fine-tuned specifically for mammography data. Image segmentation and the removal of the pectoral muscle significantly improved classification accuracy. The VGG-19 model achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.80 for segmented images and 0.86 for non-segmented images. A stacked generalization model, which combined features from all three networks, further optimized performance. Artificial Neural Network (ANN) and Extreme Gradient Boosting (XGBoost) models achieved AUCs of 0.897 and 0.890, respectively, for segmented images. Data augmentation improved performance by 2.7%–4%.

A hybrid EfficientNet-DbneAlexnet for brain tumor detection using MRI images

The rapid growth of abnormal cells in the brain presents a serious risk to the health of humans as it can result in death. Since these tumors have a varied range of shapes, sizes, and positions, identifying Brain Tumors (BTs) is challenging. Magnetic Resonance Images (MRI) are most utilized for identifying malignant tumors. This paper develops a new approach, named EfficientNet-Deep batch normalized eLUAlexnet (EfficientNet-DbneAlexnet) for detecting BTs. Firstly, the input MRI image is transmitted for image enhancement. Here, the image is enhanced by the Piecewise Linear Transformation (PLT). After this, skull stripping is carried out, which is performed by the Fuzzy Local Information C Means (FLICM). Following this, the tumor area in the image is segmented with the help of a Projective Adversarial Network (PAN). The segmented image is later applied to the feature extraction module, wherein features like textural and statistical features are extracted. Finally, the BT detection is accomplished using the developed EfficientNet-DbneAlexnet, which is created by assimilating EfficientNet and Deep batch normalized eLUAlexnet (DbneAlexnet). The results demonstrate that EfficientNet-DbneAlexnet obtained a sensitivity of 90.36 %, accuracy of 92.77 %, and specificity of 91.82 %.

A Transformer-based Semantic-Aware U-Net Model for Improving in Endometrial Cancer Detection

The rise in Endometrial Cancer (EC) necessitates early diagnosis using medical imaging. Deep learning models have been developed to address misdiagnosis, but their accuracy is limited by small-scale datasets. To address this issue, a new Deep EC Prediction (DeepECP) model, combining Feature Entanglement Generative Adversarial Network (FE-GAN) and multimodal Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM), has been designed to generate synthetic MRI images and detect EC stages. However, precise identification and categorization of various EC stages require the segmentation of MRI scans. While the U-Net model is frequently used for this task, it has constraints in capturing long-range relationships. Other models, like Transformers with self-attention mechanisms may not have strong low-level localization capabilities. Hence, this paper introduces a Transformer-based Semantic-Aware U-Net (TSA-UNet) model with DeepECP for segmenting and classifying EC stages in MRI scans. The TSA-UNet model combines Transformer and U-Net structures, consisting of encoder, fusion, and decoder units. The encoder is a CNN-Transformer that captures multilevel bitemporal features and encodes tokenized sequences to get high-level features. The Transformer unit uses Semantic Guidance Attention (SGA) to enhance feature discrimination and reduce semantic gaps. An Adaptive Cross-Fusion (ACF) unit merges bitemporal features, and a Cascaded Upsampling Decoder (CUD) combines low-level CNN and high-level Transformer characteristics to localize and segment EC stages in MRI scans. The segmented images are then inputted to the DeepECP model for classification. Finally, the experimental outcomes reveal that the TSA-UNet-DeepECP attains higher efficiency than conventional models for segmentation and classification of EC from MRI images.