Architecture For Segmentation Research Articles

HiSEG: Human assisted instance segmentation

Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is often beyond the reach of what even state-of-the-art, fully automated instance segmentation algorithms can deliver. The performance gap becomes particularly prohibitive for small and complex objects. Practitioners typically resort to fully manual annotation, which can be a laborious process. In order to overcome this problem, we propose a novel approach to enable more precise predictions and generate higher-quality segmentation masks for high-curvature, complex and small-scale objects. Our human-assisted segmentation method, HiSEG, augments the existing Strong Mask R-CNN network to incorporate human-specified partial boundaries. We also present a dataset of hand-drawn partial object boundaries, which we refer to as “human attention maps”. In addition, the Partial Sketch Object Boundaries (PSOB) dataset contains hand-drawn partial object boundaries which represent curvatures of an object’s ground truth mask with several pixels. Through extensive evaluation using the PSOB dataset, we show that HiSEG outperforms state-of-the art methods such as Mask R-CNN, Strong Mask R-CNN, Mask2Former, and Segment Anything, achieving respective increases of +42.0, +34.9, +29.9, and +13.4 points in APMask metrics for these four models. We hope that our novel approach will set a baseline for future human-aided deep learning models by combining fully automated and interactive instance segmentation architectures.

Semantic Segmentation in Large-Size Orthomosaics to Detect the Vegetation Area in Opuntia spp. Crop.

This study focuses on semantic segmentation in crop Opuntia spp. orthomosaics; this is a significant challenge due to the inherent variability in the captured images. Manual measurement of Opuntia spp. vegetation areas can be slow and inefficient, highlighting the need for more advanced and accurate methods. For this reason, we propose to use deep learning techniques to provide a more precise and efficient measurement of the vegetation area. Our research focuses on the unique difficulties posed by segmenting high-resolution images exceeding 2000 pixels, a common problem in generating orthomosaics for agricultural monitoring. The research was carried out on a Opuntia spp. cultivation located in the agricultural region of Tulancingo, Hidalgo, Mexico. The images used in this study were obtained by drones and processed using advanced semantic segmentation architectures, including DeepLabV3+, UNet, and UNet Style Xception. The results offer a comparative analysis of the performance of these architectures in the semantic segmentation of Opuntia spp., thus contributing to the development and improvement of crop analysis techniques based on deep learning. This work sets a precedent for future research applying deep learning techniques in agriculture.

Image-level supervision and self-training for transformer-based cross-modality tumor segmentation

Deep neural networks are commonly used for automated medical image segmentation, but models will frequently struggle to generalize well across different imaging modalities. This issue is particularly problematic due to the limited availability of annotated data, both in the target as well as the source modality, making it difficult to deploy these models on a larger scale. To overcome these challenges, we propose a new semi-supervised training strategy called MoDATTS. Our approach is designed for accurate cross-modality 3D tumor segmentation on unpaired bi-modal datasets. An image-to-image translation strategy between modalities is used to produce synthetic but annotated images and labels in the desired modality and improve generalization to the unannotated target modality. We also use powerful vision transformer architectures for both image translation (TransUNet) and segmentation (Medformer) tasks and introduce an iterative self-training procedure in the later task to further close the domain gap between modalities, thus also training on unlabeled images in the target modality. MoDATTS additionally allows the possibility to exploit image-level labels with a semi-supervised objective that encourages the model to disentangle tumors from the background. This semi-supervised methodology helps in particular to maintain downstream segmentation performance when pixel-level label scarcity is also present in the source modality dataset, or when the source dataset contains healthy controls. The proposed model achieves superior performance compared to other methods from participating teams in the CrossMoDA 2022 vestibular schwannoma (VS) segmentation challenge, as evidenced by its reported top Dice score of 0.87±0.04 for the VS segmentation. MoDATTS also yields consistent improvements in Dice scores over baselines on a cross-modality adult brain gliomas segmentation task composed of four different contrasts from the BraTS 2020 challenge dataset, where 95% of a target supervised model performance is reached when no target modality annotations are available. We report that 99% and 100% of this maximum performance can be attained if 20% and 50% of the target data is additionally annotated, which further demonstrates that MoDATTS can be leveraged to reduce the annotation burden.

Overcoming Remote Workforce Cyber Threats: A Comprehensive Ransomware and Bot Net Defense Strategy Utilizing VPN Networks

This study investigates endpoint security strategies for remote workforces utilizing VPN networks, focusing on mitigating ransomware and botnet attacks. A mixed-methods approach was employed, analyzing the effectiveness of existing endpoint solutions and simulating network segmentation strategies. The study highlights the enhanced effectiveness of traditional endpoint security solutions when augmented with advanced technologies with specific applications including email filtering to block phishing attempts, MFA to verify user identities, EDR systems to detect and block unauthorized access tools, and encryption to secure data during cloud services. The introduction of network segmentation and zero-trust architectures further secured data centers by limiting lateral movements and requiring continuous re-authentication. Results demonstrate that while traditional endpoint security solutions remain essential, their effectiveness can be enhanced through a multi-layered approach incorporating advanced technologies with this research showing quick response times, high containment efficiency, and fast recovery speeds across all segments, with the Finance Department notably achieving a response time of 5 minutes and containment efficiency of 95%. Specifically, our cost-benefit analysis of network segmentation strategies shows that Strategy 1, despite a higher cost, offers superior improvements in throughput and latency reduction, providing more value per dollar spent. These results underscore the plan’s capability in rapidly detecting, containing, and recovering from attacks. User education significantly improved cybersecurity awareness and reduced susceptibility to attacks. This research provides practical recommendations for organizations to strengthen their endpoint security posture and protect their remote workforce through a combination of advanced technologies, proactive measures, and continuous user education.

DeMambaNet: Deformable Convolution and Mamba Integration Network for High-Precision Segmentation of Ambiguously Defined Dental Radicular Boundaries.

The incorporation of automatic segmentation methodologies into dental X-ray images refined the paradigms of clinical diagnostics and therapeutic planning by facilitating meticulous, pixel-level articulation of both dental structures and proximate tissues. This underpins the pillars of early pathological detection and meticulous disease progression monitoring. Nonetheless, conventional segmentation frameworks often encounter significant setbacks attributable to the intrinsic limitations of X-ray imaging, including compromised image fidelity, obscured delineation of structural boundaries, and the intricate anatomical structures of dental constituents such as pulp, enamel, and dentin. To surmount these impediments, we propose the Deformable Convolution and Mamba Integration Network, an innovative 2D dental X-ray image segmentation architecture, which amalgamates a Coalescent Structural Deformable Encoder, a Cognitively-Optimized Semantic Enhance Module, and a Hierarchical Convergence Decoder. Collectively, these components bolster the management of multi-scale global features, fortify the stability of feature representation, and refine the amalgamation of feature vectors. A comparative assessment against 14 baselines underscores its efficacy, registering a 0.95% enhancement in the Dice Coefficient and a diminution of the 95th percentile Hausdorff Distance to 7.494.

MGB-Unet: An Improved Multiscale Unet with Bottleneck Transformer for Myositis Segmentation from Ultrasound Images.

Myositis is the inflammation of the muscles that can arise from various sources with diverse symptoms and require different treatments. For treatment to achieve optimal results, it is essential to obtain an accurate diagnosis promptly. This paper presents a new supervised segmentation architecture that can efficiently perform precise segmentation and classification of myositis from ultrasound images with few computational resources. The architecture of our model includes a unique encoder-decoder structure that integrates the Bottleneck Transformer (BOT) with a newly developed Residual block named Multi-Conv Ghost switchable bottleneck Residual Block (MCG_RB). This block effectively captures and analyzes ultrasound image input inside the encoder segment at several resolutions. Moreover, the BOT module is a transformer-style attention module designed to bridge the feature gap between the encoding and decoding stages. Furthermore, multi-level features are retrieved using the MCG-RB module, which combines multi-convolution with ghost switchable residual connections of convolutions for both the encoding and decoding stages. The suggested method attains state-of-the-art performance on a benchmark set of myositis ultrasound images across all parameters, including accuracy, precision, recall, dice coefficient, and Jaccard index. Despite its limited training data, the suggested approach demonstrates remarkable generalizability by yielding exceptional results. The proposed model showed a substantial enhancement in accuracy when compared to segmentation state-of-the-art methods such as Unet++, DeepLabV3, and the Duck-Net. The dice coefficient and Jaccard index obtained improvements of up to 3%, 6%, and 7%, respectively, surpassing the other methods.

Deep Learning-Based Localization and Detection of Malpositioned Nasogastric Tubes on Portable Supine Chest X-Rays in Intensive Care and Emergency Medicine: A Multi-center Retrospective Study.

Malposition of a nasogastric tube (NGT) can lead to severe complications. We aimed to develop a computer-aided detection (CAD) system to localize NGTs and detect NGT malposition on portable chest X-rays (CXRs). A total of 7378 portable CXRs were retrospectively retrieved from two hospitals between 2015 and 2020. All CXRs were annotated with pixel-level labels for NGT localization and image-level labels for NGT presence and malposition. In the CAD system, DeepLabv3 + with backbone ResNeSt50 and DenseNet121 served as the model architecture for segmentation and classification models, respectively. The CAD system was tested on images from chronologically different datasets (National Taiwan University Hospital (National Taiwan University Hospital)-20), geographically different datasets (National Taiwan University Hospital-Yunlin Branch (YB)), and the public CLiP dataset. For the segmentation model, the Dice coefficients indicated accurate delineation of the NGT course (National Taiwan University Hospital-20: 0.665, 95% confidence interval (CI) 0.630-0.696; National Taiwan University Hospital-Yunlin Branch: 0.646, 95% CI 0.614-0.678). The distance between the predicted and ground-truth NGT tips suggested accurate tip localization (National Taiwan University Hospital-20: 1.64 cm, 95% CI 0.99-2.41; National Taiwan University Hospital-Yunlin Branch: 2.83 cm, 95% CI 1.94-3.76). For the classification model, NGT presence was detected with high accuracy (area under the receiver operating characteristic curve (AUC): National Taiwan University Hospital-20: 0.998, 95% CI 0.995-1.000; National Taiwan University Hospital-Yunlin Branch: 0.998, 95% CI 0.995-1.000; CLiP dataset: 0.991, 95% CI 0.990-0.992). The CAD system also detected NGT malposition with high accuracy (AUC: National Taiwan University Hospital-20: 0.964, 95% CI 0.917-1.000; National Taiwan University Hospital-Yunlin Branch: 0.991, 95% CI 0.970-1.000) and detected abnormal nasoenteric tube positions with favorable performance (AUC: 0.839, 95% CI 0.807-0.869). The CAD system accurately localized NGTs and detected NGT malposition, demonstrating excellent potential for external generalizability.

Enhancing brain tumor segmentation in MRI images using the IC-net algorithm framework

Brain tumors, often referred to as intracranial tumors, are abnormal tissue masses that arise from rapidly multiplying cells. During medical imaging, it is essential to separate brain tumors from healthy tissue. The goal of this paper is to improve the accuracy of separating tumorous regions from healthy tissues in medical imaging, specifically for brain tumors in MRI images which is difficult in the field of medical image analysis. In our research work, we propose IC-Net (Inverted-C), a novel semantic segmentation architecture that combines elements from various models to provide effective and precise results. The architecture includes Multi-Attention (MA) blocks, Feature Concatenation Networks (FCN), Attention-blocks which performs crucial tasks in improving brain tumor segmentation. MA-block aggregates multi-attention features to adapt to different tumor sizes and shapes. Attention-block is focusing on key regions, resulting in more effective segmentation in complex images. FCN-block captures diverse features, making the model more robust to various characteristics of brain tumor images. Our proposed architecture is used to accelerate the training process and also to address the challenges posed by the diverse nature of brain tumor images, ultimately leads to potentially improved segmentation performance. IC-Net significantly outperforms the typical U-Net architecture and other contemporary effective segmentation techniques. On the BraTS 2020 dataset, our IC-Net design obtained notable outcomes in Accuracy, Loss, Specificity, Sensitivity as 99.65, 0.0159, 99.44, 99.86 and DSC (core, whole, and enhancing tumors as 0.998717, 0.888930, 0.866183) respectively.

Accurate segmentation of liver tumor from multi-modality non-contrast images using a dual-stream multi-level fusion framework

The use of multi-modality non-contrast images (i.e., T1FS, T2FS and DWI) for segmenting liver tumors provides a solution by eliminating the use of contrast agents and is crucial for clinical diagnosis. However, this remains a challenging task to discover the most useful information to fuse multi-modality images for accurate segmentation due to inter-modal interference. In this paper, we propose a dual-stream multi-level fusion framework (DM-FF) to, for the first time, accurately segment liver tumors from non-contrast multi-modality images directly. Our DM-FF first designs an attention-based encoder–decoder to effectively extract multi-level feature maps corresponding to a specified representation of each modality. Then, DM-FF creates two types of fusion modules, in which a module fuses learned features to obtain a shared representation across multi-modality images to exploit commonalities and improve the performance, and a module fuses the decision evidence of segment to discover differences between modalities to prevent interference caused by modality’s conflict. By integrating these three components, DM-FF enables multi-modality non-contrast images to cooperate with each other and enables an accurate segmentation. Evaluation on 250 patients including different types of tumors from two MRI scanners, DM-FF achieves a Dice of 81.20%, and improves performance (Dice by at least 11%) when comparing the eight state-of-the-art segmentation architectures. The results indicate that our DM-FF significantly promotes the development and deployment of non-contrast liver tumor technology.

Deep Learning-Based Real-Time Ureter Identification in Laparoscopic Colorectal Surgery.

Iatrogenic ureteral injury is a serious complication of abdominopelvic surgery. Identifying the ureters intraoperatively is essential to avoid iatrogenic ureteral injury. We developed a model that may minimize this complication. We applied a deep learning-based semantic segmentation algorithm to the ureter recognition task and developed a deep learning model called UreterNet. This study aimed to verify whether the ureters could be identified in videos of laparoscopic colorectal surgery. Semantic segmentation of the ureter area was performed using a convolutional neural network-based approach. Feature Pyramid Networks were used as the convolutional neural network architecture for semantic segmentation. Precision, recall, and the Dice coefficient were used as the evaluation metrics in this study. We created 14,069 annotated images from 304 videos, with 9537, 2266, and 2266 images in the training, validation, and test data sets, respectively. Concerning ureter recognition performance, the precision, recall, and Dice coefficient for the test data were 0.712, 0.722, and 0.716, respectively. Regarding the real-time performance on recorded videos, it took 71 milliseconds for UreterNet to infer all pixels corresponding to the ureter from a single still image and 143 milliseconds to output and display the inferred results as a segmentation mask on the laparoscopic monitor. UreterNet is a noninvasive method for identifying the ureter in videos of laparoscopic colorectal surgery and can potentially improve surgical safety. Although this deep learning model could lead to the development of an image-navigated surgical system, it is necessary to verify whether UreterNet reduces the occurrence of iatrogenic ureteral injury.

Improving Deep Learning-Based Algorithm for Ploidy Status Prediction Through Combined U-NET Blastocyst Segmentation and Sequential Time-Lapse Blastocysts Images.

Several approaches have been proposed to optimize the construction of an artificial intelligence-based model for assessing ploidy status. These encompass the investigation of algorithms, refining image segmentation techniques, and discerning essential patterns throughout embryonic development. The purpose of the current study was to evaluate the effectiveness of using U-NET architecture for embryo segmentation and time-lapse embryo image sequence extraction, three and ten hr before biopsy to improve model accuracy for prediction of embryonic ploidy status. A total of 1.020 time-lapse videos of blastocysts with known ploidy status were used to construct a convolutional neural network (CNN)-based model for ploidy detection. Sequential images of each blastocyst were extracted from the time-lapse videos over a period of three and ten hr prior to the biopsy, generating 31.642 and 99.324 blastocyst images, respectively. U-NET architecture was applied for blastocyst image segmentation before its implementation in CNN-based model development. The accuracy of ploidy prediction model without applying the U-NET segmented sequential embryo images was 0.59 and 0.63 over a period of three and ten hr before biopsy, respectively. Improved model accuracy of 0.61 and 0.66 was achieved, respectively with the implementation of U-NET architecture for embryo segmentation on the current model. Extracting blastocyst images over a 10 hr period yields higher accuracy compared to a three-hr extraction period prior to biopsy. Combined implementation of U-NET architecture for blastocyst image segmentation and the sequential compilation of ten hr of time-lapse blastocyst images could yield a CNN-based model with improved accuracy in predicting ploidy status.

Image semantic segmentation of indoor scenes: A survey

This survey provides a comprehensive evaluation of various deep learning-based segmentation architectures. It covers a wide range of models, from traditional ones like FCN and PSPNet to more modern approaches like SegFormer and FAN. In addition to assessing the methods in terms of segmentation accuracy, we propose to also evaluate the methods in terms of temporal consistency and corruption vulnerability. Most of the existing surveys on semantic segmentation focus on outdoor datasets. In contrast, this survey focuses on indoor scenarios to enhance the applicability of segmentation methods in this specific domain. Furthermore, our evaluation consists of a performance analysis of the methods in prevalent real-world segmentation scenarios that pose particular challenges. These complex situations involve scenes impacted by diverse forms of noise, blur corruptions, camera movements, optical aberrations, among other factors. By jointly exploring the segmentation accuracy, temporal consistency, and corruption vulnerability in challenging real-world situations, our survey offers insights that go beyond existing surveys, facilitating the understanding and development of better image segmentation methods for indoor scenes.

Towards Metric-Driven Difference Detection between Receptive and Nonreceptive Endometrial Samples Using Automatic Histology Image Analysis

This paper presents a technique that can potentially help to determine the receptivity stage of the endometrium from histology images by automatically measuring the stromal nuclear changes. The presented technique is composed of an image segmentation model and the statistical evolution of segmented areas in hematoxylin and eosin (HE)-stained histology images. Three different endometrium receptivity stages, namely pre-receptive, post-receptive, and receptive, were compared. An ensemble-based AI model was proposed for histology image segmentation, which is based on individual UNet++, UNet, and ResNet34-UNet segmentation models. The performance of the ensemble-based technique was assessed using the Dice score and intersection over unit (IoU) values. In comparison to alternative segmentation architectures that were applied singly, the current ensemble-based method obtained higher Dice score (0.95) and IoU (0.90) values. The statistical comparison highlighted a noticeable difference in the number of nuclei and the size of the stroma tissue. The proposed technique demonstrated the positive potential for practical implementation for automatic endometrial tissue analysis.

P2AT: Pyramid pooling axial transformer for real-time semantic segmentation

Recently, Transformer-based models have achieved promising results in various vision tasks, due to their ability to model long-range dependencies. However, transformers are computationally expensive, which limits their applications in real-time tasks such as autonomous driving. In addition, efficient local and global feature selection and fusion are vital for accurate dense prediction, especially driving scene understanding tasks. In this paper, we propose a real-time semantic segmentation architecture named Pyramid Pooling Axial Transformer (P2AT). The proposed P2AT takes a coarse feature from the CNN encoder to produce scale-aware contextual features, which are then combined with the multi-level feature aggregation scheme to produce enhanced contextual features. Specifically, we introduce a pyramid pooling axial transformer to capture intricate spatial and channel dependencies, leading to improved performance on semantic segmentation. Then, we design a Bidirectional Fusion module (BiF) to combine semantic information at different levels. Meanwhile, a Global Context Enhancer (GCE) is introduced to compensate for the inadequacy of concatenating different semantic levels. Finally, a decoder block is proposed to help maintain a larger receptive field. We evaluate P2AT variants on three challenging scene-understanding datasets. In particular, our P2AT variants achieve state-of-art results on the Camvid dataset 80.5%, 81.0%, 81.1% for P2AT-S, P2AT-M, and P2AT-L, respectively. Furthermore, our experiments on Cityscapes and Pascal VOC 2012 have demonstrated the efficiency of the proposed architecture. The source code will be available at https://github.com/mohamedac29/P2AT.

Dominant Color Detection For Online Fashion Retrievals

This paper introduces a novel approach aimed at efficiently extracting dominant colors from online fashion images. The method addresses challenges related to detecting overlapping objects and computationally expensive methods by combining K-means clustering and graph-cut techniques into a framework. This framework incorporates an adaptive weighting strategy to enhance color extraction accuracy. Additionally, it introduces a two-phase fashion apparel detection method called YOLOv4, which utilizes U-Net architecture for clothing segmentation to precisely separate clothing items from the background or other elements. Experimental results show that K-means with YOLOv4 outperforms K-means with the U-Net model. These findings suggest that the U-Net architecture and YOLOv4 models can be effective methods for complex image segmentation tasks in online fashion retrieval and image processing, particularly in the rapidly evolving e-commerce environment.

Multichannel Sandstone Thin Sections Identification Based on Improved DeepLab V3 Plus Neural Network.

As an unconventional natural gas resource, tight sandstone gas is primarily stored in the minuscule pores between rocky sand grains. A thorough understanding of the pore structure characteristics of tight sandstone reservoirs is essential for formulating an extraction plan and enhancing the efficiency of gas field development. The pore structure and mineral composition in the sandstone can be directly observed by thin sections. Nevertheless, previous approaches for the automated identification of sandstone thin sections exhibit certain limitations including slow identification, low accuracy, and challenges in the recognition of particle sizes. To achieve more accurate and convenient mineral component identification, this study introduces a multichannel identification method built upon the enhanced DeepLab V3 Plus model. Initially, all 224 × 224 × 3 cross-polarized light (CPL) and orthogonal polarized light (XPL) sandstone thin sections were amalgamated into 224 × 224 × 6 multichannel (six channels) images. Subsequently, multiple networks were employed to train the three polarized data sets, and the optimal semantic segmentation architecture and data set were selected through filtering. Following that, embedding the attention mechanism into the semantic segmentation network enhanced the identification accuracy. Ultimately, mineral sizes were calculated to enable more precise classification and naming of sandstone thin sections. The results show that the new method outperforms in terms of recognition accuracy, achieving 89.8% for Mean PA and 81.2% for Mean IOU. The novel approach's enhanced level of detailing enables more precise identification of mineral composition and pore structure, a crucial aspect in evaluating reservoirs and predicting oil and gas production. It can also provide new insights into identifying and categorizing other thin sections with similar compositions.

Automated end-to-end Architecture for Retinal Layers and Fluids Segmentation on OCT B-scans

Automated end-to-end Architecture for Retinal Layers and Fluids Segmentation on OCT B-scans

Utilization of artificial intelligence in minimally invasive right adrenalectomy: recognition of anatomical landmarks with deep learning

Background The primary surgical approach for removing adrenal masses is minimally invasive adrenalectomy. Recognition of anatomical landmarks during surgery is critical for minimizing complications. Artificial intelligence-based tools can be utilized to create real-time navigation systems during laparoscopic and robotic right adrenalectomy. In this study, we aimed to develop deep learning models that can identify critical anatomical structures during minimally invasive right adrenalectomy. Methods In this experimental feasibility study, intraoperative videos of 20 patients who underwent minimally invasive right adrenalectomy in a tertiary care center between 2011 and 2023 were analyzed and used to develop an artificial intelligence-based anatomical landmark recognition system. Semantic segmentation of the liver, the inferior vena cava (IVC), and the right adrenal gland were performed. Fifty random images per patient during the dissection phase were extracted from videos. The experiments on the annotated images were performed on two state-of-the-art segmentation models named SwinUNETR and MedNeXt, which are transformer and convolutional neural network (CNN)-based segmentation architectures, respectively. Two loss function combinations, Dice-Cross Entropy and Dice-Focal Loss were experimented with for both of the models. The dataset was split into training and validation subsets with an 80:20 distribution on a patient basis in a 5-fold cross-validation approach. To introduce a sample variability to the dataset, strong-augmentation techniques were performed using intensity modifications and perspective transformations to represent different surgery environment scenarios. The models were evaluated by Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) which are widely used segmentation metrics. For pixelwise classification performance, accuracy, sensitivity and specificity metrics were calculated on the validation subset. Results Out of 20 videos, 1000 images were extracted, and the anatomical landmarks (liver, IVC, and right adrenal gland) were annotated. Randomly distributed 800 images and 200 images were selected for the training and validation subsets, respectively. Our benchmark results show that the utilization of Dice-Cross Entropy Loss with the transformer-based SwinUNETR model achieved 78.37%, whereas the CNN-based MedNeXt model reached a 77.09% mDSC score. Conversely, MedNeXt reaches a higher mIoU score of 63.71% than SwinUNETR by 62.10% on a three-region prediction task. Conclusion Artificial intelligence-based systems can predict anatomical landmarks with high performance in minimally invasive right adrenalectomy. Such tools can later be used to create real-time navigation systems during surgery in the near future.

NnSegNeXt: A 3D Convolutional Network for Brain Tissue Segmentation Based on Quality Evaluation.

Accurate and automated segmentation of brain tissue images can significantly streamline clinical diagnosis and analysis. Manual delineation needs improvement due to its laborious and repetitive nature, while automated techniques encounter challenges stemming from disparities in magnetic resonance imaging (MRI) acquisition equipment and accurate labeling. Existing software packages, such as FSL and FreeSurfer, do not fully replace ground truth segmentation, highlighting the need for an efficient segmentation tool. To better capture the essence of cerebral tissue, we introduce nnSegNeXt, an innovative segmentation architecture built upon the foundations of quality assessment. This pioneering framework effectively addresses the challenges posed by missing and inaccurate annotations. To enhance the model's discriminative capacity, we integrate a 3D convolutional attention mechanism instead of conventional convolutional blocks, enabling simultaneous encoding of contextual information through the incorporation of multiscale convolutional features. Our methodology was evaluated on four multi-site T1-weighted MRI datasets from diverse sources, magnetic field strengths, scanning parameters, temporal instances, and neuropsychiatric conditions. Empirical evaluations on the HCP, SALD, and IXI datasets reveal that nnSegNeXt surpasses the esteemed nnUNet, achieving Dice coefficients of 0.992, 0.987, and 0.989, respectively, and demonstrating superior generalizability across four distinct projects with Dice coefficients ranging from 0.967 to 0.983. Additionally, extensive ablation studies have been implemented to corroborate the effectiveness of the proposed model. These findings represent a notable advancement in brain tissue analysis, suggesting that nnSegNeXt holds the promise to significantly refine clinical workflows.

Construction of Three-Dimensional Semantic Maps of Unstructured Lawn Scenes Based on Deep Learning

Traditional automatic gardening pruning robots generally employ electronic fences for the delineation of working boundaries. In order to quickly determine the working area of a robot, we combined an improved DeepLabv3+ semantic segmentation model with a simultaneous localization and mapping (SLAM) system to construct a three-dimensional (3D) semantic map. To reduce the computational cost of its future deployment in resource-constrained mobile robots, we replaced the backbone network of DeepLabv3+, ResNet50, with MobileNetV2 to decrease the number of network parameters and improve recognition speed. In addition, we introduced an efficient channel attention network attention mechanism to enhance the accuracy of the neural network, forming an improved Multiclass MobileNetV2 ECA DeepLabv3+ (MM-ED) network model. Through the integration of this model with the SLAM system, the entire framework was able to generate a 3D semantic point cloud map of a lawn working area and convert it into octree and occupancy grid maps, providing technical support for future autonomous robot operation and navigation. We created a lawn dataset containing 7500 images, using our own annotated images as ground truth. This dataset was employed for experimental purposes. Experimental results showed that the proposed MM-ED network model achieved 91.07% and 94.71% for MIoU and MPA metrics, respectively. Using a GTX 3060 Laptop GPU, the frames per second rate reached 27.69, demonstrating superior recognition performance compared to similar semantic segmentation architectures and better adaptation to SLAM systems.