Segmentation Benchmark Research Articles

DDNet: Depth Dominant Network for Semantic Segmentation of RGB-D Images

Convolutional neural networks (CNNs) have been widely applied to parse indoor scenes and segment objects represented by color images. Nonetheless, the lack of geometric and context information is a problem for most RGB-based methods, with which depth features are only used as an auxiliary module in RGB-D semantic segmentation. In this study, a novel depth dominant network (DDNet) is proposed to fully utilize the rich context information in the depth map. The critical insight is that obvious geometric information from the depth image is more conducive to segmentation than RGB data. Compared with other methods, DDNet is a depth-based network with two branches of CNNs to extract color and depth features. As the core of the encoder network, the depth branch is given a larger fusion weight to extract geometric information, while semantic information and complementary geometric information are provided by the color branch for the depth feature maps. The effectiveness of our proposed depth-based architecture has been demonstrated by comprehensive experimental evaluations and ablation studies on challenging RGB-D semantic segmentation benchmarks, including NYUv2 and a subset of ScanNetv2.

Highlighted Diffusion Model as Plug-in Priors for Polyp Segmentation.

Automated polyp segmentation from colonoscopy images is crucial for colorectal cancer diagnosis. The accuracy of such segmentation, however, is challenged by two main factors. First, the variability in polyps' size, shape, and color, coupled with the scarcity of well-annotated data due to the need for specialized manual annotation, hampers the efficacy of existing deep learning methods. Second, concealed polyps often blend with adjacent intestinal tissues, leading to poor contrast that challenges segmentation models. Recently, diffusion models have been explored and adapted for polyp segmentation tasks. However, the significant domain gap between RGB-colonoscopy images and grayscale segmentation masks, along with the low efficiency of the diffusion generation process, hinders the practical implementation of these models. To mitigate these challenges, we introduce the Highlighted Diffusion Model Plus (HDM+), a two-stage polyp segmentation framework. This framework incorporates the Highlighted Diffusion Model (HDM) to provide explicit semantic guidance, thereby enhancing segmentation accuracy. In the initial stage, the HDM is trained using highlighted ground-truth data, which emphasizes polyp regions while suppressing the background in the images. This approach reduces the domain gap by focusing on the image itself rather than on the segmentation mask. In the subsequent second stage, we employ the highlighted features from the trained HDM's U-Net model as plug-in priors for polyp segmentation, rather than generating highlighted images, thereby increasing efficiency. Extensive experiments conducted on six polyp segmentation benchmarks demonstrate the effectiveness of our approach.

AeroPath: An airway segmentation benchmark dataset with challenging pathology and baseline method.

To improve the prognosis of patients suffering from pulmonary diseases, such as lung cancer, early diagnosis and treatment are crucial. The analysis of CT images is invaluable for diagnosis, whereas high quality segmentation of the airway tree are required for intervention planning and live guidance during bronchoscopy. Recently, the Multi-domain Airway Tree Modeling (ATM'22) challenge released a large dataset, both enabling training of deep-learning based models and bringing substantial improvement of the state-of-the-art for the airway segmentation task. The ATM'22 dataset includes a large group of COVID'19 patients and a range of other lung diseases, however, relatively few patients with severe pathologies affecting the airway tree anatomy was found. In this study, we introduce a new public benchmark dataset (AeroPath), consisting of 27 CT images from patients with pathologies ranging from emphysema to large tumors, with corresponding trachea and bronchi annotations. Second, we present a multiscale fusion design for automatic airway segmentation. Models were trained on the ATM'22 dataset, tested on the AeroPath dataset, and further evaluated against competitive open-source methods. The same performance metrics as used in the ATM'22 challenge were used to benchmark the different considered approaches. Lastly, an open web application is developed, to easily test the proposed model on new data. The results demonstrated that our proposed architecture predicted topologically correct segmentations for all the patients included in the AeroPath dataset. The proposed method is robust and able to handle various anomalies, down to at least the fifth airway generation. In addition, the AeroPath dataset, featuring patients with challenging pathologies, will contribute to development of new state-of-the-art methods. The AeroPath dataset and the web application are made openly available.

A complete benchmark for polyp detection, segmentation and classification in colonoscopy images.

Colorectal cancer (CRC) is one of the main causes of deaths worldwide. Early detection and diagnosis of its precursor lesion, the polyp, is key to reduce its mortality and to improve procedure efficiency. During the last two decades, several computational methods have been proposed to assist clinicians in detection, segmentation and classification tasks but the lack of a common public validation framework makes it difficult to determine which of them is ready to be deployed in the exploration room. This study presents a complete validation framework and we compare several methodologies for each of the polyp characterization tasks. Results show that the majority of the approaches are able to provide good performance for the detection and segmentation task, but that there is room for improvement regarding polyp classification. While studied show promising results in the assistance of polyp detection and segmentation tasks, further research should be done in classification task to obtain reliable results to assist the clinicians during the procedure. The presented framework provides a standarized method for evaluating and comparing different approaches, which could facilitate the identification of clinically prepared assisting methods.

WildScenes: A benchmark for 2D and 3D semantic segmentation in large-scale natural environments

WildScenes: A benchmark for 2D and 3D semantic segmentation in large-scale natural environments

MEDANet: More Efficient Dual Attention Network for Scene Segmentation

The dual attention module is a potent semantic segmentation technique renowned for its capabilities, yet it often faces significant computational demands and GPU memory usage. To tackle these challenges, we introduce an advanced dual perception network comprising two modules: A streamlined Multi-scale Efficient Position Attention Module (MEPAM) and an optimized Efficient Channel Attention Module (MECAM). MEPAM incorporates multi-scale global average pooling into the Position Attention Module (PAM), substantially cutting computational overhead and memory consumption without compromising performance. Meanwhile, MECAM integrates compressed convolutions into the Channel Attention Module (CAM), improving segmentation accuracy and inference speed compared to conventional methods like DANet. Our approach underwent comprehensive evaluation on a semantic segmentation benchmark dataset, showcasing superior performance. For instance, on the Cityscapes dataset, our method achieves an IoU of 82.2%. In terms of efficiency gains, MEPAM operates nearly 1.97 times faster than the standard PAM module on GPU, while requiring 7.55 times less memory with a [Formula: see text] input. Similarly, MECAM achieves approximately 2.2 times faster processing than CAM, while cutting GPU memory usage by 7.53 times. This innovative dual perception network not only enhances segmentation accuracy and speed but also addresses the computational challenges associated with traditional dual attention modules.

Explicit-implicit priori knowledge-based diffusion model for generative medical image segmentation

The diffusion probabilistic model (DPM) has achieved unparalleled results in current image generation tasks, and some recent research works employed it in several computer vision tasks, such as image super-resolution, object detection, etc. Thanks to DPM's superior ability to generate fine-grained details, these research efforts have yielded significant successes. In this paper, we propose a new DPM-based generative medical image segmentation method, named EIDiffuSeg. Specifically, we first construct an explicit-implicit aggregation priori knowledge with directional supervision ability by mining the semantic distribution pattern in the frequency and spatial domains. Then, the explicit-implicit aggregation priori knowledge is integrated into the different encoding stages of the denoising backbone network using a novel unsupervised priori knowledge induction strategy, which can guide the model to generate a segmentation mask of the region of interest directionally from a random inference process. We evaluate our method on three medical image segmentation benchmark datasets with different modalities and achieve the best segmentation results compared to state-of-the-art methods. Especially, compared to several current diffusion-based image segmentation methods, we achieved a 9% Dice improvement in the polyp segmentation benchmark. Our code will be available at https://github.com/Notmezhan/EIDiffuSeg.

InstLane Dataset and Geometry-Aware Network for Instance Segmentation of Lane Line Detection

Despite impressive progress, obtaining appropriate data for instance-level lane segmentation remains a significant challenge. This limitation hinders the refinement of granular lane-related applications such as lane line crossing surveillance, pavement maintenance, and management. To address this gap, we introduce a benchmark for lane instance segmentation called InstLane. To the best of our knowledge, InstLane constitutes the first publicly accessible instance-level segmentation standard for lane line detection. The complexity of InstLane emanates from the fact that the original data are procured using cameras mounted laterally, as opposed to traditional front-mounted sensors. InstLane encapsulates a range of challenging scenarios, enhancing the generalization and robustness of the lane line instance segmentation algorithms. In addition, we propose GeoLaneNet, a real-time, geometry-aware lane instance segmentation network. Within GeoLaneNet, we design a finer localization of lane proto-instances based on geometric features to counteract the prevalent omission or multiple detections in dense lane scenarios resulting from non-maximum suppression (NMS). Furthermore, we present a scheme that employs a larger receptive field to achieve profound perceptual lane structural learning, thereby improving detection accuracy. We introduce an architecture based on partial feature transformation to expedite the detection process. Comprehensive experiments on InstLane demonstrate that GeoLaneNet can achieve up to twice the speed of current State-Of-The-Artmethods, reaching 139 FPS on an RTX3090 and a mask AP of 73.55%, with a permissible trade-off in AP, while maintaining comparable accuracy. These results underscore the effectiveness, robustness, and efficiency of GeoLaneNet in autonomous driving.

Development of an initial training and evaluation programme for manual lower limb muscle MRI segmentation

BackgroundMagnetic resonance imaging (MRI) quantification of intramuscular fat accumulation is a responsive biomarker in neuromuscular diseases. Despite emergence of automated methods, manual muscle segmentation remains an essential foundation. We aimed to develop a training programme for new observers to demonstrate competence in lower limb muscle segmentation and establish reliability benchmarks for future human observers and machine learning segmentation packages.MethodsThe learning phase of the training programme comprised a training manual, direct instruction, and eight lower limb MRI scans with reference standard large and small regions of interest (ROIs). The assessment phase used test–retest scans from two patients and two healthy controls. Interscan and interobserver reliability metrics were calculated to identify underperforming outliers and to determine competency benchmarks.ResultsThree experienced observers undertook the assessment phase, whilst eight new observers completed the full training programme. Two of the new observers were identified as underperforming outliers, relating to variation in size or consistency of segmentations; six had interscan and interobserver reliability equivalent to those of experienced observers. The calculated benchmark for the Sørensen-Dice similarity coefficient between observers was greater than 0.87 and 0.92 for individual thigh and calf muscles, respectively. Interscan and interobserver reliability were significantly higher for large than small ROIs (all p < 0.001).ConclusionsWe developed, implemented, and analysed the first formal training programme for manual lower limb muscle segmentation. Large ROI showed superior reliability to small ROI for fat fraction assessment.Relevance statementObservers competent in lower limb muscle segmentation are critical to application of quantitative muscle MRI biomarkers in neuromuscular diseases. This study has established competency benchmarks for future human observers or automated segmentation methods.Key points• Observers competent in muscle segmentation are critical for quantitative muscle MRI biomarkers.• A training programme for muscle segmentation was undertaken by eight new observers.• We established competency benchmarks for future human observers or automated segmentation methods.Graphical

A Novel Mamba Architecture with a Semantic Transformer for Efficient Real-Time Remote Sensing Semantic Segmentation

Real-time remote sensing segmentation technology is crucial for unmanned aerial vehicles (UAVs) in battlefield surveillance, land characterization observation, earthquake disaster assessment, etc., and can significantly enhance the application value of UAVs in military and civilian fields. To realize this potential, it is essential to develop real-time semantic segmentation methods that can be applied to resource-limited platforms, such as edge devices. The majority of mainstream real-time semantic segmentation methods rely on convolutional neural networks (CNNs) and transformers. However, CNNs cannot effectively capture long-range dependencies, while transformers have high computational complexity. This paper proposes a novel remote sensing Mamba architecture for real-time segmentation tasks in remote sensing, named RTMamba. Specifically, the backbone utilizes a Visual State-Space (VSS) block to extract deep features and maintains linear computational complexity, thereby capturing long-range contextual information. Additionally, a novel Inverted Triangle Pyramid Pooling (ITP) module is incorporated into the decoder. The ITP module can effectively filter redundant feature information and enhance the perception of objects and their boundaries in remote sensing images. Extensive experiments were conducted on three challenging aerial remote sensing segmentation benchmarks, including Vaihingen, Potsdam, and LoveDA. The results show that RTMamba achieves competitive performance advantages in terms of segmentation accuracy and inference speed compared to state-of-the-art CNN and transformer methods. To further validate the deployment potential of the model on embedded devices with limited resources, such as UAVs, we conducted tests on the Jetson AGX Orin edge device. The experimental results demonstrate that RTMamba achieves impressive real-time segmentation performance.

Infproto-Powered Adaptive Classifier and Agnostic Feature Learning for Single Domain Generalization in Medical Images

AbstractDesigning a single domain generalization (DG) framework that generalizes from one source domain to arbitrary unseen domains is practical yet challenging in medical image segmentation, mainly due to the domain shift and limited source domain information. To tackle these issues, we reason that domain-adaptive classifier learning and domain-agnostic feature extraction are key components in single DG, and further propose an adaptive infinite prototypes (InfProto) scheme to facilitate the learning of the two components. InfProto harnesses high-order statistics and infinitely samples class-conditional instance-specific prototypes to form the classifier for discriminability enhancement. We then introduce probabilistic modeling and provide a theoretic upper bound to implicitly perform the infinite prototype sampling in the optimization of InfProto. Incorporating InfProto, we design a hierarchical domain-adaptive classifier to elasticize the model for varying domains. This classifier infinitely samples prototypes from the instance and mini-batch data distributions, forming the instance-level and mini-batch-level domain-adaptive classifiers, thereby generalizing to unseen domains. To extract domain-agnostic features, we assume each instance in the source domain is a micro source domain and then devise three complementary strategies, i.e., instance-level infinite prototype exchange, instance-batch infinite prototype interaction, and consistency regularization, to constrain outputs of the hierarchical domain-adaptive classifier. These three complementary strategies minimize distribution shifts among micro source domains, enabling the model to get rid of domain-specific characterizations and, in turn, concentrating on semantically discriminative features. Extensive comparison experiments demonstrate the superiority of our approach compared with state-of-the-art counterparts, and comprehensive ablation studies verify the effect of each proposed component. Notably, our method exhibits average improvements of 15.568% and 17.429% in dice on polyp and surgical instrument segmentation benchmarks.

Attention-guided context asymmetric fusion networks for the liver tumor segmentation of computed tomography images.

Liver tumor segmentation based on medical imaging is playing an increasingly important role in liver tumor research and individualized therapeutic decision-making. However, it remains a challenging in terms of the accuracy of automatic segmentation of liver tumors. Therefore, we aimed to develop a novel deep neural network for improving the results from the automatic segmentation of liver tumors. This paper proposes the attention-guided context asymmetric fusion network (AGCAF-Net), combining attention guidance and fusion context modules on the basis of a residual neural network for the automatic segmentation of liver tumors. According to the attention-guided context block (AGCB), the feature map is first divided into multiple small blocks, the local correlation between features is calculated, and then the global nonlocal fusion module (GNFM) is used to obtain the global information between pixels. Additionally, the context pyramid module (CPM) and asymmetric semantic fusion module (AFM) are used to obtain multiscale features and resolve the feature mismatch during feature fusion, respectively. Finally, we used the liver tumor segmentation benchmark (LiTS) dataset to verify the efficiency of our designed network. Our results showed that AGCAF-Net with AFM and CPM is effective in improving the accuracy of liver tumor segmentation, with the Dice coefficient increasing from 82.5% to 84.1%. The segmentation results of liver tumors by AGCAF-Net were superior to those of several state-of-the-art U-net methods, with a Dice coefficient of 84.1%, a sensitivity of 91.7%, and an average symmetric surface distance of 3.52. AGCAF-Net can obtain better matched and accurate segmentation in liver tumor segmentation, thus effectively improving the accuracy of liver tumor segmentation.

A Retinal Vessel Segmentation Method Based on the Sharpness-Aware Minimization Model.

Retinal vessel segmentation is crucial for diagnosing and monitoring various eye diseases such as diabetic retinopathy, glaucoma, and hypertension. In this study, we examine how sharpness-aware minimization (SAM) can improve RF-UNet's generalization performance. RF-UNet is a novel model for retinal vessel segmentation. We focused our experiments on the digital retinal images for vessel extraction (DRIVE) dataset, which is a benchmark for retinal vessel segmentation, and our test results show that adding SAM to the training procedure leads to notable improvements. Compared to the non-SAM model (training loss of 0.45709 and validation loss of 0.40266), the SAM-trained RF-UNet model achieved a significant reduction in both training loss (0.094225) and validation loss (0.08053). Furthermore, compared to the non-SAM model (training accuracy of 0.90169 and validation accuracy of 0.93999), the SAM-trained model demonstrated higher training accuracy (0.96225) and validation accuracy (0.96821). Additionally, the model performed better in terms of sensitivity, specificity, AUC, and F1 score, indicating improved generalization to unseen data. Our results corroborate the notion that SAM facilitates the learning of flatter minima, thereby improving generalization, and are consistent with other research highlighting the advantages of advanced optimization methods. With wider implications for other medical imaging tasks, these results imply that SAM can successfully reduce overfitting and enhance the robustness of retinal vessel segmentation models. Prospective research avenues encompass verifying the model on vaster and more diverse datasets and investigating its practical implementation in real-world clinical situations.

A Benchmark for Morphological Segmentation in Uyghur and Kazakh

Morphological segmentation and stemming are foundational tasks in natural language processing. They have become effective ways to alleviate data sparsity in agglutinative languages because of the nature of agglutinative language word formation. Uyghur and Kazakh, as typical agglutinative languages, have made significant progress in morphological segmentation and stemming in recent years. However, the evaluation metrics used in previous work are character-level based, which may not comprehensively reflect the performance of models in morphological segmentation or stemming. Moreover, existing methods avoid manual feature extraction, but the model’s ability to learn features is inadequate in complex scenarios, and the correlation between different features has not been considered. Consequently, these models lack representation in complex contexts, affecting their effective generalization in practical scenarios. To address these issues, this paper redefines the morphological-level evaluation metrics: F1-score and accuracy (ACC) for morphological segmentation and stemming tasks. In addition, two models are proposed for morpheme segmentation and stem extraction tasks: supervised model and unsupervised model. The supervised model learns character and contextual features simultaneously, then feature embeddings are input into a Transformer encoder to study the correlation between character and context embeddings. The last layer of the model uses a CRF or softmax layer to determine morphological boundaries. In unsupervised learning, an encoder–decoder structure introduces n-gram correlation assumptions and masked attention mechanisms, enhancing the correlation between characters within n-grams and reducing the impact of characters outside n-grams on boundaries. Finally, comprehensive comparative analyses of the performance of different models are conducted from various points of view. Experimental results demonstrate that: (1) The proposed evaluation method effectively reflects the differences in morphological segmentation and stemming for Uyghur and Kazakh; (2) Learning different features and their correlation can enhance the model’s generalization ability in complex contexts. The proposed models achieve state-of-the-art performance on Uyghur and Kazakh datasets.

DIAS: A dataset and benchmark for intracranial artery segmentation in DSA sequences

The automated segmentation of Intracranial Arteries (IA) in Digital Subtraction Angiography (DSA) plays a crucial role in the quantification of vascular morphology, significantly contributing to computer-assisted stroke research and clinical practice. Current research primarily focuses on the segmentation of single-frame DSA using proprietary datasets. However, these methods face challenges due to the inherent limitation of single-frame DSA, which only partially displays vascular contrast, thereby hindering accurate vascular structure representation. In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences. We establish a comprehensive benchmark for evaluating DIAS, covering full, weak, and semi-supervised segmentation methods. Specifically, we propose the vessel sequence segmentation network, in which the sequence feature extraction module effectively captures spatiotemporal representations of intravascular contrast, achieving intracranial artery segmentation in 2D+Time DSA sequences. For weakly-supervised IA segmentation, we propose a novel scribble learning-based image segmentation framework, which, under the guidance of scribble labels, employs cross pseudo-supervision and consistency regularization to improve the performance of the segmentation network. Furthermore, we introduce the random patch-based self-training framework, aimed at alleviating the performance constraints encountered in IA segmentation due to the limited availability of annotated DSA data. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications. The dataset and code are publicly available at https://doi.org/10.5281/zenodo.11401368 and https://github.com/lseventeen/DIAS.

NKUT: Dataset and Benchmark for Pediatric Mandibular Wisdom Teeth Segmentation.

Germectomy is a common surgery in pediatric dentistry to prevent the potential dangers caused by impacted mandibular wisdom teeth. Segmentation of mandibular wisdom teeth is a crucial step in surgery planning. However, manually segmenting teeth and bones from 3D volumes is time-consuming and may cause delays in treatment. Deep learning based medical image segmentation methods have demonstrated the potential to reduce the burden of manual annotations, but they still require a lot of well-annotated data for training. In this paper, we initially curated a Cone Beam Computed Tomography (CBCT) dataset, NKUT, for the segmentation of pediatric mandibular wisdom teeth. This marks the first publicly available dataset in this domain. Second, we propose a semantic separation scale-specific feature fusion network named WTNet, which introduces two branches to address the teeth and bones segmentation tasks. In WTNet, We design a Input Enhancement (IE) block and a Teeth-Bones Feature Separation (TBFS) block to solve the feature confusions and semantic-blur problems in our task. Experimental results suggest that WTNet performs better on NKUT compared to previous state-of-the-art segmentation methods (such as TransUnet), with a maximum DSC lead of nearly 16%.

MiniSeg: An Extremely Minimum Network Based on Lightweight Multiscale Learning for Efficient COVID-19 Segmentation.

The rapid spread of the new pandemic, i.e., coronavirus disease 2019 (COVID-19), has severely threatened global health. Deep-learning-based computer-aided screening, e.g., COVID-19 infected area segmentation from computed tomography (CT) image, has attracted much attention by serving as an adjunct to increase the accuracy of COVID-19 screening and clinical diagnosis. Although lesion segmentation is a hot topic, traditional deep learning methods are usually data-hungry with millions of parameters, easy to overfit under limited available COVID-19 training data. On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional methods are usually computationally intensive. To address the above two problems, we propose MiniSeg, a lightweight model for efficient COVID-19 segmentation from CT images. Our efforts start with the design of an attentive hierarchical spatial pyramid (AHSP) module for lightweight, efficient, effective multiscale learning that is essential for image segmentation. Then, we build a two-path (TP) encoder for deep feature extraction, where one path uses AHSP modules for learning multiscale contextual features and the other is a shallow convolutional path for capturing fine details. The two paths interact with each other for learning effective representations. Based on the extracted features, a simple decoder is added for COVID-19 segmentation. For comparing MiniSeg to previous methods, we build a comprehensive COVID-19 segmentation benchmark. Extensive experiments demonstrate that the proposed MiniSeg achieves better accuracy because its only 83k parameters make it less prone to overfitting. Its high efficiency also makes it easy to deploy and develop. The code has been released at https://github.com/yun-liu/MiniSeg.

SegCFT: Context-aware Fourier Transform for efficient semantic segmentation

Semantic segmentation has been one of the most critical tasks in computer vision. Recent works mainly focus on improving segmentation performance by designing high-capacity transformer architectures. They try to solve the high data consumption and computing costs required for model training and deployment in the cloud, but the high computation overhead still makes it difficult to be directly applied to limited resource devices. In this paper, we propose a novel fast Fourier Transform (FFT) based Context-aware Feature Mixer under the transformer-like architecture for precise and efficient semantic segmentation, called SegCFT. Different from the self-attention-based transformer, SegCFT uses a Hierarchical Fourier Transform (HFT) to reduce computational cost via non-parametric calculation and promote segmentation performance by fusing the channel-wise and pixel-wise contexts. To integrate the features from the frequency domain of DFT into the spatial domain of the transformer-like architecture, an Adaptive Modulation Unit (AMU) is designed to modulate the frequency-domain features and ensure consistency between the frequency domain and the spatial domain. Experimental evaluation on two semantic segmentation benchmarks, ADE20k and Cityscapes, shows that SegCFT achieves competitive segmentation performance, while the training and inference costs are superior to the previous methods.

A region of interest focused Triple UNet architecture for skin lesion segmentation

AbstractSkin lesion segmentation is a crucial step for skin lesion analysis and subsequent treatment. However, it is still a challenging task due to the irregular and fuzzy lesion borders, and the diversity of skin lesions. In this article, we propose Triple‐UNet, an organic combination of three UNet architectures with suitable modules, to automatically segment skin lesions. To enhance the target object region of the image, we design a region of interest enhancement module (ROIE) that uses the predicted score map of the first UNet. The enhanced image and the features learned by the first UNet help the second UNet obtain a better score map. Finally, the results are fine‐tuned by the third UNet. We evaluate our algorithm on a publicly available dataset of skin lesion segmentation. Experiments have shown that TripleUNet achieves an accuracy of 92.5% on the ISIC‐2018 skin lesion segmentation benchmark, with Dice and mIoU of 0.909 and 0.836, respectively, which outperforms the state‐of‐the‐art algorithms.

Multi-Context Point Cloud Dataset and Machine Learning for Railway Semantic Segmentation

Railway scene understanding is crucial for various applications, including autonomous trains, digital twining, and infrastructure change monitoring. However, the development of the latter is constrained by the lack of annotated datasets and limitations of existing algorithms. To address this challenge, we present Rail3D, the first comprehensive dataset for semantic segmentation in railway environments with a comparative analysis. Rail3D encompasses three distinct railway contexts from Hungary, France, and Belgium, capturing a wide range of railway assets and conditions. With over 288 million annotated points, Rail3D surpasses existing datasets in size and diversity, enabling the training of generalizable machine learning models. We conducted a generic classification with nine universal classes (Ground, Vegetation, Rail, Poles, Wires, Signals, Fence, Installation, and Building) and evaluated the performance of three state-of-the-art models: KPConv (Kernel Point Convolution), LightGBM, and Random Forest. The best performing model, a fine-tuned KPConv, achieved a mean Intersection over Union (mIoU) of 86%. While the LightGBM-based method achieved a mIoU of 71%, outperforming Random Forest. This study will benefit infrastructure experts and railway researchers by providing a comprehensive dataset and benchmarks for 3D semantic segmentation. The data and code are publicly available for France and Hungary, with continuous updates based on user feedback.