Final Segmentation Research Articles

Uncertainty‐guided U‐Net for soil boundary segmentation using Monte Carlo dropout

AbstractAccurate soil stratification is essential for geotechnical engineering design. Owing to its effectiveness and efficiency, the cone penetration test (CPT) has been widely applied for subsurface stratigraphy, which relies heavily on empiricism for correlations to soil type. Recently, deep learning techniques have shown great promise in learning the relationship between CPT data and soil boundaries automatically. However, the segmentation of soil boundaries is fraught with model and measurement uncertainty. This paper introduces an uncertainty‐guided U((‐Net (UGU‐Net) for improved soil boundary segmentation. The UGU‐Net consists of three parts: (a) a Bayesian U‐Net to predict a pixel‐level uncertainty map, (b) reinforcement of original labels on the basis of the predicted uncertainty map, and (c) a traditional deterministic U‐Net, which is applied to the reinforced labels for final soil boundary segmentation. The results show that the proposed UGU‐Net outperforms the existing methods in terms of both high accuracy and low uncertainty. A sensitivity study is also conducted to explore the influence of key model parameters on model performance. The proposed method is validated by comparing the predicted subsurface profile with benchmark profiles. The code for this project is available at github.com/Xiaoqi‐Zhou‐suda/UGU‐Net.

An effective and open source interactive 3D medical image segmentation solution

3D medical image segmentation is a key step in numerous clinical applications. Even though many automatic segmentation solutions have been proposed, it is arguably that medical image segmentation is more of a preference than a reference as inter- and intra-variability are widely observed in final segmentation output. Therefore, designing a user oriented and open-source solution for interactive annotation is of great value for the community. In this paper, we present an effective interactive segmentation method that employs an adaptive dynamic programming approach to incorporates users’ interactions efficiently. The method first initializes an segmentation through a feature-based geodesic computation. Then, the segmentation is further refined by using an efficient updating scheme requiring only local computations when new user inputs are available, making it applicable to high resolution images and very complex structures. The proposed method is implemented as a user-oriented software module in 3D Slicer. Our approach demonstrates several strengths and contributions. First, we proposed an efficient and effective 3D interactive algorithm with the adaptive dynamic programming method. Second, this is not just a presented algorithm, but also a software with well-designed GUI for users. Third, its open-source nature allows users to make customized modifications according to their specific requirements.

Quantitative modeling of lenticulostriate arteries on 7-T TOF-MRA for cerebral small vessel disease.

We developed a framework for segmenting and modeling lenticulostriate arteries (LSAs) on 7-T time-of-flight magnetic resonance angiography and tested its performance on cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) patients and controls. We prospectively included 29 CADASIL patients and 21 controls. The framework includes a small-patch convolutional neural network (SP-CNN) for fine segmentation, a random forest for modeling LSAs, and a screening model for removing wrong branches. The segmentation performance of our SP-CNN was compared to competitive networks. External validation with different resolution was performed on ten patients with aneurysms. Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each network and manual segmentation were calculated. The modeling results of the centerlines, diameters, and lengths of LSAs were compared against manual labeling by four neurologists. The SP-CNN achieved higher DSC (92.741 ± 2.789, mean ± standard deviation) and lower HD (0.610 ± 0.141 mm) in the segmentation of LSAs. It also outperformed competitive networks in the external validation (DSC 82.6 ± 5.5, HD 0.829 ± 0.143 mm). The framework versus manual difference was lower than the manual inter-observer difference for the vessel length of primary branches (median -0.040 mm, interquartile range -0.209 to 0.059 mm) and secondary branches (0.202 mm, 0.016-0.537 mm), as well as for the offset of centerlines of primary branches (0.071 mm, 0.065-0.078 mm) and secondary branches (0.072, 0.064-0.080 mm), with p < 0.001 for all comparisons. Our framework for LSAs modeling/quantification demonstrated high reliability and accuracy when compared to manual labeling. NCT05902039 ( https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039 ). The proposed automatic segmentation and modeling framework offers precise quantification of the morphological parameters of lenticulostriate arteries. This innovative technology streamlines diagnosis and research of cerebral small vessel disease, eliminating the burden of manual labeling, facilitating cohort studies and clinical diagnosis. The morphology of LSAs is important in the diagnosis of CSVD but difficult to quantify. The proposed algorithm achieved the performance equivalent to manual labeling by neurologists. Our method can provide standardized quantitative results, reducing radiologists' workload in cohort studies.

TCDDU-Net: combining transformer and convolutional dual-path decoding U-Net for retinal vessel segmentation

Accurate segmentation of retinal blood vessels is crucial for enhancing diagnostic efficiency and preventing disease progression. However, the small size and complex structure of retinal blood vessels, coupled with low contrast in corresponding fundus images, pose significant challenges for this task. We propose a novel approach for retinal vessel segmentation, which combines the transformer and convolutional dual-path decoding U-Net (TCDDU-Net). We propose the selective dense connection swin transformer block, which converts the input feature map into patches, introduces MLPs to generate probabilities, and performs selective fusion at different stages. This structure forms a dense connection framework, enabling the capture of long-distance dependencies and effective fusion of features across different stages. The subsequent stage involves the design of the background decoder, which utilizes deformable convolution to learn the background information of retinal vessels by treating them as segmentation objects. This is then combined with the foreground decoder to form a dual-path decoding U-Net. Finally, the foreground segmentation results and the processed background segmentation results are fused to obtain the final retinal vessel segmentation map. To evaluate the effectiveness of our method, we performed experiments on the DRIVE, STARE, and CHASE datasets for retinal vessel segmentation. Experimental results show that the segmentation accuracies of our algorithms are 96.98, 97.40, and 97.23, and the AUC metrics are 98.68, 98.56, and 98.50, respectively.In addition, we evaluated our methods using F1 score, specificity, and sensitivity metrics. Through a comparative analysis, we found that our proposed TCDDU-Net method effectively improves retinal vessel segmentation performance and achieves impressive results on multiple datasets compared to existing methods.

A Nighttime Driving-Scene Segmentation Method Based on Light-Enhanced Network

To solve the semantic segmentation problem of night driving-scene images, which often have low brightness, low contrast, and uneven illumination, a nighttime driving-scene segmentation method based on a light-enhanced network was proposed. Firstly, we designed a light enhancement network, which comprises two parts: a color correction module and a parameter predictor. The color correction module mitigates the impact of illumination variations on the segmentation network by adjusting the color information of the image. Meanwhile, the parameter predictor accurately predicts the parameters of the image filter through the analysis of global content, including factors such as brightness, contrast, hue, and exposure level, thereby effectively enhancing the image quality. Subsequently, the output of the light enhancement network is input into the segmentation network to obtain the final segmentation prediction. Experimental results show that the proposed method achieves mean Intersection over Union (mIoU) values of 59.4% on the Dark Zurich-test dataset, outperforming other segmentation algorithms for nighttime driving-scenes.

Structure preservation constraints for unsupervised domain adaptation intracranial vessel segmentation.

Unsupervised domain adaptation (UDA) has received interest as a means to alleviate the burden of data annotation. Nevertheless, existing UDA segmentation methods exhibit performance degradation in fine intracranial vessel segmentation tasks due to the problem of structure mismatch in the image synthesis procedure. To improve the image synthesis quality and the segmentation performance, a novel UDA segmentation method with structure preservation approaches, named StruP-Net, is proposed. The StruP-Net employs adversarial learning for image synthesis and utilizes two domain-specific segmentation networks to enhance the semantic consistency between real images and synthesized images. Additionally, two distinct structure preservation approaches, feature-level structure preservation (F-SP) and image-level structure preservation (I-SP), are proposed to alleviate the problem of structure mismatch in the image synthesis procedure. The F-SP, composed of two domain-specific graph convolutional networks (GCN), focuses on providing feature-level constraints to enhance the structural similarity between real images and synthesized images. Meanwhile, the I-SP imposes constraints on structure similarity based on perceptual loss. The cross-modality experimental results from magnetic resonance angiography (MRA) images to computed tomography angiography (CTA) images indicate that StruP-Net achieves better segmentation performance compared with other state-of-the-art methods. Furthermore, high inference efficiency demonstrates the clinical application potential of StruP-Net. The code is available at https://github.com/Mayoiuta/StruP-Net .

Dual convolution-transformer UNet (DCT-UNet) for organs at risk and clinical target volume segmentation in MRI for cervical cancer brachytherapy

Objective. MRI is the standard imaging modality for high-dose-rate brachytherapy of cervical cancer. Precise contouring of organs at risk (OARs) and high-risk clinical target volume (HR-CTV) from MRI is a crucial step for radiotherapy planning and treatment. However, conventional manual contouring has limitations in terms of accuracy as well as procedural time. To overcome these, we propose a deep learning approach to automatically segment OARs (bladder, rectum, and sigmoid colon) and HR-CTV from female pelvic MRI.Approach. In the proposed pipeline, a coarse multi-organ segmentation model first segments all structures, from which a region of interest is computed for each structure. Then, each organ is segmented using an organ-specific fine segmentation model separately trained for each organ. To account for variable sizes of HR-CTV, a size-adaptive multi-model approach was employed. For coarse and fine segmentations, we designed a dual convolution-transformer UNet (DCT-UNet) which uses dual-path encoder consisting of convolution and transformer blocks. To evaluate our model, OAR segmentations were compared to the clinical contours drawn by the attending radiation oncologist. For HR-CTV, four sets of contours (clinical + three additional sets) were obtained to produce a consensus ground truth as well as for inter/intra-observer variability analysis.Main results. DCT-UNet achieved dice similarity coefficient (mean ± SD) of 0.932 ± 0.032 (bladder), 0.786 ± 0.090 (rectum), 0.663 ± 0.180 (sigmoid colon), and 0.741 ± 0.076 (HR-CTV), outperforming other state-of-the-art models. Notably, the size-adaptive multi-model significantly improved HR-CTV segmentation compared to a single-model. Furthermore, significant inter/intra-observer variability was observed, and our model showed comparable performance to all observers. Computation time for the entire pipeline per subject was 12.59 ± 0.79 s, which is significantly shorter than the typical manual contouring time of >15 min.Significance. These experimental results demonstrate that our model has great utility in cervical cancer brachytherapy by enabling fast and accurate automatic segmentation, and has potential in improving consistency in contouring. DCT-UNet source code is available athttps://github.com/JHU-MICA/DCT-UNet.

A cascaded FAS-UNet+ framework with iterative optimization strategy for segmentation of organs at risk.

Segmentation of organs at risks (OARs) in the thorax plays a critical role in radiation therapy for lung and esophageal cancer. Although automatic segmentation of OARs has been extensively studied, it remains challenging due to the varying sizes and shapes of organs, as well as the low contrast between the target and background. This paper proposes a cascaded FAS-UNet+ framework, which integrates convolutional neural networks and nonlinear multi-grid theory to solve a modified Mumford-shah model for segmenting OARs. This framework is equipped with an enhanced iteration block, a coarse-to-fine multiscale architecture, an iterative optimization strategy, and a model ensemble technique. The enhanced iteration block aims to extract multiscale features, while the cascade module is used to refine coarse segmentation predictions. The iterative optimization strategy improves the network parameters to avoid unfavorable local minima. An efficient data augmentation method is also developed to train the network, which significantly improves its performance. During the prediction stage, a weighted ensemble technique combines predictions from multiple models to refine the final segmentation. The proposed cascaded FAS-UNet+ framework was evaluated on the SegTHOR dataset, and the results demonstrate significant improvements in Dice score and Hausdorff Distance (HD). The Dice scores were 95.22%, 95.68%, and HD values were 0.1024, and 0.1194 for the segmentations of the aorta and heart in the official unlabeled dataset, respectively. Our code and trained models are available at https://github.com/zhuhui100/C-FASUNet-plus .

A fundus vessel segmentation method based on double skip connections combined with deep supervision.

Fundus vessel segmentation is vital for diagnosing ophthalmic diseases like central serous chorioretinopathy (CSC), diabetic retinopathy, and glaucoma. Accurate segmentation provides crucial vessel morphology details, aiding the early detection and intervention of ophthalmic diseases. However, current algorithms struggle with fine vessel segmentation and maintaining sensitivity in complex regions. Challenges also stem from imaging variability and poor generalization across multimodal datasets, highlighting the need for more advanced algorithms in clinical practice. This paper aims to explore a new vessel segmentation method to alleviate the above problems. We propose a fundus vessel segmentation model based on a combination of double skip connections, deep supervision, and TransUNet, namely DS2TUNet. Initially, the original fundus images are improved through grayscale conversion, normalization, histogram equalization, gamma correction, and other preprocessing techniques. Subsequently, by utilizing the U-Net architecture, the preprocessed fundus images are segmented to obtain the final vessel information. Specifically, the encoder firstly incorporates the ResNetV1 downsampling, dilated convolution downsampling, and Transformer to capture both local and global features, which upgrades its vessel feature extraction ability. Then, the decoder introduces the double skip connections to facilitate upsampling and refine segmentation outcomes. Finally, the deep supervision module introduces multiple upsampling vessel features from the decoder into the loss function, so that the model can learn vessel feature representations more effectively and alleviate gradient vanishing during the training phase. Extensive experiments on publicly available multimodal fundus datasets such as DRIVE, CHASE_DB1, and ROSE-1 demonstrate that the DS2TUNet model attains F1-scores of 0.8195, 0.8362, and 0.8425, with Accuracy of 0.9664, 0.9741, and 0.9557, Sensitivity of 0.8071, 0.8101, and 0.8586, and Specificity of 0.9823, 0.9869, and 0.9713, respectively. Additionally, the model also exhibits excellent test performance on the clinical fundus dataset CSC, with F1-score of 0.7757, Accuracy of 0.9688, Sensitivity of 0.8141, and Specificity of 0.9801 based on the weight trained on the CHASE_DB1 dataset. These results comprehensively validate that the proposed method obtains good performance in fundus vessel segmentation, thereby aiding clinicians in the further diagnosis and treatment of fundus diseases in terms of effectiveness and feasibility.

One-Click-Based Perception for Interactive Image Segmentation.

Existing deep learning-based interactive image segmentation methods have significantly reduced the user's interaction burden with simple click interactions. However, they still require excessive numbers of clicks to continuously correct the segmentation for satisfactory results. This article explores how to harvest accurate segmentation of interested targets while minimizing the user interaction cost. To achieve the above goal, we propose a one-click-based interactive segmentation approach in this work. For this particularly challenging problem in the interactive segmentation task, we build a top-down framework dividing the original problem into a one-click-based coarse localization followed by a fine segmentation. A two-stage interactive object localization network is first designed, which aims to completely enclose the target of interest based on the supervision of object integrity (OI). Click centrality (CC) is also utilized to overcome the overlapping problem between objects. This coarse localization helps to reduce the search space and increase the focus of the click at a higher resolution. A principled multilayer segmentation network is then designed by a progressive layer-by-layer structure, which aims to accurately perceive the target with extremely limited prior guidance. A diffusion module is also designed to enhance the information flow between layers. Besides, the proposed model can be naturally extended to multiobject segmentation task. Our method achieves the state-of-the-art performance under one-click interaction on several benchmarks.

The Study of Echocardiography of Left Ventricle Segmentation Combining Transformer and Convolutional Neural Networks.

Accurate prediction of echocardiographic parameters is essential for diagnosis and treatment of cardiac disease, especially for segmentation of the left ventricle to obtain measurements such as left ventricular ejection fraction and volume. However, manually outlining left ventricle on echocardiographic images is a time-consuming and physician experience-dependent task. Therefore, it is crucial to develop an accurate and efficient automatic segmentation tool. Therefore, we aimed to explore a model to perform echocardiography of left ventricle segmentation by combining transformer and convolutional neural networks (CNN).ResNet-50 was used in CNN branch. The encoder-decoder architecture was used for transformer branch, which was fused to the corresponding feature maps of the CNN branches. Fusion module was used to effectively combine feature information from the CNN and transformer. Bridge attention used to increase sensitivity and prediction accuracy of model. The entire network was trained end-to-end using the binary cross-entropy with logits loss L.In this work, we propose an automatic left ventricular (LV) segmentation model based on Transformer and CNN that efficiently captures global dependencies and spatial details and create a fusion module using CBAM that fuses Transformer and CNN features. In addition, attention is also computed using multi-level fusion features to obtain the final attention segmentation map. The model was trained and evaluated on a large cardiac image dataset, EchoNet-Dynamic, with test dice coefficient of 92.4%.The results show that our model can better segment left ventricle. We also tested our model on clinical patient ultrasound images, and visualization results proved effectiveness of the model.

Abnormal recognition-assisted and onset-offset aware network for pathological wearable ECG delineation

Electrocardiogram (ECG) delineation is essential to the identification of abnormal cardiac status, especially when ECG signals are remotely monitored with wearable devices. The complexity and diversity of cardiac conditions generate numerous pathological ECG patterns, not only requiring the recognition of normal ECG but also addressing an extensive range of abnormal ECG patterns, posing a challenging task. Therefore, we propose an abnormal recognition-assisted network to integrate supplementary information on diverse ECG patterns. Simultaneously, we design an onset-offset aware loss to enhance precise waveform localization. Specifically, we establish a two-branch framework where ECG delineation serves as the target task, producing the final segmentation results. Additionally, the abnormal recognition-assisted network serves as an auxiliary task, extracting multi-label pathological information from ECGs. This joint learning approach establishes crucial correlations between ECG delineation and associated ECG abnormalities. The correlations enable the model to demonstrate sufficient generalization in the presence of diverse abnormal ECG patterns. Besides, onset-offset aware loss focuses intensively on wave onsets and offsets by applying biased weights to various waveform positions. This approach ensures a focus on precise localization, facilitating seamless integration into cross-entropy loss function. A large-scale wearable 12-lead dataset containing 4,913 signals is collected, offering an extensive range of ECG data for model training. Results demonstrate that our method achieves outstanding performance on two test datasets, attaining sensitivity of 94.97% and 94.27% and an error tolerance lower than 20 ms. Furthermore, our method is effective for various aberrant ECG signals, including ST-segment changes, atrial premature beats, and right and left bundle branch blocks.

VQGNet: An Unsupervised Defect Detection Approach for Complex Textured Steel Surfaces

Defect detection on steel surfaces with complex textures is a critical and challenging task in the industry. The limited number of defect samples and the complexity of the annotation process pose significant challenges. Moreover, performing defect segmentation based on accurate identification further increases the task’s difficulty. To address this issue, we propose VQGNet, an unsupervised algorithm that can precisely recognize and segment defects simultaneously. A feature fusion method based on aggregated attention and a classification-aided module is proposed to segment defects by integrating different features in the original images and the anomaly maps, which direct the attention to the anomalous information instead of the irregular complex texture. The anomaly maps are generated more confidently using strategies for multi-scale feature fusion and neighbor feature aggregation. Moreover, an anomaly generation method suitable for grayscale images is introduced to facilitate the model’s learning on the anomalous samples. The refined anomaly maps and fused features are both input into the classification-aided module for the final classification and segmentation. VQGNet achieves state-of-the-art (SOTA) performance on the industrial steel dataset, with an I-AUROC of 99.6%, I-F1 of 98.8%, P-AUROC of 97.0%, and P-F1 of 80.3%. Additionally, ViT-Query demonstrates robust generalization capabilities in generating anomaly maps based on the Kolektor Surface-Defect Dataset 2.

Learning with Explicit Shape Priors for Medical Image Segmentation.

Medical image segmentation is a fundamental task for medical image analysis and surgical planning. In recent years, UNet-based networks have prevailed in the field of medical image segmentation. However, convolutional neural networks (CNNs) suffer from limited receptive fields, which fail to model the long-range dependency of organs or tumors. Besides, these models are heavily dependent on the training of the final segmentation head. And existing methods can not well address aforementioned limitations simultaneously. Hence, in our work, we proposed a novel shape prior module (SPM), which can explicitly introduce shape priors to promote the segmentation performance of UNet-based models. The explicit shape priors consist of global and local shape priors. The former with coarse shape representations provides networks with capabilities to model global contexts. The latter with finer shape information serves as additional guidance to relieve the heavy dependence on the learnable prototype in the segmentation head. To evaluate the effectiveness of SPM, we conduct experiments on three challenging public datasets. And our proposed model achieves state-of-the-art performance. Furthermore, SPM can serve as a plug-and-play structure into classic CNNs and Transformer-based backbones, facilitating the segmentation task on different datasets. Source codes are available at https://github. com/AlexYouXin/Explicit-Shape-Priors.

Exposing a dual-readout fibre calorimeter to electron beams, in preparation for HiDRa: High-resolution calorimeter for [formula omitted] colliders

Among the proposed accelerators for the post-LHC era are the Future Circular Collider (FCC) and the Circular Electron–Positron Collider (CEPC). Both projects would take advantage of the clean environment and low radiation damage of electron–positron collisions, providing the highest precision studies of electroweak and Higgs physics. The relatively high branching fraction of W, Z and Higgs bosons into hadronic jets makes the precise measurements of these objects an essential aspect on detector development for experiments at future collider facilities. One of the most promising calorimetry techniques for improved hadron energy reconstruction is the dual-readout method, which exploits signals from two different physics processes to correct for the fem of hadron showers, therefore boosting the standalone calorimeter performance. The usage of compact photosensors (e.g. Silicon PhotoMultipliers) for the readout enables a very fine segmentation, opening to particle-flow and advanced neural networks software reconstruction of events. In this contribution, the results of testing a small-scale dual-readout calorimeter prototype, characterised by a mixed PMT and SiPM readout solution, with an electron beam at the CERN SPS facility in the energy range [10, 120] GeV are presented. It follows the description of a larger prototype of the same type, currently under construction in the context of the INFN HiDRa project, that will be large enough to fully contain hadron showers. The design, construction technique and expected performance, as estimated through a Geant4 simulation parameterised on the previous prototype, are presented.

Accelerating segmentation of fossil CT scans through Deep Learning

Recent developments in Deep Learning have opened the possibility for automated segmentation of large and highly detailed CT scan datasets of fossil material. However, previous methodologies have required large amounts of training data to reliably extract complex skeletal structures. Here we present a method for automated Deep Learning segmentation to obtain high-fidelity 3D models of fossils digitally extracted from the surrounding rock, training the model with less than 1%-2% of the total CT dataset. This workflow has the capacity to revolutionise the use of Deep Learning to significantly reduce the processing time of such data and boost the availability of segmented CT-scanned fossil material for future research outputs. Our final Unet segmentation model achieved a validation Dice similarity of 0.96.

Advancing high-resolution remote sensing: a compact and powerful approach to semantic segmentation

ABSTRACT Deep learning (DL)-based approaches are notable for their ability to establish feature associations without relying on physical constraints, unlike traditional strategies that are complex and dependent on expert experience. However, three main challenges hinder the versatility of semantic segmentation models. First, the targets in these images are dense and exist at varying spatial scales, which imposes higher demands on the model for accurate segmentation across scales. Second, the segmentation of small targets in the images is often overlooked, leading to a compromise between fine segmentation and model efficiency. Lastly, the data-intensive nature of remote sensing images and the resource-intensive operations of large-scale networks impose significant communication and computation burdens on edge devices, which may not have sufficient resources to handle them effectively. To address these challenges, this paper proposes a lightweight semantic segmentation method for remote sensing images to achieve high-precision segmentation for multi-scale targets while maintaining low computational complexity. The main components include: (1) embedding the inverted residual block structure to minimize the number of model parameters and computational costs; (2) introducing the parallel irregular space pyramid pooling module to efficiently aggregate multi-scale contextual information for fine-grained recognition of small targets; and (3) embedding transfer learning into the encoder-decoder structure to speed up the convergence rate and improve multi-scale feature fusion capability, thereby reducing semantic information loss. The proposed lightweight method has been extensively tested on real-world high-resolution remote sensing datasets. It achieved PA, MPA, MIoU, and FWIoU scores of 87.90%, 75.76%, 66.29%, and 78.81% on the Vaihingen dataset; 87.03%, 85.31%, 74.85%, and 77.54% on the Potsdam dataset; and 95.37%, 83.33%, 75.70%, and 91.31% on the Aeroscapes dataset. Compared to other popular semantic segmentation models, the proposed method achieved the highest values in all four evaluation indicators, demonstrating its effectiveness and superiority.

Shape-intensity-guided U-net for medical image segmentation

Medical image segmentation has achieved impressive results thanks to U-Net or its alternatives. Yet, most existing methods perform segmentation by classifying individual pixels, tending to ignore the shape-intensity prior information. This may yield implausible segmentation results. Besides, the segmentation performance often drops greatly on unseen datasets. One possible reason is that the model is biased towards texture information, which varies more than shape information across different datasets. In this paper, we introduce a novel Shape-Intensity-Guided U-Net (SIG-UNet) for improving the generalization ability of variants of U-Net in segmenting medical images. Specifically, we adopt the U-Net architecture to reconstruct class-wisely averaged images that only contain the shape-intensity information. We then add an extra similar decoder branch with the reconstruction decoder for segmentation, and apply skip fusion between them. Since the class-wisely averaged image has no any texture information, the reconstruction decoder focuses more on shape and intensity features than the encoder on the original image. Therefore, the final segmentation decoder has less texture bias. Extensive experiments on three segmentation tasks of medical images with different modalities demonstrate that the proposed SIG-UNet achieves promising intra-dataset results while significantly improving the cross-dataset segmentation performance. The source code will be publicly available after acceptance.

ConvNext Mixer‐Based Encoder Decoder Method for Nuclei Segmentation in Histopathology Images

ABSTRACTHistopathology, vital in diagnosing medical conditions, especially in cancer research, relies on analyzing histopathology images (HIs). Nuclei segmentation, a key task, involves precisely identifying cell nuclei boundaries. Manual segmentation by pathologists is time‐consuming, prompting the need for robust automated methods. Challenges in segmentation arise from HI complexities, necessitating advanced techniques. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNNs), have transformed nuclei segmentation. This study emphasizes feature extraction, introducing the ConvNext Mixer‐based Encoder‐Decoder (CNM‐ED) model. Unlike traditional CNN based models, the proposed CNM‐ED model enables the extraction of spatial and long context features to address the inherent complexities of histopathology images. This method leverages a multi‐path strategy using a traditional CNN architecture as well as different paths focused on obtaining customized long context features using the ConvNext Mixer block structure that combines ConvMixer and ConvNext blocks. The fusion of these diverse features in the final segmentation output enables improved accuracy and performance, surpassing existing state‐of‐the‐art segmentation models. Moreover, our multi‐level feature extraction strategy is more effective than models using self‐attention mechanisms such as SwinUnet and TransUnet, which have been frequently used in recent years. Experimental studies were conducted using five different datasets (TNBC, MoNuSeg, CoNSeP, CPM17, and CryoNuSeg) to analyze the performance of the proposed CNM‐ED model. Comparisons were made with various CNN based models in the literature using evaluation metrics such as accuracy, AJI, macro F1 score, macro intersection over union, macro precision, and macro recall. It was observed that the proposed CNM‐ED model achieved highly successful results across all metrics. Through comparisons with state‐art‐of models from the literature, the proposed CNM‐ED model stands out as a promising advancement in nuclei segmentation, addressing the intricacies of histopathological images. The model demonstrates enhanced diagnostic capabilities and holds the potential for significant progress in medical research.

Search and recovery network for camouflaged object detection

Camouflaged object detection aims to accurately identify objects blending into the background. However, existing methods often struggle, especially with small object or multiple objects, due to their reliance on singular strategies. To address this, we introduce a novel Search and Recovery Network (SRNet) using a bionic approach and auxiliary features. SRNet comprises three key modules: the Region Search Module (RSM), Boundary Recovery Module (BRM), and Camouflaged Object Predictor (COP). The RSM mimics predator behavior to locate potential object regions, enhancing object location detection. The BRM refines texture features and recovers object boundaries. The COP fuse multilevel features to predict final segmentation maps. Experimental results on three benchmark datasets show SRNet's superiority over SOTA models, particularly with small and multiple objects. Notably, SRNet achieves performance improvements without significantly increasing model parameters. Moreover, the method exhibits promising performance in downstream tasks such as defect detection, polyp segmentation and military camouflage detection.