Dice Loss Research Articles

A new optimization approach based on neural architecture search to enhance deep U-Net for efficient road segmentation

Neural Architecture Search (NAS) has significantly improved the accuracy of image classification and segmentation. However, these methods concentrate on finding segmentation structures for natural or medical applications. In this study, we introduce a NAS approach based on gradient optimization to identify ideal cell designs for road segmentation. To the best of our knowledge, this work represents the first application of gradient-based NAS to road extraction. Taking insight from the U-Net model and its successful variations in different image segmentation tasks, we propose NAS-enhanced U-Net, illustrated by an equal number of cells in both encoder and decoder levels. While cross-entropy combined with dice loss is commonly used in many segmentation tasks, road extraction brings up a unique challenge due to class imbalance. To address this, we introduce a combination of loss function. This function merges cross-entropy with weighted Dice loss, focusing on elevating the importance of the road class by assigning it a weight (⍵), while background Dice values are disregarded. The results indicate that the optimal weight for the proposed model equals 2. Additionally, our work challenges the assumption that increased model parameters or depth inherently leads to improved performance. Therefore, we establish search spaces 2,3,4,5,6,7 and 8 to automatically choose the optimal depth for model. We present promising segmentation results for our proposed method, achieved without any pretraining on the Massachusetts road dataset. Furthermore, these results are compared with those of 14 models categorized into four groups: U-Net, Segnet, FCN8, and Nas-U-Net.

Enhancing wrist arthroscopy: artificial intelligence applications for bone structure recognition using machine learning

IntroductionWrist arthroscopy is a rapidly expanding surgical discipline, but has a long and challenging learning curve. One of its difficulties is distinguishing the various anatomical structures during the procedure.Although artificial intelligence has made significant progress in recent decades, its potential as a valuable tool in surgery training is largely untapped. Materials and methodsThe objective of this study was to develop an algorithm that could accurately recognize the anatomical bone structures of the wrist during arthroscopy. We prospectively included 20 wrist arthroscopies: 10 in patients and 10 in cadavers. For each surgery, we extracted and labeled images of the various carpal bones. These images were used to create a database for training, validating and testing a structure recognition algorithm. The primary criterion used was a Dice loss detection and categorization score for structures of interest, with a threshold greater than 80%. ResultsThe database contained 511 labeled images (4,088 after data augmentation). We developed a Deeplabv3+ classification algorithm with a U-Net architecture. After training and testing our algorithm, we achieved an average Dice loss score of 89% for carpal bone recognition. ConclusionThis study demonstrated reliable detection of different carpal bones during arthroscopic wrist surgery using artificial intelligence. However, some bones were detected more accurately than others, suggesting that additional algorithm training could further enhance performance. Application in real-life conditions could validate these results and potentially contribute to learning and improvement in arthroscopic wrist surgery. Level of evidenceIV.

Cascade Residual Multiscale Convolution and Mamba-Structured UNet for Advanced Brain Tumor Image Segmentation

In brain imaging segmentation, precise tumor delineation is crucial for diagnosis and treatment planning. Traditional approaches include convolutional neural networks (CNNs), which struggle with processing sequential data, and transformer models that face limitations in maintaining computational efficiency with large-scale data. This study introduces MambaBTS: a model that synergizes the strengths of CNNs and transformers, is inspired by the Mamba architecture, and integrates cascade residual multi-scale convolutional kernels. The model employs a mixed loss function that blends dice loss with cross-entropy to refine segmentation accuracy effectively. This novel approach reduces computational complexity, enhances the receptive field, and demonstrates superior performance for accurately segmenting brain tumors in MRI images. Experiments on the MICCAI BraTS 2019 dataset show that MambaBTS achieves dice coefficients of 0.8450 for the whole tumor (WT), 0.8606 for the tumor core (TC), and 0.7796 for the enhancing tumor (ET) and outperforms existing models in terms of accuracy, computational efficiency, and parameter efficiency. These results underscore the model’s potential to offer a balanced, efficient, and effective segmentation method, overcoming the constraints of existing models and promising significant improvements in clinical diagnostics and planning.

DFA-Net: Dual multi-scale feature aggregation network for vessel segmentation in X-ray digital subtraction angiography

Even though deep learning is fascinated in fields of coronary vessel segmentation in X-ray angiography and achieves prominent progresses, most of those models probably bring high false and missed detections due to indistinct contrast between coronary vessels and background, especially for tiny sub-branches. Image improvement technique is able to better such contrast, while boosting extraneous information, e.g., other tissues with similar intensities and noise. If incorporating features derived from original and enhanced images, the segmentation performance is improved because those images comprise complementary information from different contrasts. Accordingly, inspired from advantages of contrast improvement and encoding-decoding architecture, a dual multi-scale feature aggregation network (named DFA-Net) is introduced for coronary vessel segmentation in digital subtraction angiography (DSA). DFA-Net integrates the contrast improvement using exponent transformation into a semantic segmentation network that individually accepts original and enhanced images as inputs. Through parameter sharing, multi-scale complementary features are aggregated from different contrasts, which strengthens leaning capabilities of networks, and thus achieves an efficient segmentation. Meanwhile, a risk cross-entropy loss is enforced on the segmentation, for availably decreasing false negatives, which is incorporated with Dice loss for joint optimization of the proposed strategy during training. Experimental results demonstrate that DFA-Net can not only work more robustly and effectively for DSA images under diverse conditions, but also achieve better performance, in comparison with state-of-the-art methods. Consequently, DFA-Net has high fidelity and structure similarity to the reference, providing a way for early diagnosis of cardiovascular diseases.

Automatic crack detection on concrete and asphalt surfaces using semantic segmentation network with hierarchical Transformer

In recent studies, deep learning methodologies have shown significant promise in crack detection. However, their practical implementation faces challenges due to the intricate diversity of structural surfaces and the inherent narrowness of cracks. To mitigate these problems, this paper introduces SegFormer, an efficient semantic segmentation model with hierarchical Transformer, for crack detection on concrete and asphalt surfaces in multiple scenarios. The combination of Cross-Entropy (CE) and Dice loss functions is employed to enhance the detection of fine cracks. Additionally, the paper presents an evaluation framework and discusses metrics for assessing crack segmentation results to provide a more precise and comprehensive analysis of model performance. Experimental results indicate that SegFormer outperforms Convolutional Neural Networks (CNNs) such as FCN, U-Net, and DeepLabV3 utilizing different backbones. Notably, the integration of multiple loss functions contributes to a more stable training process, expedites convergence, and yields enhanced results compared to models utilizing individual loss functions.

A comparison framework for deep learning RFI detection algorithms

ABSTRACT In the realm of radio astronomy, the detection of radio frequency interference (RFI) stands as a pivotal pursuit. This study performs a novel comparative analysis of deep learning methodologies and introduces a novel transfer learning method, called fine-tuning. We compare various aspects and factors relating to this problem, including supervised fully convolutional network (FCN) architectures used within the literature, loss functions, regularization techniques, and training methodologies, to establish the most effective strategies for RFI detection. Moreover, the relationship between parameters, FLOPS, and inference times are examined. Fine-tuning involves pre-training models with low-quality aoflagger reference outputs, a very popular and accessible RFI flagging software package, and thereafter re-training the models with high-quality reference outputs. We utilize two data sets: real observations from LOFAR and simulated data from HERA. The mean squared error (MSE) loss function emerges as a robust performer if a high recall is desired. In contrast, the binary cross-entropy (BCE) loss function excels in generalization but falls short in classification performance. The Dice loss function emerges as the top performer, maximizing the F1 score and thereby serving as the choice for our further investigations. Notably, we highlight the important role of data quality and model capacity. In particular, we find that low-capacity models exhibit resilience when trained with low-quality flags from aoflagger, showcasing their ability to mitigate overfitting and overflagging tendencies. In contrast, high-capacity models excel when trained with high-quality flags. Fine-tuning proved to be an effective method to unlearn the overflagging tendencies of aoflagger, whilst requiring very little data.

Rice disease segmentation method based on CBAM-CARAFE-DeepLabv3+

Rice is an important food crop, but it is susceptible to diseases during its growth process. Rapid, accurate, and effective identification of rice diseases is important for targeted measures to control disease spread. It is crucial for improving rice yield and quality. Therefore, this study proposes a CBAM-CARAFE-DeepLabv3+ rice disease segmentation method that combines attention mechanisms and feature recombination. This method focuses on three common diseases in rice growth: bacterial blight, blast, and brown spot disease. To enhance the extraction of favorable features, the algorithm adopts CBAM-RepViT as the backbone network. That is, the Squeeze-and-Excitation (SE) attention mechanism embedded in the efficient and lightweight RepViT network is replaced by the lightweight Convolutional Block Attention Module (CBAM). Compared to the SE attention mechanism, CBAM introduces a spatial attention module that focuses on important spatial positions in the feature map. It allows the model to extract more rich and detailed feature information by attending to both the channel and spatial dimensions of the feature map. Additionally, to further improve the feature extraction ability and image edge segmentation accuracy during upsampling, the lightweight Content-Aware ReAssembly of FEatures (CARAFE) operator is introduced into the decoding module for upsampling. Finally, to address the issue of imbalance between foreground and background pixel ratios in rice disease, a hybrid loss function composed of cross-entropy (CE) loss and Dice loss is proposed. Experimental results show that, compared to other networks such as DeepLabv3+, the proposed CBAM-CARAFE-DeepLabv3+ method achieves further improvement in segmentation accuracy, providing a new method for the development of rice disease segmentation technology.

Autoencoders for real-time SUEP detection

Confining dark sectors with pseudo-conformal dynamics can produce Soft Unclustered Energy Patterns (SUEP), at the Large Hadron Collider: the production of dark quarks in proton–proton collisions leading to a dark shower and the high-multiplicity production of dark hadrons. The final experimental signature is spherically symmetric energy deposits by an anomalously large number of soft Standard Model particles with a transverse energy of O(100)MeV\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\,\ ext {MeV}$$\\end{document}. Assuming Yukawa-like couplings of the scalar portal state, the dominant production mode is gluon fusion, and the dominant background comes from multi-jet QCD events. We have developed a deep learning-based Anomaly Detection technique to reject QCD jets and identify any anomalous signature, including SUEP, in real-time in the High-Level Trigger system of experiments like the Compact Muon Solenoid at the Large Hadron Collider. A deep convolutional neural autoencoder network has been trained using QCD events by taking transverse energy deposits in the inner tracker, electromagnetic calorimeter, and hadron calorimeter sub-detectors as 3-channel image data. Due to the sparse nature of the data, only ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim $$\\end{document}0.5% of the total ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim $$\\end{document}300k\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${300}\\,\ extrm{k}$$\\end{document} image pixels have nonzero values. To tackle this challenge, a nonstandard loss function, the inverse of the so-called Dice Loss, is exploited. The trained autoencoder with learned spatial features of QCD jets can detect 40% of the SUEP events, with a QCD event mistagging rate as low as 2%. The model inference time has been measured using the Intel® CoreTM\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{\ exttt {TM}}$$\\end{document} i5-9600KF processor and found to be ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim $$\\end{document}20ms\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${20}\ extrm{ms}$$\\end{document}, which perfectly satisfies the High-Level Trigger system’s latency of O(102)ms\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal {O}(10^2)~\ extrm{ms}$$\\end{document}. Given the virtue of the unsupervised learning of the autoencoders, the trained model can be applied to any new physics model that predicts an experimental signature anomalous to QCD jets.

Semi-supervised learning towards automated segmentation of PET images with limited annotations: application to lymphoma patients.

Manual segmentation poses a time-consuming challenge for disease quantification, therapy evaluation, treatment planning, and outcome prediction. Convolutional neural networks (CNNs) hold promise in accurately identifying tumor locations and boundaries in PET scans. However, a major hurdle is the extensive amount of supervised and annotated data necessary for training. To overcome this limitation, this study explores semi-supervised approaches utilizing unlabeled data, specifically focusing on PET images of diffuse large B-cell lymphoma (DLBCL) and primary mediastinal large B-cell lymphoma (PMBCL) obtained from two centers. We considered 2-[18F]FDG PET images of 292 patients PMBCL (n = 104) and DLBCL (n = 188) (n = 232 for training and validation, and n = 60 for external testing). We harnessed classical wisdom embedded in traditional segmentation methods, such as the fuzzy clustering loss function (FCM), to tailor the training strategy for a 3D U-Net model, incorporating both supervised and unsupervised learning approaches. Various supervision levels were explored, including fully supervised methods with labeled FCM and unified focal/Dice loss, unsupervised methods with robust FCM (RFCM) and Mumford-Shah (MS) loss, and semi-supervised methods combining FCM with supervised Dice loss (MS + Dice) or labeled FCM (RFCM + FCM). The unified loss function yielded higher Dice scores (0.73 ± 0.11; 95% CI 0.67-0.8) than Dice loss (p value < 0.01). Among the semi-supervised approaches, RFCM + αFCM (α = 0.3) showed the best performance, with Dice score of 0.68 ± 0.10 (95% CI 0.45-0.77), outperforming MS + αDice for any supervision level (any α) (p < 0.01). Another semi-supervised approach with MS + αDice (α = 0.2) achieved Dice score of 0.59 ± 0.09 (95% CI 0.44-0.76) surpassing other supervision levels (p < 0.01). Given the time-consuming nature of manual delineations and the inconsistencies they may introduce, semi-supervised approaches hold promise for automating medical imaging segmentation workflows.

LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation

The intricate task of precisely segmenting retinal vessels from images, which is critical for diagnosing various eye diseases, presents significant challenges for models due to factors such as scale variation, complex anatomical patterns, low contrast, and limitations in training data. Building on these challenges, we offer novel contributions spanning model architecture, loss function design, robustness, and real-time efficacy. To comprehensively address these challenges, a new U-Net-like, lightweight Transformer network for retinal vessel segmentation is presented. By integrating MobileViT+ and a novel local representation in the encoder, our design emphasizes lightweight processing while capturing intricate image structures, enhancing vessel edge precision. A novel joint loss is designed, leveraging the characteristics of weighted cross-entropy and Dice loss to effectively guide the model through the task's challenges, such as foreground-background imbalance and intricate vascular structures. Exhaustive experiments were performed on three prominent retinal image databases. The results underscore the robustness and generalizability of the proposed LiViT-Net, which outperforms other methods in complex scenarios, especially in intricate environments with fine vessels or vessel edges. Importantly, optimized for efficiency, LiViT-Net excels on devices with constrained computational power, as evidenced by its fast performance. To demonstrate the model proposed in this study, a freely accessible and interactive website was established (https://hz-t3.matpool.com:28765?token=aQjYR4hqMI), revealing real-time performance with no login requirements.

A novel difficult-to-segment samples focusing network for oral CBCT image segmentation

Using deep learning technology to segment oral CBCT images for clinical diagnosis and treatment is one of the important research directions in the field of clinical dentistry. However, the blurred contour and the scale difference limit the segmentation accuracy of the crown edge and the root part of the current methods, making these regions become difficult-to-segment samples in the oral CBCT segmentation task. Aiming at the above problems, this work proposed a Difficult-to-Segment Focus Network (DSFNet) for segmenting oral CBCT images. The network utilizes a Feature Capturing Module (FCM) to efficiently capture local and long-range features, enhancing the feature extraction performance. Additionally, a Multi-Scale Feature Fusion Module (MFFM) is employed to merge multiscale feature information. To further improve the loss ratio for difficult-to-segment samples, a hybrid loss function is proposed, combining Focal Loss and Dice Loss. By utilizing the hybrid loss function, DSFNet achieves 91.85% Dice Similarity Coefficient (DSC) and 0.216 mm Average Symmetric Surface Distance (ASSD) performance in oral CBCT segmentation tasks. Experimental results show that the proposed method is superior to current dental CBCT image segmentation techniques and has real-world applicability.

Learning Spatio-Temporal Model of Disease Progression With NeuralODEs From Longitudinal Volumetric Data.

Robust forecasting of the future anatomical changes inflicted by an ongoing disease is an extremely challenging task that is out of grasp even for experienced healthcare professionals. Such a capability, however, is of great importance since it can improve patient management by providing information on the speed of disease progression already at the admission stage, or it can enrich the clinical trials with fast progressors and avoid the need for control arms by the means of digital twins. In this work, we develop a deep learning method that models the evolution of age-related disease by processing a single medical scan and providing a segmentation of the target anatomy at a requested future point in time. Our method represents a time-invariant physical process and solves a large-scale problem of modeling temporal pixel-level changes utilizing NeuralODEs. In addition, we demonstrate the approaches to incorporate the prior domain-specific constraints into our method and define temporal Dice loss for learning temporal objectives. To evaluate the applicability of our approach across different age-related diseases and imaging modalities, we developed and tested the proposed method on the datasets with 967 retinal OCT volumes of 100 patients with Geographic Atrophy and 2823 brain MRI volumes of 633 patients with Alzheimer's Disease. For Geographic Atrophy, the proposed method outperformed the related baseline models in the atrophy growth prediction. For Alzheimer's Disease, the proposed method demonstrated remarkable performance in predicting the brain ventricle changes induced by the disease, achieving the state-of-the-art result on TADPOLE cross-sectional prediction challenge dataset.

Plant Diseased Lesion Image Segmentation and Recognition Based on Improved Multi-Scale Attention Net

Fallen leaf disease can lead to a decrease in leaf area, a decrease in photosynthetic products, insufficient accumulation of fruit sugar, poor coloring and flavor, and a large number of fruits developing sunburn. To address the aforementioned issue, this article introduces a deep learning algorithm designed for the segmentation and recognition of agricultural disease images, particularly those involving leaf lesions. The essence of this algorithm lies in enhancing the Multi-scale Attention Net (MA-Net) encoder and attention mechanism to improve the model’s performance when processing agricultural disease images. Firstly, an analysis was conducted on MA-Net, and its limitations were identified. Compared to res-block, Mix Vision Transformer (MiT) consumes relatively less time during the training process, can better capture global and contextual information in images, and has better robustness and scalability. Then, the feature extraction parts of different networks were used as encoders to join the MA-Net network. Compared to a Position-wise Attention Block (PAB), which has higher computational complexity and requires a larger amount of computing resources, Effective Channel Attention net (ECANet) reduces the number of model parameters and computation by learning the correlation between channels, as well as having a better denoising ability. The experimental results show that the proposed solution has high accuracy and stability in agricultural disease image segmentation and recognition. The mean Intersection over Union (mIoU) is 98.1%, which is 0.2% higher than traditional MA-Net; Dice Loss is 0.9%, which is 0.1% lower than traditional MA-Net.

Building rooftop extraction from aerial imagery using low complexity UNet variant models

ABSTRACT Retrieved rooftops from satellite images have enormous applications. The diversity and complexity of the building structures is challenging. This work proposes to extract building rooftops using two low-complexity DL models: UNet-AstPPD and UNetVasyPPD. The UNet-AstPPD model enhances feature selection by incorporating Atrous Spatial Pyramidal Pooling into the UNet’s decoder. The UNetVasyPPD integrates a VGG-based backbone in the encoder and Asymmetrical Pyramidal-Pooling into the decoder section of the UNet architecture, exhibiting lesser computational complexity. The outcomes demonstrate that Accuracy and Dice Loss of UNet-AstPPD are better. The proposed models training times are just 25.44 minutes and 29.23 minutes respectively.

An N-Shaped Lightweight Network with a Feature Pyramid and Hybrid Attention for Brain Tumor Segmentation.

Brain tumor segmentation using neural networks presents challenges in accurately capturing diverse tumor shapes and sizes while maintaining real-time performance. Additionally, addressing class imbalance is crucial for achieving accurate clinical results. To tackle these issues, this study proposes a novel N-shaped lightweight network that combines multiple feature pyramid paths and U-Net architectures. Furthermore, we ingeniously integrate hybrid attention mechanisms into various locations of depth-wise separable convolution module to improve efficiency, with channel attention found to be the most effective for skip connections in the proposed network. Moreover, we introduce a combination loss function that incorporates a newly designed weighted cross-entropy loss and dice loss to effectively tackle the issue of class imbalance. Extensive experiments are conducted on four publicly available datasets, i.e., UCSF-PDGM, BraTS 2021, BraTS 2019, and MSD Task 01 to evaluate the performance of different methods. The results demonstrate that the proposed network achieves superior segmentation accuracy compared to state-of-the-art methods. The proposed network not only improves the overall segmentation performance but also provides a favorable computational efficiency, making it a promising approach for clinical applications.

HVS-Unsup: Unsupervised cervical cell instance segmentation method based on human visual simulation

Instance segmentation plays an important role in the automatic diagnosis of cervical cancer. Although deep learning-based instance segmentation methods can achieve outstanding performance, they need large amounts of labeled data. This results in a huge consumption of manpower and material resources. To solve this problem, we propose an unsupervised cervical cell instance segmentation method based on human visual simulation, named HVS-Unsup. Our method simulates the process of human cell recognition and incorporates prior knowledge of cervical cells. Specifically, firstly, we utilize prior knowledge to generate three types of pseudo labels for cervical cells. In this way, the unsupervised instance segmentation is transformed to a supervised task. Secondly, we design a Nucleus Enhanced Module (NEM) and a Mask-Assisted Segmentation module (MAS) to address problems of cell overlapping, adhesion, and even scenarios involving visually indistinguishable cases. NEM can accurately locate the nuclei by the nuclei attention feature maps generated by point-level pseudo labels, and MAS can reduce the interference from impurities by updating the weight of the shallow network through the dice loss. Next, we propose a Category-Wise droploss (CW-droploss) to reduce cell omissions in lower-contrast images. Finally, we employ an iterative self-training strategy to rectify mislabeled instances. Experimental results on our dataset MS-cellSeg, the public datasets Cx22 and ISBI2015 demonstrate that HVS-Unsup outperforms existing mainstream unsupervised cervical cell segmentation methods.

ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation

Early intervention in tumors can greatly improve human survival rates. With the development of deep learning technology, automatic image segmentation has taken a prominent role in the field of medical image analysis. Manually segmenting kidneys on CT images is a tedious task, and due to the diversity of these images and varying technical skills of professionals, segmentation results can be inconsistent. To address this problem, a novel ASD-Net network is proposed in this paper for kidney and kidney tumor segmentation tasks. First, the proposed network employs newly designed Adaptive Spatial-channel Convolution Optimization (ASCO) blocks to capture anisotropic information in the images. Then, other newly designed blocks, i.e., Dense Dilated Enhancement Convolution (DDEC) blocks, are utilized to enhance feature propagation and reuse it across the network, thereby improving its segmentation accuracy. To allow the network to segment complex and small kidney tumors more effectively, the Atrous Spatial Pyramid Pooling (ASPP) module is incorporated in its middle layer. With its generalized pyramid feature, this module enables the network to better capture and understand context information at various scales within the images. In addition to this, the concurrent spatial and channel squeeze & excitation (scSE) attention mechanism is adopted to better comprehend and manage context information in the images. Additional encoding layers are also added to the base (U-Net) and connected to the original encoding layer through skip connections. The resultant enhanced U-Net structure allows for better extraction and merging of high-level and low-level features, further boosting the network’s ability to restore segmentation details. In addition, the combined Binary Cross Entropy (BCE)-Dice loss is utilized as the network's loss function. Experiments, conducted on the KiTS19 dataset, demonstrate that the proposed ASD-Net network outperforms the existing segmentation networks according to all evaluation metrics used, except for recall in the case of kidney tumor segmentation, where it takes the second place after Attention-UNet.Graphical

Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices

Evaluating classification accuracy is a key component of the training and validation stages of thematic map production, and the choice of metric has profound implications for both the success of the training process and the reliability of the final accuracy assessment. We explore key considerations in selecting and interpreting loss and assessment metrics in the context of data imbalance, which arises when the classes have unequal proportions within the dataset or landscape being mapped. The challenges involved in calculating single, integrated measures that summarize classification success, especially for datasets with considerable data imbalance, have led to much confusion in the literature. This confusion arises from a range of issues, including a lack of clarity over the redundancy of some accuracy measures, the importance of calculating final accuracy from population-based statistics, the effects of class imbalance on accuracy statistics, and the differing roles of accuracy measures when used for training and final evaluation. In order to characterize classification success at the class level, users typically generate averages from the class-based measures. These averages are sometimes generated at the macro-level, by taking averages of the individual-class statistics, or at the micro-level, by aggregating values within a confusion matrix, and then, calculating the statistic. We show that the micro-averaged producer’s accuracy (recall), user’s accuracy (precision), and F1-score, as well as weighted macro-averaged statistics where the class prevalences are used as weights, are all equivalent to each other and to the overall accuracy, and thus, are redundant and should be avoided. Our experiment, using a variety of loss metrics for training, suggests that the choice of loss metric is not as complex as it might appear to be, despite the range of choices available, which include cross-entropy (CE), weighted CE, and micro- and macro-Dice. The highest, or close to highest, accuracies in our experiments were obtained by using CE loss for models trained with balanced data, and for models trained with imbalanced data, the highest accuracies were obtained by using weighted CE loss. We recommend that, since weighted CE loss used with balanced training is equivalent to CE, weighted CE loss is a good all-round choice. Although Dice loss is commonly suggested as an alternative to CE loss when classes are imbalanced, micro-averaged Dice is similar to overall accuracy, and thus, is particularly poor for training with imbalanced data. Furthermore, although macro-Dice resulted in models with high accuracy when the training used balanced data, when the training used imbalanced data, the accuracies were lower than for weighted CE. In summary, the significance of this paper lies in its provision of readers with an overview of accuracy and loss metric terminology, insight regarding the redundancy of some measures, and guidance regarding best practices.

Optical gas imaging for leak detection based on improved deeplabv3+ model

Optical gas imaging (OGI) is a technique to dynamically observe gas leaks with a wide detection range. As gasses are mobile and diffusive, traditional motion detection methods are difficult to adapt to the change of gas motion state with the environment, resulting in poor segmentation effect and low accuracy. Therefore, this paper proposes a deep learning-based semantic segmentation method of gas for optical gas imaging detection based on DeeplabV3+ model. Firstly, MobileNetV2 is used to replace the original backbone network to reduced model parameters and complexity and facilitates the edge deployment of the model. Second, the dense atrous spatial pyramid pooling (DenseASPP) module is introduced to improve the atrous spatial pyramid pooling (ASPP) module of the model to increase the model sensing field and improve the model gas segmentation accuracy. Finally, Dice loss is used to solve the sample imbalance problem. The experimental results show that IOU and F1 score of the model are improved by 4.10% and 2.47%, and it provides a new intelligent detection method for optical gas imaging.

Data-limited and imbalanced bladder wall segmentation with confidence map-guided residual networks via transfer learning

Purpose: To develop an algorithm using a residual base network guided by the confidence map and transfer learning for limited dataset size and imbalanced bladder wall segmentation.Methods: The geometric transformation was made to the training data for data augmentation, and a pre-trained Resnet50 model on ImageNet was also adopted for transfer learning. Three loss functions were put into the pre-trained Resnet50 network, they are the cross-entropy loss function (CELF), the generalized Dice loss function (GDLF) and the Tversky loss function (TLF). Three models were obtained through training, and three corresponding confidence maps were output after entering a new image. By selecting the point with the maximum confidence values at the corresponding position, we merged the three images into one figure, performed threshold filtering to avoid external anomalies, and finally obtained the segmentation result.Results: The average Jaccard similarity coefficient of model training based on the CELF, GDLF and TLF is 0.9173, 0.8355, 0.8757, respectively, and the average Jaccard similarity coefficient of our algorithm can be achieved at 0.9282. In contrast, the classical 2D U-Net algorithm can only achieve 0.518. We also qualitatively give the reasons for the improvement of model performance.Conclusion: Our study demonstrates that a confidence map-assisted residual base network can accurately segment bladder walls on a limited-size data set. Compared with the segmentation results of each model alone, our method originally improves the accuracy of the segmentation results by combining confidence map guidance with threshold filtering.