Developing a deep learning method for medical segmentation tasks heavily relies on a large amount of labeled data. However, the annotations require professional knowledge and are limited in number. Recently, semi-supervised learning has demonstrated great potential in medical segmentation tasks. Most existing methods related to cardiac magnetic resonance images only focus on regular images with similar domains and high image quality. A semi-supervised domain generalization method was developed in [2], which enhances the quality of pseudo labels on varied datasets. In this paper, we follow the strategy in [2] and present a domain generalization method for semi-supervised medical segmentation. Our main goal is to improve the quality of pseudo labels under extreme MRI Analysis with various domains. We perform Fourier transformation on input images to learn low-level statistics and cross-domain information. Then we feed the augmented images as input to the double cross pseudo supervision networks to calculate the variance among pseudo labels. We evaluate our method on the CMRxMotion dataset [1]. With only partially labeled data and without domain labels, our approach consistently generates accurate segmentation results of cardiac magnetic resonance images with different respiratory motions. Code is available at: https://github.com/MAWanqin2002/STACOM2022Ma
Understanding the steps required to perform a task is an important skill for AI systems. Learning these steps from instructional videos involves two subproblems: (i) identifying the temporal boundary of sequentially occurring segments and (ii) summarizing these steps in natural language. We refer to this task as Procedure Segmentation and Summarization (PSS). In this paper, we take a closer look at PSS and propose three fundamental improvements over current methods. The segmentation task is critical, as generating a correct summary requires each step of the procedure to be correctly identified. However, current segmentation metrics often overestimate the segmentation quality because they do not consider the temporal order of segments. In our first contribution, we propose a new segmentation metric that takes into account the order of segments, giving a more reliable measure of the accuracy of a given predicted segmentation. Current PSS methods are typically trained by proposing segments, matching them with the ground truth and computing a loss. However, much like segmentation metrics, existing matching algorithms do not consider the temporal order of the mapping between candidate segments and the ground truth. In our second contribution, we propose a matching algorithm that constrains the temporal order of segment mapping, and is also differentiable. Lastly, we introduce multi-modal feature training for PSS, which further improves segmentation. We evaluate our approach on two instructional video datasets (YouCook2 and Tasty) and observe an improvement over the state-of-the-art of $\sim7\%$ and $\sim2.5\%$ for procedure segmentation and summarization, respectively.
Early stopping techniques can be utilized to decrease the time cost, however currently the ultimate goal of early stopping techniques is closely related to the accuracy upgrade or the ability of the neural network to generalize better on unseen data without being large or complex in structure and not directly with its efficiency. Time efficiency is a critical factor in neural networks, especially when dealing with the segmentation of 3D point cloud data, not only because a neural network itself is computationally expensive, but also because point clouds are large and noisy data, making learning processes even more costly. In this paper, we propose a new early stopping technique based on fundamental mathematics aiming to upgrade the trade-off between the learning efficiency and accuracy of neural networks dealing with 3D point clouds. Our results show that by employing our early stopping technique in four distinct and highly utilized neural networks in segmenting 3D point clouds, the training time efficiency of the models is greatly improved, with efficiency gain values reaching up to 94\%, while the models achieving in just a few epochs approximately similar segmentation accuracy metric values like the ones that are obtained in the training of the neural networks in 200 epochs. Also, our proposal outperforms four conventional early stopping approaches in segmentation accuracy, implying a promising innovative early stopping technique in point cloud segmentation.
Convolutional Neural Networks have played a significant role in various medical imaging tasks like classification and segmentation. They provide state-of-the-art performance compared to classical image processing algorithms. However, the major downside of these methods is the high computational complexity, reliance on high-performance hardware like GPUs and the inherent black-box nature of the model. In this paper, we propose quantised stand-alone self-attention based models as an alternative to traditional CNNs. In the proposed class of networks, convolutional layers are replaced with stand-alone self-attention layers, and the network parameters are quantised after training. We experimentally validate the performance of our method on classification and segmentation tasks. We observe a $50-80\%$ reduction in model size, $60-80\%$ lesser number of parameters, $40-85\%$ fewer FLOPs and $65-80\%$ more energy efficiency during inference on CPUs. The code will be available at \href {https://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Network}{https://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Network}.
Vessel segmentation in medical images is one of the important tasks in the diagnosis of vascular diseases and therapy planning. Although learning-based segmentation approaches have been extensively studied, a large amount of ground-truth labels are required in supervised methods and confusing background structures make neural networks hard to segment vessels in an unsupervised manner. To address this, here we introduce a novel diffusion adversarial representation learning (DARL) model that leverages a denoising diffusion probabilistic model with adversarial learning, and apply it to vessel segmentation. In particular, for self-supervised vessel segmentation, DARL learns the background signal using a diffusion module, which lets a generation module effectively provide vessel representations. Also, by adversarial learning based on the proposed switchable spatially-adaptive denormalization, our model estimates synthetic fake vessel images as well as vessel segmentation masks, which further makes the model capture vessel-relevant semantic information. Once the proposed model is trained, the model generates segmentation masks in a single step and can be applied to general vascular structure segmentation of coronary angiography and retinal images. Experimental results on various datasets show that our method significantly outperforms existing unsupervised and self-supervised vessel segmentation methods.
Automated optic disc (OD) and optic cup (OC) segmentation in fundus images is relevant to efficiently measure the vertical cup-to-disc ratio (vCDR), a biomarker commonly used in ophthalmology to determine the degree of glaucomatous optic neuropathy. In general this is solved using coarse-to-fine deep learning algorithms in which a first stage approximates the OD and a second one uses a crop of this area to predict OD/OC masks. While this approach is widely applied in the literature, there are no studies analyzing its real contribution to the results. In this paper we present a comprehensive analysis of different coarse-to-fine designs for OD/OC segmentation using 5 public databases, both from a standard segmentation perspective and for estimating the vCDR for glaucoma assessment. Our analysis shows that these algorithms not necessarily outperfom standard multi-class single-stage models, especially when these are learned from sufficiently large and diverse training sets. Furthermore, we noticed that the coarse stage achieves better OD segmentation results than the fine one, and that providing OD supervision to the second stage is essential to ensure accurate OC masks. Moreover, both the single-stage and two-stage models trained on a multi-dataset setting showed results in pair or even better than other state-of-the-art alternatives, while ranking first in REFUGE for OD/OC segmentation. Finally, we evaluated the models for vCDR prediction in comparison with six ophthalmologists on a subset of AIROGS images, to understand them in the context of inter-observer variability. We noticed that vCDR estimates recovered both from single-stage and coarse-to-fine models can obtain good glaucoma detection results even when they are not highly correlated with manual measurements from experts.
Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks.
Transformers are quickly becoming one of the most heavily applied deep learning architectures across modalities, domains, and tasks. In vision, on top of ongoing efforts into plain transformers, hierarchical transformers have also gained significant attention, thanks to their performance and easy integration into existing frameworks. These models typically employ localized attention mechanisms, such as the sliding-window Neighborhood Attention (NA) or Swin Transformer's Shifted Window Self Attention. While effective at reducing self attention's quadratic complexity, local attention weakens two of the most desirable properties of self attention: long range inter-dependency modeling, and global receptive field. In this paper, we introduce Dilated Neighborhood Attention (DiNA), a natural, flexible and efficient extension to NA that can capture more global context and expand receptive fields exponentially at no additional cost. NA's local attention and DiNA's sparse global attention complement each other, and therefore we introduce Dilated Neighborhood Attention Transformer (DiNAT), a new hierarchical vision transformer built upon both. DiNAT variants enjoy significant improvements over strong baselines such as NAT, Swin, and ConvNeXt. Our large model is faster and ahead of its Swin counterpart by 1.6% box AP in COCO object detection, 1.4% mask AP in COCO instance segmentation, and 1.4% mIoU in ADE20K semantic segmentation. Paired with new frameworks, our large variant is the new state of the art panoptic segmentation model on COCO (58.5 PQ) and ADE20K (49.4 PQ), and instance segmentation model on Cityscapes (45.1 AP) and ADE20K (35.4 AP) (no extra data). It also matches the state of the art specialized semantic segmentation models on ADE20K (58.1 mIoU), and ranks second on Cityscapes (84.5 mIoU) (no extra data).
Text segmentation aims to divide text into contiguous, semantically coherent segments, while segment labeling deals with producing labels for each segment. Past work has shown success in tackling segmentation and labeling for documents and conversations. This has been possible with a combination of task-specific pipelines, supervised and unsupervised learning objectives. In this work, we propose a single encoder-decoder neural network that can handle long documents and conversations, trained simultaneously for both segmentation and segment labeling using only standard supervision. We successfully show a way to solve the combined task as a pure generation task, which we refer to as structured summarization. We apply the same technique to both document and conversational data, and we show state of the art performance across datasets for both segmentation and labeling, under both high- and low-resource settings. Our results establish a strong case for considering text segmentation and segment labeling as a whole, and moving towards general-purpose techniques that don't depend on domain expertise or task-specific components.
Fast and efficient semantic segmentation of large-scale LiDAR point clouds is a fundamental problem in autonomous driving. To achieve this goal, the existing point-based methods mainly choose to adopt Random Sampling strategy to process large-scale point clouds. However, our quantative and qualitative studies have found that Random Sampling may be less suitable for the autonomous driving scenario, since the LiDAR points follow an uneven or even long-tailed distribution across the space, which prevents the model from capturing sufficient information from points in different distance ranges and reduces the model's learning capability. To alleviate this problem, we propose a new Polar Cylinder Balanced Random Sampling method that enables the downsampled point clouds to maintain a more balanced distribution and improve the segmentation performance under different spatial distributions. In addition, a sampling consistency loss is introduced to further improve the segmentation performance and reduce the model's variance under different sampling methods. Extensive experiments confirm that our approach produces excellent performance on both SemanticKITTI and SemanticPOSS benchmarks, achieving a 2.8% and 4.0% improvement, respectively. The source code is available at https://github.com/huixiancheng/PCB-RandNet.
Planetary rover missions must utilize machine learning-based perception to continue extra-terrestrial exploration with little to no human presence. Martian terrain segmentation has been critical for rover navigation and hazard avoidance to perform further exploratory tasks, e.g. soil sample collection and searching for organic compounds. Current Martian terrain segmentation models require a large amount of labeled data to achieve acceptable performance, and also require retraining for deployment across different domains, i.e. different rover missions, or different tasks, i.e. geological identification and navigation. This research proposes a semi-supervised learning approach that leverages unsupervised contrastive pretraining of a backbone for a multi-mission semantic segmentation for Martian surfaces. This model will expand upon the current Martian segmentation capabilities by being able to deploy across different Martian rover missions for terrain navigation, by utilizing a mixed-domain training set that ensures feature diversity. Evaluation results of using average pixel accuracy show that a semi-supervised mixed-domain approach improves accuracy compared to single domain training and supervised training by reaching an accuracy of 97% for the Mars Science Laboratory's Curiosity Rover and 79.6% for the Mars 2020 Perseverance Rover. Further, providing different weighting methods to loss functions improved the models correct predictions for minority or rare classes by over 30% using the recall metric compared to standard cross-entropy loss. These results can inform future multi-mission and multi-task semantic segmentation for rover missions in a data-efficient manner.
Metabolic health is increasingly implicated as a risk factor across conditions from cardiology to neurology, and efficiency assessment of body composition is critical to quantitatively characterizing these relationships. 2D low dose single slice computed tomography (CT) provides a high resolution, quantitative tissue map, albeit with a limited field of view. Although numerous potential analyses have been proposed in quantifying image context, there has been no comprehensive study for low-dose single slice CT longitudinal variability with automated segmentation. We studied a total of 1816 slices from 1469 subjects of Baltimore Longitudinal Study on Aging (BLSA) abdominal dataset using supervised deep learning-based segmentation and unsupervised clustering method. 300 out of 1469 subjects that have two year gap in their first two scans were pick out to evaluate longitudinal variability with measurements including intraclass correlation coefficient (ICC) and coefficient of variation (CV) in terms of tissues/organs size and mean intensity. We showed that our segmentation methods are stable in longitudinal settings with Dice ranged from 0.821 to 0.962 for thirteen target abdominal tissues structures. We observed high variability in most organ with ICC<0.5, low variability in the area of muscle, abdominal wall, fat and body mask with average ICC>0.8. We found that the variability in organ is highly related to the cross-sectional position of the 2D slice. Our efforts pave quantitative exploration and quality control to reduce uncertainties in longitudinal analysis.
In the manufacturing process of heavy industrial equipment, the specific unit in the welding diagram is first manually redrawn and then the corresponding sheet metal parts are cut, which is inefficient. To this end, this paper proposes a U-net-based method for the segmentation and extraction of specific units in welding engineering drawings. This method enables the cutting device to automatically segment specific graphic units according to visual information and automatically cut out sheet metal parts of corresponding shapes according to the segmentation results. This process is more efficient than traditional human-assisted cutting. Two weaknesses in the U-net network will lead to a decrease in segmentation performance: first, the focus on global semantic feature information is weak, and second, there is a large dimensional difference between shallow encoder features and deep decoder features. Based on the CBAM (Convolutional Block Attention Module) attention mechanism, this paper proposes a U-net jump structure model with an attention mechanism to improve the network's global semantic feature extraction ability. In addition, a U-net attention mechanism model with dual pooling convolution fusion is designed, the deep encoder's maximum pooling + convolution features and the shallow encoder's average pooling + convolution features are fused vertically to reduce the dimension difference between the shallow encoder and deep decoder. The dual-pool convolutional attention jump structure replaces the traditional U-net jump structure, which can effectively improve the specific unit segmentation performance of the welding engineering drawing. Using vgg16 as the backbone network, experiments have verified that the IoU, mAP, and Accu of our model in the welding engineering drawing dataset segmentation task are 84.72%, 86.84%, and 99.42%, respectively.
Coronary Heart Disease (CHD) is a leading cause of death in the modern world. The development of modern analytical tools for diagnostics and treatment of CHD is receiving substantial attention from the scientific community. Deep learning-based algorithms, such as segmentation networks and detectors, play an important role in assisting medical professionals by providing timely analysis of a patient's angiograms. This paper focuses on X-Ray Coronary Angiography (XCA), which is considered to be a "gold standard" in the diagnosis and treatment of CHD. First, we describe publicly available datasets of XCA images. Then, classical and modern techniques of image preprocessing are reviewed. In addition, common frame selection techniques are discussed, which are an important factor of input quality and thus model performance. In the following two chapters we discuss modern vessel segmentation and stenosis detection networks and, finally, open problems and current limitations of the current state-of-the-art.
The goal of ACM MMSports2022 DeepSportRadar Instance Segmentation Challenge is to tackle the segmentation of individual humans including players, coaches and referees on a basketball court. And the main characteristics of this challenge are there is a high level of occlusions between players and the amount of data is quite limited. In order to address these problems, we designed a strong instance segmentation pipeline. Firstly, we employed a proper data augmentation strategy for this task mainly including photometric distortion transform and copy-paste strategy, which can generate more image instances with a wider distribution. Secondly, we employed a strong segmentation model, Hybrid Task Cascade based detector on the Swin-Base based CBNetV2 backbone, and we add MaskIoU head to HTCMaskHead that can simply and effectively improve the performance of instance segmentation. Finally, the SWA training strategy was applied to improve the performance further. Experimental results demonstrate the proposed pipeline can achieve a competitive result on the DeepSportRadar challenge, with [email omitted]:0.95 on the challenge set. Source code is available at https://github.com/YJingyu/Instanc_Segmentation_Pro.
Temporal action segmentation (TAS) is a critical step toward long-term video understanding. Recent studies follow a pattern that builds models based on features instead of raw video picture information. However, we claim those models are trained complicatedly and limit application scenarios. It is hard for them to segment human actions of video in real time because they must work after the full video features are extracted. As the real-time action segmentation task is different from TAS task, we define it as streaming video real-time temporal action segmentation (SVTAS) task. In this paper, we propose a real-time end-to-end multi-modality model for SVTAS task. More specifically, under the circumstances that we cannot get any future information, we segment the current human action of streaming video chunk in real time. Furthermore, the model we propose combines the last steaming video chunk feature extracted by language model with the current image feature extracted by image model to improve the quantity of real-time temporal action segmentation. To the best of our knowledge, it is the first multi-modality real-time temporal action segmentation model. Under the same evaluation criteria as full video temporal action segmentation, our model segments human action in real time with less than 40% of state-of-the-art model computation and achieves 90% of the accuracy of the full video state-of-the-art model.
Detection and segmentation of moving obstacles, along with prediction of the future occupancy states of the local environment, are essential for autonomous vehicles to proactively make safe and informed decisions. In this paper, we propose a framework that integrates the two capabilities together using deep neural network architectures. Our method first detects and segments moving objects in the scene, and uses this information to predict the spatiotemporal evolution of the environment around autonomous vehicles. To address the problem of direct integration of both static-dynamic object segmentation and environment prediction models, we propose using occupancy-based environment representations across the whole framework. Our method is validated on the real-world Waymo Open Dataset and demonstrates higher prediction accuracy than baseline methods.
Performance metrics for medical image segmentation models are used to measure the agreement between the reference annotation and the predicted segmentation. Usually, overlap metrics, such as the Dice, are used as a metric to evaluate the performance of these models in order for results to be comparable. However, there is a mismatch between the distributions of cases and difficulty level of segmentation tasks in public data sets compared to clinical practice. Common metrics fail to measure the impact of this mismatch, especially for clinical data sets that include low signal pathologies, a difficult segmentation task, and uncertain, small, or empty reference annotations. This limitation may result in ineffective research of machine learning practitioners in designing and optimizing models. Dimensions of evaluating clinical value include consideration of the uncertainty of reference annotations, independence from reference annotation volume size, and evaluation of classification of empty reference annotations. We study how uncertain, small, and empty reference annotations influence the value of metrics for medical image segmentation on an in-house data set regardless of the model. We examine metrics behavior on the predictions of a standard deep learning framework in order to identify metrics with clinical value. We compare to a public benchmark data set (BraTS 2019) with a high-signal pathology and certain, larger, and no empty reference annotations. We may show machine learning practitioners, how uncertain, small, or empty reference annotations require a rethinking of the evaluation and optimizing procedures. The evaluation code was released to encourage further analysis of this topic. https://github.com/SophieOstmeier/UncertainSmallEmpty.git
Remote sensing benefits habitat conservation by making monitoring of large areas easier compared to field surveying especially if the remote sensed data can be automatically analyzed. An important aspect of monitoring is classifying and mapping habitat types present in the monitored area. Automatic classification is a difficult task, as classes have fine-grained differences and their distributions are long-tailed and unbalanced. Usually training data used for automatic land cover classification relies on fully annotated segmentation maps, annotated from remote sensed imagery to a fairly high-level taxonomy, i.e., classes such as forest, farmland, or urban area. A challenge with automatic habitat classification is that reliable data annotation requires field-surveys. Therefore, full segmentation maps are expensive to produce, and training data is often sparse, point-like, and limited to areas accessible by foot. Methods for utilizing these limited data more efficiently are needed. We address these problems by proposing a method for habitat classification and mapping, and apply this method to classify the entire northern Finnish Lapland area into Natura2000 classes. The method is characterized by using finely-grained, sparse, single-pixel annotations collected from the field, combined with large amounts of unannotated data to produce segmentation maps. Supervised, unsupervised and semi-supervised methods are compared, and the benefits of transfer learning from a larger out-of-domain dataset are demonstrated. We propose a \ac{CNN} biased towards center pixel classification ensembled with a random forest classifier, that produces higher quality classifications than the models themselves alone. We show that cropping augmentations, test-time augmentation and semi-supervised learning can help classification even further.
Among various sensors for assisted and autonomous driving systems, automotive radar has been considered as a robust and low-cost solution even in adverse weather or lighting conditions. With the recent development of radar technologies and open-sourced annotated data sets, semantic segmentation with radar signals has become very promising. However, existing methods are either computationally expensive or discard significant amounts of valuable information from raw 3D radar signals by reducing them to 2D planes via averaging. In this work, we introduce ERASE-Net, an Efficient RAdar SEgmentation Network to segment the raw radar signals semantically. The core of our approach is the novel detect-then-segment method for raw radar signals. It first detects the center point of each object, then extracts a compact radar signal representation, and finally performs semantic segmentation. We show that our method can achieve superior performance on radar semantic segmentation task compared to the state-of-the-art (SOTA) technique. Furthermore, our approach requires up to 20x less computational resources. Finally, we show that the proposed ERASE-Net can be compressed by 40% without significant loss in performance, significantly more than the SOTA network, which makes it a more promising candidate for practical automotive applications.