1,130 results match your criteria semantic segmentation

Learned Gradient Compression for Distributed Deep Learning.

IEEE Trans Neural Netw Learn Syst 2021 Jun 10;PP. Epub 2021 Jun 10.

Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several computational nodes that have access to different chunks of the data. This approach, however, entails high communication rates and latency because of the computed gradients that need to be shared among nodes at every iteration. Read More

View Article and Full-Text PDF

Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering.

IEEE Trans Pattern Anal Mach Intell 2021 Jun 9;PP. Epub 2021 Jun 9.

Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution diverges from the target one. Mainstream UDA methods strive to learn domain-aligned features. Although impressive results have been achieved, these methods have a potential risk of damaging the intrinsic data structures of target discrimination, raising an issue of generalization particularly for UDA tasks in an inductive setting. Read More

View Article and Full-Text PDF

Part-Based Semantic Transform for Few-Shot Semantic Segmentation.

IEEE Trans Neural Netw Learn Syst 2021 Jun 8;PP. Epub 2021 Jun 8.

Few-shot semantic segmentation remains an open problem for the lack of an effective method to handle the semantic misalignment between objects. In this article, we propose part-based semantic transform (PST) and target at aligning object semantics in support images with those in query images by semantic decomposition-and-match. The semantic decomposition process is implemented with prototype mixture models (PMMs), which use an expectation-maximization (EM) algorithm to decompose object semantics into multiple prototypes corresponding to object parts. Read More

View Article and Full-Text PDF

Image Stitching Based on Semantic Planar Region Consensus.

IEEE Trans Image Process 2021 Jun 8;PP. Epub 2021 Jun 8.

Image stitching for two images without a global transformation between them is notoriously difficult. In this paper, noticing the importance of semantic planar structures under perspective geometry, we propose a new image stitching method which stitches images by allowing for the alignment of a set of matched dominant semantic planar regions. Clearly different from previous methods resorting to plane segmentation, the key to our approach is to utilize rich semantic information directly from RGB images to extract semantic planar image regions with a deep Convolutional Neural Network (CNN). Read More

View Article and Full-Text PDF

CMA-Net: Cross-modal Cross-Attention Network for Acute Ischemic Stroke Lesion Segmentation based on CT Perfusion Scans.

IEEE Trans Biomed Eng 2021 Jun 8;PP. Epub 2021 Jun 8.

Objective: Based on the hypothesis that adding a cross-modal and cross-attention (CMA) mechanism into a deep learning network improves accuracy and efficacy of medical image segmentation, we propose to test a novel network to segment acute ischemic stroke (AIS) lesions from four CT perfusion (CTP) maps.

Methods: The proposed network uses a CMA module directly to establish a spatial-wise relationship by using the multigroup non-local attention operation between two modal features and performs dynamic group-wise recalibration through group attention block. This CMA-Net has a multipath encoder-decoder architecture, in which each modality is processed in different streams on the encoding path, and the pair related parameter modalities are used to bridge attention across multimodal information through the CMA module. Read More

View Article and Full-Text PDF

Domain Shift Preservation for Zero-Shot Domain Adaptation.

IEEE Trans Image Process 2021 11;30:5505-5517. Epub 2021 Jun 11.

In learning-based image processing a model that is learned in one domain often performs poorly in another since the image samples originate from different sources and thus have different distributions. Domain adaptation techniques alleviate the problem of domain shift by learning transferable knowledge from the source domain to the target domain. Zero-shot domain adaptation (ZSDA) refers to a category of challenging tasks in which no target-domain sample for the task of interest is accessible for training. Read More

View Article and Full-Text PDF

Confidence Estimation via Auxiliary Models.

IEEE Trans Pattern Anal Mach Intell 2021 Jun 4;PP. Epub 2021 Jun 4.

Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP). We show that TCP offers better properties for confidence estimation than standard maximum class probability (MCP). Read More

View Article and Full-Text PDF

Orchard Mapping with Deep Learning Semantic Segmentation.

Sensors (Basel) 2021 May 31;21(11). Epub 2021 May 31.

Institute for Bio-Economy and Agri-Technology (iBO), Centre for Research and Technology-Hellas (CERTH), GR57001 Thessaloniki, Greece.

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e. Read More

View Article and Full-Text PDF

Research on Discrete Semantics in Continuous Hand Joint Movement Based on Perception and Expression.

Sensors (Basel) 2021 May 27;21(11). Epub 2021 May 27.

School of Mechanical Engineering, Southeast University, Nanjing 211189, China.

Continuous movements of the hand contain discrete expressions of meaning, forming a variety of semantic gestures. For example, it is generally considered that the bending of the finger includes three semantic states of bending, half bending, and straightening. However, there is still no research on the number of semantic states that can be conveyed by each movement primitive of the hand, especially the interval of each semantic state and the representative movement angle. Read More

View Article and Full-Text PDF

3T MRI-Radiomic Approach to Predict for Lymph Node Status in Breast Cancer Patients.

Cancers (Basel) 2021 May 6;13(9). Epub 2021 May 6.

Unit of Computer Systems and Bioinformatics, Department of Engineering, University of Rome "Campus Bio-medico", Via Alvaro del Portillo, 21, 00128 Rome, Italy.

Background: axillary lymph node (LN) status is one of the main breast cancer prognostic factors and it is currently defined by invasive procedures. The aim of this study is to predict LN metastasis combining MRI radiomics features with primary breast tumor histological features and patients' clinical data.

Methods: 99 lesions on pre-treatment contrasted 3T-MRI (DCE). Read More

View Article and Full-Text PDF

Multi-Scale Squeeze U-SegNet with Multi Global Attention for Brain MRI Segmentation.

Sensors (Basel) 2021 May 12;21(10). Epub 2021 May 12.

Department of Information and Communications Engineering, Chosun University, Gwangju 61452, Korea.

In this paper, we propose a multi-scale feature extraction with novel attention-based convolutional learning using the U-SegNet architecture to achieve segmentation of brain tissue from a magnetic resonance image (MRI). Although convolutional neural networks (CNNs) show enormous growth in medical image segmentation, there are some drawbacks with the conventional CNN models. In particular, the conventional use of encoder-decoder approaches leads to the extraction of similar low-level features multiple times, causing redundant use of information. Read More

View Article and Full-Text PDF

Multi-Level and Multi-Scale Feature Aggregation Network for Semantic Segmentation in Vehicle-Mounted Scenes.

Yong Liao Qiong Liu

Sensors (Basel) 2021 May 9;21(9). Epub 2021 May 9.

School of Software Engineering, South China University of Technology, Guangzhou 510006, China.

The main challenges of semantic segmentation in vehicle-mounted scenes are object scale variation and trading off model accuracy and efficiency. Lightweight backbone networks for semantic segmentation usually extract single-scale features layer-by-layer only by using a fixed receptive field. Most modern real-time semantic segmentation networks heavily compromise spatial details when encoding semantics, and sacrifice accuracy for speed. Read More

View Article and Full-Text PDF

DCANet: Dual contextual affinity network for mass segmentation in whole mammograms.

Med Phys 2021 Jun 1. Epub 2021 Jun 1.

School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China.

Purpose: Breast mass segmentation in mammograms remains a crucial yet challenging topic in computer-aided diagnosis systems. Existing algorithms mainly used mass-centered patches to achieve mass segmentation, which is time-consuming and unstable in clinical diagnosis. Therefore, we aim to directly perform fully automated mass segmentation in whole mammograms with deep learning solution. Read More

View Article and Full-Text PDF

LCC-Net: A Lightweight Cross-Consistency Network for Semisupervised Cardiac MR Image Segmentation.

Comput Math Methods Med 2021 17;2021:9960199. Epub 2021 May 17.

College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China.

Semantic segmentation plays a crucial role in cardiac magnetic resonance (MR) image analysis. Although supervised deep learning methods have made significant performance improvements, they highly rely on a large amount of pixel-wise annotated data, which are often unavailable in clinical practices. Besides, top-performing methods usually have a vast number of parameters, which result in high computation complexity for model training and testing. Read More

View Article and Full-Text PDF

Double Similarity Distillation for Semantic Image Segmentation.

IEEE Trans Image Process 2021 3;30:5363-5376. Epub 2021 Jun 3.

The balance between high accuracy and high speed has always been a challenging task in semantic image segmentation. Compact segmentation networks are more widely used in the case of limited resources, while their performances are constrained. In this paper, motivated by the residual learning and global aggregation, we propose a simple yet general and effective knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks by capturing the similarity knowledge in pixel and category dimensions, respectively. Read More

View Article and Full-Text PDF

DLnet With Training Task Conversion Stream for Precise Semantic Segmentation in Actual Traffic Scene.

IEEE Trans Neural Netw Learn Syst 2021 May 25;PP. Epub 2021 May 25.

Many successful semantic segmentation models trained on certain datasets experience a performance gap when they are applied to the actual scene images, expressing weak robustness of these models in the actual scene. The training task conversion (TTC) and domain adaption field have been originally proposed to solve the performance gap problem. Unfortunately, many existing models for TTC and domain adaptation have defects, and even if the TTC is completed, the performance is far from the original task model. Read More

View Article and Full-Text PDF

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling.

IEEE Trans Pattern Anal Mach Intell 2021 May 25;PP. Epub 2021 May 25.

We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. Read More

View Article and Full-Text PDF

Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation.

IEEE Trans Pattern Anal Mach Intell 2021 May 25;PP. Epub 2021 May 25.

Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e. Read More

View Article and Full-Text PDF

Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation.

J Biomed Inform 2021 May 19:103816. Epub 2021 May 19.

Institute of Medical Informatics, University of Lübeck, Germany. Electronic address:

Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. Read More

View Article and Full-Text PDF

Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval.

IEEE J Biomed Health Inform 2021 May 21;PP. Epub 2021 May 21.

When encountering a dubious diagnostic case, medical instance retrieval can help radiologists make evidence-based diagnoses by finding images containing instances similar to a query case from a large image database. The similarity between the query case and retrieved similar cases is determined by visual features extracted from pathologically abnormal regions. However, the manifestation of these regions often lacks specificity, i. Read More

View Article and Full-Text PDF

Automatic semantic segmentation of breast tumors in ultrasound images based on combining fuzzy logic and deep learning-A feasibility study.

PLoS One 2021 20;16(5):e0251899. Epub 2021 May 20.

Industrial Electronics and Control Engineering Department, Faculty of Electronic Engineering, Menoufia University, Menoufia, Egypt.

Computer aided diagnosis (CAD) of biomedical images assists physicians for a fast facilitated tissue characterization. A scheme based on combining fuzzy logic (FL) and deep learning (DL) for automatic semantic segmentation (SS) of tumors in breast ultrasound (BUS) images is proposed. The proposed scheme consists of two steps: the first is a FL based preprocessing, and the second is a Convolutional neural network (CNN) based SS. Read More

View Article and Full-Text PDF

Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology.

Brainlesion 2021 27;12658:80-91. Epub 2021 Mar 27.

Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, 02114, USA.

Deformable registration of magnetic resonance images between patients with brain tumors and healthy subjects has been an important tool to specify tumor geometry through location alignment and facilitate pathological analysis. Since tumor region does not match with any ordinary brain tissue, it has been difficult to deformably register a patient's brain to a normal one. Many patient images are associated with irregularly distributed lesions, resulting in further distortion of normal tissue structures and complicating registration's similarity measure. Read More

View Article and Full-Text PDF

PeriorbitAI: Artificial intelligence automation of eyelid and periorbital measurements.

Am J Ophthalmol 2021 May 16. Epub 2021 May 16.

University of Washington, Department of Ophthalmology University of Washington, Seattle, WA. Electronic address:

Purpose: To develop a deep learning semantic segmentation network to automate the assessment of eight periorbital measurements.

Design: Development and validation of an AI segmentation algorithm METHODS: A total of 418 photographs of periorbital areas were used to train a deep learning semantic segmentation model to segment iris, aperture, and brow areas. This data was used to develop a post-processing algorithm which measured margin reflex distance(MRD) 1 and 2, medial canthal height(MCH), lateral canthal height(LCH), medial brow height(MBH), lateral brow height(LBH), medial intercanthal distance(MID), and lateral intercanthal distance(LID). Read More

View Article and Full-Text PDF

Three-Dimensional Structure Analysis of Mouse Nails using Synchrotron Radiation.

Microscopy (Oxf) 2021 May 18. Epub 2021 May 18.

Department of Medical IT Engineering, College of Medical Sciences, Soonchunhyang University, 22, Soonchunhyang-ro, Asan City, Chungnam-do 31538, Republic of Korea.

Until now, studies on nail disease have been performed through microscopic diagnosis and microscopic computed tomography (micro-CT). However, these kinds of conventional methods have some limitations. Firstly, the microscopic method is considered the gold standard for medical diagnosis. Read More

View Article and Full-Text PDF

Exploiting Operation Importance for Differentiable Neural Architecture Search.

IEEE Trans Neural Netw Learn Syst 2021 May 17;PP. Epub 2021 May 17.

Recently, differentiable neural architecture search (NAS) methods have made significant progress in reducing the computational costs of NASs. Existing methods search for the best architecture by choosing candidate operations with higher architecture weights. However, architecture weights cannot accurately reflect the importance of each operation, that is, the operation with the highest weight might not be related to the best performance. Read More

View Article and Full-Text PDF

Auto-detection of cervical collagen and elastin in Mueller matrix polarimetry microscopic images using K-NN and semantic segmentation classification.

Biomed Opt Express 2021 Apr 23;12(4):2236-2249. Epub 2021 Mar 23.

Department of Biomedical Engineering, College of Engineering and Computing, Florida International University, 10555 West Flagler Street, Miami, FL 33174, USA.

We propose an approach for discriminating fibrillar collagen fibers from elastic fibers in the mouse cervix in Mueller matrix microscopy using convolutional neural networks (CNN) and K-nearest neighbor (K-NN) for classification. Second harmonic generation (SHG), two-photon excitation fluorescence (TPEF), and Mueller matrix polarimetry images of the mice cervix were collected with a self-validating Mueller matrix micro-mesoscope (SAMMM) system. The components and decompositions of each Mueller matrix were arranged as individual channels of information, forming one 3-D voxel per cervical slice. Read More

View Article and Full-Text PDF

Laser curve extraction of a train wheelset based on an encoder-decoder network.

Appl Opt 2021 May;60(14):4074-4083

An algorithm of laser curve segmentation for a train wheelset based on an encoder- decoder network is proposed. Aiming at the rich local features and simple semantic features of the train wheelset laser curve image, a neural network with shallow depth, high resolution, and good detail performance was designed. The proposed neural network makes full use of the dense connection mechanism and the upsampling module to enhance feature reuse and feature propagation. Read More

View Article and Full-Text PDF

Multitask GANs for Semantic Segmentation and Depth Completion With Cycle Consistency.

IEEE Trans Neural Netw Learn Syst 2021 May 12;PP. Epub 2021 May 12.

Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several studies have been proposed to jointly train these two tasks using some small modifications, such as changing the last layer, the result of one task is not utilized to improve the performance of the other one despite that there are some similarities between these two tasks. In this article, we propose multitask generative adversarial networks (Multitask GANs), which are not only competent in semantic segmentation and depth completion but also improve the accuracy of depth completion through generated semantic images. Read More

View Article and Full-Text PDF

Differences and Similarities in the Contributions of Phonological Awareness, Orthographic Knowledge and Semantic Competence to Reading Fluency in Chinese School-Age Children With and Without Hearing Loss.

Front Psychol 2021 12;12:649375. Epub 2021 Apr 12.

State Key Laboratory of Cognitive Neuroscience and Learning and IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing, China.

Compared with the large number of studies on reading of children with hearing loss (HL) in alphabetic languages, there are only a very limited number of studies on reading of Chinese-speaking children with HL. It remains unclear how phonological, orthographic, and semantic skills contribute to reading fluency of Chinese school-age children with HL. The present study explored this issue by examining the performances of children with HL on reading fluency and three linguistic skills compared with matched controls with normal hearing (NH). Read More

View Article and Full-Text PDF

Deep learning-based segmentation of the lung in MR-images acquired by a stack-of-spirals trajectory at ultra-short echo-times.

BMC Med Imaging 2021 May 8;21(1):79. Epub 2021 May 8.

Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Oberdürrbacher Str. 6, 97080, Würzburg, Germany.

Background: Functional lung MRI techniques are usually associated with time-consuming post-processing, where manual lung segmentation represents the most cumbersome part. The aim of this study was to investigate whether deep learning-based segmentation of lung images which were scanned by a fast UTE sequence exploiting the stack-of-spirals trajectory can provide sufficiently good accuracy for the calculation of functional parameters.

Methods: In this study, lung images were acquired in 20 patients suffering from cystic fibrosis (CF) and 33 healthy volunteers, by a fast UTE sequence with a stack-of-spirals trajectory and a minimum echo-time of 0. Read More

View Article and Full-Text PDF