scholarly journals Supervised Domain Adaptation for Automated Semantic Segmentation of the Atrial Cavity

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 898
Author(s):  
Marta Saiz-Vivó ◽  
Adrián Colomer ◽  
Carles Fonfría ◽  
Luis Martí-Bonmatí ◽  
Valery Naranjo
Keyword(s):  
High Performance ◽  
Computational Models ◽  
Domain Adaptation ◽  
Semantic Segmentation ◽  
Patient Specific ◽  
Mr Images ◽  
Training Samples ◽  
Volumetric Images ◽  
Acquisition Costs ◽  
Left And Right

Atrial fibrillation (AF) is the most common cardiac arrhythmia. At present, cardiac ablation is the main treatment procedure for AF. To guide and plan this procedure, it is essential for clinicians to obtain patient-specific 3D geometrical models of the atria. For this, there is an interest in automatic image segmentation algorithms, such as deep learning (DL) methods, as opposed to manual segmentation, an error-prone and time-consuming method. However, to optimize DL algorithms, many annotated examples are required, increasing acquisition costs. The aim of this work is to develop automatic and high-performance computational models for left and right atrium (LA and RA) segmentation from a few labelled MRI volumetric images with a 3D Dual U-Net algorithm. For this, a supervised domain adaptation (SDA) method is introduced to infer knowledge from late gadolinium enhanced (LGE) MRI volumetric training samples (80 LA annotated samples) to a network trained with balanced steady-state free precession (bSSFP) MR images of limited number of annotations (19 RA and LA annotated samples). The resulting knowledge-transferred model SDA outperformed the same network trained from scratch in both RA (Dice equals 0.9160) and LA (Dice equals 0.8813) segmentation tasks.

scholarly journals Domain Adaptation for Semantic Segmentation of Historical Panchromatic Orthomosaics in Central Africa

2021 ◽  
Vol 10 (8) ◽  
pp. 523
Author(s):  
Nicholus Mboga ◽  
Stefano D’Aronco ◽  
Tais Grippa ◽  
Charlotte Pelletier ◽  
Stefanos Georganos ◽  
...  
Keyword(s):  
Land Cover ◽  
Domain Adaptation ◽  
Central Africa ◽  
Semantic Segmentation ◽  
Target Domain ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
The Cost ◽  
Performance Gains

Multitemporal environmental and urban studies are essential to guide policy making to ultimately improve human wellbeing in the Global South. Land-cover products derived from historical aerial orthomosaics acquired decades ago can provide important evidence to inform long-term studies. To reduce the manual labelling effort by human experts and to scale to large, meaningful regions, we investigate in this study how domain adaptation techniques and deep learning can help to efficiently map land cover in Central Africa. We propose and evaluate a methodology that is based on unsupervised adaptation to reduce the cost of generating reference data for several cities and across different dates. We present the first application of domain adaptation based on fully convolutional networks for semantic segmentation of a dataset of historical panchromatic orthomosaics for land-cover generation for two focus cities Goma-Gisenyi and Bukavu. Our experimental evaluation shows that the domain adaptation methods can reach an overall accuracy between 60% and 70% for different regions. If we add a small amount of labelled data from the target domain, too, further performance gains can be achieved.

scholarly journals Research on Distance Transform and Neural Network Lidar Information Sampling Classification-Based Semantic Segmentation of 2D Indoor Room Maps

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1365
Author(s):  
Tao Zheng ◽  
Zhizhao Duan ◽  
Jin Wang ◽  
Guodong Lu ◽  
Shengjie Li ◽  
...  
Keyword(s):  
Neural Network ◽  
High Speed ◽  
High Performance ◽  
High Efficiency ◽  
Semantic Segmentation ◽  
Raspberry Pi ◽  
Distance Transform ◽  
Testing Stage ◽  
Sampling Points ◽  
Information Sampling

Semantic segmentation of room maps is an essential issue in mobile robots’ execution of tasks. In this work, a new approach to obtain the semantic labels of 2D lidar room maps by combining distance transform watershed-based pre-segmentation and a skillfully designed neural network lidar information sampling classification is proposed. In order to label the room maps with high efficiency, high precision and high speed, we have designed a low-power and high-performance method, which can be deployed on low computing power Raspberry Pi devices. In the training stage, a lidar is simulated to collect the lidar detection line maps of each point in the manually labelled map, and then we use these line maps and the corresponding labels to train the designed neural network. In the testing stage, the new map is first pre-segmented into simple cells with the distance transformation watershed method, then we classify the lidar detection line maps with the trained neural network. The optimized areas of sparse sampling points are proposed by using the result of distance transform generated in the pre-segmentation process to prevent the sampling points selected in the boundary regions from influencing the results of semantic labeling. A prototype mobile robot was developed to verify the proposed method, the feasibility, validity, robustness and high efficiency were verified by a series of tests. The proposed method achieved higher scores in its recall, precision. Specifically, the mean recall is 0.965, and mean precision is 0.943.

Fused filament printing of specialized biomedical devices: a state-of-the art review of technological feasibilities with PEEK

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Erfan Rezvani Ghomi ◽  
Saeideh Kholghi Eshkalak ◽  
Sunpreet Singh ◽  
Amutha Chinnappan ◽  
Seeram Ramakrishna ◽  
...  
Keyword(s):  
High Performance ◽  
State Of The Art ◽  
Three Dimensional ◽  
Patient Specific ◽  
Biomedical Devices ◽  
Fused Filament Fabrication ◽  
Content Type ◽  
Patient Specific Implants ◽  
Complex Design ◽  
Wide Range

Purpose The potential implications of the three-dimensional printing (3DP) technology are growing enormously in the various health-care sectors, including surgical planning, manufacturing of patient-specific implants and developing anatomical models. Although a wide range of thermoplastic polymers are available as 3DP feedstock, yet obtaining biocompatible and structurally integrated biomedical devices is still challenging owing to various technical issues. Design/methodology/approach Polyether ether ketone (PEEK) is an organic and biocompatible compound material that is recently being used to fabricate complex design geometries and patient-specific implants through 3DP. However, the thermal and rheological features of PEEK make it difficult to process through the 3DP technologies, for instance, fused filament fabrication. The present review paper presents a state-of-the-art literature review of the 3DP of PEEK for potential biomedical applications. In particular, a special emphasis has been given on the existing technical hurdles and possible technological and processing solutions for improving the printability of PEEK. Findings The reviewed literature highlighted that there exist numerous scientific and technical means which can be adopted for improving the quality features of the 3D-printed PEEK-based biomedical structures. The discussed technological innovations will help the 3DP system to enhance the layer adhesion strength, structural stability, as well as enable the printing of high-performance thermoplastics. Originality/value The content of the present manuscript will motivate young scholars and senior scientists to work in exploring high-performance thermoplastics for 3DP applications.

scholarly journals A new data classification improvement approach based on kernel clustering

2021 ◽  
Vol 2082 (1) ◽  
pp. 012021
Author(s):  
Bingsen Guo
Keyword(s):  
High Performance ◽  
Real Life ◽  
Data Classification ◽  
Classification Performance ◽  
Training Set ◽  
Kernel Clustering ◽  
Training Samples ◽  
Critical Issues ◽  
Extensive Performance ◽  
Query Sample

Abstract Data classification is one of the most critical issues in data mining with a large number of real-life applications. In many practical classification issues, there are various forms of anomalies in the real dataset. For example, the training set contains outliers, often enough to confuse the classifier and reduce its ability to learn from the data. In this paper, we propose a new data classification improvement approach based on kernel clustering. The proposed method can improve the classification performance by optimizing the training set. We first use the existing kernel clustering method to cluster the training set and optimize it based on the similarity between the training samples in each class and the corresponding class center. Then, the optimized reliable training set is trained to the standard classifier in the kernel space to classify each query sample. Extensive performance analysis shows that the proposed method achieves high performance, thus improving the classifier’s effectiveness.

scholarly journals USING SEMANTICALLY PAIRED IMAGES TO IMPROVE DOMAIN ADAPTATION FOR THE SEMANTIC SEGMENTATION OF AERIAL IMAGES

2020 ◽  
Vol V-2-2020 ◽  
pp. 483-492
Author(s):  
D. Gritzner ◽  
J. Ostermann
Keyword(s):  
Time Window ◽  
Domain Adaptation ◽  
Geographical Area ◽  
Model Performance ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Training Data ◽  
Aerial Images ◽  
Target Domain ◽  
Training Examples

Abstract. Modern machine learning, especially deep learning, which is used in a variety of applications, requires a lot of labelled data for model training. Having an insufficient amount of training examples leads to models which do not generalize well to new input instances. This is a particular significant problem for tasks involving aerial images: often training data is only available for a limited geographical area and a narrow time window, thus leading to models which perform poorly in different regions, at different times of day, or during different seasons. Domain adaptation can mitigate this issue by using labelled source domain training examples and unlabeled target domain images to train a model which performs well on both domains. Modern adversarial domain adaptation approaches use unpaired data. We propose using pairs of semantically similar images, i.e., whose segmentations are accurate predictions of each other, for improved model performance. In this paper we show that, as an upper limit based on ground truth, using semantically paired aerial images during training almost always increases model performance with an average improvement of 4.2% accuracy and .036 mean intersection-over-union (mIoU). Using a practical estimate of semantic similarity, we still achieve improvements in more than half of all cases, with average improvements of 2.5% accuracy and .017 mIoU in those cases.

scholarly journals Age- and sex-related changes of the volume of maxillary sinuses quantified via cone beam computed tomography

2021 ◽  
Vol 10 (14) ◽  
pp. e312101422220
Author(s):  
Lucas Eigi Borges Tanaka ◽  
Ademir Franco ◽  
Rafael Ferreira Abib ◽  
Luiz Roberto Coutinho Manhães-Junior ◽  
Sergio Lucio Pereira de Castro Lopes
Keyword(s):  
Computed Tomography ◽  
Cone Beam Computed Tomography ◽  
Three Dimensional ◽  
Specific Treatment ◽  
Cone Beam ◽  
Patient Specific ◽  
Sample Collection ◽  
Left And Right ◽  
Age And Sex ◽  
Maxillary Sinuses

Anatomical studies found in cone beam computed tomography (CBCT) an optimal resource for the three-dimensional (3D) assessment of the head and neck. When it comes to the maxillary sinuses, CBCT enables a life-size reliable volumetric analysis. This study aimed to assess the age and sex-related changes of the maxillary sinuses using volumetric CBCT analysis. The sample consisted of CBCT scans of 112 male (n = 57) and female (n = 55) individuals (224 maxillary sinuses) distributed in 5 age categories: 20 |— 30, 31 |— 40, 41 |— 50, 51 |— 60 and > 60 years. Image acquisition was accomplished with the i-CAT Next Generation device set with voxel size of 0.25 mm and field of view that included the maxillary sinuses (retrospective sample collection from an existing database). Image segmentation was performed in itk-SNAP (www.itksnap.org) software. The volume (mm3) of the segmented sinuses was quantified and compared pairwise based on side (left and right), sex (male and female) and age (five groups). Differences between left and right sides volume were not statistically significant (p > 0.05). The mean volume of maxillary sinuses in males was 22% higher than females (p = 0.0001). Volumetric differences were not statistically significant between age categories for males and females (p > 0.05). The discriminant power of sinuses’ volume may support customized and patient-specific treatment planning based on sex.

scholarly journals Towards NeuroML: Model Description Methods for Collaborative Modelling in Neuroscience

2001 ◽  
Vol 356 (1412) ◽  
pp. 1209-1228 ◽  
Author(s):  
Nigel H. Goddard ◽  
Michael Hucka ◽  
Fred Howell ◽  
Hugo Cornelis ◽  
Kavita Shankar ◽  
...  
Keyword(s):  
High Performance ◽  
Computational Models ◽  
Object Oriented ◽  
Model Description ◽  
Specific Component ◽  
Nervous Systems ◽  
Efficient Simulation ◽  
Performance Framework ◽  
Structural Levels ◽  
Modelling Process

Biological nervous systems and the mechanisms underlying their operation exhibit astonishing complexity. Computational models of these systems have been correspondingly complex. As these models become ever more sophisticated, they become increasingly difficult to define, comprehend, manage and communicate. Consequently, for scientific understanding of biological nervous systems to progress, it is crucial for modellers to have software tools that support discussion, development and exchange of computational models. We describe methodologies that focus on these tasks, improving the ability of neuroscientists to engage in the modelling process. We report our findings on the requirements for these tools and discuss the use of declarative forms of model description—equivalent to object–oriented classes and database schema—which we call templates. We introduce NeuroML, a mark–up language for the neurosciences which is defined syntactically using templates, and its specific component intended as a common format for communication between modelling–related tools. Finally, we propose a template hierarchy for this modelling component of NeuroML, sufficient for describing models ranging in structural levels from neuron cell membranes to neural networks. These templates support both a framework for user–level interaction with models, and a high–performance framework for efficient simulation of the models.

Sign in / Sign up

Export Citation Format

Share Document