Performance divergence with data discrepancy: a review

Dakua, Sarada Prasad

doi:10.1007/s10462-011-9289-8

Cited by 22 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computed Tomography (CT) scan is a non-invasive medical imaging technique for obtaining 3D high-resolution images of different organs 1 . Interventional radiologists rely heavily on CT scans for the diagnosis and treatment of cancer and metastasis in the visceral organs (e.g., hepatocellular carcinoma (HCC)).…”

Section: Introductionmentioning

confidence: 99%

A lightweight neural network with multiscale feature enhancement for liver CT segmentation

Ansari

Yang

Balakrishnan

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Segmentation of abdominal Computed Tomography (CT) scan is essential for analyzing, diagnosing, and treating visceral organ diseases (e.g., hepatocellular carcinoma). This paper proposes a novel neural network (Res-PAC-UNet) that employs a fixed-width residual UNet backbone and Pyramid Atrous Convolutions, providing a low disk utilization method for precise liver CT segmentation. The proposed network is trained on medical segmentation decathlon dataset using a modified surface loss function. Additionally, we evaluate its quantitative and qualitative performance; the Res16-PAC-UNet achieves a Dice coefficient of 0.950 ± 0.019 with less than half a million parameters. Alternatively, the Res32-PAC-UNet obtains a Dice coefficient of 0.958 ± 0.015 with an acceptable parameter count of approximately 1.2 million.

show abstract

Section: Introductionmentioning

confidence: 99%

A lightweight neural network with multiscale feature enhancement for liver CT segmentation

Ansari

Yang

Balakrishnan

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Generally, the conventional image segmentation methods are either model-based (e.g., active contours, and snake algorithms) [23], [24], [25], [26], [27] or intensitybased (e.g., thresholding). Some algorithms utilize primitive image features, e.g., pixels intensities in region-growing/thresholding based approaches [28], [29], [24], [30].…”

Section: Literature Reviewmentioning

confidence: 99%

Practical Utility of Liver Segmentation Techniques in Clinical Surgeries and Interventions

Dakua

Ansari

Abdalla

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Medical images (e.g., magnetic resonance imaging (MRI) and computed tomography (CT)) provide critical information to the clinicians in order to diagnose pathology and plan interventions. Image segmentation is the first and foremost step taken by the clinicians while optimizing analytic diagnosis and treatment planning for interventions (e.g., transplantation and complete resection) and therapeutic procedures (e.g., radiotherapy, PVE, and embolization approaches), especially in hepatocellular carcinoma. Thus, segmentation techniques certainly impact the diagnosis and treatment outcomes. This paper studies the literature during the year 2012 until 2021 and reviews the segmentation methods classifying them into three categories based on their clinical utility (i.e., surgical and radiological interventions). The classification is based on the parameters such as precision, accuracy, location, liver condition, and other clinical considerations.

show abstract

“…As a result, it is hard to quantificationally evaluate the discrepancy of geometrical shape and flight conditions on aerodynamic performances, which also leads to the difficulty of fusing them. Recently, some researchers have recognized the importance of aerodynamic data discrepancy [12], and tried to create new models that learn discrepant aerodynamic data in a distributed way according to the type of input arXiv:2206.12254v1 [cs.LG] 23 Jun 2022 data, for examples, AeroCNN-I [13], physics guided machine learning (PGML) [14], multi-layer perceptron (MLP) [15] and Multi-task learning (MTL) scheme [16], [17]. All the above studies, however, take the coordinates or images of airfoils as representations of airfoil structures in Euclidean space.…”

mentioning

confidence: 99%

An airfoil geometric-feature extraction and discrepant data fusion learning method

Xiang

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

The perception of geometric-features of airfoils is the basis in aerodynamic area for performance prediction, parameterization, aircraft inverse design, etc. There are three approaches to percept the geometric shape of airfoils, namely manual design of airfoil geometry parameters, polynomial definition and deep learning. The first two methods directly define geometric-features or polynomials of airfoil curves, but the number of extracted features is limited. Deep learning algorithms can extract a large number of potential features (called latent features). However, the features extracted by deep learning lack explicit geometrical meaning. Motivated by the advantages of polynomial definition and deep learning, we propose a geometric-feature extraction method (named Bézier-based feature extraction, BFE) for airfoils, which consists of two parts: manifold metric feature extraction and geometric-feature fusion encoder (GF encoder). Manifold metric feature extraction, with the help of the Bézier curve, captures manifold metrics (a sort of geometric-features) from tangent space of airfoil curves, and the GF-encoder combines airfoil coordinate data and manifold metrics together to form novel fused geometric-features. To validate the feasibility of the fused geometric-features, two experiments based on the public UIUC airfoil dataset are conducted. Experiment I is used to extract manifold metrics of airfoils and export the fused geometric-features. Experiment II, based on the Multi-task learning (MTL), is used to fuse the discrepant data (i.e., the fused geometric-features and the flight conditions) to predict the aerodynamic performance of airfoils. The results show that the BFE can generate more smooth and realistic airfoils than Auto-Encoder, and the fused geometric-features extracted by BFE can be used to reduce the prediction errors of C L and C D .

show abstract

Performance divergence with data discrepancy: a review

Cited by 22 publications

References 53 publications

A lightweight neural network with multiscale feature enhancement for liver CT segmentation

A lightweight neural network with multiscale feature enhancement for liver CT segmentation

Practical Utility of Liver Segmentation Techniques in Clinical Surgeries and Interventions

An airfoil geometric-feature extraction and discrepant data fusion learning method

Contact Info

Product

Resources

About