Data Preprocessing for Automatic WMH Segmentation with FCNNs

Duque, Pablo; Cuadra, J. M.; Jiménez, Ester; Rincón, M.

doi:10.1007/978-3-030-19651-6_44

Cited by 4 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One problem related to image classification is image segmentation, in which the model has to detect and delimitate regions in images. In [44], this circumstance arises in neurology, specifically in automatic segmentation of white matter intensities in magnetic resonance images. Instead of a standard CNN classifier as in the previous problems, segmentation can be carried out by a CNN, which means that the network does not include any dense layers, and instead it has a bidimensional output produced by convolution or deconvolution operations.…”

Section: Building DL Applicationsmentioning

confidence: 99%

“…Instead of a standard CNN classifier as in the previous problems, segmentation can be carried out by a CNN, which means that the network does not include any dense layers, and instead it has a bidimensional output produced by convolution or deconvolution operations. The work revolves around the preprocessing techniques that can be applied to images before feeding them Outputs from DL models for different application domains, from left to right: person detection and identification [43], white matter hyperintensity segmentation [44], 2-dimensional embedding of satellite images [45].…”

Section: Building DL Applicationsmentioning

confidence: 99%

“…The system efficiency is measured by Figure 19: Composition of the EEG signal from different frequencies (oscillatory activities). Five classical physiological bands are shown for the same raw EEG signal: delta (1-3 Hz); theta (46 Hz); alpha (7-13 Hz); beta (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25); and gamma (35)(36)(37)(38)(39)(40)(41)(42)(43)(44)(45). These basic EEG bands are assumed to reflect different functional processes in the brain [155].…”

Section: Clinical Neurosciencementioning

confidence: 99%

“…Figure6: Outputs from DL models for different application domains, from left to right: person detection and identification[43], white matter hyperintensity segmentation[44], 2-dimensional embedding of satellite images[45].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Artificial intelligence within the interplay between natural and artificial computation: Advances in data science, trends and applications

et al. 2020

View full text Add to dashboard Cite

Artificial intelligence and all its supporting tools, e.g. machine and deep learning in computational intelligence-based systems, are rebuilding our society (economy, education, life-style, etc.) and promising a new era for the social welfare state. In this paper we summarize recent advances in data science and artificial intelligence within the interplay between natural and artificial computation. A review of recent works published in the latter field and the state the art are summarized in a comprehensive and self-contained way to provide a baseline framework for the international community in artificial intelligence. Moreover, this paper aims to provide a complete analysis and some relevant discussions of the current trends and insights within several theoretical and application fields covered in the essay, from theoretical models in

show abstract

Section: Building DL Applicationsmentioning

confidence: 99%

Section: Building DL Applicationsmentioning

confidence: 99%

Section: Clinical Neurosciencementioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence within the interplay between natural and artificial computation: Advances in data science, trends and applications

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Preprocessing plays a critical role in enhancing the performance of deep-learning-based automatic segmentation by transforming data into a format that is more readily processed [ 27 ]. The preprocessing methods proposed to enhance the performance of deep-learning-based automatic segmentation include window leveling, filtering, matching, histogram techniques [ 28 ], T1, FLAIR (skull stripping) [ 29 ], wavelet decomposition, local binary patterns [ 30 ], region of interest (ROI) selection, bias field correction, resampling methods [ 31 ], normalization [ 28 , 29 , 30 , 31 ], and crop ROI [ 32 , 33 ].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Deep-Learning-Based Automatic Left-Femur Segmentation Scheme with Attribute Augmentation

Apivanichkul

Phasukkit

Dankulchai

et al. 2023

Sensors

View full text Add to dashboard Cite

This research proposes augmenting cropped computed tomography (CT) slices with data attributes to enhance the performance of a deep-learning-based automatic left-femur segmentation scheme. The data attribute is the lying position for the left-femur model. In the study, the deep-learning-based automatic left-femur segmentation scheme was trained, validated, and tested using eight categories of CT input datasets for the left femur (F-I–F-VIII). The segmentation performance was assessed by Dice similarity coefficient (DSC) and intersection over union (IoU); and the similarity between the predicted 3D reconstruction images and ground-truth images was determined by spectral angle mapper (SAM) and structural similarity index measure (SSIM). The left-femur segmentation model achieved the highest DSC (88.25%) and IoU (80.85%) under category F-IV (using cropped and augmented CT input datasets with large feature coefficients), with an SAM and SSIM of 0.117–0.215 and 0.701–0.732. The novelty of this research lies in the use of attribute augmentation in medical image preprocessing to enhance the performance of the deep-learning-based automatic left-femur segmentation scheme.

show abstract

Cascaded regression with dual CNN frame work for time effective detection of gliomas cancers

Deepak,

Sarath

2024

Intelligence-Based Medicine

View full text Add to dashboard Cite

Data Preprocessing for Automatic WMH Segmentation with FCNNs

Cited by 4 publications

References 10 publications

Artificial intelligence within the interplay between natural and artificial computation: Advances in data science, trends and applications

Artificial intelligence within the interplay between natural and artificial computation: Advances in data science, trends and applications

Enhanced Deep-Learning-Based Automatic Left-Femur Segmentation Scheme with Attribute Augmentation

Cascaded regression with dual CNN frame work for time effective detection of gliomas cancers

Contact Info

Product

Resources

About