Supervised brain segmentation and classification in diagnostic of Attention-Deficit/Hyperactivity Disorder

Igual, Laura; Soliva, Joan Carles; Hernández-Vela, Antonio; Escalera, Sérgio; Vilarroya, Óscar; Radeva, Petia

doi:10.1109/hpcsim.2012.6266909

Cited by 7 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Adam optimizer ( 33 ) and “reduce learning rate on the plateau” manner were also absorbed in our model, whose batch size was 2, the learning rate was 0.003, and total learning epochs was 500. In this work, we regarded the Dice similarity coefficient (Dice) ( 34 ), Jaccard index (JI) ( 35 ), Precision (Pre) ( 36 ), Recall ( 37 ), Average symmetric surface distance (ASD, in voxel) ( 38 ) and 95% Hausdorff distance (95HD, in voxel) ( 39 ) as the metrics for quantitatively segmentation performance evaluation. On the one hand, Dice and JI can compare the similarity between ground truths and segmented volumes while Pre and Recall are able to measure segmentation outcomes in voxel-wise through evaluating classification accuracy.…”

Section: Experiments and Resultsmentioning

confidence: 99%

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor

Liu

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

Automatic segmentation of gastric tumor not only provides image-guided clinical diagnosis but also assists radiologists to read images and improve the diagnostic accuracy. However, due to the inhomogeneous intensity distribution of gastric tumors in CT scans, the ambiguous/missing boundaries, and the highly variable shapes of gastric tumors, it is quite challenging to develop an automatic solution. This study designs a novel 3D improved feature pyramidal network (3D IFPN) to automatically segment gastric tumors in computed tomography (CT) images. To meet the challenges of this extremely difficult task, the proposed 3D IFPN makes full use of the complementary information within the low and high layers of deep convolutional neural networks, which is equipped with three types of feature enhancement modules: 3D adaptive spatial feature fusion (ASFF) module, single-level feature refinement (SLFR) module, and multi-level feature refinement (MLFR) module. The 3D ASFF module adaptively suppresses the feature inconsistency in different levels and hence obtains the multi-level features with high feature invariance. Then, the SLFR module combines the adaptive features and previous multi-level features at each level to generate the multi-level refined features by skip connection and attention mechanism. The MLFR module adaptively recalibrates the channel-wise and spatial-wise responses by adding the attention operation, which improves the prediction capability of the network. Furthermore, a stage-wise deep supervision (SDS) mechanism and a hybrid loss function are also embedded to enhance the feature learning ability of the network. CT volumes dataset collected in three Chinese medical centers was used to evaluate the segmentation performance of the proposed 3D IFPN model. Experimental results indicate that our method outperforms state-of-the-art segmentation networks in gastric tumor segmentation. Moreover, to explore the generalization for other segmentation tasks, we also extend the proposed network to liver tumor segmentation in CT images of the MICCAI 2017 Liver Tumor Segmentation Challenge.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor

Liu

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…In line with the BraTS challenges, tumor segmentations for each algorithm were assessed using median and inter-quartile range Dice similarity coefficient (DSC) 38 and Hausdorff distance (HD) 39 for all experiments. Results were generated using methods described by Taha and Hanbury 40 and associated software.…”

Section: Model Performance Assessmentmentioning

confidence: 99%

Multi-class glioma segmentation on real-world data with missing MRI sequences: comparison of three deep learning algorithms

Pemberton,

Wu,

Kommers

et al. 2023

Sci Rep

View full text Add to dashboard Cite

This study tests the generalisability of three Brain Tumor Segmentation (BraTS) challenge models using a multi-center dataset of varying image quality and incomplete MRI datasets. In this retrospective study, DeepMedic, no-new-Unet (nn-Unet), and NVIDIA-net (nv-Net) were trained and tested using manual segmentations from preoperative MRI of glioblastoma (GBM) and low-grade gliomas (LGG) from the BraTS 2021 dataset (1251 in total), in addition to 275 GBM and 205 LGG acquired clinically across 12 hospitals worldwide. Data was split into 80% training, 5% validation, and 15% internal test data. An additional external test-set of 158 GBM and 69 LGG was used to assess generalisability to other hospitals’ data. All models’ median Dice similarity coefficient (DSC) for both test sets were within, or higher than, previously reported human inter-rater agreement (range of 0.74–0.85). For both test sets, nn-Unet achieved the highest DSC (internal = 0.86, external = 0.93) and the lowest Hausdorff distances (10.07, 13.87 mm, respectively) for all tumor classes (p < 0.001). By applying Sparsified training, missing MRI sequences did not statistically affect the performance. nn-Unet achieves accurate segmentations in clinical settings even in the presence of incomplete MRI datasets. This facilitates future clinical adoption of automated glioma segmentation, which could help inform treatment planning and glioma monitoring.

show abstract

“…Support Vector Machine is a supervised machine learning algorithm which plots each data item as a point in the n-dimensional space with the value of a feature. Support Vector Machine generates a border which best segregates the two classes [13] as shown in Figure 4.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

An Evaluation of Structural Brain Tissue Abnormalities to Diagnose Attention Deficit Hyperactivity Disorder

Radhamani,

Krishnaveni

2019

IJEAT

View full text Add to dashboard Cite

Attention-deficit/hyperactivity disorder (ADHD) is highly associated with brain abnormality. In this paper, an evaluation of structural brain tissue abnormalities to diagnose ADHD is proposed. A Brain Image Data Set containing 40, T2 axial Human ADHD Brain MR Images is created, normalized, preprocessed by Skull stripping method and Caudate Nucleus(CN), Grey Matter(GM) and White Matter(WM)data sets are formed by segregating the structural brain parts CN, GM and WM using Fuzzy C-Means algorithm. The texture, intensity and shape based features of each data set is extracted, and the images with abnormal (reduced) volume and shape are classified with the help of Pearson’s chi-squared (χ2) test by statistical measures and machine learning classifiers. The results show that out of 40, the brain tissues of 25 ADHD brain images are found with reduced volume and size of all CN, GM and WM and remaining images are found with at least any one of these abnormality compared to control group. The findings confirm that ADHD is a brain disorder which mainly affects the growth of the brain tissues and recommends the physicians to initiate the diagnosis process of ADHD with MRI brain scans instead of high risk medication and counseling among the children.

show abstract

Supervised brain segmentation and classification in diagnostic of Attention-Deficit/Hyperactivity Disorder

Cited by 7 publications

References 13 publications

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor

3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor

Multi-class glioma segmentation on real-world data with missing MRI sequences: comparison of three deep learning algorithms

An Evaluation of Structural Brain Tissue Abnormalities to Diagnose Attention Deficit Hyperactivity Disorder

Contact Info

Product

Resources

About