Multi-task neural networks for joint hippocampus segmentation and clinical score regression

Cao, Liang; Li, Long; Zheng, Jifeng; Fan, Xin; Yin, Feng; Shen, Hui; Zhang, Jun

doi:10.1007/s11042-017-5581-1

Cited by 59 publications

(38 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performing multitasks with segmentation and classification, regression or registration has synergy to gain more precise segmentation performance. 48,49 As segmentation performance increases, studies have been conducted to consider the uncertainty of labels. 50 Furthermore, due to the high cost of medical labels, Semisupervised/unsupervised learning approaches were suggested using unlabelled data.…”

Section: Image Segmentation and Registrationmentioning

confidence: 99%

Deep Learning in Medical Imaging

et al. 2019

View full text Add to dashboard Cite

The artificial neural network (ANN), one of the machine learning (ML) algorithms, inspired by the human brain system, was developed by connecting layers with artificial neurons. However, due to the low computing power and insufficient learnable data, ANN has suffered from overfitting and vanishing gradient problems for training deep networks. The advancement of computing power with graphics processing units and the availability of large data acquisition, deep neural network outperforms human or other ML capabilities in computer vision and speech recognition tasks. These potentials are recently applied to healthcare problems, including computer-aided detection/diagnosis, disease prediction, image segmentation, image generation, etc. In this review article, we will explain the history, development, and applications in medical imaging

show abstract

Section: Image Segmentation and Registrationmentioning

confidence: 99%

Deep Learning in Medical Imaging

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The deep CNN model is constructed to learn features of the 3D patches extracted based on the hippocampal segmentation results for the classification task [141]. A multi-task deep learning (MDL) method was proposed for joint hippocampal segmentation and clinical score regression using MRI scans [142]. Choi et al [143] shown that deep CNN based biomarkers are strongly correlated with future cognitive decline using PET.…”

Section: The Segmentation Of Brain Mri Improves the Classification Of Admentioning

confidence: 99%

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer’s Disease: A Survey

Yamanakkanavar

Choi

Lee

2020

Sensors

131

View full text Add to dashboard Cite

Many neurological diseases and delineating pathological regions have been analyzed, and the anatomical structure of the brain researched with the aid of magnetic resonance imaging (MRI). It is important to identify patients with Alzheimer’s disease (AD) early so that preventative measures can be taken. A detailed analysis of the tissue structures from segmented MRI leads to a more accurate classification of specific brain disorders. Several segmentation methods to diagnose AD have been proposed with varying complexity. Segmentation of the brain structure and classification of AD using deep learning approaches has gained attention as it can provide effective results over a large set of data. Hence, deep learning methods are now preferred over state-of-the-art machine learning methods. We aim to provide an outline of current deep learning-based segmentation approaches for the quantitative analysis of brain MRI for the diagnosis of AD. Here, we report how convolutional neural network architectures are used to analyze the anatomical brain structure and diagnose AD, discuss how brain MRI segmentation improves AD classification, describe the state-of-the-art approaches, and summarize their results using publicly available datasets. Finally, we provide insight into current issues and discuss possible future research directions in building a computer-aided diagnostic system for AD.

show abstract

“…Because 2 × 2 × 2 convolution filters cannot maintain the size of feature-map comparing to the input, we construct our initial model using the feasible and smallest filters of 3 × 3 × 3 convolution. In addition, most of the previous hippocampus segmentation methods use pooling as a downsampling layer [23]- [25], whereas the pooling layer can be viewed as performing a feature-wise convolution in which the activation function is replaced by the p-norm. We use convolution with stride 2 for replacing the pooling layer because it can add inter-feature dependencies [39].…”

Section: ) Densely Connected Blockmentioning

confidence: 99%

“…However, handcrafted features usually suffer from limited representation capability, and these methods also require careful engineering and specific expertise for accurate recognition. (4) Deep learning-based method [23]- [28]. These approaches allow models to learn the features that optimally represent the data for the problem at hand, such as the stacked autoencoder [27], multiview ensemble 2D convolutional neural network [23], parallelized long short-term memory (LSTM) [28], or 3D convolutional neural network methods [24], [25].…”

Section: Introductionmentioning

confidence: 99%

“…As far as we know, two main categories of end-to-end CNNs are available for volumetric image segmentation. (1) This type of method applies 2D CNNs by taking one slice, assembled adjacent slices, orthogonal planes, or multiple diagonal planes as input to compensate for spatial information [23], [30]. However, these models often contain multistream architectures that require longer training and testing time as well as additional storage.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hippocampus Segmentation for Preterm and Aging Brains Using 3D Densely Connected Fully Convolutional Networks

Zeng

2020

IEEE Access

View full text Add to dashboard Cite

Efficient and accurate segmentation of hippocampi from preterm and aging brain MR images is one of the most fundamental steps in understanding hippocampal growth and development or diagnosing and monitoring various clinical conditions. Current hippocampus segmentation methods for preterm and aging brain are limited due to: 1) they can rarely achieve preterm infant hippocampus segmentation; 2) the computation cost is high; 3) current deep learning models cannot well handle the hippocampal feature learning; 4) they are not open obtainable. To deal with these problems, we propose an efficient, open-source algorithm, 3D densely connected fully convolutional network (3D-DCFCN) for the infant and aging hippocampal segmentation. Specifically, we search for a suitable distribution of the hierarchical receptive field size and a joint loss function to balance local and global information and lead to better optimization. In addition, we use image cross-registration for vast augmentation of the infant training data and incorporate multi-modality infant brain information. We compare the performance of our algorithm with those of several state-of-the-art methods. The results show that our method outperforms all comparison methods on infant and aging datasets and achieves much faster speed (less than 0.11s per image). We also provide a notably comprehensive evaluation of the method. Our experiments further demonstrate our model can 1) well generalize to the dataset with different magnetic fields; 2) satisfactorily find hippocampal atrophy in cognitive-decline groups compare with normal controls. INDEX TERMS Preterm, aging, hippocampus segmentation, hippocampal volume analysis, 3D densely connected fully convolutional network (3D-DCFCN).

show abstract

Multi-task neural networks for joint hippocampus segmentation and clinical score regression

Cited by 59 publications

References 47 publications

Deep Learning in Medical Imaging

Deep Learning in Medical Imaging

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer’s Disease: A Survey

Hippocampus Segmentation for Preterm and Aging Brains Using 3D Densely Connected Fully Convolutional Networks

Contact Info

Product

Resources

About