Automatic Segmentation of Left Ventricular Myocardium by Deep Convolutional and De:convolutional Neural Networks

Yang, Xue; Gobeawan, Like; Yeo, Si Yong; Tang, Wai Teng; Wu, Zhan; Su, Yao

doi:10.22489/cinc.2016.025-237

Cited by 6 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the work performed by Saeed [ 15 ], the Kaggle competition participants [ 16 ], and our preliminary experiments, we make the legitimate assumption that this problem is model-agnostic. Models based on 3D convolution are proven and show impressive results when dealing with medical imaging [ 32 , 33 , 34 ]. For the sake of clarity and thoroughness, we choose to train 3D convolution models and, in particular, a state-of-the-art ResNet10-3D, which is also the winning architecture of the Kaggle challenge [ 16 ].…”

Section: Methodsmentioning

confidence: 99%

MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation

Robinet

Siegfried

Roques

et al. 2023

Cancers

View full text Add to dashboard Cite

Glioblastoma is the most aggressive primary brain tumor, which almost systematically relapses despite surgery (when possible) followed by radio-chemotherapy temozolomide-based treatment. Upon relapse, one option for treatment is another chemotherapy, lomustine. The efficacy of these chemotherapy regimens depends on the methylation of a specific gene promoter known as MGMT, which is the main prognosis factor for glioblastoma. Knowing this biomarker is a key issue for the clinician to personalize and adapt treatment to the patient at primary diagnosis for elderly patients, in particular, and also upon relapse. The association between MRI-derived information and the prediction of MGMT promoter status has been discussed in many studies, and some, more recently, have proposed the use of deep learning algorithms on multimodal scans to extract this information, but they have failed to reach a consensus. Therefore, in this work, beyond the classical performance figures usually displayed, we seek to compute confidence scores to see if a clinical application of such methods can be seriously considered. The systematic approach carried out, using different input configurations and algorithms as well as the exact methylation percentage, led to the following conclusion: current deep learning methods are unable to determine MGMT promoter methylation from MRI data.

show abstract

Section: Methodsmentioning

confidence: 99%

MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation

Robinet

Siegfried

Roques

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…CNN-based segmentation algorithms have abilities to solve numerous issues, particularly in the analysis of medical images, as they have shown their extraordinary accuracy [51] and robustness in the past recent years [52,53]. With the advancements in CNN [54][55][56][57][58][59][60], the majority of the fields in pattern identification and CV experience a tremendous improvement and revolution, including image cataloging, object recognition and image segmentation.…”

Section: Related Workmentioning

confidence: 99%

A Novel Light U-Net Model for Left Ventricle Segmentation Using MRI

et al. 2023

View full text Add to dashboard Cite

MRI segmentation and analysis are significant tasks in clinical cardiac computations. A cardiovascular MR scan with left ventricular segmentation seems necessary to diagnose and further treat the disease. The proposed method for left ventricle segmentation works as a combination of the intelligent histogram-based image enhancement technique with a Light U-Net model. This technique serves as the basis for choosing the low-contrast image subjected to the stretching technique and produces sharp object contours with good contrast settings for the segmentation process. After enhancement, the images are subjected to the encoder–decoder configuration of U-Net using a novel lightweight processing model. Encoder sampling is supported by a block of three parallel convolutional layers with supporting functions that improve the semantics for segmentation at various levels of resolutions and features. The proposed method finally increased segmentation efficiency, extracting the most relevant image resources from depth-to-depth convolutions, filtering them through each network block, and producing more precise resource maps. The dataset of MICCAI 2009 served as an assessment tool of the proposed methodology and provides a dice coefficient value of 97.7%, accuracy of 92%, and precision of 98.17%.

show abstract

“…However, such methods still cannot fully leverage the structural information of the third dimension. Most of the studies on 3D medical imaging such as [22,23,24] prefer to train a small 3D convolution neural network from scratch.…”

Section: Related Workmentioning

confidence: 99%

Med3D: Transfer Learning for 3D Medical Image Analysis

Chen,

Ma,

Zheng

2019

Preprint

112

145

View full text Add to dashboard Cite

The performance on deep learning is significantly affected by volume of training data. Models pretrained from massive dataset such as ImageNet become a powerful weapon for speeding up training convergence and improving accuracy. Similarly, models based on large dataset are important for the development of deep learning in 3D medical images. However, it is extremely challenging to build a sufficiently large dataset due to difficulty of data acquisition and annotation in 3D medical imaging. We aggregate the dataset from several medical challenges to build 3DSeg-8 dataset with diverse modalities, target organs, and pathologies. To extract general medical three-dimension (3D) features, we design a heterogeneous 3D network called Med3D to co-train multi-domain 3DSeg-8 so as to make a series of pre-trained models. We transfer Med3D pre-trained models to lung segmentation in LIDC dataset, pulmonary nodule classification in LIDC dataset and liver segmentation on LiTS challenge. Experiments show that the Med3D can accelerate the training convergence speed of target 3D medical tasks 2 times compared with model pre-trained on Kinetics dataset, and 10 times compared with training from scratch as well as improve accuracy ranging from 3% to 20%. Transferring our Med3D model on state-the-of-art DenseASPP segmentation network, in case of single model, we achieve 94.6% Dice coefficient which approaches the result of top-ranged algorithms on the LiTS challenge.

show abstract

Automatic Segmentation of Left Ventricular Myocardium by Deep Convolutional and De:convolutional Neural Networks

Abstract: Deep learning has been integrated into several existing left ventricle (LV)

Cited by 6 publications

References 20 publications

MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation

MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation

A Novel Light U-Net Model for Left Ventricle Segmentation Using MRI

Med3D: Transfer Learning for 3D Medical Image Analysis

Contact Info

Product

Resources

About