Brain Tumor Segmentation Based on 3D Unet with Multi-Class Focal Loss

Chang, J. Morris; Zhang, Xiaoci; Ye, Minquan; Huang, Daobin; Wang, Peipei; Yao, Chuanwen

doi:10.1109/cisp-bmei.2018.8633056

Cited by 25 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It calculates the degree of overlap between the actual segmentation results S of the algorithm and the gold mask R, 19 defined as Eq. (12). The value range of DSC is [0,1], the closer it is to 1, the better the performance of the segmentation algorithm.…”

Section: B1 Experiments Imentioning

confidence: 99%

“…Existing medical image segmentation methods based on deep learning 9,11–13 have one thing in common: When training the segmentation network model, the network weights are first obtained through the training set. By continuously updating the network weights in such a loop iterative manner, the sample output of the training set gradually approaches the training set sample label, and the loss rate is reduced until the model tends to be stable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of pulmonary nodules in CT images based on 3D‐UNET combined with three‐dimensional conditional random field optimization

Gao

Duan

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose: Pulmonary nodules are a potential manifestation of lung cancer. In computer-aided diagnosis (CAD) of lung cancer, it is of great significance to extract the complete boundary of the pulmonary nodules in the computed tomography (CT) scans accurately. It can provide doctors with important information such as tumor size and density, which assist doctors in subsequent diagnosis and treatment. In addition to this, in the molecular subtype and radiomics of lung cancer, segmentation of lung nodules also plays a pivotal role. Existing methods are difficult to use only one model to simultaneously treat the boundaries of multiple types of lung nodules in CT images. Method: In order to solve the problem, this paper proposed a three-dimensional (3D)-UNET network model optimized by a 3D conditional random field (3D-CRF) to segment pulmonary nodules. On the basis of 3D-UNET, the 3D-CRF is used to optimize the sample output of the training set, so as to update the network weights in training process, reduce the model training time, and reduce the loss rate of the model. We selected 936 sets of pulmonary nodule data for the lung image database consortium and image database resource initiative (LIDC-IDRI) 1 database to train and test the model. What's more, we used clinical data from partner hospitals for additional validation. Results and conclusions: The results show that our method is accurate and effective. Particularly, it shows more significance for the optimization of the segmentation of adhesive pulmonary nodules (the juxta-pleural and juxta-vascular nodules) and ground glass pulmonary nodules (GGNs).

show abstract

Section: B1 Experiments Imentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Segmentation of pulmonary nodules in CT images based on 3D‐UNET combined with three‐dimensional conditional random field optimization

Gao

Duan

et al. 2020

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Authors in [36] introduced a network that extends the u-net architecture from [37] by replacing all 2D processes with their 3D equivalent. Regarding brain segmentation, Chang et al [38] proposed an effective 3D U-Net model to improve segmentation accuracy and feature labeling.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep MRI Segmentation: A Convolutional Method Applied to Alzheimer Disease Detection

Allioui¹,

Sadgal²,

Elfazziki³

2019

IJACSA

View full text Add to dashboard Cite

The learning techniques have a particular need especially for the detection of invisible brain diseases. Learningbased methods rely on MRI medical images to reconstruct a solution for detecting aberrant values or areas in the human brain. In this article, we present a method that automatically performs segmentation of the brain to detect brain damage and diagnose Alzheimer's disease (AD). In order to take advantages of the benefits of 3D and reduce complexity and computational costs, we present a 2.5D method for locating brain inflammation and detecting their classes. Our proposed system is evaluated on a set of public data. Preliminary results indicate the reliability and effectiveness of our Alzheimer's Disease Detection System and demonstrate that our method is beyond current knowledge of Alzheimer's disease diagnosis.

show abstract

“…Because of its effectiveness, it has been successfully applied in many applications, e.g., medical diagnosis (Al Rahhal et al, 2019;Shu et al, 2019;Ulloa et al, 2020;Xu et al, 2020), speech processing (Tripathi et al, 2019), and natural language processing (Shi et al, 2018). Although the focal loss has been successfully applied in many real-world problems (Al Rahhal et al, 2019;Chang et al, 2018;Lotfy et al, 2019;Romdhane and Pr, 2020;Shu et al, 2019;Sun et al, 2019;Ulloa et al, 2020;Xu et al, 2020), considerably less attention has *Nontawat and Jayakorn contributed equally. 1 arXiv:2011.09172v2 [stat.ML] 14 Dec 2020 been paid to the theoretical understanding of this loss function.…”

Section: Introductionmentioning

confidence: 99%

On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective

Charoenphakdee

Vongkulbhisal²,

Chairatanakul

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

The focal loss has demonstrated its effectiveness in many real-world applications such as object detection and image classification, but its theoretical understanding has been limited so far. In this paper, we first prove that the focal loss is classification-calibrated, i.e., its minimizer surely yields the Bayes-optimal classifier and thus the use of the focal loss in classification can be theoretically justified. However, we also prove a negative fact that the focal loss is not strictly proper, i.e., the confidence score of the classifier obtained by focal loss minimization does not match the true class-posterior probability and thus it is not reliable as a class-posterior probability estimator. To mitigate this problem, we next prove that a particular closed-form transformation of the confidence score allows us to recover the true class-posterior probability. Through experiments on benchmark datasets, we demonstrate that our proposed transformation significantly improves the accuracy of class-posterior probability estimation.

show abstract

Brain Tumor Segmentation Based on 3D Unet with Multi-Class Focal Loss

Cited by 25 publications

References 15 publications

Segmentation of pulmonary nodules in CT images based on 3D‐UNET combined with three‐dimensional conditional random field optimization

Segmentation of pulmonary nodules in CT images based on 3D‐UNET combined with three‐dimensional conditional random field optimization

Deep MRI Segmentation: A Convolutional Method Applied to Alzheimer Disease Detection

On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective

Contact Info

Product

Resources

About