Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification

Zhu, Wentao; Lou, Qi; Vang, Yeeleng Scott; Xie, Xiaohui

doi:10.1007/978-3-319-66179-7_69

Cited by 205 publications

(148 citation statements)

References 24 publications

(41 reference statements)

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…Fully Convolutional Network CRF structural learning such as low signal-to-noise ratio, the poor contrast nature of mass and normal breast tissues. There are few work using deep networks to process the mammogram [7,34]. Dhungel et al employed multiple deep belief networks (DBNs), GMM classifier and priori knowledge as the potential functions, and structural SVM (SSVM) to perform the spatially structural learning [8].…”

Section: Radvmentioning

confidence: 99%

Adversarial Deep Structural Networks for Mammographic Mass Segmentation

Zhu

Xie

2016

Preprint

Self Cite

View full text Add to dashboard Cite

Mass segmentation is an important task in mammogram analysis, providing effective morphological features and regions of interest (ROI) for mass detection and classification. Inspired by the success of using deep convolutional features for natural image analysis and conditional random fields (CRF) for structural learning, we propose an end-to-end network for mammographic mass segmentation. The network employs a fully convolutional network (FCN) to model potential function, followed by a CRF to perform structural learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with position priori for the task. Due to the small size of mammogram datasets, we use adversarial training to control over-fitting. Four models with different convolutional kernels are further fused to improve the segmentation results. Experimental results on two public datasets, INbreast and DDSM-BCRP, show that our end-to-end network combined with adversarial training achieves the-state-of-the-art results.

show abstract

Section: Radvmentioning

confidence: 99%

Adversarial Deep Structural Networks for Mammographic Mass Segmentation

Zhu

Xie

2016

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Small volume segmentation suffers from the imbalanced data problem, where the number of voxels inside the small region is much smaller than those outside, leading to the difficulty of training. New classes of loss functions have been proposed to address this issue, including Tversky loss [32], generalized Dice coefficients [33,34], focal loss [35], adversarial loss [36], sparsity label assignment constrains [37], and exponential logarithm loss [38]. However, we found none of these solutions alone was adequate to solve the extremely data imbalanced problem (1/100,000) we face in segmenting small OARs, such as optic nerves and chiasm, from HaN images.…”

Section: Introductionmentioning

confidence: 93%

AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation

Zhu

Huang

Tang

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: Radiation therapy (RT) is a common treatment for head and neck (HaN) cancer where therapists are often required to manually delineate boundaries of the organs-at-risks (OARs). The radiation therapy planning is time-consuming as each computed tomography (CT) volumetric data set typically consists of hundreds to thousands of slices and needs to be individually inspected. Automated head and neck anatomical segmentation provides a way to speed up and improve the reproducibility of radiation therapy planning. Previous work on anatomical segmentation is primarily based on atlas registrations, which takes up to hours for one patient and requires sophisticated atlas creation. In this work, we propose the AnatomyNet, an end-to-end and atlas-free three dimensional squeeze-and-excitation U-Net (3D SE U-Net), for fast and fully automated whole-volume HaN anatomical segmentation.Methods: There are two main challenges for fully automated HaN OARs segmentation: 1) challenge in segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and 2) training model with inconsistent data annotations with missing ground truth for some anatomical structures because of different RT planning. We propose the AnatomyNet that has one down-sampling layer with the trade-off between GPU memory and feature representation capacity, and 3D SE residual blocks for effective feature learning to alleviate these challenges. Moreover, we design a hybrid loss function with the Dice loss and the focal loss. The Dice loss is a class level distribution loss that depends less on the number of voxels in the anatomy, and the focal loss is designed to deal with highly unbalanced segmentation. For missing annotations, we propose masked loss and weighted loss for accurate and balanced weights updating in the learning of the AnatomyNet.Results: We collect 261 HaN CT images to train the AnatomyNet, and use MICCAI Head and Neck Auto Segmentation Challenge 2015 as the benchmark dataset to evaluate the performance of the AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state-of-the-art methods for each anatomy from the MICCAI 2015 competition, the AnatomyNet increases Dice similarity coefficient (DSC) by 3.3% on average. The proposed AnatomyNet takes only 0.12 seconds on average to segment a whole-volume HaN CT image of an average dimension of 178 × 302 × 225. All the data and code will be available a .Conclusion: We propose an end-to-end, fast and fully automated deep convolutional network, AnatomyNet, for accurate and whole-volume HaN anatomical segmentation. The proposed AnatomyNet outperforms previous state-of-the-art methods on the benchmark dataset. Extensive experiments demonstrate the effectiveness and good generalization ability of the components in the AnatomyNet.

show abstract

“…29,30 Among these metrics, the ACC describes the proportion between the number of positive and The calculation formulas of these metrics are shown in Eqs. (11), (12), (13), and (14), respectively, in which the contents and relations of TP, FP, FN, and TN are shown in Table II. "True" and "False" are used to represent the real nodules and non-nodules in ground-truth, and "Positive" and "Negative" are used to represent the evaluation results of nodules and non-nodules determined by the classifier.…”

Section: B1 Evaluation Metrics For Classification Performancementioning

confidence: 99%

Automatic classification of lung nodule candidates based on a novel 3D convolution network and knowledge transferred from a 2D network

Wang

Zhou²,

He³

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Objective In the automatic lung nodule detection system, the authenticity of a large number of nodule candidates needs to be judged, which is a classification task. However, the variable shapes and sizes of the lung nodules have posed a great challenge to the classification of candidates. To solve this problem, we propose a method for classifying nodule candidates through three‐dimensional (3D) convolution neural network (ConvNet) model which is trained by transferring knowledge from a multiresolution two‐dimensional (2D) ConvNet model. Methods In this scheme, a novel 3D ConvNet model is preweighted with the weights of the trained 2D ConvNet model, and then the 3D ConvNet model is trained with 3D image volumes. In this way, the knowledge transfer method can make 3D network easier to converge and make full use of the spatial information of nodules with different sizes and shapes to improve the classification accuracy. Results The experimental results on 551 065 pulmonary nodule candidates in the LUNA16 dataset show that our method gains a competitive average score in the false‐positive reduction track in lung nodule detection, with the sensitivities of 0.619 and 0.642 at 0.125 and 0.25 FPs per scan, respectively. Conclusions The proposed method can maintain satisfactory classification accuracy even when the false‐positive rate is extremely small in the face of nodules of different sizes and shapes. Moreover, as a transfer learning idea, the method to transfer knowledge from 2D ConvNet to 3D ConvNet is the first attempt to carry out full migration of parameters of various layers including convolution layers, full connection layers, and classifier between different dimensional models, which is more conducive to utilizing the existing 2D ConvNet resources and generalizing transfer learning schemes.

show abstract

Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification

Cited by 205 publications

References 24 publications

Adversarial Deep Structural Networks for Mammographic Mass Segmentation

Adversarial Deep Structural Networks for Mammographic Mass Segmentation

AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation

Automatic classification of lung nodule candidates based on a novel 3D convolution network and knowledge transferred from a 2D network

Contact Info

Product

Resources

About