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

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

doi:10.1101/095794

Cited by 42 publications

(31 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For some types of data, especially images, it is straightforward to augment training datasets by splitting a single labelled example into multiple examples. For example, an image can easily be rotated, flipped or translated and retain its label [ 43 ]. 3D MRI and 4D fMRI (with time as a dimension) data can be decomposed into sets of 2D images [ 491 ].…”

Section: Discussionmentioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2018

J. R. Soc. Interface.

1,580

1,001

View full text Add to dashboard Cite

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems—patient classification, fundamental biological processes and treatment of patients—and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

show abstract

Section: Discussionmentioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2018

J. R. Soc. Interface.

1,580

1,001

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, generalized Dice coefficients, focal loss, sparsity label assignment deep multi‐instance learning, and exponential logarithm loss . However, we found that 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: 95%

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

Zhu

Huang

Zeng³

et al. 2018

Medical Physics

Self Cite

430

333

View full text Add to dashboard Cite

Purpose Radiation therapy (RT) is a common treatment option for head and neck (HaN) cancer. An important step involved in RT planning is the delineation of organs‐at‐risks (OARs) based on HaN computed tomography (CT). However, manually delineating OARs is time‐consuming as each slice of CT images needs to be individually examined and a typical CT consists of hundreds of slices. Automating OARs segmentation has the benefit of both reducing the time and improving the quality of RT planning. Existing anatomy autosegmentation algorithms use primarily atlas‐based methods, which require sophisticated atlas creation and cannot adequately account for anatomy variations among patients. In this work, we propose an end‐to‐end, atlas‐free three‐dimensional (3D) convolutional deep learning framework for fast and fully automated whole‐volume HaN anatomy segmentation. Methods Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end‐to‐end fashion, receiving whole‐volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U‐net architecture, but extends it in three important ways: (a) a new encoding scheme to allow autosegmentation on whole‐volume CT images instead of local patches or subsets of slices, (b) incorporating 3D squeeze‐and‐excitation residual blocks in encoding layers for better feature representation, and (c) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep learning‐based HaN segmentation: (a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and (b) training with inconsistent data annotations with missing ground truth for some anatomical structures. Results We collected 261 HaN CT images to train AnatomyNet and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of 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 results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 s to fully segment a head and neck CT image of dimension 178 × 302 × 225, significantly faster than previous methods. In addition, the model is able to process whole‐volume CT images and delineate all OARs in one pass, requiring little pre‐ or postprocessing. Conclusion Deep learning models offer a feasible solution to the problem of delineating OARs from CT images. We demonstrate that our proposed model can improve segmentation accuracy and simplify the autosegmentation pipeline. With this method, it is possible to delineate OARs of a head and neck CT within a fraction of a second.

show abstract

“…The obtained results are reported in Tables 2 and 3. Table 3 results have been taken from paper [17] for DeepCAD, CNN-MAX-CAD-Qiu and CNN-CAD-Jiao and for Ball and Varela has been taken from [18]. Ball shows 87% accuracy on DDMS dataset, Varela shows 81% on DDMS dataset.…”

Section: Resultsmentioning

confidence: 99%

“…Again there is no rule that which features are most suitable. Classification has been performed by using some old classifiers like artificial neural network, KNN, Bayesian [17], [18]. But most of the times, these features extraction and classifiers are not suitable.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning based Computer Aided Diagnosis System for Breast Mammograms

Arfan¹

2017

ijacsa

View full text Add to dashboard Cite

Abstract-In this paper, a framework has been presented by using a combination of deep Convolutional Neural Network (CNN) with Support Vector Machine (SVM). Proposed method first perform preprocessing to resize the image so that it can be suitable for CNN and perform enhancement quality of the images can be enhanced. Deep Convolutional Neural Network (CNN) has been used for features extraction and classification with Support Vector Machine (SVM). Standard dataset MIAS and DDMS has been employed for testing the proposed framework by generating new images from these datasets by the process of augmentation. Different performance measures like Accuracy, Sensitivity, Specificity and area under the curve (AUC) has been employed as a quantitative measure and compared with state of the art existing methods. Results shows that proposed framework has attained accuracy 93.35% and 93% sensitivity.

show abstract

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

Cited by 42 publications

References 19 publications

Opportunities and obstacles for deep learning in biology and medicine

Opportunities and obstacles for deep learning in biology and medicine

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

Deep Learning based Computer Aided Diagnosis System for Breast Mammograms

Contact Info

Product

Resources

About