Deep learning of feature representation with multiple instance learning for medical image analysis

  title={Deep learning of feature representation with multiple instance learning for medical image analysis},
  author={Yan Xu and Tao Mo and Qiwei Feng and Peilin Zhong and Maode Lai and Eric I-Chao Chang},
  journal={2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  • Yan XuTao Mo E. Chang
  • Published 4 May 2014
  • Computer Science
  • 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
This paper studies the effectiveness of accomplishing high-level tasks with a minimum of manual annotation and good feature representations for medical images. [] Key Method We use multiple instance learning (MIL) framework in classification training with deep learning features. Several interesting conclusions can be drawn from our work: (1) automatic feature learning outperforms manual feature; (2) the unsupervised approach can achieve performance that's close to fully supervised approach (93.56%) vs. (94…

Figures and Tables from this paper

Classification of Medical Images in the Biomedical Literature by Jointly Using Deep and Handcrafted Visual Features

A combined deep and handcrafted visual feature (CDHVF) based algorithm that uses features learned by three fine-tuned and pretrained deep convolutional neural networks and two handcrafted descriptors in a joint approach to improve accuracy in certain medical image classification problems is proposed.

Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation

We propose a simple, efficient and effective method using deep convolutional activation features (CNNs) to achieve stat- of-the-art classification and segmentation for the MICCAI 2014 Brain Tumor

Deep multiple instance learning for image classification and auto-annotation

This paper attempts to model deep learning in a weakly supervised learning (multiple instance learning) framework, where each image follows a dual multi-instance assumption, where its object proposals and possible text annotations can be regarded as two instance sets.

Multiple-Instance Learning for Medical Image and Video Analysis

This meta-analysis shows that, besides being more convenient than SIL solutions, MIL algorithms are also more accurate in many cases, in other words, MIL is the ideal solution for many MIVA tasks.

Deep multiple instance learning for automatic detection of diabetic retinopathy in retinal images

A deep MIL method is proposed for DR detection, which jointly learns features and classifiers from data and achieves a significant improvement on detecting DR images and their inside lesions.

Deep Multi-Instance Learning with Induced Self-Attention for Medical Image Classification

The experimental results reveal that the induced self-attention mechanism can learn very discriminative and different features for target and non-target instances within a bag, and thus fits more generalized MIL problems.

Deep learning in digital pathology image analysis: a survey

This paper comprehensively summarize recent DL-based image analysis studies in histopathology, including different tasks (e.g., classification, semantic segmentation, detection, and instance segmentation) and various applications and DL methods can provide consistent and accurate outcomes.

Constrained Deep Weak Supervision for Histopathology Image Segmentation

A new weakly supervised learning algorithm to learn to segment cancerous regions in histopathology images with fully convolutional networks and an effective way to introduce constraints to the authors' neural networks to assist the learning process is proposed.

MIDCN: A Multiple Instance Deep Convolutional Network for Image Classification

The results of the proposed MIDCN consistently outperforms the state-of-the-art methods and contains global information of all the training bags, which is more robust and noise free.



Contexts-Constrained Multiple Instance Learning for Histopathology Image Analysis

A new algorithm along the line of weakly supervised learning is proposed; context constraints as a prior for multiple instance learning (ccMIL) is introduced, which significantly reduces the ambiguity in weak supervision (a 20% gain).

Learning invariant features of tumor signatures

A novel method for automated learning of features from unlabeled image patches for classification of tumor architecture that outperforms more complex expert-designed approaches and promises a wider application of self-learning strategies for tissue characterization.

An Analysis of Single-Layer Networks in Unsupervised Feature Learning

The results show that large numbers of hidden nodes and dense feature extraction are critical to achieving high performance—so critical, in fact, that when these parameters are pushed to their limits, they achieve state-of-the-art performance on both CIFAR-10 and NORB using only a single layer of features.

Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives

Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, manifold learning, anddeep learning.

Sparse Feature Learning for Deep Belief Networks

This work proposes a simple criterion to compare and select different unsupervised machines based on the trade-off between the reconstruction error and the information content of the representation, and describes a novel and efficient algorithm to learn sparse representations.

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

The convolutional deep belief network is presented, a hierarchical generative model which scales to realistic image sizes and is translation-invariant and supports efficient bottom-up and top-down probabilistic inference.

Learning invariant features through topographic filter maps

This work proposes a method that automatically learns feature extractors in an unsupervised fashion by simultaneously learning the filters and the pooling units that combine multiple filter outputs together.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

What is the best multi-stage architecture for object recognition?

It is shown that using non-linearities that include rectification and local contrast normalization is the single most important ingredient for good accuracy on object recognition benchmarks and that two stages of feature extraction yield better accuracy than one.

Discriminative learned dictionaries for local image analysis

This article proposes an energy formulation with both sparse reconstruction and class discrimination components, jointly optimized during dictionary learning, for local image discrimination tasks, and paves the way for a novel scene analysis and recognition framework based on simultaneously learning discriminative and reconstructive dictionaries.