Robust Medical Image Classification From Noisy Labeled Data With Global and Local Representation Guided Co-Training

  title={Robust Medical Image Classification From Noisy Labeled Data With Global and Local Representation Guided Co-Training},
  author={Cheng Xue and Lequan Yu and Pengfei Chen and Qi Dou and Pheng-Ann Heng},
  journal={IEEE Transactions on Medical Imaging},
Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifier. This problem is even more severe in the medical image analysis field, as the annotation quality of medical images heavily relies on the expertise… 

BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification

A new method is proposed for the noisy multi-label CXR learning, which detects and smoothly re-labels samples from the dataset, which is then used to train common multi- label classifiers.

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification

A new training module called Non-Volatile Unbiased Memory (NVUM), which non-volatility stores running average of model logits for a new regularization loss on noisy multi-label problem, which outperforms previous state-of-the-art CXR classifiers and previous methods that can deal with noisy labels on all evaluations.

DeepHeartCT: A fully automatic artificial intelligence hybrid framework based on convolutional neural network and multi-atlas segmentation for multi-structure cardiac computed tomography angiography image segmentation

The results demonstrated that the proposed DeepHeartCT framework provides accurate and rapid cardiac CTA segmentation that can be readily generalized for handling large-scale medical imaging applications.

Specificity-Preserving Federated Learning for MR Image Reconstruction

The core idea is to divide the MR reconstruction model into two parts: a globally shared encoder to obtain a generalized representation at the global level, and a client-specific decoder to preserve the domain-specific properties of each client, which is important for collaborative reconstruction when the clients have unique distribution.

Enabling Intelligent IoTs for Histopathology Image Analysis Using Convolutional Neural Networks

This paper implements a quantized ResNet model on two histopathology image datasets to optimize the inference power consumption and shows that lower bit-width implementations yield higher resource utilization and a lower memory bottleneck ratio.

A novel decentralized federated learning approach to train on globally distributed, poor quality, and protected private medical data

AI accuracy using this approach is found to be comparable to centralized training, and when nodes comprise poor-quality data, which is common in healthcare, AI accuracy can exceed the performance of traditional centralized training.



Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification

This paper proposes an effective iterative learning framework for noisy-labeled medical image classification, to combat the lacking of high quality annotated medical data, and designs a sample re-weighting strategy to preserve the usefulness of correctly- labeled hard samples.

Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation

This paper proposes a solution for network automatically evaluating the relative quality of the labels in the training set and using good ones to tune the network parameters, and designs an overfitting control module to let the network maximally learn from the precise annotations during the training process.

Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation

A novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation at the boundary is presented, which consists of three independent networks, which can effectively learn useful information from peer networks.

Iterative Learning with Open-set Noisy Labels

A novel iterative learning framework for training CNNs on datasets with open-set noisy labels that detects noisy labels and learns deep discriminative features in an iterative fashion and designs a Siamese network to encourage clean labels and noisy labels to be dissimilar.

Pancreatic Cancer Detection in Whole Slide Images Using Noisy Label Annotations

An approach to accurately predict regions of pancreatic cancer in whole-slide images (WSIs) by leveraging a relatively large, but noisy, dataset by employing a noisy label classification (NLC) method that utilizes a small set of clean training samples and assigns the appropriate weights to training samples to deal with sample noise.

A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels

This paper contends that it is actually better to ignore the labels of some of the data points than to keep them if the labels are incorrect, especially when the noisy rate is high, and suggests a two-stage framework for the learning from noisy labels.

SELF: Learning to Filter Noisy Labels with Self-Ensembling

This work presents a simple and effective method self-ensemble label filtering (SELF) to progressively filter out the wrong labels during training that substantially outperforms all previous works on noise-aware learning across different datasets and can be applied to a broad set of network architectures.

Training Convolutional Networks with Noisy Labels

An extra noise layer is introduced into the network which adapts the network outputs to match the noisy label distribution and can be estimated as part of the training process and involve simple modifications to current training infrastructures for deep networks.

Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach

This work proposes a method for disease available during training that is able to demonstrate performance comparable with models trained with strong annotations on the Camelyon-16 lymph node metastases detection challenge, and achieves this through the use of pre-trained deep convolutional networks, feature embedding, as well as learning via top instances and negative evidence.