0%

(ACM ICBCB 2018) Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays

Posted on In , ,

Keyword [ChestX-ray14]

Yan C, Yao J, Li R, et al. Weakly supervised deep learning for thoracic disease classification and localization on chest x-rays[C]//Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM, 2018: 103-110.


1. Overview

1.1. Motivation

  • existing methods do not treat different diseases separately

In this paper, it exploits DenseNet-121 as backbone, and equip with

  • SE block
  • multi-map transfer
  • max-min pooling
  • JSRT dataset
  • BSE-JSRT dataset
  • Indiana chast X-ray
  • MIMIC-CXR dataset. lateral views are available
  • AGCNN


2. Architecture



2.1. SE Block



model the interdependency between channels

  • (b, c, h, w) –avg– (b, c, 1, 1)


  • (b, c, 1, 1) –FC+FC– (b, c, 1, 1)



1. r. reduction rate

- (b, c, 1, 1) * (b, c, h, w)



2.2. Multi-Map Layer

  • (b, c, h, w) -M 1x1_Conv- (b, Mc, h, w). (M: the number of class)
  • (b, Mc, h, w) –Classwise Pooling– (b, c, h, w)

2.3. Max-Min Pooling

  • (b, c, h, w) – (b, c)


  1. z^c. c-th pooled feature map
  2. k+ = k- = 1
  3. α = 0.7


3. Experiments

3.1. Dataset

  • ChestX-ray14. official 70-10-20
  • 512 x 512, 3RGB, normalize

3.2. Details

  • BCE loss
  • Adam with 0.0001, *0.1 when 5 time
  • batch size 16
  • random crop 448x448 (4 corner + 1 center)
  • horizontal flipping
  • reimplement CheXNet
  • not using BBox

3.3. Comparison



3.4. Ablation Study