mlsanityData to 7 Oct 2026

Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey

arXiv 2106.00997 ↗First posted 2 Jun 2021eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNNs) intrinsically requires large-scale data whereas Chest X-Ray (CXR) images tend to be data/annotation-scarce, leading to over-fitting. Therefore, based on our development experience and related work, this paper thoroughly introduces tricks to improve generalization in the CXR diagnosis: how to (i) leverage additional data, (ii) augment/distillate data, (iii) regularize training, and (iv) conduct efficient segmentation. As a development example based on such optimization techniques, we also feature LPIXEL's CNN-based CXR solution, EIRL Chest Nodule, which improved radiologists/non-radiologists' nodule detection sensitivity by 0.100/0.131, respectively, while maintaining specificity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

22 of 45 references.

References · 22

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  5. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  6. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  7. 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
  8. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 258
  9. 2021Deep Learning for Chest X-ray Analysis: A Surveycited by 84
  10. 2020MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Modelscited by 61
  11. 2020Disentangling Human Error from the Ground Truth in Segmentation of Medical Imagescited by 58
  12. 2021CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretationcited by 57
10 more
  1. 2020MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstructioncited by 50
  2. 2018Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Imagescited by 42
  3. 2020Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoderscited by 38
  4. 2019Interactive segmentation of medical images through fully convolutional neural networkscited by 29
  5. 2019Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detectioncited by 29
  6. 2018A Two-Stream Mutual Attention Network for Semi-supervised Biomedical Segmentation with Noisy Labelscited by 26
  7. 2019Image to Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray Radiographycited by 10
  8. 2019Caveats in Generating Medical Imaging Labels from Radiology Reportscited by 9
  9. 2019Semi-Supervised Multi-Task Learning With Chest X-Ray Imagescited by 8
  10. 2019Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Imagescited by 7

Built on by

Not cited yet.