Explainable multiple abnormality classification of chest CT volumes with AxialNet and HiResCAM

@article{Draelos2021ExplainableMA,
  title={Explainable multiple abnormality classification of chest CT volumes with AxialNet and HiResCAM},
  author={Rachel Lea Draelos and Lawrence Carin},
  journal={Artificial intelligence in medicine},
  year={2021},
  volume={132},
  pages={
          102372
        }
}
  • R. DraelosL. Carin
  • Published 24 November 2021
  • Computer Science
  • Artificial intelligence in medicine

Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks

It is shown that while HiResCAM’s explanations faithfully reflect the model, Grad-CAM often expands the attention to create bigger and smoother visualizations, which may aid in the development of trustworthy models for sensitive applications.

The role of artificial intelligence in the differential diagnosis of wheezing symptoms in children

A review of studies that have used artificial intelligence to diagnose wheeze in children aims to comprehensively assess these studies in this field, analyze their interpretability and limitations, and explore and discuss future research directions in real-world clinical applications.

References

SHOWING 1-10 OF 70 REFERENCES

Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks

Qualitative and quantitative results using a publicly available ILD database demonstrate state-of-the-art classification accuracy under the patch-based classification and shows the potential of predicting the ILD type using holistic image.

Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study

Pneumonia-screening CNNs robustly identified hospital system and department within a hospital, which can have large differences in disease burden and may confound predictions.

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

A labeler is designed to automatically detect the presence of 14 observations in radiology reports, capturing uncertainties inherent in radiograph interpretation, in CheXpert, a large dataset that contains 224,316 chest radiographs of 65,240 patients.

Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes

Classification of Interstitial Lung Abnormality Patterns with an Ensemble of Deep Convolutional Neural Networks

A novel methodology for automated identification and classification of ILA patterns in computed tomography images using an ensemble of deep convolutional neural networks that detect more discriminative features by incorporating two, two-and-a-half and three- dimensional architectures, thereby enabling more accurate classification.

Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis

An improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification is presented, with an absolute increase of about 2% in the performance of the proposed CNN.

Multi-label Deep Regression and Unordered Pooling for Holistic Interstitial Lung Disease Pattern Detection

This work proposes two variations of multi-label deep convolutional neural networks that use a deep CNN to detect the presence of multiple ILDs using a regression-based loss function, and improves performance, using spatially invariant Fisher Vector encoding of the CNN feature activations.

An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets

An interpretable deep-learning algorithm trained on a small dataset of computed-tomography scans of the head detects acute ICH and classifies the pathology subtypes, with a performance comparable to expert radiologists.

Weakly-supervised deep learning of interstitial lung disease types on CT images

This paper presents DeepILD, as a novel computer-aided diagnostic framework to address the ILD classification task only from single modality (CT image) using a deep neural network, and proposes integrating spherical semi-supervised K- means clustering and convolutional neural networks for I LD classification and disease quantification.

Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

A comparative analysis proved the effectiveness of the proposed CNN against previous methods in a challenging dataset, and demonstrated the potential of CNNs in analyzing lung patterns.
...