Thoracic Disease Identification and Localization with Limited Supervision

By Zhe Li, Chong Wang, Mei Han, Yuan Xue, Wei Wei, Li-Jia Li, F. Li. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017

364 citations recorded by the source corpus.

Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning. Building a highly accurate prediction model for these tasks usually requires a large number of images manually annotated with labels and finding sites of abnormalities. In reality, however, such annotated data are expensive to acquire, especially the ones with location annotations. We need methods that can work well with only a small amount of location annotations. To address this challenge, we present a unified approach that simultaneously performs disease identification and localization through the same underlying model for all images. We demonstrate that our approach can effectively leverage both class information as well as limited location annotation, and significantly outperforms the comparative reference baseline in both classification and localization tasks.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/8bdfb96e2865ad0d1e263f04fc0dab134052d64e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification (2018, methodology): “In addition, differing dataset splits were used and only [9] reported 5-fold cross-validated results.”
RadBot-CXR: Classification of Four Clinical Finding Categories in Chest X-Ray Using Deep Learning (2018, background): “We compared our AUCs to Li et al. [10] in Table 2.”
Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences (2018, neutral): “[46] to jointly perform classification and localization using a small number of weakly labeled examples.”
CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison (2019, methodology): “…models, predicting on transformed versions of the inputs instead of training multiple models, and output a target label for each unlabeled example; soft labels, which are continuous probability outputs rather than binary, have also been used (Hin-ton, Vinyals, and Dean 2015; Li et al. 2017a).”
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (2020, result): “In this case, previous studies confirm the effectiveness of adopting extra images by pseudo label mining [5,10] or multiple instance learning [21].”
Pneumonia Detection Using CNN based Feature Extraction (2019, background): “Zhe Li (2018) [20] recently proposed a convolutional network model for disease identification and localization.”
XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations (2021, neutral): “In comparison with recent methods using additional supervision (Table 3) and analysis with a prior condition to have speciﬁc prototypes (Section 4.5), we conduct a ﬁve-fold cross validation, similar to that in [17,19].”
Multiresolution Knowledge Distillation for Anomaly Detection (2020, background): “It has been a vital demanding task in computer vision with various applications, like in industrial image-based product quality control [27, 7] or in health monitoring processes [26].”