Structured dataset documentation: a datasheet for CheXpert

Billions of X-ray images are taken worldwide each year. Machine learning, and deep learning in particular, has shown potential to help radiologists triage and diagnose images. However, deep learning requires large datasets with reliable labels. The CheXpert dataset was created with the participation of board-certified radiologists, resulting in the strong ground truth needed to train deep learning networks. Following the structured format of Datasheets for Datasets, this paper expands on the original CheXpert paper and other sources to show the critical role played by radiologists in the creation of reliable labels and to describe the different aspects of the dataset composition in detail. Such structured documentation intends to increase the awareness in the machine learning and medical communities of the strengths, applications, and evolution of CheXpert, thereby advancing the field of medical image analysis. Another objective of this paper is to put forward this dataset datasheet as an example to the community of how to create detailed and structured descriptions of datasets. We believe that clearly documenting the creation process, the contents, and applications of datasets accelerates the creation of useful and reliable models.

Automatic Separation of Compound Figures in Scientific Articles

Content-based analysis and retrieval of digital images found in scientific articles is often hindered by images consisting of multiple subfigures (compound figures). We address this problem by proposing a method to automatically classify and separate compound figures, which consists of two main steps: (i) a supervised compound figure classifier (CFC) discriminates between compound and non-compound figures using task-specific image features; and (ii) an image processing algorithm is applied to predicted compound images to perform compound figure separation (CFS). Our CFC approach is shown to achieve state-of-the-art classification performance on a published dataset. Our CFS algorithm shows superior separation accuracy on two different datasets compared to other known automatic approaches. Finally, we propose a method to evaluate the effectiveness of the CFC-CFS process chain and use it to optimize the misclassification loss of CFC for maximal effectiveness in the process chain.