ENRICHing medical imaging training sets enables more efficient machine learning

Abstract

Objective Deep learning (DL) has been applied in proofs of concept across biomedical imaging, including across modalities and medical specialties. Labeled data are critical to training and testing DL models, but human expert labelers are limited. In addition, DL traditionally requires copious training data, which is computationally expensive to process and iterate over. Consequently, it is useful to prioritize using those images that are most likely to improve a model’s performance, a practice known as instance selection. The challenge is determining how best to prioritize. It is natural to prefer straightforward, robust, quantitative metrics as the basis for prioritization for instance selection. However, in current practice, such metrics are not tailored to, and almost never used for, image datasets. Materials and Methods To address this problem, we introduce ENRICH—Eliminate Noise and Redundancy for Imaging Challenges—a customizable method that prioritizes images based on how much diversity each image adds to the training set. Results First, we show that medical datasets are special in that in general each image adds less diversity than in nonmedical datasets. Next, we demonstrate that ENRICH achieves nearly maximal performance on classification and segmentation tasks on several medical image datasets using only a fraction of the available images and without up-front data labeling. ENRICH outperforms random image selection, the negative control. Finally, we show that ENRICH can also be used to identify errors and outliers in imaging datasets. Conclusions ENRICH is a simple, computationally efficient method for prioritizing images for expert labeling and use in DL.

Deep‐learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection

“…Our study has several strengths. First is the diversity of the imaging cohort 22 . This cohort was external to the dataset on which the model was trained, differed with respect to image formats and scanning protocol (Figure 1) and included imaging studies from several clinics and sonographers.…”

Artificial Intelligence in Fluorescence Lifetime Imaging Ophthalmoscopy (FLIO) Data Analysis—Toward Retinal Metabolic Diagnostics

“…These include, in particular, the analysis of large and complex datasets and the discovery of relationships in these datasets. Most recent studies on the application of AI on medical image data have relied on training neural networks on thousands to hundreds of thousands of training samples [40][41][42][43].…”