Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT

by   Jacopo Teneggi, et al.

Modern machine learning pipelines, in particular those based on deep learning (DL) models, require large amounts of labeled data. For classification problems, the most common learning paradigm consists of presenting labeled examples during training, thus providing strong supervision on what constitutes positive and negative samples. This constitutes a major obstacle for the development of DL models in radiology–in particular for cross-sectional imaging (e.g., computed tomography [CT] scans)–where labels must come from manual annotations by expert radiologists at the image or slice-level. These differ from examination-level annotations, which are coarser but cheaper, and could be extracted from radiology reports using natural language processing techniques. This work studies the question of what kind of labels should be collected for the problem of intracranial hemorrhage detection in brain CT. We investigate whether image-level annotations should be preferred to examination-level ones. By framing this task as a multiple instance learning problem, and employing modern attention-based DL architectures, we analyze the degree to which different levels of supervision improve detection performance. We find that strong supervision (i.e., learning with local image-level annotations) and weak supervision (i.e., learning with only global examination-level labels) achieve comparable performance in examination-level hemorrhage detection (the task of selecting the images in an examination that show signs of hemorrhage) as well as in image-level hemorrhage detection (highlighting those signs within the selected images). Furthermore, we study this behavior as a function of the number of labels available during training. Our results suggest that local labels may not be necessary at all for these tasks, drastically reducing the time and cost involved in collecting and curating datasets.


page 5

page 8

page 18


Mixed supervision for surface-defect detection: from weakly to fully supervised learning

Deep-learning methods have recently started being employed for addressin...

Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection

Multiple instance learning (MIL) is a supervised learning methodology th...

Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach

Analysis of histopathology slides is a critical step for many diagnoses,...

Strength from Weakness: Fast Learning Using Weak Supervision

We study generalization properties of weakly supervised learning. That i...

Pi-PE: A Pipeline for Pulmonary Embolism Detection using Sparsely Annotated 3D CT Images

Pulmonary embolisms (PE) are known to be one of the leading causes for c...

Deep Omni-supervised Learning for Rib Fracture Detection from Chest Radiology Images

Deep learning (DL)-based rib fracture detection has shown promise of pla...

Identification of Hemorrhage and Infarct Lesions on Brain CT Images using Deep Learning

Head Non-contrast computed tomography (NCCT) scan remain the preferred p...

Please sign up or login with your details

Forgot password? Click here to reset