Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A dataset of medication images with instance segmentation masks for preventing adverse drug events

W. I. Chu, S. Hirani, G. Tarroni, L. Li

TL;DR

MEDISEG is evaluated under a few-shot detection protocol, demonstrating that base training on MEDISEG significantly improves recognition of unseen pill classes in occluded multi-pill scenarios compared to existing datasets, highlighting the dataset's ability not only to support robust supervised training but also to promote transferable representations under limited supervision.

Abstract

Medication errors and adverse drug events (ADEs) pose significant risks to patient safety, often arising from difficulties in reliably identifying pharmaceuticals in real-world settings. AI-based pill recognition models offer a promising solution, but the lack of comprehensive datasets hinders their development. Existing pill image datasets rarely capture real-world complexities such as overlapping pills, varied lighting, and occlusions. MEDISEG addresses this gap by providing instance segmentation annotations for 32 distinct pill types across 8262 images, encompassing diverse conditions from individual pill images to cluttered dosette boxes. We trained YOLOv8 and YOLOv9 on MEDISEG to demonstrate their usability, achieving mean average precision at IoU 0.5 of 99.5 percent on the 3-Pills subset and 80.1 percent on the 32-Pills subset. We further evaluate MEDISEG under a few-shot detection protocol, demonstrating that base training on MEDISEG significantly improves recognition of unseen pill classes in occluded multi-pill scenarios compared to existing datasets. These results highlight the dataset's ability not only to support robust supervised training but also to promote transferable representations under limited supervision, making it a valuable resource for developing and benchmarking AI-driven systems for medication safety.

A dataset of medication images with instance segmentation masks for preventing adverse drug events

TL;DR

MEDISEG is evaluated under a few-shot detection protocol, demonstrating that base training on MEDISEG significantly improves recognition of unseen pill classes in occluded multi-pill scenarios compared to existing datasets, highlighting the dataset's ability not only to support robust supervised training but also to promote transferable representations under limited supervision.

Abstract

Medication errors and adverse drug events (ADEs) pose significant risks to patient safety, often arising from difficulties in reliably identifying pharmaceuticals in real-world settings. AI-based pill recognition models offer a promising solution, but the lack of comprehensive datasets hinders their development. Existing pill image datasets rarely capture real-world complexities such as overlapping pills, varied lighting, and occlusions. MEDISEG addresses this gap by providing instance segmentation annotations for 32 distinct pill types across 8262 images, encompassing diverse conditions from individual pill images to cluttered dosette boxes. We trained YOLOv8 and YOLOv9 on MEDISEG to demonstrate their usability, achieving mean average precision at IoU 0.5 of 99.5 percent on the 3-Pills subset and 80.1 percent on the 32-Pills subset. We further evaluate MEDISEG under a few-shot detection protocol, demonstrating that base training on MEDISEG significantly improves recognition of unseen pill classes in occluded multi-pill scenarios compared to existing datasets. These results highlight the dataset's ability not only to support robust supervised training but also to promote transferable representations under limited supervision, making it a valuable resource for developing and benchmarking AI-driven systems for medication safety.
Paper Structure (23 sections, 7 equations, 19 figures, 7 tables)

This paper contains 23 sections, 7 equations, 19 figures, 7 tables.

Table of Contents

  1. Background & Summary
  2. Methods
  3. Data Records
  4. Technical Validation
  5. Usage Notes
  6. Code Availability
  7. Acknowledgements
  8. Author Contributions
  9. Competing Interests
  10. Figures
  11. Tables

Figures (19)

  • Figure 1: (A) Trends in AEMT events from 1980 to 2014 and (B) the distribution of these events across age groups sunshine:aemt:2019.
  • Figure 2: Examples of images taken from (A) the dataset by Lee et al.lee:Pill-ID:2012, (B) the NIH Pillbox datasetyaniv:nlm:2016, (C) the CURE datasetling:few-shot:2020, (D) the dataset by Wong et al.wong:finegrain:2017, and (E) the dataset by Tan et al.tan:comparison:2021.
  • Figure 3: Pills organised in a standard four-by-seven dosette box (left) and after cropping into individual images (right).
  • Figure 4: Top-down and side profile views of Pill A (left), Pill B (centre), and Pill C (right).
  • Figure 5: Examples of image variability in the MEDISEG dataset, ranging from single-pill frames to compositions containing up to six pills.
  • ...and 14 more figures