Pharmaceutical Blister Package Identification Based on Induced Deep Learning

Abstract

Prescription dispensing accuracy is of paramount importance for all hospitals. However, human errors are inevitable due to multiple reasons, such as fatigue, stress, heavy workload, lack of effective verification measures, mismanagement. Such human errors pose serious safety and health concerns on the part of patients and may as well lead to a series of medical disputes. Based on induced deep learning, this paper proposes a real-time Blister Package Identification System (BPIS) to assist pharmacists' drug verification and dispensing. Under the guidance of the induction strategy, image preprocessing is introduced to form a standardized image containing the front and back side of the blister package, which is subsequently sent to CNN-based object identification network for feature extraction and identification. This preprocessing method allows the identification system to promote the deep learning system to focus on feature learning to obtain more information about the appearance of the package ruling out confounding factors such as background noise, size, shape or positioning. In addition, this article collects and establishes an image dataset of adult lozenges. Under this dataset, this paper verifies the enhancement of Induced Deep Learning (IDL) on YOLO v2, ResNet, and SENet. By optimizing the deep learning identification network with the help of the embedded technology and a two-side extraction mechanism, a real-time BPIS is built. Long-term tests in hospitals prove the effectiveness of the proposed system.INDEX TERMS Blister package identification, deep learning, induction, dispensing error, CNN.

A Novel Two-Stage Induced Deep Learning System for Classifying Similar Drugs with Diverse Packaging

“…Some research indicates that drugs’ similarity impacts the classification accuracy of deep learning models. Han, Y. et al proposed a novel IDL for medication image recognition and significantly improved the accuracy [ 26 ]. IDL incorporates human experience and cognition into deep learning, enhancing its ability to recognize medications.…”

“…Y. Han et al first applied IDL for drug-image recognition [ 26 ]. They adjusted the images based on their experience in drug classification.…”

“…et al proposed a highlighting deep learning method to classify the blister packaging of medications [ 25 ]. Han Y. et al employed an induced deep learning (IDL) approach to classify medications in blister packaging [ 26 ].…”

“…Han Y. et al proposed a special IDL framework for medication-image recognition. Image processing was performed to obtain images more conducive to capturing the appearance of medication features [ 26 ]. IDL incorporates human experience and cognition into deep learning by performing image processing to enhance classification capabilities, thus reducing the requirement for extensive training data.…”

MediCaption: Integrating YOLO-Driven Computer Vision and NLP for Advanced Pharmaceutical Package Recognition and Annotation

“…Inspired by this, MediCaption employs NLP techniques to generate informative captions about medications, aiding healthcare decisions and ensuring informed patient care. The technological backbone of MediCaption is fortified by the exploration of pharmaceutical blister package identification by Yun Han et al [11], and the comparative analyses of YOLO models by Marko Horvat et al [12], [13]. These studies not only inform the choice of the YOLOv8 architecture for MediCaption but also emphasize the project's commitment to utilizing the most effective models for real-time analysis of pharmaceutical packaging.…”