Related Experiment Video
Updated: Apr 25, 2026
Author Spotlight: Combining Proximity Ligand Assay with Gamma-H2AX Staining to Characterize Protein Interactions in DNA Damage Response
Published on: August 2, 2024
Simple and efficient method for region of interest value extraction from picture archiving and communication system
Young Han Lee1, Eun Hae Park1, Jin-Suck Suh1
1Department of Radiology, Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, Republic of Korea; Medical Convergence Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea; Severance Biomedical Science Institute, Yonsei University College of Medicine, 50 Yonsei-ro, Seodaemun-gu, Seoul 120-752, Republic of Korea.
Rationale And Objectives:
The objectives are: 1) to introduce a simple and efficient method for extracting region of interest (ROI) values from a Picture Archiving and Communication System (PACS) viewer using optical character recognition (OCR) software and a macro program, and 2) to evaluate the accuracy of this method with a PACS workstation.
Materials And Methods:
This module was designed to extract the ROI values on the images of the PACS, and created as a development tool by using open-source OCR software and an open-source macro program. The principal processes are as follows: (1) capture a region of the ROI values as a graphic file for OCR, (2) recognize the text from the captured image by OCR software, (3) perform error-correction, (4) extract the values including area, average, standard deviation, max, and min values from the text, (5) reformat the values into temporary strings with tabs, and (6) paste the temporary strings into the spreadsheet. This principal process was repeated for the number of ROIs. The accuracy of this module was evaluated on 1040 recognitions from 280 randomly selected ROIs of the magnetic resonance images. The input times of ROIs were compared between conventional manual method and this extraction module-assisted input method.
Results:
The module for extracting ROI values operated successfully using the OCR and macro programs. The values of the area, average, standard deviation, maximum, and minimum could be recognized and error-corrected with AutoHotkey-coded module. The average input times using the conventional method and the proposed module-assisted method were 34.97 seconds and 7.87 seconds, respectively.
Conclusions:
A simple and efficient method for ROI value extraction was developed with open-source OCR and a macro program. Accurate inputs of various numbers from ROIs can be extracted with this module. The proposed module could be applied to the next generation of PACS or existing PACS that have not yet been upgraded.
