New techniques identify body parts and patients in a PACS environment

Article

With increasing demand for imaging, many PACSs are experiencing a deluge of images and information. Techniques to identify body parts on specific images and to correlate images with the correct patients are integral to ensuring data integrity, according

With increasing demand for imaging, many PACSs are experiencing a deluge of images and information. Techniques to identify body parts on specific images and to correlate images with the correct patients are integral to ensuring data integrity, according to researchers in Japan.

"In a PACS, information on body parts is often not recorded, or is sometimes incorrectly recorded," said Dr. Ikuo Kawashita, a researcher at Hiroshima International University.

If body parts within images are incorrectly labeled in a PACS, applying computer-aided diagnosis becomes impossible. The researchers sought to remedy this problem using a computerized way to identify body parts.

"This method is useful for automated identification of the body parts in digital radiographs when various CAD systems will be implemented in a PACS environment," Kawashita said Monday at the RSNA meeting.

Kawashita and colleagues created an image database containing:

  • 938 chest images
  • 248 abdominal images
  • 117 pelvic images
  • 167 extremity and spine images

The researchers separated the images to use as templates representing average radiographs for different body parts. They then used the computerized method to cycle through a series of steps with each image to identify the appropriate body part. This included separating images into three main categories (chest/abdomen, pelvis, and upper/lower limbs and thoracic spine), classifying images by direction, and shifting templates horizontally and vertically.

Using their computerized method, the group correctly identified body parts in 99.8% of 1290 images.

In a related study, researchers in Sonobe, Japan developed an automated method for correlating the correct posteroanterior images with the correct patient in a PACS environment.

"All images in a PACS environment should be stored in correct locations such as the proper patient's folder," said Junji Morishita, Ph.D., of Kyoto College of Medical Technology.

Using a template technique, Morishita and colleagues identified a correlation threshold. A warning that the wrong patient had been identified was issued if the correlation value was less than the threshold. If the correlation value was more than the threshold, the researchers were notified that the correct patient had been identified.

"The frequency of filing errors for posteroanterior chest images was 1.3% in our prospective study," Morishita said.

In cases in which the system did not recognize that the incorrect patient had been identified, radiologists were on hand and recognized the error. For patients falsely identified by the system as the incorrect patient, pathological changes in the lungs, such as pneumonia, were easily identified by the radiologists.

According to radiologists' feedback, the method would be acceptable in a clinical situation, Morishita said.

Newsletter

Stay at the forefront of radiology with the Diagnostic Imaging newsletter, delivering the latest news, clinical insights, and imaging advancements for today’s radiologists.

Recent Videos
SNMMI: Emerging PET Insights on Neuroinflammation with Progressive Apraxia of Speech (PAOS) and Parkinson-Plus Syndrome
Improving Access to Nuclear Imaging: An Interview with SNMMI President Jean-Luc C. Urbain, MD, PhD
SNMMI: 18F-Piflufolastat PSMA PET/CT Offers High PPV for Local PCa Recurrence Regardless of PSA Level
SNMMI: NIH Researcher Discusses Potential of 18F-Fluciclovine for Multiple Myeloma Detection
SNMMI: What Tau PET Findings May Reveal About Modifiable Factors for Alzheimer’s Disease
Emerging Insights on the Use of FES PET for Women with Lobular Breast Cancer
Can Generative AI Reinvent Radiology Reporting?: An Interview with Samir Abboud, MD
Mammography Study Reveals Over Sixfold Higher Risk of Advanced Cancer Presentation with Symptom-Detected Cancers
Combining Advances in Computed Tomography Angiography with AI to Enhance Preventive Care
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
Related Content
© 2025 MJH Life Sciences

All rights reserved.