Related Experiment Video
Updated: Jun 3, 2025
Induction of Experimental Autoimmune Hypophysitis in SJL Mice
Published on: December 17, 2010
Assessing the Diagnostic Performance of Automated Pituitary Gland Volume Measurement for Idiopathic Central
1Departments of Radiology, Eulji University Hospital, Eulji University College of Medicine, 95 Dunsanseo-ro, Seo-gu, Daejeon 35233, Republic of Korea.
Insights
Artificial intelligence accurately measures pituitary gland volume (PV) in idiopathic central precocious puberty (IPP), showing significantly larger PV in IPP patients. This AI method enhances diagnostic efficiency for IPP.
Area of Science:
- Endocrinology
- Radiology
- Artificial Intelligence in Medicine
Background:
- Pituitary gland volume (PV) is elevated in idiopathic central precocious puberty (IPP) compared to healthy children.
- Traditional manual PV measurement is inefficient and labor-intensive.
- Developing automated methods for PV measurement is crucial for efficient IPP diagnosis.
Purpose of the Study:
- To automatically measure PV in IPP patients using artificial intelligence (AI).
- To accurately quantify the correlation between IPP and PV.
- To improve the diagnostic efficiency of IPP through automated PV measurement.
Main Methods:
- Utilized MA-net AI for automatic PV measurement on brain MR imaging from 226 IPP patients and 52 controls.
- Analyzed T1 sagittal images (1-3 mm thickness) from non-enhanced brain MR imaging.
- Correlated physical characteristics with PV and compared PV between IPP and control groups, with bias reduction via PSM.
Main Results:
- High agreement between manual and automatic PV measurements (Intraclass correlation coefficient = 0.993).
- PV was positively correlated with age and body weight in the IPP group.
- Median PV was significantly higher in the IPP group (432 mm³) than in the control group (380 mm³).
Conclusions:
- Pituitary gland volume is significantly larger in patients with idiopathic central precocious puberty.
- Automated PV measurement using AI offers a faster and more efficient diagnostic approach for IPP.
- Combining automated PV assessment with hormone level evaluation can streamline IPP diagnosis.
Abstract:
Background/Objectives: It is known that the pituitary gland volume (PV) in idiopathic central precocious puberty (IPP) is significantly higher than in healthy children. However, most PV measurements rely on manual quantitative methods, which are time-consuming and labor-intensive. This study aimed to automatically measure the PV of patients with IPP using artificial intelligence to accurately quantify the correlation between IPP and PV, and to improve the efficiency of diagnosing IPP. Methods: From July 2016 to February 2024, 226 patients who had been diagnosed with IPP and undergone brain MR imaging were included (117 males and 109 females; median age, 8 years; interquartile range, 7-9 years). A control group of 52 patients who had undergone brain MR imaging without symptoms of precocious puberty was also included (37 males and 15 females; median age, 8 years; interquartile range, 8-9 years). Measurement variability was examined between manual and automatic measurements (n = 57). The pituitary gland volume was measured using 1-3 mm thickness T1 sagittal images from non-enhanced brain MR imaging, analyzed with the MA-net artificial intelligence learning method. Physical characteristics (height, weight, and age) were correlated with PV, and the difference in PV between the IPP group and the control group was evaluated. Results: The intraclass correlation coefficient was 0.993 for agreement between manual and automatic measurement. Confounding bias was reduced by PSM. PV was positively correlated with age and body weight in the IPP group (17.4%, p = 0.009, and 14.0%, p = 0.037). The median values of PV were 432 mm³ in the IPP group and 380 mm³ in the control group, showing a significant difference of 52 mm³ (p < 0.05). Conclusions: The PV in the IPP group was significantly higher than in the control group. Automatically measuring PV along with assessing hormone levels could enable a faster and more straightforward diagnosis of IPP.
