Cross‐Institutional Prediction System for Estimating Patient‐Specific Organ Dose from Chest CT Scans without Segmenting Internal Organs
This study aims to establish and validate a cross‐institutional prediction system for estimating patient‐specific organ doses from chest CT scans. By collaborating across multiple institutions, the study seeks to develop models that allow rapid online estimation of organ doses, eliminating the need...
Saved in:
Published in | Advanced intelligent systems |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
23.09.2024
|
Online Access | Get full text |
Cover
Loading…
Summary: | This study aims to establish and validate a cross‐institutional prediction system for estimating patient‐specific organ doses from chest CT scans. By collaborating across multiple institutions, the study seeks to develop models that allow rapid online estimation of organ doses, eliminating the need for complex organ segmentation. Researchers delineate skin outlines from chest CT images obtained from two different institutions. Radiomics features are extracted from the chest CT data and skin contours. Organ doses are computed using Monte Carlo simulations as reference organ doses. Single‐ and cross‐institutional support vector regression (SVR) models are trained with radiomics features to predict organ doses from chest CT scans. Model performance is assessed using metrics like maean absolute percentage error (MAPE) and R ‐squared ( R 2 ). For chest organs (lungs, heart, spinal cord, trachea, and esophagus), single‐institutional SVR models achieve MAPE values ranging from 4.72% to 15.31% and R 2 values from 0.73 to 0.93. Cross‐institutional models have MAPE values in the range of 2.16–7.49% and R 2 values from 0.84 to 0.99. SVR models trained with radiomics features from skin outlines can reliably estimate organ doses from chest CT scans. The proposed method is applicable across different institutions, and cross‐institutional models enhance predictive accuracy, generality, and robustness. |
---|---|
ISSN: | 2640-4567 2640-4567 |
DOI: | 10.1002/aisy.202400357 |