A myocardial reorientation method based on feature point detection for quantitative analysis of PET myocardial perfusion imaging.
Authors
Affiliations (3)
Affiliations (3)
- School of Medical Technology, Beijing Institution of Technology, No. 5, South Street, Zhongguancun, Haidian District, Beijing 100081, PR China.
- Department of Nuclear Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Science, 1# Shuaifuyuan, Dongcheng District, Beijing 100730, PR China.
- School of Medical Technology, Beijing Institution of Technology, No. 5, South Street, Zhongguancun, Haidian District, Beijing 100081, PR China. Electronic address: [email protected].
Abstract
Reorienting cardiac positron emission tomography (PET) images to the transaxial plane is essential for cardiac PET image analysis. This study aims to design a convolutional neural network (CNN) for automatic reorientation and evaluate its generalizability. An artificial intelligence (AI) method integrating U-Net and the differentiable spatial to numeric transform module (DSNT-U) was proposed to automatically position three feature points (P<sub>apex</sub>, P<sub>base</sub>, and P<sub>RV</sub>), with these three points manually located by an experienced radiologist as the reference standard (RS). A second radiologist performed manual location for reproducibility evaluation. The DSNT-U, initially trained and tested on a [<sup>11</sup>C]acetate dataset (training/testing: 40/17), was further compared with a CNN-spatial transformer network (CNN-STN). The network fine-tuned with 4 subjects was tested on a [<sup>13</sup>N]ammonia dataset (n = 30). The performance of the DSNT-U was evaluated in terms of coordinates, volume, and quantitative indexes (pharmacokinetic parameters and total perfusion deficit). The proposed DSNT-U successfully achieved automatic myocardial reorientation for both [<sup>11</sup>C]acetate and [<sup>13</sup>N]ammonia datasets. For the former dataset, the intraclass correlation coefficients (ICCs) between the coordinates predicted by the DSNT-U and the RS exceeded 0.876. The average normalized mean squared error (NMSE) between the short-axis (SA) images obtained through DSNT-U-based reorientation and the reference SA images was 0.051 ± 0.043. For pharmacokinetic parameters, the R² between the DSNT-U and the RS was larger than 0.968. Compared with the CNN-STN, the DSNT-U demonstrated a higher ICC between the estimated rigid transformation parameters and the RS. After fine-tuning on the [<sup>13</sup>N]ammonia dataset, the average NMSE between the SA images reoriented by the DSNT-U and the reference SA images was 0.056 ± 0.046. The ICC between the total perfusion deficit (TPD) values computed from DSNT-U-derived images and the reference values was 0.981. Furthermore, no significant differences were observed in the performance of the DSNT-U prediction among subjects with different genders or varying myocardial perfusion defect (MPD) statuses. The proposed DSNT-U can accurately position P<sub>apex</sub>, P<sub>base</sub>, and P<sub>RV</sub> on the [<sup>11</sup>C]acetate dataset. After fine-tuning, the positioning model can be applied to the [<sup>13</sup>N]ammonia perfusion dataset, demonstrating good generalization performance. This method can adapt to data of different genders (with or without MPD) and different tracers, displaying the potential to replace manual operations.