Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT
Abstract Background This study investigates the integration of Artificial Intelligence (AI) in compensating the lack of time-of-flight (TOF) of the GE Omni Legend PET/CT, which utilizes BGO scintillation crystals. Methods The current study evaluates the image quality of the GE Omni Legend PET/CT usi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-10-01
|
| Series: | EJNMMI Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40658-024-00688-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850275671435116544 |
|---|---|
| author | Meysam Dadgar Amaryllis Verstraete Jens Maebe Yves D’Asseler Stefaan Vandenberghe |
| author_facet | Meysam Dadgar Amaryllis Verstraete Jens Maebe Yves D’Asseler Stefaan Vandenberghe |
| author_sort | Meysam Dadgar |
| collection | DOAJ |
| description | Abstract Background This study investigates the integration of Artificial Intelligence (AI) in compensating the lack of time-of-flight (TOF) of the GE Omni Legend PET/CT, which utilizes BGO scintillation crystals. Methods The current study evaluates the image quality of the GE Omni Legend PET/CT using a NEMA IQ phantom. It investigates the impact on imaging performance of various deep learning precision levels (low, medium, high) across different data acquisition durations. Quantitative analysis was performed using metrics such as contrast recovery coefficient (CRC), background variability (BV), and contrast to noise Ratio (CNR). Additionally, patient images reconstructed with various deep learning precision levels are presented to illustrate the impact on image quality. Results The deep learning approach significantly reduced background variability, particularly for the smallest region of interest. We observed improvements in background variability of 11.8 $$\%$$ % , 17.2 $$\%$$ % , and 14.3 $$\%$$ % for low, medium, and high precision deep learning, respectively. The results also indicate a significant improvement in larger spheres when considering both background variability and contrast recovery coefficient. The high precision deep learning approach proved advantageous for short scans and exhibited potential in improving detectability of small lesions. The exemplary patient study shows that the noise was suppressed for all deep learning cases, but low precision deep learning also reduced the lesion contrast (about −30 $$\%$$ % ), while high precision deep learning increased the contrast (about 10 $$\%$$ % ). Conclusion This study conducted a thorough evaluation of deep learning algorithms in the GE Omni Legend PET/CT scanner, demonstrating that these methods enhance image quality, with notable improvements in CRC and CNR, thereby optimizing lesion detectability and offering opportunities to reduce image acquisition time. |
| format | Article |
| id | doaj-art-22bf009d24e94cc9b263228e0e4fe451 |
| institution | OA Journals |
| issn | 2197-7364 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EJNMMI Physics |
| spelling | doaj-art-22bf009d24e94cc9b263228e0e4fe4512025-08-20T01:50:39ZengSpringerOpenEJNMMI Physics2197-73642024-10-0111111410.1186/s40658-024-00688-2Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CTMeysam Dadgar0Amaryllis Verstraete1Jens Maebe2Yves D’Asseler3Stefaan Vandenberghe4Department of Electronics and Information Systems, Medical Image and Signal Processing, Ghent UniversityDepartment of Electronics and Information Systems, Medical Image and Signal Processing, Ghent UniversityDepartment of Electronics and Information Systems, Medical Image and Signal Processing, Ghent UniversityDepartment of Electronics and Information Systems, Medical Image and Signal Processing, Ghent UniversityDepartment of Electronics and Information Systems, Medical Image and Signal Processing, Ghent UniversityAbstract Background This study investigates the integration of Artificial Intelligence (AI) in compensating the lack of time-of-flight (TOF) of the GE Omni Legend PET/CT, which utilizes BGO scintillation crystals. Methods The current study evaluates the image quality of the GE Omni Legend PET/CT using a NEMA IQ phantom. It investigates the impact on imaging performance of various deep learning precision levels (low, medium, high) across different data acquisition durations. Quantitative analysis was performed using metrics such as contrast recovery coefficient (CRC), background variability (BV), and contrast to noise Ratio (CNR). Additionally, patient images reconstructed with various deep learning precision levels are presented to illustrate the impact on image quality. Results The deep learning approach significantly reduced background variability, particularly for the smallest region of interest. We observed improvements in background variability of 11.8 $$\%$$ % , 17.2 $$\%$$ % , and 14.3 $$\%$$ % for low, medium, and high precision deep learning, respectively. The results also indicate a significant improvement in larger spheres when considering both background variability and contrast recovery coefficient. The high precision deep learning approach proved advantageous for short scans and exhibited potential in improving detectability of small lesions. The exemplary patient study shows that the noise was suppressed for all deep learning cases, but low precision deep learning also reduced the lesion contrast (about −30 $$\%$$ % ), while high precision deep learning increased the contrast (about 10 $$\%$$ % ). Conclusion This study conducted a thorough evaluation of deep learning algorithms in the GE Omni Legend PET/CT scanner, demonstrating that these methods enhance image quality, with notable improvements in CRC and CNR, thereby optimizing lesion detectability and offering opportunities to reduce image acquisition time.https://doi.org/10.1186/s40658-024-00688-2Time of flightContrast recovery coefficientBackground variabilityContrast to noise ratioDeep learningGE Omni Legend |
| spellingShingle | Meysam Dadgar Amaryllis Verstraete Jens Maebe Yves D’Asseler Stefaan Vandenberghe Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT EJNMMI Physics Time of flight Contrast recovery coefficient Background variability Contrast to noise ratio Deep learning GE Omni Legend |
| title | Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT |
| title_full | Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT |
| title_fullStr | Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT |
| title_full_unstemmed | Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT |
| title_short | Assessing the deep learning based image quality enhancements for the BGO based GE omni legend PET/CT |
| title_sort | assessing the deep learning based image quality enhancements for the bgo based ge omni legend pet ct |
| topic | Time of flight Contrast recovery coefficient Background variability Contrast to noise ratio Deep learning GE Omni Legend |
| url | https://doi.org/10.1186/s40658-024-00688-2 |
| work_keys_str_mv | AT meysamdadgar assessingthedeeplearningbasedimagequalityenhancementsforthebgobasedgeomnilegendpetct AT amaryllisverstraete assessingthedeeplearningbasedimagequalityenhancementsforthebgobasedgeomnilegendpetct AT jensmaebe assessingthedeeplearningbasedimagequalityenhancementsforthebgobasedgeomnilegendpetct AT yvesdasseler assessingthedeeplearningbasedimagequalityenhancementsforthebgobasedgeomnilegendpetct AT stefaanvandenberghe assessingthedeeplearningbasedimagequalityenhancementsforthebgobasedgeomnilegendpetct |