The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography
Chest imaging plays a pivotal role in screening and monitoring patients, and various predictive artificial intelligence (AI) models have been developed in support of this. However, little is known about the effect of decreasing the radiation dose and, thus, image quality on AI performance. This stud...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/3/90 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850280166910066688 |
|---|---|
| author | Hendrik Erenstein Wim P. Krijnen Annemieke van der Heij-Meijer Peter van Ooijen |
| author_facet | Hendrik Erenstein Wim P. Krijnen Annemieke van der Heij-Meijer Peter van Ooijen |
| author_sort | Hendrik Erenstein |
| collection | DOAJ |
| description | Chest imaging plays a pivotal role in screening and monitoring patients, and various predictive artificial intelligence (AI) models have been developed in support of this. However, little is known about the effect of decreasing the radiation dose and, thus, image quality on AI performance. This study aims to design a low-dose simulation and evaluate the effect of this simulation on the performance of CNNs in plain chest radiography. Seven pathology labels and corresponding images from Medical Information Mart for Intensive Care datasets were used to train AI models at two spatial resolutions. These 14 models were tested using the original images, 50% and 75% low-dose simulations. We compared the area under the receiver operator characteristic (AUROC) of the original images and both simulations using DeLong testing. The average absolute change in AUROC related to simulated dose reduction for both resolutions was <0.005, and none exceeded a change of 0.014. Of the 28 test sets, 6 were significantly different. An assessment of predictions, performed through the splitting of the data by gender and patient positioning, showed a similar trend. The effect of simulated dose reductions on CNN performance, although significant in 6 of 28 cases, has minimal clinical impact. The effect of patient positioning exceeds that of dose reduction. |
| format | Article |
| id | doaj-art-e04fd60a5c1543b28e5c6899ca7a6b36 |
| institution | OA Journals |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-e04fd60a5c1543b28e5c6899ca7a6b362025-08-20T01:48:52ZengMDPI AGJournal of Imaging2313-433X2025-03-011139010.3390/jimaging11030090The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest RadiographyHendrik Erenstein0Wim P. Krijnen1Annemieke van der Heij-Meijer2Peter van Ooijen3Department of Medical Imaging and Radiation Therapy, Hanze University of Applied Sciences, 9714 CA Groningen, The NetherlandsResearch Group Healthy Ageing, Allied Health Care and Nursing, Hanze University of Applied Sciences, 9714 CA Groningen, The NetherlandsDepartment of Medical Imaging and Radiation Therapy, Hanze University of Applied Sciences, 9714 CA Groningen, The NetherlandsDepartment of Radiotherapy, University of Groningen, University Medical Centre Groningen, 9713 GZ Groningen, The NetherlandsChest imaging plays a pivotal role in screening and monitoring patients, and various predictive artificial intelligence (AI) models have been developed in support of this. However, little is known about the effect of decreasing the radiation dose and, thus, image quality on AI performance. This study aims to design a low-dose simulation and evaluate the effect of this simulation on the performance of CNNs in plain chest radiography. Seven pathology labels and corresponding images from Medical Information Mart for Intensive Care datasets were used to train AI models at two spatial resolutions. These 14 models were tested using the original images, 50% and 75% low-dose simulations. We compared the area under the receiver operator characteristic (AUROC) of the original images and both simulations using DeLong testing. The average absolute change in AUROC related to simulated dose reduction for both resolutions was <0.005, and none exceeded a change of 0.014. Of the 28 test sets, 6 were significantly different. An assessment of predictions, performed through the splitting of the data by gender and patient positioning, showed a similar trend. The effect of simulated dose reductions on CNN performance, although significant in 6 of 28 cases, has minimal clinical impact. The effect of patient positioning exceeds that of dose reduction.https://www.mdpi.com/2313-433X/11/3/90AIdose reductionnoiseimage qualitychest radiography |
| spellingShingle | Hendrik Erenstein Wim P. Krijnen Annemieke van der Heij-Meijer Peter van Ooijen The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography Journal of Imaging AI dose reduction noise image quality chest radiography |
| title | The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography |
| title_full | The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography |
| title_fullStr | The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography |
| title_full_unstemmed | The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography |
| title_short | The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography |
| title_sort | effect of simulated dose reduction on the performance of artificial intelligence in chest radiography |
| topic | AI dose reduction noise image quality chest radiography |
| url | https://www.mdpi.com/2313-433X/11/3/90 |
| work_keys_str_mv | AT hendrikerenstein theeffectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT wimpkrijnen theeffectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT annemiekevanderheijmeijer theeffectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT petervanooijen theeffectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT hendrikerenstein effectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT wimpkrijnen effectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT annemiekevanderheijmeijer effectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography AT petervanooijen effectofsimulateddosereductionontheperformanceofartificialintelligenceinchestradiography |