Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes
Recently, the use of saliency maps to evaluate the image quality of nuclear medicine images has been reported. However, that study only compared qualitative visual evaluations and did not perform a quantitative assessment. The study’s aim was to demonstrate the possibility of using saliency maps (ca...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Radiation |
Subjects: | |
Online Access: | https://www.mdpi.com/2673-592X/2/3/18 |
_version_ | 1797482915975659520 |
---|---|
author | Shota Hosokawa Yasuyuki Takahashi Kazumasa Inoue Chimo Nagasawa Yuya Watanabe Hiroki Yamamoto Masahiro Fukushi |
author_facet | Shota Hosokawa Yasuyuki Takahashi Kazumasa Inoue Chimo Nagasawa Yuya Watanabe Hiroki Yamamoto Masahiro Fukushi |
author_sort | Shota Hosokawa |
collection | DOAJ |
description | Recently, the use of saliency maps to evaluate the image quality of nuclear medicine images has been reported. However, that study only compared qualitative visual evaluations and did not perform a quantitative assessment. The study’s aim was to demonstrate the possibility of using saliency maps (calculated from intensity and flicker) to assess nuclear medicine image quality by comparison with the evaluator’s gaze data obtained from an eye-tracking device. We created 972 positron emission tomography images by changing the position of the hot sphere, imaging time, and number of iterations in the iterative reconstructions. Pearson’s correlation coefficient between the saliency map calculated from each image and the evaluator’s gaze data during image presentation was calculated. A strong correlation (<i>r</i> ≥ 0.94) was observed between the saliency map (intensity) and the evaluator’s gaze data. This trend was also observed in images obtained from a clinical device. For short acquisition times, the gaze to the hot sphere position was higher for images with fewer iterations during the iterative reconstruction. However, no differences in iterations were found when the acquisition time increased. Saliency by flicker could be applied to clinical images without preprocessing, although compared with the gaze image, it increased slowly. |
first_indexed | 2024-03-09T22:40:20Z |
format | Article |
id | doaj.art-1b4d62bbeb5e4fa09dca5ffdc7787cf4 |
institution | Directory Open Access Journal |
issn | 2673-592X |
language | English |
last_indexed | 2024-03-09T22:40:20Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Radiation |
spelling | doaj.art-1b4d62bbeb5e4fa09dca5ffdc7787cf42023-11-23T18:40:22ZengMDPI AGRadiation2673-592X2022-07-012324825810.3390/radiation2030018Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study OutcomesShota Hosokawa0Yasuyuki Takahashi1Kazumasa Inoue2Chimo Nagasawa3Yuya Watanabe4Hiroki Yamamoto5Masahiro Fukushi6Department of Radiation Science, Hirosaki University, Hirosaki 036-8564, JapanDepartment of Radiation Science, Hirosaki University, Hirosaki 036-8564, JapanDepartment of Radiological Sciences, Tokyo Metropolitan University, Tokyo 116-8551, JapanDepartment of Radiology Technology, Iwate Prefectural Ofunato Hospital, Ofunato 022-0002, JapanDepartment of Radiation Science, Hirosaki University, Hirosaki 036-8564, JapanDepartment of Radiology, Division of Medical Technology, Hirosaki University Hospital, Hirosaki 036-8563, JapanDepartment of Radiological Technology, Tsukuba International University, Tsuchiura 300-0051, JapanRecently, the use of saliency maps to evaluate the image quality of nuclear medicine images has been reported. However, that study only compared qualitative visual evaluations and did not perform a quantitative assessment. The study’s aim was to demonstrate the possibility of using saliency maps (calculated from intensity and flicker) to assess nuclear medicine image quality by comparison with the evaluator’s gaze data obtained from an eye-tracking device. We created 972 positron emission tomography images by changing the position of the hot sphere, imaging time, and number of iterations in the iterative reconstructions. Pearson’s correlation coefficient between the saliency map calculated from each image and the evaluator’s gaze data during image presentation was calculated. A strong correlation (<i>r</i> ≥ 0.94) was observed between the saliency map (intensity) and the evaluator’s gaze data. This trend was also observed in images obtained from a clinical device. For short acquisition times, the gaze to the hot sphere position was higher for images with fewer iterations during the iterative reconstruction. However, no differences in iterations were found when the acquisition time increased. Saliency by flicker could be applied to clinical images without preprocessing, although compared with the gaze image, it increased slowly.https://www.mdpi.com/2673-592X/2/3/18PETimage quality assessmentsaliencyeye-trackingMonte Carlo simulation |
spellingShingle | Shota Hosokawa Yasuyuki Takahashi Kazumasa Inoue Chimo Nagasawa Yuya Watanabe Hiroki Yamamoto Masahiro Fukushi Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes Radiation PET image quality assessment saliency eye-tracking Monte Carlo simulation |
title | Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes |
title_full | Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes |
title_fullStr | Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes |
title_full_unstemmed | Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes |
title_short | Validation of a Saliency Map for Assessing Image Quality in Nuclear Medicine: Experimental Study Outcomes |
title_sort | validation of a saliency map for assessing image quality in nuclear medicine experimental study outcomes |
topic | PET image quality assessment saliency eye-tracking Monte Carlo simulation |
url | https://www.mdpi.com/2673-592X/2/3/18 |
work_keys_str_mv | AT shotahosokawa validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes AT yasuyukitakahashi validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes AT kazumasainoue validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes AT chimonagasawa validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes AT yuyawatanabe validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes AT hirokiyamamoto validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes AT masahirofukushi validationofasaliencymapforassessingimagequalityinnuclearmedicineexperimentalstudyoutcomes |