TY - JOUR
T1 - Artificial CT images can enhance variation of case images in diagnostic radiology skills training
AU - Hofmeijer, Elfi Inez Saïda
AU - Wu, Sheng Chih
AU - Vliegenthart, Rozemarijn
AU - Slump, Cornelis Herman
AU - van der Heijden, Ferdi
AU - Tan, Can Ozan
N1 - Publisher Copyright:
© 2023, The Author(s).
Financial transaction number:
2500089994
PY - 2023/12
Y1 - 2023/12
N2 - Objectives: We sought to investigate if artificial medical images can blend with original ones and whether they adhere to the variable anatomical constraints provided. Methods: Artificial images were generated with a generative model trained on publicly available standard and low-dose chest CT images (805 scans; 39,803 2D images), of which 17% contained evidence of pathological formations (lung nodules). The test set (90 scans; 5121 2D images) was used to assess if artificial images (512 × 512 primary and control image sets) blended in with original images, using both quantitative metrics and expert opinion. We further assessed if pathology characteristics in the artificial images can be manipulated. Results: Primary and control artificial images attained an average objective similarity of 0.78 ± 0.04 (ranging from 0 [entirely dissimilar] to 1[identical]) and 0.76 ± 0.06, respectively. Five radiologists with experience in chest and thoracic imaging provided a subjective measure of image quality; they rated artificial images as 3.13 ± 0.46 (range of 1 [unrealistic] to 4 [almost indistinguishable to the original image]), close to their rating of the original images (3.73 ± 0.31). Radiologists clearly distinguished images in the control sets (2.32 ± 0.48 and 1.07 ± 0.19). In almost a quarter of the scenarios, they were not able to distinguish primary artificial images from the original ones. Conclusion: Artificial images can be generated in a way such that they blend in with original images and adhere to anatomical constraints, which can be manipulated to augment the variability of cases. Critical relevance statement: Artificial medical images can be used to enhance the availability and variety of medical training images by creating new but comparable images that can blend in with original images. Key points: • Artificial images, similar to original ones, can be created using generative networks. • Pathological features of artificial images can be adjusted through guiding the network. • Artificial images proved viable to augment the depth and broadening of diagnostic training. Graphical Abstract: [Figure not available: see fulltext.].
AB - Objectives: We sought to investigate if artificial medical images can blend with original ones and whether they adhere to the variable anatomical constraints provided. Methods: Artificial images were generated with a generative model trained on publicly available standard and low-dose chest CT images (805 scans; 39,803 2D images), of which 17% contained evidence of pathological formations (lung nodules). The test set (90 scans; 5121 2D images) was used to assess if artificial images (512 × 512 primary and control image sets) blended in with original images, using both quantitative metrics and expert opinion. We further assessed if pathology characteristics in the artificial images can be manipulated. Results: Primary and control artificial images attained an average objective similarity of 0.78 ± 0.04 (ranging from 0 [entirely dissimilar] to 1[identical]) and 0.76 ± 0.06, respectively. Five radiologists with experience in chest and thoracic imaging provided a subjective measure of image quality; they rated artificial images as 3.13 ± 0.46 (range of 1 [unrealistic] to 4 [almost indistinguishable to the original image]), close to their rating of the original images (3.73 ± 0.31). Radiologists clearly distinguished images in the control sets (2.32 ± 0.48 and 1.07 ± 0.19). In almost a quarter of the scenarios, they were not able to distinguish primary artificial images from the original ones. Conclusion: Artificial images can be generated in a way such that they blend in with original images and adhere to anatomical constraints, which can be manipulated to augment the variability of cases. Critical relevance statement: Artificial medical images can be used to enhance the availability and variety of medical training images by creating new but comparable images that can blend in with original images. Key points: • Artificial images, similar to original ones, can be created using generative networks. • Pathological features of artificial images can be adjusted through guiding the network. • Artificial images proved viable to augment the depth and broadening of diagnostic training. Graphical Abstract: [Figure not available: see fulltext.].
KW - Artificial image
KW - Artificial intelligence
KW - Medical image education
KW - Personalized education
KW - Radiology
UR - http://www.scopus.com/inward/record.url?scp=85175982856&partnerID=8YFLogxK
U2 - 10.1186/s13244-023-01508-4
DO - 10.1186/s13244-023-01508-4
M3 - Article
AN - SCOPUS:85175982856
SN - 1869-4101
VL - 14
JO - Insights into Imaging
JF - Insights into Imaging
IS - 1
M1 - 186
ER -