arrow
返回

Artificial Intelligence Algorithms Are Not Clairvoyant REPLY

delete2024-05-02
delete0
PRE
AI
J
Joyita Dutta *
T
Tzu-An Song
DOI:10.2967/jnumed.124.267541delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
would mean that the AI algorithm was doing a better job than the obvious to the radiologist. At the extreme, the AI algorithm could tally, though, this is lesion detection, not image enhancement. It is important to understand that this is what is going on, not actual improvement in image quality or information content. The radiologist is (effectively) no longer making the assessment. Moreover, applicatumor volume, or total lesion glycolysis) may no longer be accurate. When processing data to form images, we are often very careful about the type of prior information we incorporate. Generally, we understand the degree (and sometimes direction) of the bias that the prior information imposes (e.g., expectation maximization's constraint to positive solutions). However, we usually avoid biases in favor of gaining an image assay that is as independent and unbiased as possible. Thus, to the extent possible, the image assay provides completely new information. For example, in PET image reconstruction of PET/MRI data, we generally forgo using the MRI as a prior even though these images will likely appear lower in noise and higher in resolution. This is because it is understood that biasing the PET image toward the MRI will result in a loss of PET information in precisely the regions containing the greatest amount of new information (i.e., the regions lacking mutual information between the PET and MRI). There is some space within the context of PET and SPECT image reconstruction (or other means of generating medical images) where it might be appropriate to apply AI techniques. For PET raw or proThus, improving accuracy in one subregion along this projection the MRI (or AI-derived prior information) during PET image reconstruction is to some extent defendable, whereas reducing scan time and then applying AI-based image enhancement after reconstruction simply is not.
Keyword:
PET

期刊

Journal of Nuclear Medicine 封面图
Journal of Nuclear Medicine
IF:
9.1
论文数:
6.2K
被引数:
3.0W

机构

U
university of massachusetts system
学者数:
3.8W
论文数: 3.5W
被引数: 42
引用论文

引用论文

PET image denoising using unsupervised deep learning
err2019-08-29
err174
errOAAI
errCui, Jianan; Gong, Kuang; Guo, Ning; Wu, Chenxi; Meng, Xiaxia; Kim, Kyungsang; Zheng, Kun; Wu, Zhifang; Fu, Liping; Xu, Baixuan; Zhu, Zhaohui; Tian, Jiahe; Liu, Huafeng; Li, Quanzheng
err分享
err收藏
err分享
err收藏
Artificial Intelligence for PET and SPECT Image EnhancementPET和SPECT图像增强的人工智能
err2023-11-09
err7
errOAAI
errBalaji, Vibha; Song, Tzu-An; Malekzadeh, Masoud; Heidari, Pedram; Dutta, Joyita
err分享
err收藏
On Hallucinations in Tomographic Image Reconstruction
err2021-11-01
err59
errOAAI
errBhadra, Sayantan; Kelkar, Varun A.; Brooks, Frank J.; Anastasio, Mark A.
err分享
err收藏
Noise2Void: unsupervised denoising of PET images
err2021-11-01
err33
errOAAI
errSong, Tzu-An; Yang, Fan; Dutta, Joyita
err分享
err收藏
MRI-based correction for partial-volume effect improves detectability of intractable epileptogenic foci on 123I-iomazenil brain SPECT images
err2008-02-20
err23
errOAAI
errKato, Hiroki; Shimosegawa, Eku; Oku, Naohiko; Kitagawa, Kazuo; Kishima, Haruhiko; Saitoh, Youichi; Kato, Amami; Yoshimine, Toshiki; Hatazawa, Jun
err分享
err收藏
没有更多内容