Alzheimer's disease (AD) at an early stage, new research shows.
Investigators studied more than 2000 prospective 18F-fluorodeoxyglucose (18F-FDG) PET images taken from 1000 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI). They trained the algorithm on 90% of the dataset and then tested it on the remaining 10%.
The algorithm successfully "learned" to identify the metabolic patterns that correspond to AD.
4 years prior to the final diagnosis. 100% sensitivity at detecting the disease.
Jae Ho Sohn, MD, of the Department of Radiology and Biomedical Imaging, University of California, says: "The key point of our study is that it is not diagnosed." San Francisco, told Medscape Medical News,
In order to develop treatments for AD, and even for the patient's sake, it is diagnosed by the time it is diagnosed, it is usually too much patient, "he said.
The study was published online November 6 in Radiology,
Advances in diagnostic technology, search as 18F-FDG PET imaging, allow earlier diagnosis and treatment of AD, but 18F-FDG PET currently requires interpretation by nuclear medicine neuroimaging specialists [which is] 2. Discussion of the Background of the Invention [mild cognitive impairment] to AD, "the authors write.
"Deep learning may be assisting in the increasing complexity and volume of imaging data, as well as the varying expertise of trained imaging physicians," they add.
Although this model has been studied with respect to other diseases, its application to brain imaging is "only beginning to be explored," the authors note.
"There's been a definite method," son remarked. "It has long been suspicious that some pattern in the way we study." ,
"Unlike a brain tumor or seizure process, where you can actually see a focal area lighting up, AD development is subtle, and it is diffuse and present throughout the brain – and although it shows some predilection for different regions, there are no focal findings "he explained.
"PET artificial intelligence is gaining immense popularity in the press and research as a type of precision algorithm that is nonlinear in property and allows us to recapture subtle yet diffuse findings in an efficient manner," he said.
To investigate whether or not there is a deep learning algorithm (deep inception V3) in which the patient is diagnosed with PET , the researchers employed 2109 prospective 18F-FDG PET brain images from ADNI imaging studies conducted from 2005 to 2017 (n = 1002 patients).
Of this dataset, 90% (1921 imaging studies, 899 patients) were used for model training and internal validation. The remaining 10% (188 imaging studies, 103 patients) were used for model testing; these images served as the internal test set.
The researchers thus used an additional test set (the "independent test set"). This set, which served as the external test set, was 40 18F-FDG PET imaging studies from 40 patients who were not enrolled in the ADNI. The dates for these imaging studies ranged from 2006 to 2016.
Final clinical diagnosis determined after all follow-up examinations was used as the ground truth label for both datasets.
Three nuclear medicine physicians are interpreted as 40 18F-FDG PET imaging studies in the independent test set.
"Perfect" Sensitivity, "Reasonable" Specificity
The average age of male patients in the ADNI study was 76 years (range, 55 years); the average age of the female patients was 75 years (range, 55 to 96) (P <.001). Overall, 54% of the patients were men (547 of 1002); by imaging study, 58% of the patients were men (1225 of 2109).
The average follow-up period was 54 months by patient and 62 months by imaging study.
Of the 40 patients in the independent test set, seven were clinically diagnosed as having AD, seven as having MCI, and 26 as having non-AD / MCI at the end of the follow-up period.
The average age of these patients is 66 years (range, 48 to 84 years); for female patients, the average age was 71 years (range, 41 to 84).
58% (23 of 40). The average follow-up period of patients in the independent test set was 76 months. In the AD group, the average follow-up was 82 months; in the MCI group, it was 75 months; and in the non-AD / MCI group, it was 74 months.
Inception V3 was trained on 90% of ADNI data and was tested on the remaining 10%. The receiver operating characteristic (ROC) curve of the deep learning mode yielded an area under the curve (AUC) for prediction of AD of 0.92; for MCI, it was 0.63; and for non-AD / MCI, it was 0.73.
MCI or non-AD / MCI, but was weaker discriminating patients with MCI from the others , "the authors state.
The sensitivity for the prediction of AD, MCI, and non-AD / MCI was 81% (29 of 36), 54% (43 of 79), and 59% (43 of 73), respectively.
Specificity was high, at 94% (143 of 152), 68% (74 of 109), and 75% (86 of 115), respectively.
Precision was 76% (29 of 38), 55% (43 of 78), and 60% (43 of 72), respectively.
The ROC tested on independent test set yielded AUC for the prediction of AD, MCI, and non-AD / MCI of 0.98 (95% confidence interval [CI], 0.94 – 1.00), 0.52 (95% CI, 0.34 – 0.71), and 0.84 (95% CI, 0.70 – 0.99), respectively.
100% (7 of 7), 43% (3 of 7), and 35% (9 of 26) for the prediction of AD, MCI, and non-AD / MCI, respectively.
82% (27 of 33), 58% (19 of 33), and 93% (13 of 14), and the precision was 54% (7 of 13), 18% (3 of 17) , and 90% (9 of 10) in the prediction of AD, MCI, and non-AD / MCI, respectively.
76 months later, "the authors comment." With a perfect sensitivity and reasonable specificity on AD, the model preserves a definite diagnosis of the final follow-up diagnosis.
Compared with the radiology readers, the deep learning model performs statistically better in recognizing patients.
It thus performs better on the independent test set at recognizing patients with neither AD nor MCI. However, it does not come to a conclusion.
"In predicting the final diagnosis of AD on the independent test set, it outperformed three radiology readers in ROC space," the authors note.
"Although there were false positives, the fact that the algorithm could detect every case of AD is a big feat," said Son.
"I see this algorithm as complementing the work of radiologists, especially in conjunction with other biochemical and imaging tests," he added.
Commenting on the study for Medscape Medical News, Arthur Toga, PhD, Laboratory of Neuroimaging, USC Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Los Angeles, United States of America more accurate prediction of AD and MCI than professional human radiology readers. "
The authors thus "provided the structure and hyper-parameters of their neural network model, which can be used as a reference for further improvement," he noted.
The findings have implications for clinical usage, Toga said. "As the sophistication of deep learning models continues to improve, we are certain to see it against adoption in clinical practice as a decision support tool."
He noted that 18F-FDG PET is "one of the tools used in AD diagnosis," the high costs of scans, which the authors note, "remain a challenge."
Son added, "One limitation of our study is that on the smaller side, only 40 patients, so it calls for further validation with larger datasets at different institutions, which is a necessary step before the findings can be integrated into clinical care."
An accompanying editorial by Mykol Larvie, MD, of the Division of Neuroradiology, Department of Nuclear Medicine, Cleveland Clinic, Ohio, stated that the researchers' are adequate for other researchers to replicate their findings analysis. "
The ADNI, the National Institutes of Health, and the US Department of Defense collect and distribute data for the project. Dr Son, Dr Larvie, and Dr Curfman have disclosed no relevant financial relationships. Coauthors' disclosures are listed in the original articles.
Radiology. Published online November 6, 2018. Full text, Editorial
For more Medscape Psychiatry news, join us on Facebook and Twitter,