Top

31-10-2024 | Alzheimer's Disease | Imaging Informatics and Artificial Intelligence

Using interpretable deep learning radiomics model to diagnose and predict progression of early AD disease spectrum: a preliminary [¹⁸F]FDG PET study

Authors: Jiehui Jiang, Chenyang Li, Jiaying Lu, Jie Sun, Xiaoming Sun, Jiacheng Yang, Luyao Wang, Chuantao Zuo, Kuangyu Shi, for the Alzheimer’s Disease Neuroimaging Initiative

Published in: European Radiology

Abstract

Objectives

In this study, we propose an interpretable deep learning radiomics (IDLR) model based on [¹⁸F]FDG PET images to diagnose the clinical spectrum of Alzheimer’s disease (AD) and predict the progression from mild cognitive impairment (MCI) to AD.

Methods

This multicentre study included 1962 subjects from two ethnically diverse, independent cohorts (a Caucasian cohort from ADNI and an Asian cohort merged from two hospitals in China). The IDLR model involved feature extraction, feature selection, and classification/prediction. We evaluated the IDLR model’s ability to distinguish between subjects with different cognitive statuses and MCI trajectories (sMCI and pMCI) and compared results with radiomic and deep learning (DL) models. A Cox model tested the IDLR signature’s predictive capability for MCI to AD progression. Correlation analyses identified critical IDLR features and verified their clinical diagnostic value.

Results

The IDLR model achieved the best classification results for subjects with different cognitive statuses as well as in those with MCI with distinct trajectories, with an accuracy of 76.51% [72.88%, 79.60%], (95% confidence interval, CI) while those of radiomic and DL models were 69.13% [66.28%, 73.12%] and 73.89% [68.99%, 77.89%], respectively. According to the Cox model, the hazard ratio (HR) of the IDLR model was 1.465 (95% CI: 1.236–1.737, p < 0.001). Moreover, three crucial IDLR features were significantly different across cognitive stages and were significantly correlated with cognitive scale scores (p < 0.01).

Conclusions

Preliminary results demonstrated that the IDLR model based on [¹⁸F]FDG PET images enhanced accuracy in diagnosing the clinical spectrum of AD.

Key Points

Question The study addresses the lack of interpretability in existing DL classification models for diagnosing the AD spectrum.

Findings The proposed interpretable DL radiomics model, using radiomics-supervised DL features, enhances interpretability from traditional DL models and improves classification accuracy.

Clinical relevance The IDLR model interprets DL features through radiomics supervision, potentially advancing the application of DL in clinical classification tasks.

Available only for authorised users

Huang K, Lin Y, Yang L et al (2020) A multipredictor model to predict the conversion of mild cognitive impairment to Alzheimer’s disease by using a predictive nomogram. Neuropsychopharmacology 45:358–366. https://doi.org/10.1038/s41386-019-0551-0CrossRefPubMed

Fan D-Y, Wang Y-J (2020) Early intervention in Alzheimer’s disease: How early is early enough? Neurosci Bull 36:195–197. https://doi.org/10.1007/s12264-019-00429-xCrossRefPubMed

Schneider JA, Arvanitakis Z, Leurgans SE, Bennett DA (2009) The neuropathology of probable Alzheimer disease and mild cognitive impairment. Ann Neurol 66:200–208. https://doi.org/10.1002/ana.21706CrossRefPubMedPubMedCentral

Petersen RC, Roberts RO, Knopman DS et al (2009) Mild cognitive impairment: ten years later. Arch Neurol 66:1447–1455. https://doi.org/10.1001/archneurol.2009.266CrossRefPubMedPubMedCentral

Yang L, Yan Y, Wang Y et al (2018) Gradual disturbances of the amplitude of low-frequency fluctuations (ALFF) and fFractional ALFF in Alzheimer spectrum. Front Neurosci 12:975. https://doi.org/10.3389/fnins.2018.00975CrossRefPubMedPubMedCentral

Jack CR, Bennett DA, Blennow K et al (2018) NIA-AA research framework: toward a biological definition of Alzheimer’s disease. Alzheimers Dement 14:535–562. https://doi.org/10.1016/j.jalz.2018.02.018CrossRefPubMed

Blazhenets G, Ma Y, Sörensen A et al (2019) Principal components analysis of brain metabolism predicts development of Alzheimer dementia. J Nucl Med 60:837–843. https://doi.org/10.2967/jnumed.118.219097CrossRefPubMed

Chaddad A, Desrosiers C, Hassan L, Tanougast C (2017) Hippocampus and amygdala radiomic biomarkers for the study of autism spectrum disorder. BMC Neurosci 18:52. https://doi.org/10.1186/s12868-017-0373-0CrossRefPubMedPubMedCentral

Dubois B, Feldman HH, Jacova C et al (2014) Advancing research diagnostic criteria for Alzheimer’s disease: the IWG-2 criteria. Lancet Neurol 13:614–629. https://doi.org/10.1016/S1474-4422(14)70090-0CrossRefPubMed

10.

Tian M, Zuo C, Civelek AC et al (2023) International nuclear medicine consensus on the clinical use of amyloid positron emission tomography in Alzheimer’s disease. Phenomics 3:375–389. https://doi.org/10.1007/s43657-022-00068-9CrossRefPubMed

11.

Lan L, Feng K, Wu Y et al (2023) Phenomic imaging. Phenomics 3:597–612. https://doi.org/10.1007/s43657-023-00128-8CrossRefPubMedPubMedCentral

12.

Tian M, Civelek AC, Carrio I et al (2022) International consensus on the use of tau PET imaging agent 18F-flortaucipir in Alzheimer’s disease. Eur J Nucl Med Mol Imaging 49:895–904. https://doi.org/10.1007/s00259-021-05673-wCrossRefPubMedPubMedCentral

13.

Nobili F, Arbizu J, Bouwman F et al (2018) European Association of Nuclear Medicine and European Academy of Neurology recommendations for the use of brain 18F-fluorodeoxyglucose positron emission tomography in neurodegenerative cognitive impairment and dementia: Delphi consensus. Eur J Neurol 25:1201–1217. https://doi.org/10.1111/ene.13728CrossRefPubMed

14.

Boccardi M, Festari C, Altomare D et al (2018) Assessing FDG-PET diagnostic accuracy studies to develop recommendations for clinical use in dementia. Eur J Nucl Med Mol Imaging 45:1470–1486. https://doi.org/10.1007/s00259-018-4024-1CrossRefPubMed

15.

Arbizu J, Festari C, Altomare D et al (2018) Clinical utility of FDG-PET for the clinical diagnosis in MCI. Eur J Nucl Med Mol Imaging 45:1497–1508. https://doi.org/10.1007/s00259-018-4039-7CrossRefPubMed

16.

Jiang J, Wang M, Alberts I et al (2022) Using radiomics-based modelling to predict individual progression from mild cognitive impairment to Alzheimer’s disease. Eur J Nucl Med Mol Imaging 49:2163–2173. https://doi.org/10.1007/s00259-022-05687-yCrossRefPubMed

17.

Li Y, Jiang J, Lu J et al (2019) Radiomics: a novel feature extraction method for brain neuron degeneration disease using 18F-FDG PET imaging and its implementation for Alzheimer’s disease and mild cognitive impairment. Ther Adv Neurol Disord 12:1756286419838682. https://doi.org/10.1177/1756286419838682CrossRefPubMedPubMedCentral

18.

Zhao Y, Zhang J, Chen Y, Jiang J (2022) A novel deep learning radiomics model to discriminate AD, MCI and NC: an exploratory study based on tau PET scans from ADNI. Brain Sci 12:1067. https://doi.org/10.3390/brainsci12081067CrossRefPubMedPubMedCentral

19.

Jiang J, Zhang J, Li C et al (2022) Development of a machine learning model to discriminate mild cognitive impairment subjects from normal controls in community screening. Brain Sci 12:1149. https://doi.org/10.3390/brainsci12091149CrossRefPubMedPubMedCentral

20.

De Santi LA, Pasini E, Santarelli MF et al (2023) An explainable convolutional neural network for the early diagnosis of Alzheimer’s disease from 18F-FDG PET. J Digit Imaging 36:189–203. https://doi.org/10.1007/s10278-022-00719-3CrossRefPubMed

21.

Sun X, Ge J, Li L et al (2022) Use of deep learning-based radiomics to differentiate Parkinson’s disease patients from normal controls: a study based on [18F]FDG PET imaging. Eur Radiol 32:8008–8018. https://doi.org/10.1007/s00330-022-08799-zCrossRefPubMed

22.

Sorantin E, Grasser MG, Hemmelmayr A et al (2022) The augmented radiologist: artificial intelligence in the practice of radiology. Pediatr Radiol 52:2074–2086. https://doi.org/10.1007/s00247-021-05177-7CrossRefPubMed

23.

Holzinger A, Haibe-Kains B, Jurisica I (2019) Why imaging data alone is not enough: AI-based integration of imaging, omics, and clinical data. Eur J Nucl Med Mol Imaging 46:2722–2730. https://doi.org/10.1007/s00259-019-04382-9CrossRefPubMed

24.

Pang T, Wong JHD, Ng WL, Chan CS (2020) Deep learning radiomics in breast cancer with different modalities: overview and future. Expert Syst Appl 158:113501CrossRef

25.

Tan M-S, Yang Y-X, Wang H-F et al (2020) PET amyloid and tau status are differently affected by patient features. J Alzheimers Dis 78:1129–1136. https://doi.org/10.3233/JAD-200124CrossRefPubMed

26.

Wu Y, Jiang J-H, Chen L et al (2019) Use of radiomic features and support vector machine to distinguish Parkinson’s disease cases from normal controls. Ann Transl Med 7:773. https://doi.org/10.21037/atm.2019.11.26CrossRefPubMedPubMedCentral

27.

Nie D, Lu J, Zhang H et al (2019) Multi-channel 3D deep feature learning for survival time prediction of brain tumor patients using multi-modal neuroimages. Sci Rep 9:1103. https://doi.org/10.1038/s41598-018-37387-9CrossRefPubMedPubMedCentral

28.

Aldughayfiq B, Ashfaq F, Jhanjhi NZ, Humayun M (2023) Explainable AI for retinoblastoma diagnosis: interpreting deep learning models with LIME and SHAP. Diagnostics 13:1932. https://doi.org/10.3390/diagnostics13111932CrossRefPubMedPubMedCentral

29.

Liu S-C, Lai J, Huang J-Y et al (2021) Predicting microvascular invasion in hepatocellular carcinoma: a deep learning model validated across hospitals. Cancer Imaging 21:56. https://doi.org/10.1186/s40644-021-00425-3CrossRefPubMedPubMedCentral

30.

Babu G, Sundaram S, Mahanand BS (2014) A novel PBL-McRBFN-RFE approach for identification of critical brain regions responsible for Parkinson’s disease. Expert Syst Appl 41:478–488. https://doi.org/10.1016/j.eswa.2013.07.073CrossRef

31.

Risacher SL, Saykin AJ (2019) Neuroimaging in aging and neurologic diseases. Handb Clin Neurol 167:191–227. https://doi.org/10.1016/B978-0-12-804766-8.00012-1CrossRefPubMedPubMedCentral

32.

Pini L, Pievani M, Bocchetta M et al (2016) Brain atrophy in Alzheimer’s disease and aging. Ageing Res Rev 30:25–48. https://doi.org/10.1016/j.arr.2016.01.002CrossRefPubMed

33.

Lotan E, Friedman KP, Davidson T, Shepherd TM (2020) Brain 18F-FDG-PET: utility in the diagnosis of dementia and epilepsy. Isr Med Assoc J 22:178–184PubMed

34.

Somayah A, Maha T, Asim A et al (2021) Machine learning and deep learning methods that use omics data for metastasis prediction. Comput Struct Biotechnol. https://pubmed.ncbi.nlm.nih.gov/34589181/. Accessed 6 Mar 2024

35.

Tang X, Zhang J, He Y et al (2023) Explainable multi-task learning for multi-modality biological data analysis. Nat Commun 14:2546. https://doi.org/10.1038/s41467-023-37477-xCrossRefPubMedPubMedCentral

Title: Using interpretable deep learning radiomics model to diagnose and predict progression of early AD disease spectrum: a preliminary [18F]FDG PET study
Authors: Jiehui Jiang
Chenyang Li
Jiaying Lu
Jie Sun
Xiaoming Sun
Jiacheng Yang
Luyao Wang
Chuantao Zuo
Kuangyu Shi
for the Alzheimer’s Disease Neuroimaging Initiative
Publication date: 31-10-2024
Publisher: Springer Berlin Heidelberg
Keywords: Alzheimer's Disease
Alzheimer's Disease
Mild Neurocognitive Disorder
Positron Emission Tomography
Published in: European Radiology
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-024-11158-9

Keynote series | Spotlight on menopause

Springer Medicine

Using interpretable deep learning radiomics model to diagnose and predict progression of early AD disease spectrum: a preliminary [¹⁸F]FDG PET study

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Keynote series | Spotlight on menopause

Springer Medicine

Abstract

Objectives

Methods

Results

Conclusions

Key Points

Please log in to get access to this content