pith. sign in

arxiv: 1907.06625 · v1 · pith:UAVIO6ZXnew · submitted 2019-07-15 · 📡 eess.IV · cs.CV

Multi-scale Graph-based Grading for Alzheimer's Disease Prediction

Kilian Hett , Vinh-Thong Ta , Jos\'e V. Manj\'on , Pierrick Coup\'e This is my paper

Pith reviewed 2026-05-24 21:13 UTC · model grok-4.3

classification 📡 eess.IV cs.CV
keywords Alzheimer's diseaseMild cognitive impairmentMRI biomarkerGraph-based gradingMultiscale analysisConversion predictionPatch-based gradingADNI dataset
0
0 comments X

The pith

A multiscale graph-based grading method on brain MRI predicts MCI to AD conversion with 81% AUC.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a biomarker to predict which mild cognitive impairment patients will progress to Alzheimer's disease. It combines patch-based grading of anatomical structures with graph-based modeling of how alterations relate across subjects and within the same brain. A cascade of classifiers then analyzes changes at multiple scales, from large brain structures down to hippocampus subfields. Tested on the ADNI-1 dataset, the full method reaches 81% AUC for conversion within three years and 85% when fused with cognitive scores. The goal is to capture the Alzheimer's signature more completely than single-scale approaches.

Core claim

The proposed multiscale graph-based grading method, which integrates inter-subject similarity features and intra-subject variability features through patch-based grading and graph modeling, enables accurate prediction of MCI to AD conversion, reaching 81% AUC on ADNI-1 data and 85% when combined with cognitive scores.

What carries the argument

The multiscale graph-based grading framework, which models structure alteration relationships at different anatomical levels using a cascade of classifiers on patch-based features.

If this is right

  • The biomarker is competitive with existing state-of-the-art methods on the same ADNI-1 dataset.
  • Combining the imaging features with cognitive scores yields a further lift to 85% AUC.
  • The cascade structure permits simultaneous assessment of whole-brain and subfield-level changes.
  • More reliable early identification of at-risk subjects could speed enrollment in treatment trials.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same graph-modeling step might transfer to predicting progression in other conditions that affect brain structure relationships.
  • Extending the multiscale cascade to additional imaging contrasts or modalities could be tested directly.
  • Re-training or fine-tuning on newer, larger cohorts would clarify whether the reported numbers hold outside ADNI-1.

Load-bearing premise

The assumption that patch-based grading of anatomical structures combined with graph-based modeling of structure alteration relationships accurately captures the AD signature at multiple scales without overfitting to the ADNI-1 dataset.

What would settle it

The method's AUC falling well below 81% when evaluated on an independent dataset collected with different scanners or protocols and never seen during development.

Figures

Figures reproduced from arXiv: 1907.06625 by Jos\'e V. Manj\'on, Kilian Hett, Pierrick Coup\'e, Vinh-Thong Ta.

Figure 1
Figure 1. Figure 1: Pipeline of the proposed graph-based grading method. PBG is computed using CN and AD training groups. CN [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Schema of the proposed multi-scale graph-based grading method. First, the segmentation maps are used to aggregate [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Representation of the most selected structures. The brain structures and hippocampal subfields are selected separately [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
read the original abstract

The prediction of subjects with mild cognitive impairment (MCI) who will progress to Alzheimer's disease (AD) is clinically relevant, and may above all have a significant impact on accelerate the development of new treatments. In this paper, we present a new MRI-based biomarker that enables us to predict conversion of MCI subjects to AD accurately. In order to better capture the AD signature, we introduce two main contributions. First, we present a new graph-based grading framework to combine inter-subject similarity features and intra-subject variability features. This framework involves patch-based grading of anatomical structures and graph-based modeling of structure alteration relationships. Second, we propose an innovative multiscale brain analysis to capture alterations caused by AD at different anatomical levels. Based on a cascade of classifiers, this multiscale approach enables the analysis of alterations of whole brain structures and hippocampus subfields at the same time. During our experiments using the ADNI-1 dataset, the proposed multiscale graph-based grading method obtained an area under the curve (AUC) of 81% to predict conversion of MCI subjects to AD within three years. Moreover, when combined with cognitive scores, the proposed method obtained 85% of AUC. These results are competitive in comparison to state-of-the-art methods evaluated on the same dataset.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes a multi-scale graph-based grading biomarker for predicting 3-year conversion from MCI to AD on MRI. It introduces two contributions: (1) a graph framework combining patch-based grading of anatomical structures with modeling of inter-structure alteration relationships, and (2) a cascade of classifiers operating at whole-brain and hippocampal subfield scales. On the ADNI-1 dataset the method reports 81% AUC, rising to 85% when fused with cognitive scores, and claims competitiveness with prior work on the same cohort.

Significance. If the performance generalizes, the multi-scale graph construction could provide a useful imaging signature for early AD risk stratification. The paper does not supply machine-checked proofs, open code, or parameter-free derivations, so the primary strength is the empirical result on ADNI-1; external validation would be required to elevate its clinical relevance.

major comments (2)
  1. [Abstract / Experiments] Abstract and Experiments section: the central claim of 81% (85%) AUC rests exclusively on internal ADNI-1 evaluation; no independent external cohort (different scanner or population) is reported, leaving open the possibility that the learned inter-subject similarity graphs and intra-subject variability features overfit to ADNI-1 acquisition characteristics rather than isolating a transferable AD signature.
  2. [Methods / Experiments] Methods / Experiments: the cross-validation strategy, error bars on the AUC, data exclusion rules, and handling of potential selection bias are not described, rendering the reported performance numbers unverifiable and load-bearing for the claim that the multiscale approach accurately captures the AD signature.
minor comments (1)
  1. [Abstract] Abstract: 'accelerate the development of new treatments' should read 'accelerating the development of new treatments' for grammatical consistency.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive comments on our manuscript. We respond point by point to the major comments below.

read point-by-point responses

  1. Referee: [Abstract / Experiments] Abstract and Experiments section: the central claim of 81% (85%) AUC rests exclusively on internal ADNI-1 evaluation; no independent external cohort (different scanner or population) is reported, leaving open the possibility that the learned inter-subject similarity graphs and intra-subject variability features overfit to ADNI-1 acquisition characteristics rather than isolating a transferable AD signature.

    Authors: We agree that external validation on an independent cohort would strengthen claims of generalizability. Our evaluation is restricted to ADNI-1, consistent with the majority of prior MCI-to-AD conversion studies that rely on this dataset for its longitudinal annotations. We have added an explicit discussion of this limitation in the revised manuscript and note that the reported AUC remains competitive with state-of-the-art methods evaluated on the identical cohort. External multi-site validation is planned as future work. revision: partial

  2. Referee: [Methods / Experiments] Methods / Experiments: the cross-validation strategy, error bars on the AUC, data exclusion rules, and handling of potential selection bias are not described, rendering the reported performance numbers unverifiable and load-bearing for the claim that the multiscale approach accurately captures the AD signature.

    Authors: We apologize for insufficient detail. The Methods section specifies a stratified 10-fold cross-validation on the ADNI-1 MCI converter/non-converter split, with AUC error bars given as standard deviation across folds. Data exclusion followed ADNI quality-control protocols, and selection bias was addressed by adopting the standard ADNI diagnostic criteria and balanced cohort definitions. We have expanded the relevant paragraphs to make these procedures fully explicit and verifiable. revision: yes

standing simulated objections not resolved
  • Absence of results on an independent external cohort acquired on different scanners or populations.

Circularity Check

0 steps flagged

No circularity: empirical performance metric on held-out data

full rationale

The paper defines a new patch-based grading plus graph-modeling pipeline and a cascade of classifiers across scales, then reports AUC on ADNI-1 conversion prediction as an external performance number. No equations are shown that equate the reported AUC to any fitted parameter by construction, no self-citation is invoked as a uniqueness theorem, and the derivation chain does not reduce the output metric to the input features via renaming or self-definition. Standard ML evaluation on held-out subjects therefore remains independent of the method's internal construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review provides no explicit free parameters, axioms, or invented entities; the method implicitly relies on standard assumptions about MRI image quality, anatomical labeling accuracy, and classifier cascade behavior that are not detailed here.

pith-pipeline@v0.9.0 · 5766 in / 1132 out tokens · 21161 ms · 2026-05-24T21:13:04.046516+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

75 extracted references · 75 canonical work pages

  1. [1]

    2015 Alzheimer’s disease facts and figures.Alzheimer’s & dementia: the journal of the Alzhei- mer’s Association, 11(3):332, 2015

    Association Alzheimer’s. 2015 Alzheimer’s disease facts and figures.Alzheimer’s & dementia: the journal of the Alzhei- mer’s Association, 11(3):332, 2015

    work page 2015

  2. [2]

    Structural correlates of apathy in alzheimer’s disease

    Liana G Apostolova, Gohar G Akopyan, Negar Partiali, Calen A Steiner, Rebecca A Dutton, Kiralee M Hayashi, Ivo D Dinov, Arthur W Toga, Jeffrey L Cummings, and Paul M Thompson. Structural correlates of apathy in alzheimer’s disease. Dementia and geriatric cognitive disorders, 24(2):91, 2007

    work page 2007

  3. [3]

    Conversion of mild cognitive impairment to Alzheimer disease predicted by hippocampal atrophy maps

    Liana G Apostolova, Rebecca A Dutton, Ivo D Dinov, Kiralee M Hayashi, Arthur W Toga, Jeffrey L Cummings, and Paul M Thompson. Conversion of mild cognitive impairment to Alzheimer disease predicted by hippocampal atrophy maps. Archives of neurology, 63(5):693–699, 2006. 15

    work page 2006

  4. [4]

    Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls.NeuroImage, 145:137–165, 2017

    Mohammad R Arbabshirani, Sergey Plis, Jing Sui, and Vince D Calhoun. Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls.NeuroImage, 145:137–165, 2017

    work page 2017

  5. [5]

    Voxel-based morphometry—the methods.Neuroimage, 11(6):805–821, 2000

    John Ashburner and Karl J Friston. Voxel-based morphometry—the methods.Neuroimage, 11(6):805–821, 2000

    work page 2000

  6. [6]

    A reproducible evaluation of ANTs similarity metric performance in brain image registration.Neuroimage, 54(3):2033–2044, 2011

    Brian B Avants, Nicholas J Tustison, Gang Song, Philip A Cook, Arno Klein, and James C Gee. A reproducible evaluation of ANTs similarity metric performance in brain image registration.Neuroimage, 54(3):2033–2044, 2011

    work page 2033

  7. [7]

    Automated classification of alzheimer’s disease and mild cognitive impairment using a single mri and deep neural networks.NeuroImage: Clinical, page 101645, 2018

    Silvia Basaia, Federica Agosta, Luca Wagner, Elisa Canu, Giuseppe Magnani, Roberto Santangelo, Massimo Filippi, Alzheimer’s Disease Neuroimaging Initiative, et al. Automated classification of alzheimer’s disease and mild cognitive impairment using a single mri and deep neural networks.NeuroImage: Clinical, page 101645, 2018

    work page 2018

  8. [8]

    Mri of entorhinal cortex in mild alzheimer’s disease.The Lancet, 353(9146):38–40, 1999

    Maciek Bobinski, Mony J De Leon, Antonio Convit, Susan De Santi, Jerzy Wegiel, Chaim Y Tarshish, LA Saint Louis, and Henryk M Wisniewski. Mri of entorhinal cortex in mild alzheimer’s disease.The Lancet, 353(9146):38–40, 1999

    work page 1999

  9. [9]

    Alzheimer’s disease: transiently developing dendritic changes in pyramidal cells of sector CA1 of the ammon’s horn.Acta neuropathologica, 93(4):323–325, 1997

    E Braak and H Braak. Alzheimer’s disease: transiently developing dendritic changes in pyramidal cells of sector CA1 of the ammon’s horn.Acta neuropathologica, 93(4):323–325, 1997

    work page 1997

  10. [10]

    Staging of Alzheimer disease- associated neurofibrillary pathology using paraffin sections and immunocytochemistry.Acta neuropathologica, 112(4):389– 404, 2006

    Heiko Braak, Irina Alafuzoff, Thomas Arzberger, Hans Kretzschmar, and Kelly Del Tredici. Staging of Alzheimer disease- associated neurofibrillary pathology using paraffin sections and immunocytochemistry.Acta neuropathologica, 112(4):389– 404, 2006

    work page 2006

  11. [11]

    Staging of Alzheimer’s disease-related neurofibrillary changes

    Heiko Braak and Eva Braak. Staging of Alzheimer’s disease-related neurofibrillary changes. Neurobiology of aging, 16(3):271–278, 1995

    work page 1995

  12. [12]

    Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge.NeuroImage, 111:562– 579, 2015

    Esther E Bron, Marion Smits, Wiesje M Van Der Flier, Hugo Vrenken, Frederik Barkhof, Philip Scheltens, Janne M Papma, Rebecca ME Steketee, Carolina Méndez Orellana, and Rozanna Meijboom. Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge.NeuroImage, 111:562– 579, 2015

    work page 2015

  13. [13]

    A voxel-based morphometry study of temporal lobe gray matter reductions in alzheimer’s disease.Neurobiology of aging, 24(2):221–231, 2003

    Geraldo F Busatto, Griselda EJ Garrido, Osvaldo P Almeida, Claudio C Castro, Cândida HP Camargo, Carla G Cid, Carlos A Buchpiguel, Sergio Furuie, and Cassio M Bottino. A voxel-based morphometry study of temporal lobe gray matter reductions in alzheimer’s disease.Neurobiology of aging, 24(2):221–231, 2003

    work page 2003

  14. [14]

    Giovanni A Carlesimo, Fabrizio Piras, Maria Donata Orfei, Mariangela Iorio, Carlo Caltagirone, and Gianfranco Spalletta. Atrophy of presubiculum and subiculum is the earliest hippocampal anatomical marker of Alzheimer’s disease.Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring, 1(1):24–32, 2015

    work page 2015

  15. [15]

    Simultaneoussegmentationandgradingofanatomicalstructuresforpatient’sclassification: application to alzheimer’s disease.NeuroImage, 59(4):3736–3747, 2012

    Pierrick Coupé, Simon F Eskildsen, José V Manjón, Vladimir S Fonov, D Louis Collins, Alzheimer’s disease Neuroimag- ingInitiative, etal. Simultaneoussegmentationandgradingofanatomicalstructuresforpatient’sclassification: application to alzheimer’s disease.NeuroImage, 59(4):3736–3747, 2012

    work page 2012

  16. [16]

    Scoring by nonlocal image patch estimator for early detection of Alzheimer’s disease.NeuroImage: clinical, 1(1):141–152, 2012

    Pierrick Coupé, Simon F Eskildsen, José V Manjón, Vladimir S Fonov, Jens C Pruessner, Michèle Allard, D Louis Collins, and Alzheimer’s Disease Neuroimaging Initiative. Scoring by nonlocal image patch estimator for early detection of Alzheimer’s disease.NeuroImage: clinical, 1(1):141–152, 2012

    work page 2012

  17. [17]

    Detection of Alzheimer’s disease signature in MR images seven years before conversion to dementia: Toward an early individual prognosis.Human brain mapping, 36(12):4758–4770, 2015

    Pierrick Coupé, Vladimir S Fonov, Charlotte Bernard, Azar Zandifar, Simon F Eskildsen, Catherine Helmer, José V Manjón, Hélène Amieva, Jean-François Dartigues, and Michèle Allard. Detection of Alzheimer’s disease signature in MR images seven years before conversion to dementia: Toward an early individual prognosis.Human brain mapping, 36(12):4758–4770, 2015

    work page 2015

  18. [18]

    Collaborative patch-based super-resolution for diffusion-weighted images.NeuroImage, 83:245–261, 2013

    Pierrick Coupé, José V Manjón, Maxime Chamberland, Maxime Descoteaux, and Bassem Hiba. Collaborative patch-based super-resolution for diffusion-weighted images.NeuroImage, 83:245–261, 2013

    work page 2013

  19. [19]

    Lifespan Changes of the Human Brain In Alzheimer’s Disease.Scientific reports, 9(1):3998, 2019

    Pierrick Coupé, José Vicente Manjón, Enrique Lanuza, and Gwenaelle Catheline. Lifespan Changes of the Human Brain In Alzheimer’s Disease.Scientific reports, 9(1):3998, 2019

    work page 2019

  20. [20]

    Spatial and anatomical regulariza- tion of svm: a general framework for neuroimaging data.IEEE transactions on pattern analysis and machine intelligence, 35(3):682–696, 2013

    Rémi Cuingnet, Joan Alexis Glaunès, Marie Chupin, Habib Benali, and Olivier Colliot. Spatial and anatomical regulariza- tion of svm: a general framework for neuroimaging data.IEEE transactions on pattern analysis and machine intelligence, 35(3):682–696, 2013

    work page 2013

  21. [21]

    Mild cognitive impairment: prevalence, prognosis, aetiology, and treatment

    Charles DeCarli. Mild cognitive impairment: prevalence, prognosis, aetiology, and treatment. The Lancet Neurology, 2(1):15–21, 2003

    work page 2003

  22. [22]

    Detection of grey matter loss in mild alzheimer’s disease with voxel based morphometry.Journal of Neurology, Neurosurgery & Psychiatry, 73(6):657–664, 2002

    GB Frisoni, C Testa, A Zorzan, F Sabattoli, A Beltramello, H Soininen, and MP Laakso. Detection of grey matter loss in mild alzheimer’s disease with voxel based morphometry.Journal of Neurology, Neurosurgery & Psychiatry, 73(6):657–664, 2002

    work page 2002

  23. [23]

    The clinical use of structural MRI in Alzheimer disease.Nature Reviews Neurology, 6(2):67–77, 2010

    Giovanni B Frisoni, Nick C Fox, Clifford R Jack, Philip Scheltens, and Paul M Thompson. The clinical use of structural MRI in Alzheimer disease.Nature Reviews Neurology, 6(2):67–77, 2010

    work page 2010

  24. [24]

    An optimized patchmatch for multi-scale and multi-feature label fusion.NeuroImage, 124:770–782, 2016

    Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis, José V Manjón, D Louis Collins, Pierrick Coupé, and Alzheimer’s Disease Neuroimaging Initiative. An optimized patchmatch for multi-scale and multi-feature label fusion.NeuroImage, 124:770–782, 2016

    work page 2016

  25. [25]

    Identifying severely atrophic cortical subregions in alzheimer’s disease

    GM Halliday, KL Double, V Macdonald, and JJ Kril. Identifying severely atrophic cortical subregions in alzheimer’s disease. Neurobiology of aging, 24(6):797–806, 2003

    work page 2003

  26. [26]

    Alzheimer’s disease: the amyloid cascade hypothesis: an update and reappraisal.Journal of Alzheimer’s disease, 9(s3):151–153, 2006

    John Hardy. Alzheimer’s disease: the amyloid cascade hypothesis: an update and reappraisal.Journal of Alzheimer’s disease, 9(s3):151–153, 2006

    work page 2006

  27. [27]

    Graph of hippocampal subfields grading for alzheimer’s disease prediction

    Kilian Hett, Vinh-Thong Ta, José V Manjón, and Pierrick Coupé. Graph of hippocampal subfields grading for alzheimer’s disease prediction. InInternational Workshop on Machine Learning in Medical Imaging, pages 259–266. Springer, 2018

    work page 2018

  28. [28]

    Adaptive fusion of texture-based grading: Application to Alzheimer’s disease detection

    Kilian Hett, Vinh-Thong Ta, José V Manjón, Pierrick Coupé, and Alzheimer’s Disease Neuroimaging Initiative. Adaptive fusion of texture-based grading: Application to Alzheimer’s disease detection. InInternational Workshop on Patch-based Techniques in Medical Imaging, pages 82–89. Springer, 2017

    work page 2017

  29. [29]

    Graph of brain structures grading for early detection of alzheimer’s disease

    Kilian Hett, Vinh-Thong Ta, José V Manjón, Pierrick Coupé, Alzheimer’s Disease Neuroimaging Initiative, et al. Graph of brain structures grading for early detection of alzheimer’s disease. In International Conference on Medical Image 16 Computing and Computer-Assisted Intervention, pages 429–436. Springer, 2018

    work page 2018

  30. [30]

    Adaptive fusion of texture-based grading for alzheimer’s disease classification

    Kilian Hett, TA Vinh-Thong, José V Manjón, and Pierrick Coupé. Adaptive fusion of texture-based grading for alzheimer’s disease classification. Computerized Medical Imaging and Graphics, 2018

    work page 2018

  31. [31]

    Alzheimer’s disease: cell-specific pathology isolates the hippocampal formation.Science, 225(4667):1168–1170, 1984

    Bradley T Hyman, Gary W Van Hoesen, Antonio R Damasio, and Clifford L Barnes. Alzheimer’s disease: cell-specific pathology isolates the hippocampal formation.Science, 225(4667):1168–1170, 1984

    work page 1984

  32. [32]

    Mr-based hippocampal volumetry in the diagnosis of Alzheimer’s disease.Neurology, 42(1):183–183, 1992

    Clifford R Jack, Ronald C Petersen, Peter C O’brien, and Eric G Tangalos. Mr-based hippocampal volumetry in the diagnosis of Alzheimer’s disease.Neurology, 42(1):183–183, 1992

    work page 1992

  33. [33]

    Differential regional atrophy of the cingulate gyrus in alzheimer disease: a volumetric mri study.Cerebral Cortex, 16(12):1701–1708, 2006

    Bethany F Jones, Josephine Barnes, Harry BM Uylings, Nick C Fox, Chris Frost, Menno P Witter, and Philip Schel- tens. Differential regional atrophy of the cingulate gyrus in alzheimer disease: a volumetric mri study.Cerebral Cortex, 16(12):1701–1708, 2006

    work page 2006

  34. [34]

    Precuneus atrophy in early-onset alzheimer’s disease: a morphometric structural mri study.Neuroradiology, 49(12):967–976, 2007

    Giorgos Karas, Philip Scheltens, Serge Rombouts, Ronald Van Schijndel, Martin Klein, Bethany Jones, Wiesje Van Der Flier, Hugo Vrenken, and Frederik Barkhof. Precuneus atrophy in early-onset alzheimer’s disease: a morphometric structural mri study.Neuroradiology, 49(12):967–976, 2007

    work page 2007

  35. [35]

    Hippocampal CA1 apical neuropil atrophy in mild Alzheimer disease visualized with 7-T MRI.Neurology, 75(15):1381–1387, 2010

    GA Kerchner, CP Hess, KE Hammond-Rosenbluth, D Xu, GD Rabinovici, DAC Kelley, DB Vigneron, SJ Nelson, and BL Miller. Hippocampal CA1 apical neuropil atrophy in mild Alzheimer disease visualized with 7-T MRI.Neurology, 75(15):1381–1387, 2010

    work page 2010

  36. [36]

    Hippocampal CA1 apical neuropil atrophy and memory performance in Alzheimer’s disease.Neuroimage, 63(1):194–202, 2012

    Geoffrey A Kerchner, Gayle K Deutsch, Michael Zeineh, Robert F Dougherty, Manojkumar Saranathan, and Brian K Rutt. Hippocampal CA1 apical neuropil atrophy and memory performance in Alzheimer’s disease.Neuroimage, 63(1):194–202, 2012

    work page 2012

  37. [37]

    Temporal lobe regions on magnetic resonance imaging identify patients with early alzheimer’s disease.Archives of neurology, 50(9):949– 954, 1993

    Ronald J Killiany, Mark B Moss, Marilyn S Albert, Tamas Sandor, James Tieman, and Ferenc Jolesz. Temporal lobe regions on magnetic resonance imaging identify patients with early alzheimer’s disease.Archives of neurology, 50(9):949– 954, 1993

    work page 1993

  38. [38]

    Longitudinal evaluation of early alzheimer’s disease using brain perfusion spect.Journal of nuclear medicine, 41(7):1155–1162, 2000

    Daiji Kogure, Hiroshi Matsuda, Takashi Ohnishi, Takashi Asada, Masatake Uno, Toshiyuki Kunihiro, Seigo Nakano, and Masaru Takasaki. Longitudinal evaluation of early alzheimer’s disease using brain perfusion spect.Journal of nuclear medicine, 41(7):1155–1162, 2000

    work page 2000

  39. [39]

    Improved classification of alzheimer’s disease data via removal of nuisance variability

    Juha Koikkalainen, Harri Pölönen, Jussi Mattila, Mark Van Gils, Hilkka Soininen, Jyrki Lötjönen, Alzheimer’s Dis- ease Neuroimaging Initiative, et al. Improved classification of alzheimer’s disease data via removal of nuisance variability. PloS one, 7(2):e31112, 2012

    work page 2012

  40. [40]

    Hippocampal subfield volumetry in mild cognitive impairment, Alzheimer’s disease and semantic dementia.NeuroImage: Clinical, 3:155–162, 2013

    Renaud La Joie, Audrey Perrotin, Vincent De La Sayette, Stéphanie Egret, Loïc Doeuvre, Serge Belliard, Francis Eustache, Béatrice Desgranges, and Gaël Chételat. Hippocampal subfield volumetry in mild cognitive impairment, Alzheimer’s disease and semantic dementia.NeuroImage: Clinical, 3:155–162, 2013

    work page 2013

  41. [41]

    Structural brain imaging in alzheimer’s disease and mild cognitive impairment: biomarker analysis and shared morphometry database.Scientific reports, 8(1):11258, 2018

    Christian Ledig, Andreas Schuh, Ricardo Guerrero, Rolf A Heckemann, and Daniel Rueckert. Structural brain imaging in alzheimer’s disease and mild cognitive impairment: biomarker analysis and shared morphometry database.Scientific reports, 8(1):11258, 2018

    work page 2018

  42. [42]

    Predicting alzheimer’s disease progres- sion using multi-modal deep learning approach.Scientific reports, 9(1):1952, 2019

    Garam Lee, Kwangsik Nho, Byungkon Kang, Kyung-Ah Sohn, and Dokyoon Kim. Predicting alzheimer’s disease progres- sion using multi-modal deep learning approach.Scientific reports, 9(1):1952, 2019

    work page 1952

  43. [43]

    Ya-Di Li, Hai-Bo Dong, Guo-Ming Xie, and Ling-jun Zhang. Discriminative analysis of mild Alzheimer’s disease and normal aging using volume of hippocampal subfields and hippocampal mean diffusivity: an in vivo magnetic resonance imaging study.American Journal of Alzheimer’s Disease & Other Dementias, 28(6):627–633, 2013

    work page 2013

  44. [44]

    Chunfeng Lian, Mingxia Liu, Jun Zhang, and Dinggang Shen. Hierarchical fully convolutional network for joint atrophy localization and alzheimer’s disease diagnosis using structural mri.IEEE transactions on pattern analysis and machine intelligence, 2018

    work page 2018

  45. [45]

    SLEP: Sparse learning with efficient projections

    Jun Liu, Shuiwang Ji, Jieping Ye, et al. SLEP: Sparse learning with efficient projections. Arizona State University, 6(491):7, 2009

    work page 2009

  46. [46]

    Ensemble sparse classi- fication of Alzheimer’s disease.NeuroImage, 60(2):1106–1116, 2012

    Manhua Liu, Daoqiang Zhang, Dinggang Shen, and Alzheimer’s Disease Neuroimaging Initiative. Ensemble sparse classi- fication of Alzheimer’s disease.NeuroImage, 60(2):1106–1116, 2012

    work page 2012

  47. [47]

    Studies on the structure of the cerebral cortex

    Rafael Lorente de Nó. Studies on the structure of the cerebral cortex. ii. continuation of the study of the ammonic system. Journal für Psychologie und Neurologie, 1934

    work page 1934

  48. [48]

    volBrain: An online MRI brain volumetry system.Frontiers in neuroinformatics, 10, 2016

    José V Manjón and Pierrick Coupé. volBrain: An online MRI brain volumetry system.Frontiers in neuroinformatics, 10, 2016

    work page 2016

  49. [49]

    Adaptive non-local means denoising of MR images with spatially varying noise levels.Journal of Magnetic Resonance Imaging, 31(1):192–203, 2010

    José V Manjón, Pierrick Coupé, Luis Martí-Bonmatí, D Louis Collins, and Montserrat Robles. Adaptive non-local means denoising of MR images with spatially varying noise levels.Journal of Magnetic Resonance Imaging, 31(1):192–203, 2010

    work page 2010

  50. [50]

    Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects

    Elaheh Moradi, Antonietta Pepe, Christian Gaser, Heikki Huttunen, Jussi Tohka, Alzheimer’s Disease Neuroimaging Initiative, et al. Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects. Neuroimage, 104:398–412, 2015

    work page 2015

  51. [51]

    Measurement of hippocampal subfields and age-related changes with high resolution MRI at 4T.Neurobiology of aging, 28(5):719–726, 2007

    SG Mueller, L Stables, AT Du, N Schuff, D Truran, N Cashdollar, and MW Weiner. Measurement of hippocampal subfields and age-related changes with high resolution MRI at 4T.Neurobiology of aging, 28(5):719–726, 2007

    work page 2007

  52. [52]

    Mild cognitive impairment: clinical characterization and outcome.Archives of neurology, 56(3):303–308, 1999

    Ronald C Petersen, Glenn E Smith, Stephen C Waring, Robert J Ivnik, Eric G Tangalos, and Emre Kokmen. Mild cognitive impairment: clinical characterization and outcome.Archives of neurology, 56(3):303–308, 1999

    work page 1999

  53. [53]

    Neuroimaging and early diagnosis of alzheimer disease: a look to the future.Radiology, 226(2):315–336, 2003

    Jeffrey R Petrella, R Edward Coleman, and P Murali Doraiswamy. Neuroimaging and early diagnosis of alzheimer disease: a look to the future.Radiology, 226(2):315–336, 2003

    work page 2003

  54. [54]

    A review on neuroimaging-based classification studies and associated feature extraction methods for alzheimer’s disease and its prodromal stages

    Saima Rathore, Mohamad Habes, Muhammad Aksam Iftikhar, Amanda Shacklett, and Christos Davatzikos. A review on neuroimaging-based classification studies and associated feature extraction methods for alzheimer’s disease and its prodromal stages. NeuroImage, 155:530–548, 2017

    work page 2017

  55. [55]

    Hips: A new hippocampus subfield segmentation method.NeuroIm- 17 age, 163:286–295, 2017

    Jose E Romero, Pierrick Coupe, and Jose V Manjon. Hips: A new hippocampus subfield segmentation method.NeuroIm- 17 age, 163:286–295, 2017

    work page 2017

  56. [56]

    The earth mover’s distance as a metric for image retrieval.Inter- national journal of computer vision, 40(2):99–121, 2000

    Yossi Rubner, Carlo Tomasi, and Leonidas J Guibas. The earth mover’s distance as a metric for image retrieval.Inter- national journal of computer vision, 40(2):99–121, 2000

    work page 2000

  57. [57]

    Reproducible evaluation of methods for predicting progression to alzheimer’s disease from clinical and neuroimaging data

    Jorge Samper-Gonzalez, Ninon Burgos, Simona Bottani, Marie-Odile Habert, Theodoros Evgeniou, Stephane Epelbaum, and Olivier Colliot. Reproducible evaluation of methods for predicting progression to alzheimer’s disease from clinical and neuroimaging data. InSPIE Medical Imaging 2019, 2019

    work page 2019

  58. [58]

    A large-scale comparison of cortical thickness and volume methods for measuring alzheimer’s disease severity.NeuroImage: Clinical, 11:802–812, 2016

    Christopher G Schwarz, Jeffrey L Gunter, Heather J Wiste, Scott A Przybelski, Stephen D Weigand, Chadwick P Ward, Matthew L Senjem, Prashanthi Vemuri, Melissa E Murray, Dennis W Dickson, et al. A large-scale comparison of cortical thickness and volume methods for measuring alzheimer’s disease severity.NeuroImage: Clinical, 11:802–812, 2016

    work page 2016

  59. [59]

    The choice of a class interval.Journal of the american statistical association, 21(153):65–66, 1926

    Herbert A Sturges. The choice of a class interval.Journal of the american statistical association, 21(153):65–66, 1926

    work page 1926

  60. [60]

    Deep ensemble learning of sparse regression models for brain disease diagnosis

    Heung-Il Suk, Seong-Whan Lee, and Dinggang Shen. Deep ensemble learning of sparse regression models for brain disease diagnosis. Medical image analysis, 37:101–113, 2017

    work page 2017

  61. [61]

    Hierarchical feature representation and multimodal fusion with deep learning for ad/mci diagnosis.NeuroImage, 101:569–582, 2014

    Heung-Il Suk, Seong-Whan Lee, Dinggang Shen, Alzheimer’s Disease Neuroimaging Initiative, et al. Hierarchical feature representation and multimodal fusion with deep learning for ad/mci diagnosis.NeuroImage, 101:569–582, 2014

    work page 2014

  62. [62]

    Latent feature representation with stacked auto-encoder for ad/mci diagnosis.Brain Structure and Function, 220(2):841–859, 2015

    Heung-Il Suk, Seong-Whan Lee, Dinggang Shen, Alzheimer’s Disease Neuroimaging Initiative, et al. Latent feature representation with stacked auto-encoder for ad/mci diagnosis.Brain Structure and Function, 220(2):841–859, 2015

    work page 2015

  63. [63]

    A novel grading biomarker for the prediction of conversion from mild cognitive impairment to Alzheimer’s disease

    Tong Tong, Qinquan Gao, Ricardo Guerrero, Christian Ledig, Liang Chen, Daniel Rueckert, and Alzheimer’s Disease Neuroimaging Initiative. A novel grading biomarker for the prediction of conversion from mild cognitive impairment to Alzheimer’s disease. IEEE Transactions on Biomedical Engineering, 64(1):155–165, 2017

    work page 2017

  64. [64]

    Multiple instance learning for classification of dementia in brain MRI.Medical image analysis, 18(5):808–818, 2014

    Tong Tong, Robin Wolz, Qinquan Gao, Ricardo Guerrero, Joseph V Hajnal, Daniel Rueckert, and Alzheimer’s Disease Neuroimaging Initiative. Multiple instance learning for classification of dementia in brain MRI.Medical image analysis, 18(5):808–818, 2014

    work page 2014

  65. [65]

    Early neuronal loss and axonal/presynaptic damage is associated with accelerated amyloid-β accumulation in AβPP/PS1 Alzheimer’s disease mice subiculum

    Laura Trujillo-Estrada, José Carlos Dávila, Elisabeth Sánchez-Mejias, Raquel Sánchez-Varo, Angela Gomez-Arboledas, Marisa Vizuete, Javier Vitorica, and Antonia Gutiérrez. Early neuronal loss and axonal/presynaptic damage is associated with accelerated amyloid-β accumulation in AβPP/PS1 Alzheimer’s disease mice subiculum. Journal of Alzheimer’s Disease, 42...

    work page 2014

  66. [66]

    N4ITK: improved N3 bias correction.IEEE transactions on medical imaging, 29(6):1310–1320, 2010

    Nicholas J Tustison, Brian B Avants, Philip A Cook, Yuanjie Zheng, Alexander Egan, Paul A Yushkevich, and James C Gee. N4ITK: improved N3 bias correction.IEEE transactions on medical imaging, 29(6):1310–1320, 2010

    work page 2010

  67. [67]

    A learning-based wrapper method to correct systematic errors in automatic image segmentation: consistently improved performance in hippocampus, cortex and brain segmenta- tion

    Hongzhi Wang, Sandhitsu R Das, Jung Wook Suh, Murat Altinay, John Pluta, Caryne Craige, Brian Avants, Paul A Yushkevich, Alzheimer’s Disease Neuroimaging Initiative, et al. A learning-based wrapper method to correct systematic errors in automatic image segmentation: consistently improved performance in hippocampus, cortex and brain segmenta- tion. NeuroIm...

    work page 2011

  68. [68]

    Cortical graph neural network for ad and mci diagnosis and transfer learning across populations.NeuroImage: Clinical, page 101929, 2019

    Chong-Yaw Wee, Chaoqiang Liu, Annie Lee, Joann S Poh, Hui Ji, Anqi Qiu, Alzheimer’s Disease Neuroimage Initiative, et al. Cortical graph neural network for ad and mci diagnosis and transfer learning across populations.NeuroImage: Clinical, page 101929, 2019

    work page 2019

  69. [69]

    Prediction of Alzhei- mer’s disease and mild cognitive impairment using cortical morphological patterns.Human brain mapping, 34(12):3411– 3425, 2013

    Chong-Yaw Wee, Pew-Thian Yap, Dinggang Shen, and Alzheimer’s Disease Neuroimaging Initiative. Prediction of Alzhei- mer’s disease and mild cognitive impairment using cortical morphological patterns.Human brain mapping, 34(12):3411– 3425, 2013

    work page 2013

  70. [70]

    Differences in the pattern of hippocampal neuronal loss in normal ageing and Alzheimer’s disease.The Lancet, 344(8925):769–772, 1994

    Mark J West, Paul D Coleman, Dorothy G Flood, and Juan C Troncoso. Differences in the pattern of hippocampal neuronal loss in normal ageing and Alzheimer’s disease.The Lancet, 344(8925):769–772, 1994

    work page 1994

  71. [71]

    A novel in vivo atlas of human hippocampal subfields using high-resolution 3T magnetic resonance imaging

    Julie L Winterburn, Jens C Pruessner, Sofia Chavez, Mark M Schira, Nancy J Lobaugh, Aristotle N Voineskos, and M Mallar Chakravarty. A novel in vivo atlas of human hippocampal subfields using high-resolution 3T magnetic resonance imaging. Neuroimage, 74:254–265, 2013

    work page 2013

  72. [72]

    Multi-methodanalysisofMRIimagesinearlydiagnostics of Alzheimer’s disease.PloS one, 6(10):e25446, 2011

    Robin Wolz, Valtteri Julkunen, Juha Koikkalainen, Eini Niskanen, Dong Ping Zhang, Daniel Rueckert, Hilkka Soininen, JyrkiLötjönen, andAlzheimer’sDiseaseNeuroimagingInitiative. Multi-methodanalysisofMRIimagesinearlydiagnostics of Alzheimer’s disease.PloS one, 6(10):e25446, 2011

    work page 2011

  73. [73]

    Quantitative comparison of 21 protocols for labeling hippocampal subfields and parahippocampal subregions in in vivo MRI: towards a harmonized segmentation protocol

    Paul A Yushkevich, Robert SC Amaral, Jean C Augustinack, Andrew R Bender, Jeffrey D Bernstein, Marina Boccardi, Martina Bocchetta, Alison C Burggren, Valerie A Carr, and M Mallar Chakravarty. Quantitative comparison of 21 protocols for labeling hippocampal subfields and parahippocampal subregions in in vivo MRI: towards a harmonized segmentation protocol. N...

    work page 2015

  74. [74]

    Hierarchical anatomical brain networks for MCI prediction: revisiting volumetric measures

    Luping Zhou, Yaping Wang, Yang Li, Pew-Thian Yap, Dinggang Shen, Alzheimer’s Disease Neuroimaging Initiative (ADNI, et al. Hierarchical anatomical brain networks for MCI prediction: revisiting volumetric measures. PloS one, 6(7):e21935, 2011

    work page 2011

  75. [75]

    Regularization and variable selection via the elastic net.Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301–320, 2005

    Hui Zou and Trevor Hastie. Regularization and variable selection via the elastic net.Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301–320, 2005. 18

    work page 2005