OSCR

MambaKAN: An Interpretable Framework for Alzheimer's Disease Diagnosis via Selective State Space Modeling of Dynamic Functional Connectivity.

Code ↔ Paper

17 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

12 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.

The 17 matches
  1. [1] § 3. Methods › 3.5. Joint Training Strategy › 3.5.1. Two-Phase Training Protocol ↔ train_stage1.py, lines 1 to 30 · score 0.92 · lowest validation reconstruction, VAE Unsupervised Pre, noise robust latent, best checkpoint, pre training, Adam · block oscr:b:VC52DMV2J331R-Z · Report a mismatch
  2. [2] § 3. Methods › 3.4. Kolmogorov–Arnold Network Classifier › 3.4.1. KAN Architecture Motivation ↔ models/kan_classifier.py, lines 1 to 17 · score 0.84 · Kolmogorov Arnold Networks, learnable weights, visualizable curve, intrinsically interpretable, inspired, MLPs · block oscr:b:G8ABP777R75JV-Y · Report a mismatch
  3. [3] § 3. Methods › 3.3. Mamba Selective State Space Temporal Encoder › 3.3.3. Selective State Space Model (S6) ↔ models/mamba_encoder.py, lines 13 to 22 · score 0.82 · Selective State Space, depthwise convolution, selectivity mechanism, Mamba block, S6, Model · block oscr:b:0ZT3JYHCSAECR-M · Report a mismatch
  4. [4] § 3. Methods › 3.5. Joint Training Strategy › 3.5.1. Two-Phase Training Protocol ↔ train_stage2.py, lines 1 to 44 · score 0.76 · End Joint Fine, trained jointly, MambaKAN, tuning, pipeline, accuracy · block oscr:b:5ZGZGBQ5K1KE6-9 · Report a mismatch
  5. [5] § 3. Methods › 3.4. Kolmogorov–Arnold Network Classifier › 3.4.5. MambaKAN Classifier Structure ↔ models/kan_classifier.py, lines 180 to 280 · score 0.73 · layer KAN, context vector, Mamba encoder, KAN classifier, learnable, weights · block oscr:b:9H3TE4HAVMPJ2-U · Report a mismatch
  6. [6] § 3. Methods › 3.1. Overview of MambaKAN ↔ train_stage2.py, lines 1 to 44 · score 0.72 · VAE encoding, MambaKAN, KAN classification, Mamba temporal, pipeline, joint · block oscr:b:5ZGZGBQ5K1KE6-9 · Report a mismatch
  7. [7] § 5. Interpretability Analysis › 5.3. Layer 3: Gradient-Based Brain Region Attribution ↔ analysis.py, lines 230 to 357 · score 0.67 · bar charts, attribution scores, chord, heatmap, connectivity, Gradient · block oscr:b:J5FCKAR62EDQS-W · Report a mismatch
  8. [8] § 3. Methods › 3.5. Joint Training Strategy › 3.5.2. Differential Learning Rates ↔ train_stage2.py, lines 46 to 74 · score 0.63 · warmup epochs, fine tuning, frozen, trained, KAN, Mamba · block oscr:b:9Q8Y6M8960991-U · Report a mismatch
  9. [9] § 3. Methods › 3.3. Mamba Selective State Space Temporal Encoder › 3.3.1. Rationale for Mamba over LSTM and Transformer ↔ models/mamba_encoder.py, lines 152 to 179 · score 0.63 · parallel scan, hardware aware, efficient, matrices, Selective, Mamba · block oscr:b:9FMDTWVAZE3ZD-O · Report a mismatch
  10. [10] § 3. Methods › 3.4. Kolmogorov–Arnold Network Classifier › 3.4.2. Rationale for KAN over MLP ↔ models/kan_classifier.py, lines 1 to 17 · score 0.63 · provides intrinsic interpretability, latent dimension, MLP, mapping, linear, logits · block oscr:b:G8ABP777R75JV-Y · Report a mismatch
  11. [11] § 5. Interpretability Analysis › 5.3. Layer 3: Gradient-Based Brain Region Attribution ↔ analysis.py, lines 230 to 357 · score 0.59 · chord diagram, attribution scores, connectivity, Gradient, Brain, class · block oscr:b:J5FCKAR62EDQS-W · Report a mismatch
  12. [12] § 3. Methods › 3.4. Kolmogorov–Arnold Network Classifier › 3.4.3. B-Spline Edge Activations ↔ models/kan_classifier.py, lines 29 to 66 · score 0.59 · spline coefficients, spline basis functions, uniform, learnable, weight · block oscr:b:SD6SBJK169PJA-K · Report a mismatch
  13. [13] § 3. Methods › 3.3. Mamba Selective State Space Temporal Encoder › 3.3.5. Temporal Context Aggregation ↔ models/mamba_encoder.py, lines 182 to 235 · score 0.58 · stacked Mamba blocks, temporal context, sequence, vector · block oscr:b:EKQM0RCFQ0N05-1 · Report a mismatch
  14. [14] § 5. Interpretability Analysis › 5.3. Layer 3: Gradient-Based Brain Region Attribution ↔ analysis.py, lines 1 to 41 · score 0.55 · attribution matrix, pairwise, ROI, brain, map, Gradient · block oscr:b:BGPXW8Y5PYKE0-O · Report a mismatch
  15. [15] § 3. Methods › 3.2. Variational Autoencoder for Per-Window Feature Extraction › 3.2.3. VAE Loss Function ↔ models/vae.py, lines 51 to 55 · score 0.54 · KL divergence, reconstruction loss, VAE · block oscr:b:41W3ZCPEEY50V-E · Report a mismatch
  16. [16] § 3. Methods › 3.5. Joint Training Strategy › 3.5.3. Regularization ↔ models/mamba_encoder.py, lines 13 to 22 · score 0.54 · depthwise convolution, Mamba block, Dropout, space · block oscr:b:0ZT3JYHCSAECR-M · Report a mismatch
  17. [17] § 4. Experiments › 4.2. Evaluation Metrics ↔ analysis.py, lines 1 to 41 · score 0.52 · ROC curve, MambaKAN, AUC · block oscr:b:BGPXW8Y5PYKE0-O · Report a mismatch

Paper

Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 297 lines · 10 KB · no license · 4 matches

  1. """
  2. Kolmogorov-Arnold Network (KAN) Classifier — B-Spline implementation.
  3. Reference: Liu et al., "KAN: Kolmogorov-Arnold Networks" (2024)
  4. Inspired by efficient-kan (https://github.com/Blealtan/efficient-kan)
  5. Key difference from MLP:
  6. MLP: y = W · σ(x) — fixed activation, learnable weights
  7. KAN: y = Σ φ_{q,p}(x_p) — learnable spline activations per connection
  8. Visualizing φ curves directly reveals the non-linear mapping from each
  9. latent dimension to class logits, providing intrinsic interpretability.
  10. """
  11. import math
  12. import torch
  13. import torch.nn as nn
  14. import torch.nn.functional as F
  15. class KANLinear(nn.Module):
  16. """
  17. A single KAN layer: replaces Linear + fixed activation with
  18. per-connection learnable B-spline activations.
  19. Input: (batch, in_features)
  20. Output: (batch, out_features)
  21. """
  22. def __init__(
  23. self,
  24. in_features: int,
  25. out_features: int,
  26. grid_size: int = 5,
  27. spline_order: int = 3,
  28. scale_noise: float = 0.1,
  29. scale_base: float = 1.0,
  30. grid_range: tuple = (-1.0, 1.0),
  31. ):
  32. super().__init__()
  33. self.in_features = in_features
  34. self.out_features = out_features
  35. self.grid_size = grid_size
  36. self.spline_order = spline_order
  37. # Build extended B-spline grid
  38. h = (grid_range[1] - grid_range[0]) / grid_size
  39. grid = torch.linspace(
  40. grid_range[0] - spline_order * h,
  41. grid_range[1] + spline_order * h,
  42. grid_size + 2 * spline_order + 1,
  43. )
  44. self.register_buffer("grid", grid)
  45. # Number of B-spline basis functions
  46. n_basis = grid_size + spline_order
  47. self.base_weight = nn.Parameter(torch.empty(out_features, in_features))
  48. # Spline coefficients: (out, in, n_basis)
  49. self.spline_weight = nn.Parameter(torch.empty(out_features, in_features, n_basis))
  50. # Per-connection scaling factors (learnable)
  51. self.scale_base = nn.Parameter(torch.ones(out_features, in_features) * scale_base)
  52. self.scale_spline = nn.Parameter(torch.ones(out_features, in_features))
  53. nn.init.kaiming_uniform_(self.base_weight, a=math.sqrt(5))
  54. nn.init.normal_(self.spline_weight, mean=0.0, std=scale_noise)
  55. def b_splines(self, x: torch.Tensor) -> torch.Tensor:
  56. """
  57. Evaluate B-spline basis functions at x via Cox–de Boor recursion.
  58. Args:
  59. x: (batch, in_features)
  60. Returns:
  61. bases: (batch, in_features, n_basis)
  62. """
  63. assert x.dim() == 2
  64. x = x.unsqueeze(-1)
  65. grid = self.grid
  66. # Order-0 indicator basis
  67. bases = ((x >= grid[:-1]) & (x < grid[1:])).float()
  68. # Cox–de Boor recursion
  69. for k in range(1, self.spline_order + 1):
  70. denom_l = grid[k:-1] - grid[: -(k + 1)]
  71. denom_r = grid[k + 1 :] - grid[1: -k]
  72. # Avoid division by zero
  73. left = torch.where(
  74. denom_l != 0,
  75. (x - grid[: -(k + 1)]) / denom_l * bases[..., :-1],
  76. torch.zeros_like(bases[..., :-1]),
  77. )
  78. right = torch.where(
  79. denom_r != 0,
  80. (grid[k + 1 :] - x) / denom_r * bases[..., 1:],
  81. torch.zeros_like(bases[..., 1:]),
  82. )
  83. bases = left + right
  84. return bases # (b, in, n_basis)
  85. def forward(self, x: torch.Tensor) -> torch.Tensor:
  86. """
  87. Args:
  88. x: (batch, in_features)
  89. Returns:
  90. out: (batch, out_features)
  91. """
  92. # Base (SiLU) branch
  93. base_out = F.linear(F.silu(x), self.base_weight * self.scale_base)
  94. # Spline branch: contract (b, in, n_basis) × (out, in, n_basis) → (b, out)
  95. bases = self.b_splines(x)
  96. spline_out = torch.einsum(
  97. "bik,oik->bo",
  98. bases,
  99. self.spline_weight * self.scale_spline.unsqueeze(-1),
  100. )
  101. return base_out + spline_out
  102. def get_activation_curve(self, dim: int, n_points: int = 200, x_range=(-3.0, 3.0)):
  103. """
  104. Evaluate the learned spline activation φ(x) for a single input dimension.
  105. Args:
  106. dim: input dimension index
  107. n_points: number of evaluation points
  108. x_range: evaluation range
  109. Returns:
  110. x_vals: (n_points,)
  111. y_vals: (out_features, n_points)
  112. """
  113. x_vals = torch.linspace(x_range[0], x_range[1], n_points, device=self.grid.device)
  114. dummy = torch.zeros(n_points, self.in_features, device=self.grid.device)
  115. dummy[:, dim] = x_vals
  116. bases = self.b_splines(dummy)
  117. sw = self.spline_weight[:, dim, :] * self.scale_spline[:, dim].unsqueeze(-1)
  118. y_vals = (bases[:, dim, :] @ sw.T).T # (out, n_pts)
  119. return x_vals.detach(), y_vals.detach()
  120. def update_grid(self, x: torch.Tensor, margin: float = 0.01):
  121. """
  122. Adapt the B-spline grid to span the activation range of x.
  123. Note on coefficient resampling:
  124. A full grid update should re-fit spline_weight onto the new basis
  125. (e.g. via least squares) to preserve learned activation shapes.
  126. This implementation omits that step because the current architecture
  127. uses a single shared 1-D grid for all in_features; when the grid
  128. shifts significantly the new and old basis spaces diverge and simple
  129. least-squares resampling is numerically unreliable (larger error
  130. than no resampling at all on large feature dimensions).
  131. In practice, call this method infrequently (every 50 epochs) so the
  132. network has enough gradient steps to recover from the small
  133. coefficient mismatch before the next update.
  134. Args:
  135. x: (batch, in_features) — representative input batch
  136. margin: fractional padding added beyond [x_min, x_max]
  137. """
  138. with torch.no_grad():
  139. x_min, x_max = x.min().item(), x.max().item()
  140. span = max(x_max - x_min, 1e-6)
  141. x_min -= margin * span
  142. x_max += margin * span
  143. h = (x_max - x_min) / self.grid_size
  144. new_grid = torch.linspace(
  145. x_min - self.spline_order * h,
  146. x_max + self.spline_order * h,
  147. len(self.grid),
  148. device=self.grid.device,
  149. dtype=self.grid.dtype,
  150. )
  151. self.grid.copy_(new_grid)
  152. class KANClassifier(nn.Module):
  153. """
  154. Two-layer KAN for classification.
  155. Structure: in_features → hidden_dim → num_classes
  156. Parameter count note:
  157. This implementation includes per-connection learnable scaling factors
  158. (scale_base and scale_spline in each KANLinear layer) for training
  159. stability. These add (out * in) extra parameters per layer compared
  160. to counting only the spline and base weights. As a result the KAN
  161. head has ~93 K parameters, somewhat larger than the ~43 K figure
  162. reported in the paper (which counted only spline_weight + base_weight).
  163. """
  164. def __init__(
  165. self,
  166. in_features: int,
  167. hidden_dim: int,
  168. num_classes: int,
  169. grid_size: int = 5,
  170. spline_order: int = 3,
  171. ):
  172. super().__init__()
  173. self.layer1 = KANLinear(in_features, hidden_dim, grid_size, spline_order)
  174. self.layer2 = KANLinear(hidden_dim, num_classes, grid_size, spline_order)
  175. def forward(self, x: torch.Tensor) -> torch.Tensor:
  176. return self.layer2(self.layer1(x))
  177. def update_grid(self, x: torch.Tensor):
  178. """
  179. Update B-spline grids in both layers.
  180. Call with a representative context batch (output of MambaEncoder)
  181. every few epochs during Phase-2 training.
  182. Args:
  183. x: (batch, in_features) — Mamba context vectors
  184. """
  185. self.layer1.update_grid(x)
  186. with torch.no_grad():
  187. h = self.layer1(x)
  188. self.layer2.update_grid(h)
  189. def get_input_importance(self) -> torch.Tensor:
  190. """
  191. L1 norm of spline weights in layer 1, summed over outputs and basis functions.
  192. Returns:
  193. importance: (in_features,) — higher = more influential
  194. """
  195. w = self.layer1.spline_weight # (out, in, n_basis)
  196. return w.abs().sum(dim=[0, 2]) # (in_features,)
  197. def get_class_curves(
  198. self,
  199. dim: int,
  200. x_mean: torch.Tensor,
  201. n_points: int = 200,
  202. x_range: tuple = (-3.0, 3.0),
  203. ):
  204. """
  205. Ceteris-paribus class activation curve for input dimension `dim`.
  206. Varies dim over x_range while holding all other dims at x_mean.
  207. Args:
  208. dim: input dimension to vary
  209. x_mean: (in_features,) anchor values for non-varied dims
  210. n_points: evaluation resolution
  211. x_range: range of variation for `dim`
  212. Returns:
  213. x_vals: (n_points,)
  214. logits: (num_classes, n_points)
  215. """
  216. device = next(self.parameters()).device
  217. x_vals = torch.linspace(x_range[0], x_range[1], n_points, device=device)
  218. probe = x_mean.unsqueeze(0).expand(n_points, -1).clone().to(device)
  219. probe[:, dim] = x_vals
  220. with torch.no_grad():
  221. out = self.forward(probe) # (n_points, num_classes)
  222. return x_vals.cpu(), out.T.cpu() # (num_classes, n_points)
  223. def get_top_activation_curves(self, top_k: int = 10, n_points: int = 200):
  224. """
  225. Returns activation curves for the top-k most important input dimensions.
  226. Returns:
  227. top_dims: (top_k,)
  228. x_vals: (n_points,)
  229. curves: (top_k, out_features, n_points)
  230. """
  231. importance = self.get_input_importance()
  232. top_dims = importance.topk(top_k).indices
  233. curves, x_vals = [], None
  234. for d in top_dims.tolist():
  235. xv, yv = self.layer1.get_activation_curve(d, n_points)
  236. x_vals = xv
  237. curves.append(yv)
  238. return top_dims, x_vals, torch.stack(curves, dim=0)
  239. if __name__ == "__main__":
  240. torch.manual_seed(0)
  241. b, in_f, hidden, num_cls = 16, 128, 64, 4
  242. model = KANClassifier(in_f, hidden, num_cls)
  243. x = torch.randn(b, in_f)
  244. logits = model(x)
  245. print("Logits shape:", logits.shape) # (16, 4)
  246. imp = model.get_input_importance()
  247. print("Importance shape:", imp.shape) # (128,)
  248. top_dims, x_vals, curves = model.get_top_activation_curves(top_k=5)
  249. print("Top dims:", top_dims.tolist())
  250. print("Curves shape:", curves.shape) # (5, 64, 200)

kan_classifier.py at commit 0ff30c0, no license · at the source

Overview

Authors: Libin Gao1, Zhongyi Hu2
ORCID iDs: Libin Gao, Zhongyi Hu
  1. Artificial Intelligence College, Zhejiang Industry & Trade Vocational College, Wenzhou 325000, China
  2. College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
Journal: Brain sciences, volume 16, issue 4, article 421
Dates: received 25 March 2026; accepted 16 April 2026; published online 17 April 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/brainsci16040421 · PMID 42041829 · PMCID PMC13114612 · OpenAlex W7154712876
Open access: gold, a free copy (OpenAlex)
Status: code verified (how the code is found and verified)
Categories: fMRI (modality), Alzheimer's / dementia (population)
Methods: Spectral & time-frequency, Statistics, Preprocessing, Connectivity, Machine learning, fMRI & imaging
Keywords: Alzheimer’s disease, dynamic functional connectivity, state space model, Mamba, Kolmogorov–Arnold network, variational autoencoder, interpretability, resting-state fMRI, deep learning, brain connectivity
Topic: Functional Brain Connectivity Studies (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: Wenzhou major scientific and technological innovation project plan “reveal the list” (ZG2023022); Wenzhou Fundamental Scientific Research Program (Y20240185, G20240065); General Program of Wenzhou Municipal Science and Technology Bureau (S2023013); General Program of Zhejiang Provincial Department of Education (Y202250720); Teacher Scientific Research Project of Zhejiang Industry & Trade Vocational College (G250101)
Citations: cited by 1 paper (Europe PMC); 24 references in the paper

Abstract

Background/Objectives: Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder that imposes a profound burden on global public health. While resting-state functional magnetic resonance imaging (rs-fMRI)-based dynamic functional connectivity (dFC) analysis has demonstrated promise in capturing time-varying brain network abnormalities, existing deep learning methods suffer from three fundamental limitations: (1) an inability to model temporal dependencies across dynamic connectivity windows, (2) reliance on post hoc black-box explainability tools, and (3) misalignment between feature learning and classification objectives. Methods: To address these challenges, we propose MambaKAN, an end-to-end interpretable framework integrating a Variational Autoencoder (VAE), a Selective State Space Model (Mamba), and a Kolmogorov–Arnold Network (KAN). The VAE encodes each dFC snapshot into a compact latent representation, preserving nonlinear connectivity patterns. The Mamba encoder captures long-range temporal dynamics across the sequence of latent representations via input-selective state transitions. The KAN classifier provides intrinsic interpretability through learnable B-spline activation functions, enabling direct visualization of how latent features influence diagnostic decisions without post-hoc approximation. The entire pipeline is trained end-to-end with a joint loss function that aligns feature learning with classification. Results: Evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset across five classification tasks (CN vs. AD, CN vs. EMCI, EMCI vs. LMCI, LMCI vs. AD, and four-class), MambaKAN achieves accuracies of 95.1%, 89.8%, 84.0%, 86.7%, and 70.5%, respectively, outperforming strong baselines including LSTM, Transformer, and MLP-based variants. Conclusions: Comprehensive ablation studies confirm the indispensable contribution of each module, and the three-layer interpretability analysis reveals key temporal patterns and brain regions associated with AD progression.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 17 matches between paragraphs and lines of code.

l1binn/MambaKAN

License: none: the authors keep all their rights
State: the link answers, verified on 29 September 2026
Evidence: files inventoried
Commit: 0ff30c0a3602f29e7eb6b90543f4ef7978b34707, 17 April 2026
Languages: Python (9)
Size: 11 files, 9 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README
Not found: license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: PyTorch (8 files), Matplotlib (1 file), NumPy (1 file), scikit-learn (1 file), SciPy (1 file)
Availability: 1 check, the latest on 29 September 2026: the link answers
  • 29 September 2026: the link answers
10 files

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 9 scripts, each with its path and the digest of its content;
  • 17 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The ADNI dataset is publicly available at https://adni.loni.usc.edu/ (accessed on 14 April 2026) upon registration. The core model and algorithm code is publicly available at https://github.com/l1binn/MambaKAN.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 29 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 2 authors, 10 keywords, 5 funders, 20 references.

Cite

This paper

Gao, L., & Hu, Z. (2026). MambaKAN: An Interpretable Framework for Alzheimer's Disease Diagnosis via Selective State Space Modeling of Dynamic Functional Connectivity. Brain sciences, 16(4), 421. https://doi.org/10.3390/brainsci16040421

BibTeX

@article{gao2026mambakan,
author = {Gao, Libin and Hu, Zhongyi},
title = {{MambaKAN: An Interpretable Framework for Alzheimer's Disease Diagnosis via Selective State Space Modeling of Dynamic Functional Connectivity}},
journal = {Brain sciences},
year = {2026},
month = apr,
volume = {16},
number = {4},
pages = {421},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2076-3425},
doi = {10.3390/brainsci16040421},
url = {https://doi.org/10.3390/brainsci16040421},
pmid = {42041829},
pmcid = {PMC13114612}
}

RIS

TY - JOUR
AU - Gao, Libin
AU - Hu, Zhongyi
TI - MambaKAN: An Interpretable Framework for Alzheimer's Disease Diagnosis via Selective State Space Modeling of Dynamic Functional Connectivity
T2 - Brain sciences
J2 - Brain Sci
PY - 2026
DA - 2026/04/17
VL - 16
IS - 4
SP - 421
SN - 2076-3425
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/brainsci16040421
UR - https://doi.org/10.3390/brainsci16040421
LA - en
ER -

CSL-JSON

{
"id": "10.3390/brainsci16040421",
"type": "article-journal",
"title": "MambaKAN: An Interpretable Framework for Alzheimer's Disease Diagnosis via Selective State Space Modeling of Dynamic Functional Connectivity",
"container-title": "Brain sciences",
"author": [
{
"family": "Gao",
"given": "Libin"
},
{
"family": "Hu",
"given": "Zhongyi"
}
],
"container-title-short": "Brain Sci",
"volume": "16",
"issue": "4",
"page": "421",
"DOI": "10.3390/brainsci16040421",
"PMID": "42041829",
"PMCID": "PMC13114612",
"ISSN": "2076-3425",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/brainsci16040421",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
17
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1093/braincomms/fcae010 [code]
Dysfunctions of multiscale dynamic brain functional networks in subjective cognitive decline.
Journal: Brain communications
In common: PyTorch, scikit-learn, SciPy, 1 other tool, fMRI, Alzheimer's / dementia, 2 references
[2] doi:10.1002/hbm.70280 [code]
Cross-Dataset Evaluation of Dementia Longitudinal Progression Prediction Models.
Journal: Human brain mapping
In common: PyTorch, scikit-learn, SciPy, 2 other tools, Alzheimer's / dementia, 2 references
[3] doi:10.1038/s41467-022-31037-5 [code]
Multimodal deep learning for Alzheimer's disease dementia assessment.
Journal: Nature communications
In common: PyTorch, scikit-learn, SciPy, 2 other tools, Alzheimer's / dementia, 2 references
[4] doi:10.1016/j.neuroimage.2024.120909 [code]
A simple but tough-to-beat baseline for fMRI time-series classification.
Journal: NeuroImage
In common: PyTorch, scikit-learn, SciPy, 2 other tools, fMRI, 2 references
[5] doi:10.1038/s41467-025-61292-1 [code]
Utility of synthetic musculoskeletal gaits for generalizable healthcare applications.
Journal: Nature communications
In common: PyTorch, scikit-learn, SciPy, 2 other tools, 2 references
[6] doi:10.3389/fnins.2023.1322967 [code]
Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification.
Journal: Frontiers in neuroscience
In common: PyTorch, scikit-learn, SciPy, 2 other tools, fMRI, 1 reference
[7] doi:10.3390/brainsci12101413 [code]
Resting-State Functional MRI Adaptation with Attention Graph Convolution Network for Brain Disorder Identification.
Journal: Brain sciences
In common: PyTorch, scikit-learn, SciPy, 2 other tools, fMRI, 1 reference
[8] doi:10.1038/s41746-024-01123-7 [code]
Constructing personalized characterizations of structural brain aberrations in patients with dementia using explainable artificial intelligence.
Journal: NPJ digital medicine
In common: scikit-learn, SciPy, Matplotlib, 1 other tool, Alzheimer's / dementia, 2 references
[9] doi:10.1016/j.xcrm.2026.102629 [code]
Enhancing diagnosis of mild cognitive impairment through brain-heart-gut metabolic networks in whole-body PET imaging.
Journal: Cell reports. Medicine
In common: PyTorch, scikit-learn, Matplotlib, 1 other tool, Alzheimer's / dementia, 2 references
[10] doi:10.1371/journal.pone.0303278 [code]
Explainability of three-dimensional convolutional neural networks for functional magnetic resonance imaging of Alzheimer's disease classification based on gradient-weighted class activation mapping.
Journal: PloS one
In common: PyTorch, SciPy, Matplotlib, 1 other tool, fMRI, Alzheimer's / dementia, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Add the badge to the code's README

OSCR: the badge of this paper

If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.

Markdown
<!-- oscr-badge:start -->
[![OSCR](https://openscicode.org/badge/doi/10.3390/brainsci16040421.svg)](https://openscicode.org/badge/doi/10.3390/brainsci16040421)
<!-- oscr-badge:end -->
reStructuredText
.. oscr-badge:start

.. image:: https://openscicode.org/badge/doi/10.3390/brainsci16040421.svg
   :target: https://openscicode.org/badge/doi/10.3390/brainsci16040421
   :alt: OSCR

.. oscr-badge:end
HTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.3390/brainsci16040421"><img src="https://openscicode.org/badge/doi/10.3390/brainsci16040421.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->

On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".

If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Report a mismatch between the code and the paper · Report a code error (signed in)

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Report a reproduction failure (signed in)

Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.