Hierarchical Sparse Attention Framework for Computationally Efficient Classification of Biological Cells

• URL: http://arxiv.org/abs/2505.07661v1
• Date: Mon, 12 May 2025 15:29:08 GMT
• Title: Hierarchical Sparse Attention Framework for Computationally Efficient Classification of Biological Cells
• Authors: Elad Yoshai, Dana Yagoda-Aharoni, Eden Dotan, Natan T. Shaked,
• Abstract summary: We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification.<n>For biological cell images, we demonstrate that SparseAttnNet can process approximately 15% of the pixels instead of the full image.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification that adaptively selects and processes only the most informative pixels from images. Traditional convolutional neural networks typically process the entire images regardless of information density, leading to computational inefficiency and potential focus on irrelevant features. Our approach leverages a dynamic selection mechanism that uses coarse attention distilled by fine multi-head attention from the downstream layers of the model, allowing the model to identify and extract the most salient k pixels, where k is adaptively learned during training based on loss convergence trends. Once the top-k pixels are selected, the model processes only these pixels, embedding them as words in a language model to capture their semantics, followed by multi-head attention to incorporate global context. For biological cell images, we demonstrate that SparseAttnNet can process approximately 15% of the pixels instead of the full image. Applied to cell classification tasks using white blood cells images from the following modalities: optical path difference (OPD) images from digital holography for stain-free cells, images from motion-sensitive (event) camera from stain-free cells, and brightfield microscopy images of stained cells, For all three imaging modalities, SparseAttnNet achieves competitive accuracy while drastically reducing computational requirements in terms of both parameters and floating-point operations per second, compared to traditional CNNs and Vision Transformers. Since the model focuses on biologically relevant regions, it also offers improved explainability. The adaptive and lightweight nature of SparseAttnNet makes it ideal for deployment in resource-constrained and high-throughput settings, including imaging flow cytometry.

Related papers

• Improving Sickle Cell Disease Classification: A Fusion of Conventional Classifiers, Segmented Images, and Convolutional Neural Networks [0.31457219084519006]
  We propose a novel approach combining conventional classifiers, segmented images, and CNNs for the automated classification of sickle cell disease.<n>Our results demonstrate that using segmented images and CNN features with an SVM achieves an accuracy of 96.80%.
  arXiv  Detail & Related papers  (2024-12-23T20:42:15Z)
• Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing [72.45257414889478]
  We aim to reduce human workload by predicting connectivity between over-segmented neuron pieces. We first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain. We propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding.
  arXiv  Detail & Related papers  (2024-01-05T19:45:12Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• Pixel-Inconsistency Modeling for Image Manipulation Localization [59.968362815126326]
  Digital image forensics plays a crucial role in image authentication and manipulation localization. This paper presents a generalized and robust manipulation localization model through the analysis of pixel inconsistency artifacts. Experiments show that our method successfully extracts inherent pixel-inconsistency forgery fingerprints.
  arXiv  Detail & Related papers  (2023-09-30T02:54:51Z)
• LMBiS-Net: A Lightweight Multipath Bidirectional Skip Connection based CNN for Retinal Blood Vessel Segmentation [0.0]
  Blinding eye diseases are often correlated with altered retinal morphology, which can be clinically identified by segmenting retinal structures in fundus images. Deep learning has shown promise in medical image segmentation, but its reliance on repeated convolution and pooling operations can hinder the representation of edge information. We propose a lightweight pixel-level CNN named LMBiS-Net for the segmentation of retinal vessels with an exceptionally low number of learnable parameters.
  arXiv  Detail & Related papers  (2023-09-10T09:03:53Z)
• Asymmetric Co-Training with Explainable Cell Graph Ensembling for Histopathological Image Classification [28.949527817202984]
  We propose an asymmetric co-training framework combining a deep graph convolutional network and a convolutional neural network. We build a 14-layer deep graph convolutional network to handle cell graph data. We evaluate our approach on the private LUAD7C and public colorectal cancer datasets.
  arXiv  Detail & Related papers  (2023-08-24T12:27:03Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• A novel approach for glaucoma classification by wavelet neural networks using graph-based, statisitcal features of qualitatively improved images [0.0]
  We have proposed a new glaucoma classification approach that employs a wavelet neural network (WNN) on optimally enhanced retinal images features. The performance of the WNN classifier is compared with multilayer perceptron neural networks with various datasets.
  arXiv  Detail & Related papers  (2022-06-24T06:19:30Z)
• Class Balanced PixelNet for Neurological Image Segmentation [20.56747443955369]
  We propose an automatic brain tumor segmentation approach (e.g., PixelNet) using a pixel-level convolutional neural network (CNN) The proposed model has achieved promising results in brain tumor and ischemic stroke segmentation datasets.
  arXiv  Detail & Related papers  (2022-04-23T10:57:54Z)
• Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation [133.02190910009384]
  We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes. Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
  arXiv  Detail & Related papers  (2022-04-19T10:41:09Z)
• Neural Cellular Automata Manifold [84.08170531451006]
  We show that the neural network architecture of the Neural Cellular Automata can be encapsulated in a larger NN. This allows us to propose a new model that encodes a manifold of NCA, each of them capable of generating a distinct image. In biological terms, our approach would play the role of the transcription factors, modulating the mapping of genes into specific proteins that drive cellular differentiation.
  arXiv  Detail & Related papers  (2020-06-22T11:41:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.