HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy

• URL: http://arxiv.org/abs/2607.04353v1
• Date: Sun, 05 Jul 2026 15:18:12 GMT
• Title: HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy
• Abstract summary: We propose a hierarchy-aware self-supervised training framework to address this problem.<n>We train and evaluate our method on a curated corpus of 2.3 million single cells aggregated from 20 microscopy datasets.
• Score: 0.9759936503350192
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hierarchical structure is common in image data, where fine-grained clusters often merge into larger, coarser semantic groups. In biological cell images, current self-supervised learning models often suppress this hierarchy, as coarse factors such as imaging modality can obscure finer morphological attributes in the latent space. We propose a hierarchy-aware self-supervised training framework to address this problem. Our method combines two components: a distillation framework with a segmentation teacher to improve morphological awareness in the latent space, and a hierarchy-aware contrastive loss based on HDBSCAN to improve decision boundaries between closely related subtypes at different hierarchical levels. Together, these components reduce the tendency of self-supervised learning to overemphasize coarse factors and instead align embeddings with semantic and morphological cues. This yields biologically meaningful sub-clusters driven by fine morphological detail. We train and evaluate our method on a curated corpus of 2.3 million single cells aggregated from 20 microscopy datasets, both labeled and unlabeled, covering 208 cell classes. Our method improves over baseline and counterpart methods, increasing average top-K accuracy by 2.8%, top-9 retrieval on the dataset with the deepest hierarchy by 6.3%, and downstream F1-score for biologically relevant drug classification from perturbed cell morphology by 7.8%.

Related papers

• Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification [50.20892407648858]
  Multimodal contrastive learning has enabled zero-shot visual classification by aligning images with textual categories.<n>Existing methods often produce predictions that are inconsistent across taxonomic levels.<n>We propose a group-balanced design, ensuring each taxonomic level receives adequate optimization.<n>We train our model with TreeOfLife-10M based on BioCLIP and evaluate it across multiple hierarchical classification benchmarks.
  arXiv  Detail & Related papers  (2026-06-20T02:12:05Z)
• CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular Localization [50.559485139565076]
  We introduce a new benchmark called $mathbfCAPSUL$, a dataset that integrates diverse 3D structural representations with fine-grained subcellular localization annotations.<n>We evaluate this benchmark using a variety of state-of-the-art sequence-based and structure-based models, showcasing the importance of involving structural features in this task.<n> Lastly, we showcase the powerful interpretability of structure-based methods through a case study on the Golgi apparatus.
  arXiv  Detail & Related papers  (2026-03-19T07:33:04Z)
• Hierarchical Classification for Improved Histopathology Image Analysis [7.036962871076997]
  HiClass is a hierarchical classification framework for improved histopathology image analysis.<n>Built upon a multiple instance learning approach, HiClass extends it by introducing bidirectional feature integration.<n>We assess the performance of HiClass on a gastric biopsy dataset with 4 coarse-grained and 14 fine-grained classes.
  arXiv  Detail & Related papers  (2026-02-28T07:01:04Z)
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling [74.25438319700929]
  We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that models local-global dependencies between molecules and cellular responses.<n> evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines.<n>Results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations.
  arXiv  Detail & Related papers  (2025-11-26T07:15:00Z)
• Adaptive Multi-Scale Integration Unlocks Robust Cell Annotation in Histopathology Images [3.504506659662406]
  We build a marker-guided dataset from Xenium spatial transcriptomics with single-cell resolution labels for more than two million cells across eight organs.<n>We introduce NuClass, a pathologist workflow inspired framework for cell-wise multi-scale integration of nuclear morphology and microenvironmental context.<n>Our results demonstrate that multi-scale, uncertainty-aware fusion can bridge the gap between slide-level pathological foundation models and reliable, cell-level phenotype prediction.
  arXiv  Detail & Related papers  (2025-11-17T16:49:59Z)
• Biologically Inspired Deep Learning Approaches for Fetal Ultrasound Image Classification [0.0]
  We introduce a simple yet powerful, biologically inspired deep learning ensemble framework.<n>Our model stacks two complementary branches (a "shallow" path for coarse, low-resolution cues and a "detailed" path for fine, high-resolution features)<n>We trained and evaluated on 5,298 routinely acquired clinical images.
  arXiv  Detail & Related papers  (2025-06-10T09:34:33Z)
• Knowledge-Guided Prompt Learning for Lifespan Brain MR Image Segmentation [53.70131202548981]
  We present a two-step segmentation framework employing Knowledge-Guided Prompt Learning (KGPL) for brain MRI. Specifically, we first pre-train segmentation models on large-scale datasets with sub-optimal labels. The introduction of knowledge-wise prompts captures semantic relationships between anatomical variability and biological processes.
  arXiv  Detail & Related papers  (2024-07-31T04:32:43Z)
• UniCell: Universal Cell Nucleus Classification via Prompt Learning [76.11864242047074]
  We propose a universal cell nucleus classification framework (UniCell) It employs a novel prompt learning mechanism to uniformly predict the corresponding categories of pathological images from different dataset domains. In particular, our framework adopts an end-to-end architecture for nuclei detection and classification, and utilizes flexible prediction heads for adapting various datasets.
  arXiv  Detail & Related papers  (2024-02-20T11:50:27Z)
• CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification [1.9574002186090493]
  We propose a semi-supervised patch-level histological image classification model, named CLASS-M, that does not require extensively labeled datasets. We compare our model with other state-of-the-art models on two clear cell renal cell carcinoma datasets.
  arXiv  Detail & Related papers  (2023-12-12T04:38:30Z)
• Single-Cell Deep Clustering Method Assisted by Exogenous Gene Information: A Novel Approach to Identifying Cell Types [50.55583697209676]
  We develop an attention-enhanced graph autoencoder, which is designed to efficiently capture the topological features between cells. During the clustering process, we integrated both sets of information and reconstructed the features of both cells and genes to generate a discriminative representation. This research offers enhanced insights into the characteristics and distribution of cells, thereby laying the groundwork for early diagnosis and treatment of diseases.
  arXiv  Detail & Related papers  (2023-11-28T09:14:55Z)
• Dynamic Sub-Cluster-Aware Network for Few-Shot Skin Disease Classification [31.539129126161978]
  This paper introduces a novel approach called the Sub-Cluster-Aware Network (SCAN) that enhances accuracy in diagnosing rare skin diseases. The key insight motivating the design of SCAN is the observation that skin disease images within a class often exhibit multiple sub-clusters. We evaluate the proposed approach on two public datasets for few-shot skin disease classification.
  arXiv  Detail & Related papers  (2022-07-03T16:06:04Z)
• The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
  We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
  arXiv  Detail & Related papers  (2022-03-10T23:35:00Z)

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.