CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies

• URL: http://arxiv.org/abs/2512.16700v1
• Date: Thu, 18 Dec 2025 16:04:55 GMT
• Title: CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies
• Authors: John M. Statheros, Hairong Wang, Richard Klein,
• Abstract summary: CLARiTy is a vision transformer-based model for joint multi-label classification and weakly-supervised localization of thoracic pathologies.<n>It is trained on image-level labels from the NIH ChestX-ray14 dataset.<n>It achieves competitive classification performance across 14 pathologies, and state-of-the-art weakly-supervised localization performance on 8 pathologies.
• Score: 5.833805519002777
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The interpretation of chest X-rays (CXRs) poses significant challenges, particularly in achieving accurate multi-label pathology classification and spatial localization. These tasks demand different levels of annotation granularity but are frequently constrained by the scarcity of region-level (dense) annotations. We introduce CLARiTy (Class Localizing and Attention Refining Image Transformer), a vision transformer-based model for joint multi-label classification and weakly-supervised localization of thoracic pathologies. CLARiTy employs multiple class-specific tokens to generate discriminative attention maps, and a SegmentCAM module for foreground segmentation and background suppression using explicit anatomical priors. Trained on image-level labels from the NIH ChestX-ray14 dataset, it leverages distillation from a ConvNeXtV2 teacher for efficiency. Evaluated on the official NIH split, the CLARiTy-S-16-512 (a configuration of CLARiTy), achieves competitive classification performance across 14 pathologies, and state-of-the-art weakly-supervised localization performance on 8 pathologies, outperforming prior methods by 50.7%. In particular, pronounced gains occur for small pathologies like nodules and masses. The lower-resolution variant of CLARiTy, CLARiTy-S-16-224, offers high efficiency while decisively surpassing baselines, thereby having the potential for use in low-resource settings. An ablation study confirms contributions of SegmentCAM, DINO pretraining, orthogonal class token loss, and attention pooling. CLARiTy advances beyond CNN-ViT hybrids by harnessing ViT self-attention for global context and class-specific localization, refined through convolutional background suppression for precise, noise-reduced heatmaps.

Related papers

• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection [50.343419243749054]
  Anomaly detection is critical in fields such as medical diagnostics and industrial defect detection.<n> CLIP's coarse-grained image-text alignment limits localization and detection performance for fine-grained anomalies.<n>Crane improves the state-of-the-art ZSAD from 2% to 28%, at both image and pixel levels, while remaining competitive in inference speed.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• Visual Prompt Engineering for Vision Language Models in Radiology [0.17183214167143138]
  Contrastive Language-Image Pretraining (CLIP) offers a promising solution by enabling zero-shot classification through multimodal large-scale pretraining.<n>While CLIP effectively captures global image content, radiology requires a more localized focus on specific pathology regions to enhance both interpretability and diagnostic accuracy.<n>We explore the potential of incorporating visual cues into zero-shot classification, embedding visual markers, such as arrows, bounding boxes, and circles, directly into radiological images to guide model attention.
  arXiv  Detail & Related papers  (2024-08-28T13:53:27Z)
• Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition [59.28732531600606]
  We propose a framework named textbfClass textbfAttention to textbfREgions of the lesion (CARE) to handle data imbalance issues. The CARE framework needs bounding boxes to represent the lesion regions of rare diseases. Results show that the CARE variants with automated bounding box generation are comparable to the original CARE framework.
  arXiv  Detail & Related papers  (2023-07-19T15:19:02Z)
• Data-Efficient Vision Transformers for Multi-Label Disease Classification on Chest Radiographs [55.78588835407174]
  Vision Transformers (ViTs) have not been applied to this task despite their high classification performance on generic images. ViTs do not rely on convolutions but on patch-based self-attention and in contrast to CNNs, no prior knowledge of local connectivity is present. Our results show that while the performance between ViTs and CNNs is on par with a small benefit for ViTs, DeiTs outperform the former if a reasonably large data set is available for training.
  arXiv  Detail & Related papers  (2022-08-17T09:07:45Z)
• Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays [65.88435151891369]
  Radiomics-Guided Transformer (RGT) fuses textitglobal image information with textitlocal knowledge-guided radiomics information. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information.
  arXiv  Detail & Related papers  (2022-07-10T06:32:56Z)
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
  An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
  arXiv  Detail & Related papers  (2022-05-08T15:29:54Z)
• Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference [28.409679398886304]
  We develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets.
  arXiv  Detail & Related papers  (2022-05-06T08:37:02Z)
• Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer [25.144248675578286]
  Under the global pandemic of COVID-19, building an automated framework that quantifies the severity of COVID-19 has become increasingly important. We propose a novel Vision Transformer tailored for both quantification of the severity and clinically applicable localization of the COVID-19 related lesions. Our model is trained in a weakly-supervised manner to generate the full probability maps from weak array-based labels.
  arXiv  Detail & Related papers  (2021-03-12T03:17:19Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• Feature based Sequential Classifier with Attention Mechanism [0.7123982871971924]
  Cervical intraepithelial neoplasia assessment using histopathology slides is subject to interobserver variability. We propose a network pipeline, DeepCIN, to analyze high-resolution epithelium images hierarchically. Experiments show that DeepCIN achieves pathologist-level CIN classification accuracy.
  arXiv  Detail & Related papers  (2020-07-22T12:54:30Z)
• Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Images [0.0]
  We propose a novel approach to the semantic segmentation of medical chest X-ray images with only image-level class labels as supervision. We show that this approach is applicable to chest X-rays for detecting an anomalous volume of air between the lung and the chest wall.
  arXiv  Detail & Related papers  (2020-07-01T20:48:35Z)

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.