mlsanityData to 14 Oct 2026

RadFormer: Transformers with Global-Local Attention for Interpretable and Accurate Gallbladder Cancer Detection

arXiv 2211.04793 ↗First posted 9 Nov 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

We propose a novel deep neural network architecture to learn interpretable representation for medical image analysis. Our architecture generates a global attention for region of interest, and then learns bag of words style deep feature embeddings with local attention. The global, and local feature maps are combined using a contemporary transformer architecture for highly accurate Gallbladder Cancer (GBC) detection from Ultrasound (USG) images. Our experiments indicate that the detection accuracy of our model beats even human radiologists, and advocates its use as the second reader for GBC diagnosis. Bag of words embeddings allow our model to be probed for generating interpretable explanations for GBC detection consistent with the ones reported in medical literature. We show that the proposed model not only helps understand decisions of neural network models but also aids in discovery of new visual features relevant to the diagnosis of GBC. Source-code and model will be available at https://github.com/sbasu276/RadFormer

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 31 of its 93 references that are in the map. First posted on arXiv 9 Nov 2022.

Builds on

31 of 93 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  10. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  12. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
19 more
  1. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  2. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
  3. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 320
  4. 2021TransBTS: Multimodal Brain Tumor Segmentation Using Transformercited by 265
  5. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  6. 2021Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformerscited by 159
  7. 2020Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classificationcited by 100
  8. 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 86
  9. 2020Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Modelcited by 59
  10. 2021GLiT: Neural Architecture Search for Global and Local Image Transformercited by 53
  11. 2020HookNet: multi-resolution convolutional neural networks for semantic segmentation in histopathology whole-slide imagescited by 45
  12. 2020USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learningcited by 34
  13. 2021Global-Local Transformer for Brain Age Estimationcited by 34
  14. 2016Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Imagescited by 26
  15. 2022Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learningcited by 16
  16. 2018Robust Tumor Localization with Pyramid Grad-CAMcited by 13
  17. 2018DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanationcited by 9
  18. 2019SISC: End-to-end Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cellscited by 3
  19. 2019Deep Local Global Refinement Network for Stent Analysis in IVOCT Imagescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 4; 2026: 2.

12 papers.

  1. 2024From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learningcited by 15
  2. 2024FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoderscited by 8
  3. 2024SAM-FNet: SAM-Guided Fusion Network for Laryngo-Pharyngeal Tumor Detectioncited by 4
  4. 2025Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detectioncited by 4
  5. 2023Gall Bladder Cancer Detection from US Images with Only Image Level Labelscited by 3
  6. 2025Focus on Texture: Rethinking Pre-training in Masked Autoencoders for Medical Image Classificationcited by 3
  7. 2024SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detectioncited by 2
  8. 2024LQ-Adapter: ViT-Adapter with Learnable Queries for Gallbladder Cancer Detection from Ultrasound Imagecited by 1
  9. 2026CortiNet: A Physics-Perception Hybrid Cortical-Inspired Dual-Stream Network for Gallbladder Disease Diagnosis from Ultrasoundcited by 1
  10. 2025Assessing Risk of Stealing Proprietary Models for Medical Imaging Taskscited by 0
  11. 2025Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trustcited by 0
  12. 2026Bridging visual saliency and large language models for explainable deep learning in medical imagingcited by 0