mlsanityData to 7 Oct 2026

Segmentation of Non-Small Cell Lung Carcinomas: Introducing DRU-Net and Multi-Lens Distortion

arXiv 2406.14287 ↗First posted 20 Jun 2024eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Considering the increased workload in pathology laboratories today, automated tools such as artificial intelligence models can help pathologists with their tasks and ease the workload. In this paper, we are proposing a segmentation model (DRU-Net) that can provide a delineation of human non-small cell lung carcinomas and an augmentation method that can improve classification results. The proposed model is a fused combination of truncated pre-trained DenseNet201 and ResNet101V2 as a patch-wise classifier followed by a lightweight U-Net as a refinement model. We have used two datasets (Norwegian Lung Cancer Biobank and Haukeland University Hospital lung cancer cohort) to create our proposed model. The DRU-Net model achieves an average of 0.91 Dice similarity coefficient. The proposed spatial augmentation method (multi-lens distortion) improved the network performance by 3%. Our findings show that choosing image patches that specifically include regions of interest leads to better results for the patch-wise classifier compared to other sampling methods. The qualitative analysis showed that the DRU-Net model is generally successful in detecting the tumor. On the test set, some of the cases showed areas of false positive and false negative segmentation in the periphery, particularly in tumors with inflammatory and reactive changes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 86 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

27 of 86 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  9. 2022A ConvNet for the 2020scited by 3,545
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  11. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
15 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  3. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  4. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  5. 2022How Do Vision Transformers Work?cited by 305
  6. 2023Segment Anything in Medical Imagescited by 226
  7. 2019Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologycited by 172
  8. 2023Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imagingcited by 161
  9. 2019U-CAM: Visual Explanation using Uncertainty based Class Activation Mapscited by 36
  10. 2018Fast and Accurate Tumor Segmentation of Histology Images using Persistent Homology and Deep Convolutional Featurescited by 28
  11. 2019Deep Multi-Magnification Networks for Multi-Class Breast Cancer Image Segmentationcited by 22
  12. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  13. 2017ScanNet: A Fast and Dense Scanning Framework for Metastatic Breast Cancer Detection from Whole-Slide Imagescited by 13
  14. 2020FastPathology: An open-source platform for deep learning-based research and decision support in digital pathologycited by 7
  15. 2022A Task-aware Dual Similarity Network for Fine-grained Few-shot Learningcited by 3

Built on by

Not cited yet.