Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies

• URL: http://arxiv.org/abs/2211.02967v1
• Date: Sat, 5 Nov 2022 19:49:03 GMT
• Title: Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies
• Authors: Elias Villalvazo-Avila, Francisco Lopez-Tiro, Jonathan El-Beze, Jacques Hubert, Miguel Gonzalez-Mendoza, Gilberto Ochoa-Ruiz, Christian Daul
• Abstract summary: This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. In comparison to the state-of-the-art, the fusion of the deep features improved the overall results up to 11% in terms of kidney stone classification accuracy.
• Score: 0.9236074230806579
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. This approach is specifically designed to mimic the morpho-constitutional analysis performed in ex-vivo by biologists to visually identify kidney stones by inspecting both views. The addition of attention mechanisms to the backbone improved the results of single view extraction backbones by 4% on average. Moreover, in comparison to the state-of-the-art, the fusion of the deep features improved the overall results up to 11% in terms of kidney stone classification accuracy.

Related papers

• Optimizing Skin Lesion Classification via Multimodal Data and Auxiliary Task Integration [54.76511683427566]
  This research introduces a novel multimodal method for classifying skin lesions, integrating smartphone-captured images with essential clinical and demographic information. A distinctive aspect of this method is the integration of an auxiliary task focused on super-resolution image prediction. The experimental evaluations have been conducted using the PAD-UFES20 dataset, applying various deep-learning architectures.
  arXiv  Detail & Related papers  (2024-02-16T05:16:20Z)
• Multi-task Explainable Skin Lesion Classification [54.76511683427566]
  We propose a few-shot-based approach for skin lesions that generalizes well with few labelled data. The proposed approach comprises a fusion of a segmentation network that acts as an attention module and classification network.
  arXiv  Detail & Related papers  (2023-10-11T05:49:47Z)
• Improving automatic endoscopic stone recognition using a multi-view fusion approach enhanced with two-step transfer learning [1.077541993594101]
  It aims to produce more discriminant object features for the identification of the type of kidney stones seen in endoscopic images. Deep feature fusion strategies improved the results of single view extraction backbone models by more than 6% in terms of accuracy of the kidney stones classification.
  arXiv  Detail & Related papers  (2023-04-06T16:17:28Z)
• Boosting Kidney Stone Identification in Endoscopic Images Using Two-Step Transfer Learning [0.8431877864777444]
  The proposed approach transfers knowledge learned on a set of images of kidney stones acquired with a CCD camera to a final model that classifies images from endoscopic images. The results show that learning features from different domains with similar information helps to improve the performance of a model that performs classification in real conditions.
  arXiv  Detail & Related papers  (2022-10-24T23:22:22Z)
• Improving Radiology Summarization with Radiograph and Anatomy Prompts [60.30659124918211]
  We propose a novel anatomy-enhanced multimodal model to promote impression generation. In detail, we first construct a set of rules to extract anatomies and put these prompts into each sentence to highlight anatomy characteristics. We utilize a contrastive learning module to align these two representations at the overall level and use a co-attention to fuse them at the sentence level.
  arXiv  Detail & Related papers  (2022-10-15T14:05:03Z)
• Stain based contrastive co-training for histopathological image analysis [61.87751502143719]
  We propose a novel semi-supervised learning approach for classification of histovolution images. We employ strong supervision with patch-level annotations combined with a novel co-training loss to create a semi-supervised learning framework. We evaluate our approach in clear cell renal cell and prostate carcinomas, and demonstrate improvement over state-of-the-art semi-supervised learning methods.
  arXiv  Detail & Related papers  (2022-06-24T22:25:31Z)
• Comparing feature fusion strategies for Deep Learning-based kidney stone identification [0.9236074230806579]
  Our approach was specifically designed to mimic the morpho-constitutional analysis used by urologists to visually classify kidney stones. Deep feature fusion strategies improved the results of single view extraction backbone models by more than 10% in terms of precision of the kidney stones classification.
  arXiv  Detail & Related papers  (2022-05-31T19:27:54Z)
• On the in vivo recognition of kidney stones using machine learning [1.6273083168563973]
  This paper compares the kidney stone recognition performances of six shallow machine learning methods and three deep-learning architectures. It is also shown that choosing an appropriate colour space and texture features allows a shallow machine learning method to approach closely the performances of the most promising deep-learning methods.
  arXiv  Detail & Related papers  (2022-01-21T19:18:42Z)
• Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis [88.39466012709205]
  This paper builds a novel medical slice to increase the between-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy. Our method outperforms state-of-the-art algorithms by clear margins.
  arXiv  Detail & Related papers  (2021-12-20T03:38:37Z)
• Assessing deep learning methods for the identification of kidney stones in endoscopic images [0.0]
  Knowing the type (i.e., the biochemical composition) of kidney stones is crucial to prevent relapses. During ureteroscopies, kidney stones are fragmented, extracted from the urinary tract, and their composition is determined using a morpho-constitutional analysis. This paper discusses and compares five classification methods including deep convolutional neural networks (DCNN)-based approaches and traditional (non DCNN-based) ones.
  arXiv  Detail & Related papers  (2021-03-01T17:31:01Z)
• Attention Model Enhanced Network for Classification of Breast Cancer Image [54.83246945407568]
  AMEN is formulated in a multi-branch fashion with pixel-wised attention model and classification submodular. To focus more on subtle detail information, the sample image is enhanced by the pixel-wised attention map generated from former branch. Experiments conducted on three benchmark datasets demonstrate the superiority of the proposed method under various scenarios.
  arXiv  Detail & Related papers  (2020-10-07T08:44:21Z)

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.