Augmenting Chest X-ray Datasets with Non-Expert Annotations

• URL: http://arxiv.org/abs/2309.02244v1
• Date: Tue, 5 Sep 2023 13:52:43 GMT
• Title: Augmenting Chest X-ray Datasets with Non-Expert Annotations
• Authors: Cathrine Damgaard, Trine Naja Eriksen, Dovile Juodelyte, Veronika Cheplygina, Amelia Jim\'enez-S\'anchez
• Abstract summary: A popular and cost-effective approach is automated annotation extraction from free-text medical reports. We enhance two publicly available chest X-ray datasets by incorporating non-expert annotations. We train a chest drain detector with the non-expert annotations that generalizes well to expert labels.
• Score: 1.9991771189143435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advancement of machine learning algorithms in medical image analysis requires the expansion of training datasets. A popular and cost-effective approach is automated annotation extraction from free-text medical reports, primarily due to the high costs associated with expert clinicians annotating chest X-ray images. However, it has been shown that the resulting datasets are susceptible to biases and shortcuts. Another strategy to increase the size of a dataset is crowdsourcing, a widely adopted practice in general computer vision with some success in medical image analysis. In a similar vein to crowdsourcing, we enhance two publicly available chest X-ray datasets by incorporating non-expert annotations. However, instead of using diagnostic labels, we annotate shortcuts in the form of tubes. We collect 3.5k chest drain annotations for CXR14, and 1k annotations for 4 different tube types in PadChest. We train a chest drain detector with the non-expert annotations that generalizes well to expert labels. Moreover, we compare our annotations to those provided by experts and show "moderate" to "almost perfect" agreement. Finally, we present a pathology agreement study to raise awareness about ground truth annotations. We make our annotations and code available.

Related papers

• Augmentation Matters: A Mix-Paste Method for X-Ray Prohibited Item Detection under Noisy Annotations [52.065764858163476]
  Automatic X-ray prohibited item detection is vital for public safety. Existing deep learning-based methods all assume that the annotations of training X-ray images are correct. We propose an effective label-aware mixed patch paste augmentation method (Mix-Paste) We show the superiority of our method on X-ray datasets under noisy annotations.
  arXiv  Detail & Related papers  (2025-01-03T09:51:51Z)
• Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis [53.809054774037214]
  This paper proposes leveraging vision-language pretraining on bone X-rays paired with French reports. It is the first study to integrate French reports to shape the embedding space devoted to bone X-Rays representations.
  arXiv  Detail & Related papers  (2024-05-14T19:53:20Z)
• Annotator Consensus Prediction for Medical Image Segmentation with Diffusion Models [70.3497683558609]
  A major challenge in the segmentation of medical images is the large inter- and intra-observer variability in annotations provided by multiple experts. We propose a novel method for multi-expert prediction using diffusion models.
  arXiv  Detail & Related papers  (2023-06-15T10:01:05Z)
• Act Like a Radiologist: Radiology Report Generation across Anatomical Regions [50.13206214694885]
  X-RGen is a radiologist-minded report generation framework across six anatomical regions. In X-RGen, we seek to mimic the behaviour of human radiologists, breaking them down into four principal phases. We enhance the recognition capacity of the image encoder by analysing images and reports across various regions.
  arXiv  Detail & Related papers  (2023-05-26T07:12:35Z)
• Detecting Shortcuts in Medical Images -- A Case Study in Chest X-rays [0.22940141855172028]
  We present a case study on chest X-rays using two publicly available datasets. We share annotations for a subset of pneumothorax images with drains.
  arXiv  Detail & Related papers  (2022-11-08T14:36:33Z)
• 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)
• Did You Get What You Paid For? Rethinking Annotation Cost of Deep Learning Based Computer Aided Detection in Chest Radiographs [8.079269139747131]
  We investigate how the cost of data annotation ultimately impacts the Computer Aided Detection model performance. We find that cost-efficient annotations provide great value when collected in large amounts and lead to competitive performance when compared to models trained with only gold-standard annotations.
  arXiv  Detail & Related papers  (2022-09-30T08:42:22Z)
• Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study [75.05049024176584]
  We present a benchmark study of the long-tailed learning problem in the specific domain of thorax diseases on chest X-rays. We focus on learning from naturally distributed chest X-ray data, optimizing classification accuracy over not only the common "head" classes, but also the rare yet critical "tail" classes. The benchmark consists of two chest X-ray datasets for 19- and 20-way thorax disease classification, containing classes with as many as 53,000 and as few as 7 labeled training images.
  arXiv  Detail & Related papers  (2022-08-29T04:34:15Z)
• Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation [4.8035104863603575]
  Eye-tracking (ET) data can be collected in a non-intrusive way during the clinical workflow of a radiologist. We use ET data recorded from radiologists while dictating CXR reports to train CNNs. We extract snippets from the ET data by associating them with the dictation of keywords and use them to supervise the localization of abnormalities.
  arXiv  Detail & Related papers  (2022-07-20T09:26:29Z)
• 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)
• Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training [23.506879497561712]
  We employ a contrastive global-local dual-encoder architecture to learn concepts directly from unstructured medical reports. We evaluate our approach on the large-scale chest X-Ray datasets MIMIC-CXR, CheXpert, and ChestX-Ray14 for disease classification.
  arXiv  Detail & Related papers  (2022-05-14T21:44:05Z)
• Cross-Modal Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop [63.81818077092879]
  We propose an end-to-end semi-supervised cross-modal contrastive learning framework for medical images. We first apply an image encoder to classify the chest X-rays and to generate the image features. The radiomic features are then passed through another dedicated encoder to act as the positive sample for the image features generated from the same chest X-ray.
  arXiv  Detail & Related papers  (2021-04-11T09:16:29Z)
• Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation [61.09321488002978]
  We present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation. Our model consists of three independent network, which can effectively learn useful information from the peer networks. Our methods could achieve a significant improvement on the accuracy in segmentation tasks compared to the previous methods.
  arXiv  Detail & Related papers  (2021-04-05T15:50:16Z)
• A Relational-learning Perspective to Multi-label Chest X-ray Classification [1.4489463428855132]
  Multi-label classification of chest X-ray images is frequently performed using discriminative approaches. We propose a novel knowledge graph reformulation of multi-label classification.
  arXiv  Detail & Related papers  (2021-03-10T17:44:59Z)
• Crowdsourcing Airway Annotations in Chest Computed Tomography Images [3.862190309412109]
  Measuring airways in chest computed tomography (CT) scans is important for characterizing diseases such as cystic fibrosis. Machine learning algorithms offer an alternative, but need large sets of annotated scans for good performance. We generate image slices at known locations of airways in 24 subjects and request the crowd workers to outline the airway wall.
  arXiv  Detail & Related papers  (2020-11-20T14:54:32Z)
• Learning Invariant Feature Representation to Improve Generalization across Chest X-ray Datasets [55.06983249986729]
  We show that a deep learning model performing well when tested on the same dataset as training data starts to perform poorly when it is tested on a dataset from a different source. By employing an adversarial training strategy, we show that a network can be forced to learn a source-invariant representation.
  arXiv  Detail & Related papers  (2020-08-04T07:41:15Z)
• CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT [6.458158112222296]
  We introduce a BERT-based approach to medical image report labeling. We demonstrate superior performance of a biomedically pretrained BERT model first trained on annotations of a rule-based labeler. We find that our final model, CheXbert, is able to outperform the previous best rules-based labeler with statistical significance.
  arXiv  Detail & Related papers  (2020-04-20T09:46:40Z)
• Do Public Datasets Assure Unbiased Comparisons for Registration Evaluation? [96.53940048041248]
  We use the variogram to screen the manually annotated landmarks in two datasets used to benchmark registration in image-guided neurosurgeries. Using variograms, we identified potentially problematic cases and had them examined by experienced radiologists.
  arXiv  Detail & Related papers  (2020-03-20T20:04:47Z)

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.