Critical Evaluation of Deep Neural Networks for Wrist Fracture Detection

• URL: http://arxiv.org/abs/2012.02577v2
• Date: Fri, 5 Mar 2021 08:32:54 GMT
• Title: Critical Evaluation of Deep Neural Networks for Wrist Fracture Detection
• Authors: Abu Mohammed Raisuddin, Elias Vaattovaara, Mika Nevalainen, Marko Nikki, Elina J\"arvenp\"a\"a, Kaisa Makkonen, Pekka Pinola, Tuula Palsio, Arttu Niemensivu, Osmo Tervonen, Aleksei Tiulpin
• Abstract summary: Wrist Fracture is the most common type of fracture with a high incidence rate. Recent advances in the field of Deep Learning (DL) have shown that wrist fracture detection can be automated using Convolutional Neural Networks. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, has a substantially lower performance on the challenging test set.
• Score: 1.0617212070722408
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection -- DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set -- average precision of 0.99 (0.99-0.99) vs 0.64 (0.46-0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98-0.99) vs 0.84 (0.72-0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems.

Related papers

• Unsupervised dMRI Artifact Detection via Angular Resolution Enhancement and Cycle Consistency Learning [45.3610312584439]
  Diffusion magnetic resonance imaging (dMRI) is a crucial technique in neuroimaging studies, allowing for the non-invasive probing of the underlying structures of brain tissues. Clinical dMRI data is susceptible to various artifacts during acquisition, which can lead to unreliable subsequent analyses. We propose a novel unsupervised deep learning framework called $textbfU$n $textbfd$MRI $textbfA$rtifact $textbfD$etection via $textbfA$ngular Resolution Enhancement and $textbfC$ycle
  arXiv  Detail & Related papers  (2024-09-24T08:56:10Z)
• Enhancing Wrist Fracture Detection with YOLO [3.2049746597433746]
  This study employs state-of-the-art single-stage deep neural network-based detection models YOLOv5, YOLOv6, YOLOv7, and YOLOv8 to detect wrist abnormalities. We found that these YOLO models outperform the commonly used two-stage detection algorithm, Faster R-CNN, in fracture detection.
  arXiv  Detail & Related papers  (2024-07-17T14:21:53Z)
• Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge [66.86170104167608]
  The RibFrac Challenge provides a benchmark dataset of over 5,000 rib fractures from 660 CT scans. During the MICCAI 2020 challenge period, 243 results were evaluated, and seven teams were invited to participate in the challenge summary. The analysis revealed that several top rib fracture detection solutions achieved performance comparable or even better than human experts.
  arXiv  Detail & Related papers  (2024-02-14T18:18:33Z)
• Fast and Robust Femur Segmentation from Computed Tomography Images for Patient-Specific Hip Fracture Risk Screening [48.46841573872642]
  We propose a deep neural network for fully automated, accurate, and fast segmentation of the proximal femur from CT. Our method is apt for hip-fracture risk screening, bringing us one step closer to a clinically viable option for screening at-risk patients for hip-fracture susceptibility.
  arXiv  Detail & Related papers  (2022-04-20T16:16:16Z)
• Interpretable Vertebral Fracture Quantification via Anchor-Free Landmarks Localization [0.04925906256430176]
  Vertebral body compression fractures are early signs of osteoporosis. We propose a new two-step algorithm to localize the vertebral column in 3D CT images. We then detect individual vertebrae and quantify fractures in 2D simultaneously.
  arXiv  Detail & Related papers  (2022-04-14T08:31:25Z)
• Multi-Label Classification of Thoracic Diseases using Dense Convolutional Network on Chest Radiographs [0.0]
  We propose a multi-label disease prediction model that allows the detection of more than one pathology at a given test time. Our proposed model achieved the highest AUC score of 0.896 for the condition Cardiomegaly.
  arXiv  Detail & Related papers  (2022-02-08T00:43:57Z)
• StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder [48.2010192865749]
  Unsupervised anomaly detection (UAD) can learn a data distribution from an unlabelled dataset of healthy subjects and then be applied to detect out of distribution samples. This research proposes a compact version of the "context-encoding" VAE (ceVAE) model, combined with pre and post-processing steps, creating a UAD pipeline (StRegA) The proposed pipeline achieved a Dice score of 0.642$pm$0.101 while detecting tumours in T2w images of the BraTS dataset and 0.859$pm$0.112 while detecting artificially induced anomalies.
  arXiv  Detail & Related papers  (2022-01-31T14:27:35Z)
• Universal Lesion Detection in CT Scans using Neural Network Ensembles [5.341593824515018]
  A prerequisite for lesion sizing is their detection, as it promotes the downstream assessment of tumor spread. We propose the use of state-of-the-art detection neural networks to flag suspicious lesions present in the NIH DeepLesion dataset for sizing. We construct an ensemble of the best detection models to localize lesions for sizing with a precision of 65.17% and sensitivity of 91.67% at 4 FP per image.
  arXiv  Detail & Related papers  (2021-11-09T00:11:01Z)
• Vision Transformers for femur fracture classification [59.99241204074268]
  The Vision Transformer (ViT) was able to correctly predict 83% of the test images. Good results were obtained in sub-fractures with the largest and richest dataset ever.
  arXiv  Detail & Related papers  (2021-08-07T10:12:42Z)
• Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images [58.85481248101611]
  We propose a novel PCa detection network that incorporates a lesion-level cost-sensitive loss and an additional slice-level loss based on a lesion-to-slice mapping function. Our experiments based on 290 clinical patients concludes that 1) The lesion-level FNR was effectively reduced from 0.19 to 0.10 and the lesion-level FPR was reduced from 1.03 to 0.66 by changing the lesion-level cost.
  arXiv  Detail & Related papers  (2021-06-04T09:51:27Z)
• Deep Sequential Learning for Cervical Spine Fracture Detection on Computed Tomography Imaging [20.051649556262216]
  We propose a deep convolutional neural network (DCNN) with a bidirectional long-short term memory (BLSTM) layer for the automated detection of cervical spine fractures in CT axial images. We used an annotated dataset of 3,666 CT scans (729 positive and 2,937 negative cases) to train and validate the model. The validation results show a classification accuracy of 70.92% and 79.18% on the balanced (104 positive and 104 negative cases) and imbalanced (104 positive and 419 negative cases) test datasets, respectively.
  arXiv  Detail & Related papers  (2020-10-26T04:36:29Z)

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.