computer-vision

Fracture detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in fracture-detection

Trend

Dataset

Best Model

Actions

GRAZPEDWRI-DX

Libraries

i

Use these libraries to find fracture-detection models and implementations

Datasets

GRAZPEDWRI-DX

Subtasks

No subtasks available.

Most implemented papers

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Quoc V. Le, Mingxing Tan•Thu May 23 2019

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.

22147

Content

0

Paper Graph

Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm

Rui Ju, Weiming Cai•Mon Apr 10 2023

Data augmentation is used to improve the model performance of YOLOv8 algorithm (the latest version of You Only Look Once) on a pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX), which is a public dataset, and the model has reached the state-of-the-art (SOTA) mean average precision (mAP 50).

201 0

Paper Graph

Interpreting and Correcting Medical Image Classification with PIP-Net

Christin Seifert, Meike Nauta, J. H. Hegeman, J. Geerdink, Jörg Schlötterer, M. V. Keulen•Tue Jul 18 2023

This paper is the first to show that humans can manually correct the reasoning of PIP-Net by directly disabling undesired prototypes, and conclude that part-prototype models are promising for medical applications due to their interpretability and potential for advanced model debugging.

15 0

Paper Graph

Deep Omni-Supervised Learning for Rib Fracture Detection From Chest Radiology Images

Hao Chen, Huangjing Lin, P. Heng, Zhizhong Chai, Luyang Luo•Thu Jun 22 2023

A novel omni-supervised object detection network, ORF-Netv2, to leverage as much available supervision as possible and consistently outperforms other competitive label-efficient methods over various scenarios, showing a promising framework for label-efficient fracture detection.

13 0

Paper Graph

A Simple Framework Uniting Visual In-context Learning with Masked Image Modeling to Improve Ultrasound Segmentation

Yuyue Zhou, B. Felfeliyan, Shrimanti Ghosh, Jessica Knight, Fatima Alves-Pereira, Christopher Keen, Jessica Küpper, A. Hareendranathan, Jacob L. Jaremko•Wed Feb 21 2024

A new simple visual ICL method called SimICL is proposed, combining visual ICL pairing images with masked image modeling (MIM) designed for self-supervised learning, which could dramatically decrease the human expert time required for image labeling compared to conventional approaches, and enhance the real-world use of AI assistance in US image analysis.

0 0

Paper Graph

YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection

Ruikang Ju, Jen-Shiun Chiang, Chun-Tse Chien, Kuang-Yi Chou, Enkaer Xieerke•Tue Feb 13 2024

This work proposes YOLOv8-AM, which incorporates the attention modules into the YOLOv8 architecture, and employs four different attention modules, ResBlock with Convolutional Block Attention Module (ResCBAM), Shuffle Attention, Efficient Channel Attention, and ResBlock with Global Attention Mechanism (ResGAM), to improve the model architecture.

36 0

Paper Graph

Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detection

Ruikang Ju, Jen-Shiun Chiang, Chun-Tse Chien, Chia-Min Lin•Tue Jul 02 2024

The YOLOv8+GC model for fracture detection is proposed, which is an improved version of the YOLOv8 model with the GC block, which increases the mean average precision calculated at intersection over union threshold of 0.5 and achieves the state-of-the-art (SOTA) level.

9 0

Paper Graph

Domain Specific Transporter Framework to Detect Fractures in Ultrasound

A. Hareendranathan, Arpan Tripathi, M. Panicker, Jack Zhang, Naveenjyote Boora, J. Jaremko•Tue Jun 08 2021

An unsupervised, domain-specific transporter framework is proposed to identify relevant key points from ultrasound scans providing a concise geometric representation highlighting regions with high structural variation, and is able to accurately detect 180/250 bone regions.

0 0

Paper Graph

Critical evaluation of deep neural networks for wrist fracture detection

Aleksei Tiulpin, A. M. Raisuddin, Elias Vaattovaara, M. Nevalainen, Marko Nikki, Elina Järvenpää, Kaisa Makkonen, P. Pinola, Tuula Palsio, Arttu Niemensivu, O. Tervonen•Mon Mar 15 2021

A state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection—DeepWrist is developed and analyzed, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT.

75 0

Paper Graph

Adding a benchmark result helps the community track progress.