Literature DB >> 32193036

Detection and localization of distal radius fractures: Deep learning system versus radiologists.

Christian Blüthgen1, Anton S Becker2, Ilaria Vittoria de Martini2, Andreas Meier2, Katharina Martini2, Thomas Frauenfelder2.   

Abstract

PURPOSE: To evaluate a deep learning based image analysis software for the detection and localization of distal radius fractures.
METHOD: A deep learning system (DLS) was trained on 524 wrist radiographs (166 showing fractures). Performance was tested on internal (100 radiographs, 42 showing fractures) and external test sets (200 radiographs, 100 showing fractures). Single and combined views of the radiographs were shown to DLS and three readers. Readers were asked to indicate fracture location with regions of interest (ROI). The DLS yielded scores (range 0-1) and a heatmap. Detection performance was expressed as AUC, sensitivity and specificity at the optimal threshold and compared to radiologists' performance. Heatmaps were compared to radiologists' ROIs.
RESULTS: The DLS showed excellent performance on the internal test set (AUC 0.93 (95% confidence interval (CI) 0.82-0.98) - 0.96 (0.87-1.00), sensitivity 0.81 (0.58-0.95) - 0.90 (0.70-0.99), specificity 0.86 (0.68-0.96) - 1.0 (0.88-1.0)). DLS performance decreased on the external test set (AUC 0.80 (0.71-0.88) - 0.89 (0.81-0.94), sensitivity 0.64 (0.49-0.77) - 0.92 (0.81-0.98), specificity 0.60 (0.45-0.74) - 0.90 (0.78-0.97)). Radiologists' performance was comparable on internal data (sensitivity 0.71 (0.48-0.89) - 0.95 (0.76-1.0), specificity 0.52 (0.32-0.71) - 0.97 (0.82-1.0)) and better on external data (sensitivity 0.88 (0.76-0.96) - 0.98 (0.89-1.0), specificities 0.66 (0.51-0.79) - 1.0 (0.93-1.0), p < 0.05). In over 90%, the areas of peak activation aligned with radiologists' annotations.
CONCLUSIONS: The DLS was able to detect and localize wrist fractures with a performance comparable to radiologists, using only a small dataset for training.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Mesh:

Year:  2020        PMID: 32193036     DOI: 10.1016/j.ejrad.2020.108925

Source DB:  PubMed          Journal:  Eur J Radiol        ISSN: 0720-048X            Impact factor:   3.528


  12 in total

1.  Deep learning based detection of intracranial aneurysms on digital subtraction angiography: A feasibility study.

Authors:  Nicolin Hainc; Manoj Mannil; Vaia Anagnostakou; Hatem Alkadhi; Christian Blüthgen; Lorenz Wacht; Andrea Bink; Shakir Husain; Zsolt Kulcsár; Sebastian Winklhofer
Journal:  Neuroradiol J       Date:  2020-07-07

2.  Detecting Distal Radial Fractures from Wrist Radiographs Using a Deep Convolutional Neural Network with an Accuracy Comparable to Hand Orthopedic Surgeons.

Authors:  Takeshi Suzuki; Satoshi Maki; Takahiro Yamazaki; Hiromasa Wakita; Yasunari Toguchi; Manato Horii; Tomonori Yamauchi; Koui Kawamura; Masaaki Aramomi; Hiroshi Sugiyama; Yusuke Matsuura; Takeshi Yamashita; Sumihisa Orita; Seiji Ohtori
Journal:  J Digit Imaging       Date:  2021-12-15       Impact factor: 4.056

3.  External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review.

Authors:  Alice C Yu; Bahram Mohajer; John Eng
Journal:  Radiol Artif Intell       Date:  2022-05-04

4.  Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis.

Authors:  Rachel Y L Kuo; Conrad Harrison; Terry-Ann Curran; Benjamin Jones; Alexander Freethy; David Cussons; Max Stewart; Gary S Collins; Dominic Furniss
Journal:  Radiology       Date:  2022-03-29       Impact factor: 29.146

5.  A pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX) for machine learning.

Authors:  Eszter Nagy; Michael Janisch; Franko Hržić; Erich Sorantin; Sebastian Tschauner
Journal:  Sci Data       Date:  2022-05-20       Impact factor: 8.501

6.  Deep learning detection of subtle fractures using staged algorithms to mimic radiologist search pattern.

Authors:  Mark Ren; Paul H Yi
Journal:  Skeletal Radiol       Date:  2021-02-12       Impact factor: 2.199

7.  Critical evaluation of deep neural networks for wrist fracture detection.

Authors:  Abu Mohammed Raisuddin; Elias Vaattovaara; Mika Nevalainen; Marko Nikki; Elina Järvenpää; Kaisa Makkonen; Pekka Pinola; Tuula Palsio; Arttu Niemensivu; Osmo Tervonen; Aleksei Tiulpin
Journal:  Sci Rep       Date:  2021-03-16       Impact factor: 4.379

8.  RiFNet: Automated rib fracture detection in postmortem computed tomography.

Authors:  Victor Ibanez; Samuel Gunz; Svenja Erne; Eric J Rawdon; Garyfalia Ampanozi; Sabine Franckenberg; Till Sieberth; Raffael Affolter; Lars C Ebert; Akos Dobay
Journal:  Forensic Sci Med Pathol       Date:  2021-10-28       Impact factor: 2.007

9.  Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy: ensemble decision-making with antero-posterior and lateral radiographs.

Authors:  Yutoku Yamada; Satoshi Maki; Shunji Kishida; Haruki Nagai; Junnosuke Arima; Nanako Yamakawa; Yasushi Iijima; Yuki Shiko; Yohei Kawasaki; Toshiaki Kotani; Yasuhiro Shiga; Kazuhide Inage; Sumihisa Orita; Yawara Eguchi; Hiroshi Takahashi; Takeshi Yamashita; Shohei Minami; Seiji Ohtori
Journal:  Acta Orthop       Date:  2020-08-12       Impact factor: 3.717

10.  AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size.

Authors:  Patrick Tobler; Joshy Cyriac; Balazs K Kovacs; Verena Hofmann; Raphael Sexauer; Fabiano Paciolla; Bram Stieltjes; Felix Amsler; Anna Hirschmann
Journal:  Eur Radiol       Date:  2021-03-19       Impact factor: 5.315

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.