Literature DB >> 30049723

Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT.

P D Chang1,2, E Kuoy1, J Grinband3, B D Weinberg4, M Thompson1, R Homo1, J Chen5, H Abcede6, M Shafie6, L Sugrue2, C G Filippi7, M-Y Su1, W Yu6, C Hess2, D Chow8.   

Abstract

BACKGROUND AND
PURPOSE: Convolutional neural networks are a powerful technology for image recognition. This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, epidural/subdural, and subarachnoid hemorrhages on noncontrast CT.
MATERIALS AND METHODS: This study was performed in 2 phases. First, a training cohort of all NCCTs acquired at a single institution between January 1, 2017, and July 31, 2017, was used to develop and cross-validate a custom hybrid 3D/2D mask ROI-based convolutional neural network architecture for hemorrhage evaluation. Second, the trained network was applied prospectively to all NCCTs ordered from the emergency department between February 1, 2018, and February 28, 2018, in an automated inference pipeline. Hemorrhage-detection accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value were assessed for full and balanced datasets and were further stratified by hemorrhage type and size. Quantification was assessed by the Dice score coefficient and the Pearson correlation.
RESULTS: A 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages) were used in this study. Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative-predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set. Dice scores for intraparenchymal hemorrhage, epidural/subdural hemorrhage, and SAH were 0.931, 0.863, and 0.772, respectively.
CONCLUSIONS: A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.
© 2018 by American Journal of Neuroradiology.

Entities:  

Mesh:

Year:  2018        PMID: 30049723      PMCID: PMC6128745          DOI: 10.3174/ajnr.A5742

Source DB:  PubMed          Journal:  AJNR Am J Neuroradiol        ISSN: 0195-6108            Impact factor:   3.825


  22 in total

1.  Hematoma growth is a determinant of mortality and poor outcome after intracerebral hemorrhage.

Authors:  S M Davis; J Broderick; M Hennerici; N C Brun; M N Diringer; S A Mayer; K Begtrup; T Steiner
Journal:  Neurology       Date:  2006-04-25       Impact factor: 9.910

2.  Multi-scale Convolutional Neural Networks for Lung Nodule Classification.

Authors:  Wei Shen; Mu Zhou; Feng Yang; Caiyun Yang; Jie Tian
Journal:  Inf Process Med Imaging       Date:  2015

3.  Computer-aided assessment of head computed tomography (CT) studies in patients with suspected traumatic brain injury.

Authors:  Esther L Yuh; Alisa D Gean; Geoffrey T Manley; Andrew L Callen; Max Wintermark
Journal:  J Neurotrauma       Date:  2008-10       Impact factor: 5.269

4.  Critical care management of acute intracerebral hemorrhage.

Authors:  Joshua N Goldstein; Aaron J Gilson
Journal:  Curr Treat Options Neurol       Date:  2011-04       Impact factor: 3.598

5.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

Authors:  Shaoqing Ren; Kaiming He; Ross Girshick; Jian Sun
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2016-06-06       Impact factor: 6.226

6.  Development and Validation of an Automatic Segmentation Algorithm for Quantification of Intracerebral Hemorrhage.

Authors:  Moritz Scherer; Jonas Cordes; Alexander Younsi; Yasemin-Aylin Sahin; Michael Götz; Markus Möhlenbruch; Christian Stock; Julian Bösel; Andreas Unterberg; Klaus Maier-Hein; Berk Orakcioglu
Journal:  Stroke       Date:  2016-10-04       Impact factor: 7.914

7.  A multi-resolution approach for spinal metastasis detection using deep Siamese neural networks.

Authors:  Juan Wang; Zhiyuan Fang; Ning Lang; Huishu Yuan; Min-Ying Su; Pierre Baldi
Journal:  Comput Biol Med       Date:  2017-03-27       Impact factor: 4.589

8.  Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique.

Authors:  K N Bhanu Prakash; Shi Zhou; Tim C Morgan; Daniel F Hanley; Wieslaw L Nowinski
Journal:  Int J Comput Assist Radiol Surg       Date:  2012-09       Impact factor: 2.924

Review 9.  Surgical management of acute epidural hematomas.

Authors:  M Ross Bullock; Randall Chesnut; Jamshid Ghajar; David Gordon; Roger Hartl; David W Newell; Franco Servadei; Beverly C Walters; Jack E Wilberger
Journal:  Neurosurgery       Date:  2006-03       Impact factor: 4.654

Review 10.  Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: a systematic review and meta-analysis.

Authors:  Charlotte Jj van Asch; Merel Ja Luitse; Gabriël Je Rinkel; Ingeborg van der Tweel; Ale Algra; Catharina Jm Klijn
Journal:  Lancet Neurol       Date:  2010-01-05       Impact factor: 44.182

View more
  40 in total

1.  Convolutional Neural Network for Automated FLAIR Lesion Segmentation on Clinical Brain MR Imaging.

Authors:  M T Duong; J D Rudie; J Wang; L Xie; S Mohan; J C Gee; A M Rauschecker
Journal:  AJNR Am J Neuroradiol       Date:  2019-07-25       Impact factor: 3.825

Review 2.  Technical and clinical overview of deep learning in radiology.

Authors:  Daiju Ueda; Akitoshi Shimazaki; Yukio Miki
Journal:  Jpn J Radiol       Date:  2018-12-01       Impact factor: 2.374

3.  Artificial Intelligence in Neuroradiology: Current Status and Future Directions.

Authors:  Y W Lui; P D Chang; G Zaharchuk; D P Barboriak; A E Flanders; M Wintermark; C P Hess; C G Filippi
Journal:  AJNR Am J Neuroradiol       Date:  2020-07-30       Impact factor: 3.825

4.  Distributed deep learning across multisite datasets for generalized CT hemorrhage segmentation.

Authors:  Samuel W Remedios; Snehashis Roy; Camilo Bermudez; Mayur B Patel; John A Butman; Bennett A Landman; Dzung L Pham
Journal:  Med Phys       Date:  2019-11-19       Impact factor: 4.071

5.  Classification of Aortic Dissection and Rupture on Post-contrast CT Images Using a Convolutional Neural Network.

Authors:  Robert J Harris; Shwan Kim; Jerry Lohr; Steve Towey; Zeljko Velichkovich; Tim Kabachenko; Ian Driscoll; Brian Baker
Journal:  J Digit Imaging       Date:  2019-12       Impact factor: 4.056

6.  Fully automated intracranial ventricle segmentation on CT with 2D regional convolutional neural network to estimate ventricular volume.

Authors:  Trevor J Huff; Parker E Ludwig; David Salazar; Justin A Cramer
Journal:  Int J Comput Assist Radiol Surg       Date:  2019-07-26       Impact factor: 2.924

7.  Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI.

Authors:  Andreas M Rauschecker; Jeffrey D Rudie; Long Xie; Jiancong Wang; Michael Tran Duong; Emmanuel J Botzolakis; Asha M Kovalovich; John Egan; Tessa C Cook; R Nick Bryan; Ilya M Nasrallah; Suyash Mohan; James C Gee
Journal:  Radiology       Date:  2020-04-07       Impact factor: 11.105

8.  Improving Sensitivity on Identification and Delineation of Intracranial Hemorrhage Lesion Using Cascaded Deep Learning Models.

Authors:  Junghwan Cho; Ki-Su Park; Manohar Karki; Eunmi Lee; Seokhwan Ko; Jong Kun Kim; Dongeun Lee; Jaeyoung Choe; Jeongwoo Son; Myungsoo Kim; Sukhee Lee; Jeongho Lee; Changhyo Yoon; Sinyoul Park
Journal:  J Digit Imaging       Date:  2019-06       Impact factor: 4.056

9.  Development of a deep learning model to identify hyperdense MCA sign in patients with acute ischemic stroke.

Authors:  Yuki Shinohara; Noriyuki Takahashi; Yongbum Lee; Tomomi Ohmura; Toshibumi Kinoshita
Journal:  Jpn J Radiol       Date:  2019-10-31       Impact factor: 2.374

10.  Impact of Upstream Medical Image Processing on Downstream Performance of a Head CT Triage Neural Network.

Authors:  Sarah M Hooper; Jared A Dunnmon; Matthew P Lungren; Domenico Mastrodicasa; Daniel L Rubin; Christopher Ré; Adam Wang; Bhavik N Patel
Journal:  Radiol Artif Intell       Date:  2021-04-28
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.