Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Tytuł pozycji:

Automated processing of social media content for radiologists: applied deep learning to radiological content on twitter during COVID-19 pandemic.

Tytuł:
Automated processing of social media content for radiologists: applied deep learning to radiological content on twitter during COVID-19 pandemic.
Autorzy:
Khurana S; M.S. Ramaiah Medical College, M.S. Ramaiah Nagar, Bangalore, Karnataka, 560054, India.
Chopra R; Trauma Imaging Research and Innovation Center, Department of Radiology, Brigham and Women's Hospital, 75 Francis St, Boston, MA, 02115, USA.
Khurana B; Trauma Imaging Research and Innovation Center, Department of Radiology, Brigham and Women's Hospital, 75 Francis St, Boston, MA, 02115, USA. .; Divison of Emergency Radiology, Department of Radiology, Brigham and Women's Hospital, 75 Francis St, Boston, MA, 02115, USA. .
Źródło:
Emergency radiology [Emerg Radiol] 2021 Jun; Vol. 28 (3), pp. 477-483. Date of Electronic Publication: 2021 Jan 18.
Typ publikacji:
Journal Article
Język:
English
Imprint Name(s):
Publication: New York, NY : Springer-Verlag New York Inc
Original Publication: Baltimore, MD. : Williams & Wilkins, c1994-
MeSH Terms:
Deep Learning*
Social Media*
COVID-19/*diagnostic imaging
Pneumonia, Viral/*diagnostic imaging
COVID-19/epidemiology ; Humans ; Pandemics ; Pneumonia, Viral/epidemiology ; SARS-CoV-2 ; Software
References:
RSNA Responds to COVID-19 outbreak with rapid publication of original research and images. (n.d.). Retrieved September 19, 2020, from https://www.rsna.org/news/2020/April/Rapid-Publication-COVID-19-Research.
COVID-19 Resources. (n.d.). Retrieved September 28, 2020, from https://www.rsna.org/covid-19.
Learner for the vision applications | fastai. (n.d.). Retrieved September 28, 2020, from https://docs.fast.ai/vision.learner.
Hawkins CM, Duszak R, Rawson JV (2014) Social media in radiology: early trends in Twitter microblogging at radiology’s largest international meeting. Journal of the American College of Radiology: JACR 11(4):387–390. https://doi.org/10.1016/j.jacr.2013.07.015. (PMID: 10.1016/j.jacr.2013.07.01524139963)
Currie G, Woznitza N, Bolderston A, Westerink A, Watson J, Beardmore C, di Prospero L, McCuaig C, Nightingale J (2017) Twitter Journal Club in Medical Radiation Science. Journal of Medical Imaging and Radiation Sciences 48(1):83–89. https://doi.org/10.1016/j.jmir.2016.09.001. (PMID: 10.1016/j.jmir.2016.09.00131047215)
Miles RC, Patel AK (2019) The radiology twitterverse: a starter’s guide to utilization and success. J Am Coll Radiol 16(9):1225–1231. https://doi.org/10.1016/j.jacr.2019.03.014. (PMID: 10.1016/j.jacr.2019.03.01431092350)
Newman N (n.d.) Reuters Institute Digital News Report 2020:112.
Kumar A, Singh JP, Dwivedi YK, Rana NP (2020) A deep multi-modal neural network for informative twitter content classification during emergencies. Ann Oper Res. https://doi.org/10.1007/s10479-020-03514-x.
Chen, T., Lu, D., Kan, M.-Y., & Cui, P. (2013). Understanding and classifying image tweets. In Proceedings of the 21st ACM international conference on Multimedia - MM ‘13 (pp. 781–784). Presented at the 21st ACM international conference, Barcelona, Spain: ACM Press. https://doi.org/10.1145/2502081.2502203.
Edo-Osagie O, Smith G, Lake I, Edeghere O, Iglesia BDL (2019) Twitter mining using semi-supervised classification for relevance filtering in syndromic surveillance. PLoS One 14(7):e0210689. https://doi.org/10.1371/journal.pone.0210689. (PMID: 10.1371/journal.pone.0210689313188856638773)
3 reasons why radiology leaders need to be on Twitter or risk falling behind. (n.d.). Retrieved September 19, 2020, from https://www.radiologybusiness.com/topics/leadership/radiology-leaders-need-be-twitter.
Gonzalez SM, Gadbury-Amyot CC (2016) Using Twitter for teaching and learning in an oral and maxillofacial radiology course. J Dent Educ 80(2):149–155. (PMID: 10.1002/j.0022-0337.2016.80.2.tb06070.x)
Rosenberg H, Syed S, Rezaie S (2020) The Twitter pandemic: the critical role of Twitter in the dissemination of medical information and misinformation during the COVID-19 pandemic. Canadian Journal of Emergency Medicine 22(4):418–421. https://doi.org/10.1017/cem.2020.361. (PMID: 10.1017/cem.2020.36132248871)
Ranginwala S, Towbin AJ (2018) Use of social media in radiology education. J Am Coll Radiol 15(1):190–200. https://doi.org/10.1016/j.jacr.2017.09.010. (PMID: 10.1016/j.jacr.2017.09.01029102536)
Contributed Indexing:
Keywords: CNN; COVID-19; Image classification; Social media; Twitter
Entry Date(s):
Date Created: 20210118 Date Completed: 20210524 Latest Revision: 20210524
Update Code:
20211214
PubMed Central ID:
PMC7811945
DOI:
10.1007/s10140-020-01885-z
PMID:
33459907
Czasopismo naukowe
Purpose: The purpose of this study was to develop an automated process to analyze multimedia content on Twitter during the COVID-19 outbreak and classify content for radiological significance using deep learning (DL).
Materials and Methods: Using Twitter search features, all tweets containing keywords from both "radiology" and "COVID-19" were collected for the period January 01, 2020 up to April 24, 2020. The resulting dataset comprised of 8354 tweets. Images were classified as (i) images with text (ii) radiological content (e.g., CT scan snapshots, X-ray images), and (iii) non-medical content like personal images or memes. We trained our deep learning model using Convolutional Neural Networks (CNN) on training dataset of 1040 labeled images drawn from all three classes. We then trained another DL classifier for segmenting images into categories based on human anatomy. All software used is open-source and adapted for this research. The diagnostic performance of the algorithm was assessed by comparing results on a test set of 1885 images.
Results: Our analysis shows that in COVID-19 related tweets on radiology, nearly 32% had textual images, another 24% had radiological content, and 44% were not of radiological significance. Our results indicated a 92% accuracy in classifying images originally labeled as chest X-ray or chest CT and a nearly 99% accurate classification of images containing medically relevant text. With larger training dataset and algorithmic tweaks, the accuracy can be further improved.
Conclusion: Applying DL on rich textual images and other metadata in tweets we can process and classify content for radiological significance in real time.

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies

Prześlij opinię

Twoje opinie są dla nas bardzo ważne i mogą być niezwykle pomocne w pokazaniu nam, gdzie możemy dokonać ulepszeń. Bylibyśmy bardzo wdzięczni za poświęcenie kilku chwil na wypełnienie krótkiego formularza.

Formularz