Top

BMC Medical Informatics and Decision Making

Published in:

Open Access 01-12-2019 | Magnetic Resonance Imaging | Research article

The implementation of natural language processing to extract index lesions from breast magnetic resonance imaging reports

Authors: Yi Liu, Qing Liu, Chao Han, Xiaodong Zhang, Xiaoying Wang

Published in: BMC Medical Informatics and Decision Making | Issue 1/2019

Abstract

Background

There are often multiple lesions in breast magnetic resonance imaging (MRI) reports and radiologists usually focus on describing the index lesion that is most crucial to clinicians in determining the management and prognosis of patients. Natural language processing (NLP) has been used for information extraction from mammography reports. However, few studies have investigated NLP in breast MRI data based on free-form text. The objective of the current study was to assess the validity of our NLP program to accurately extract index lesions and their corresponding imaging features from free-form text of breast MRI reports.

Methods

This cross-sectional study examined 1633 free-form text reports of breast MRIs from 2014 to 2017. First, the NLP system was used to extract 9 features from all the lesions in the reports according to the Breast Imaging Reporting and Data System (BI-RADS) descriptors. Second, the index lesion was defined as the lesion with the largest number of imaging features. Third, we extracted the values of each imaging feature and the BI-RADS category from each index lesion. To evaluate the accuracy of our system, 478 reports were manually reviewed by two individuals. The time taken to extract data by NLP was compared with that by reviewers.

Results

The NLP system extracted 889 lesions from 478 reports. The mean number of imaging features per lesion was 6.5 ± 2.1 (range: 3–9; 95% CI: 6.362–6.638). The mean number of imaging features per index lesion was 8.0 ± 1.1 (range: 5–9; 95% CI: 7.901–8.099). The NLP system demonstrated a recall of 100.0% and a precision of 99.6% for correct identification of the index lesion. The recall and precision of NLP to correctly extract the value of imaging features from the index lesions were 91.0 and 92.6%, respectively. The recall and precision for the correct identification of the BI-RADS categories were 96.6 and 94.8%, respectively. NLP generated the total results in less than 1 s, whereas the manual reviewers averaged 4.47 min and 4.56 min per report.

Conclusions

Our NLP method successfully extracted the index lesion and its corresponding information from free-form text.

Jemal A, Bray F, Center MM, Ferlay J, Ward E, Forman D. Global cancer statistics. CA Cancer J Clin. 2011;61:69–90. https://doi.org/10.3322/caac.20107.CrossRefPubMed

Tillman GF, Orel SG, Schnall MD, Schultz DJ, Tan JE, Solin LJ. Effect of breast magnetic resonance imaging on the clinical management of women with early-stage breast carcinoma. J Clin Oncol. 2002;20(16):3413–23. https://doi.org/10.1200/JCO.2002.08.600.CrossRefPubMed

Bedrosian I, Mick R, Orel SG, Schnall M, Reynolds C, Spitz FR, et al. Changes in the surgical management of patients with breast carcinoma based on preoperative magnetic resonance imaging. Cancer. 2003;98(3):468–73. https://doi.org/10.1002/cncr.11490.CrossRefPubMed

Hylton N. Magnetic resonance imaging of the breast: opportunities to improve breast cancer management. J Clin Oncol. 2005;23(8):1678–84. https://doi.org/10.1200/JCO.2005.12.002.CrossRefPubMed

Braun M, Pölcher M, Schrading S, Zivanovic O, Kowalski T, Flucke U, et al. Influence of preoperative MRI on the surgical management of patients with operable breast cancer. Breast Cancer Res Treat. 2008;111(1):179–87. https://doi.org/10.1007/s10549-007-9767-5.CrossRefPubMed

Beatty JD, Porter BA. Contrast-enhanced breast magnetic resonance imaging: the surgical perspective. Am J Surg. 2007;193(5):600–5. https://doi.org/10.1016/j.amjsurg.2007.01.015.CrossRefPubMed

Schelfout K, Van Goethem M, Kersschot E, Colpaert C, Schelfhout AM, Leyman P, et al. Contrast-enhanced MR imaging of breast lesions and effect on treatment. Eur J Surg Oncol. 2004;30:501–7. https://doi.org/10.1016/j.ejso.2004.02.003.CrossRefPubMed

Zhang Y, Fukatsu H, Naganawa S, Satake H, Sato Y, Ohiwa M, et al. The role of contrast-enhanced MR mammography for determining candidates for breast conservation surgery. Breast Cancer. 2002;9(3):231–9.CrossRefPubMed

Esserman L, Hylton N, Yassa L, Barclay J, Frankel S, Sickles E. Utility of magnetic resonance imaging in the management of breast cancer: evidence for improved preoperative staging. J Clin Oncol. 1999;17(1):110–9. https://doi.org/10.1200/JCO.1999.17.1.110.CrossRefPubMed

10.

Burnside ES, Sickles EA, Bassett LW, Rubin DL, Lee CH, Ikeda DM, et al. The ACR BI-RADS experience: learning from history. J Am Coll Radiol. 2009;6(12):851–60. https://doi.org/10.1016/j.jacr.2009.07.023.CrossRefPubMedPubMedCentral

11.

Meystre SM, Savova GK, Kipper-Schuler KC, Hurdle JF. Extracting information from textual documents in the electronic health record: a review of recent research. Yearb Med Inform. 2008;1:128–44.

12.

Demner-Fushman D, Chapman WW, McDonald CJ. What can natural language processing do for clinical decision support? J Biomed Inform. 2009;42:760–72. https://doi.org/10.1016/j.jbi.2009.08.007.CrossRefPubMedPubMedCentral

13.

Bozkurt S, Lipson JA, Senol U, Rubin DL. Automatic abstraction of imaging features with their characteristics from mammography reports. J Am Med Inform Assoc. 2015;22:81–92. https://doi.org/10.1136/amiajnl-2014-003009.CrossRef

14.

Cai T, Giannopoulos AA, Yu S, Kelil T, Ripley B, Kumamaru KK, et al. Natural language processing technologies in radiology research and clinical applications. Radiographics. 2016;36(1):76–91. https://doi.org/10.1148/rg.2016150080.CrossRef

15.

Nadkarni PM, Ohno-Machado L, Chapman WW. Natural language processing: an introduction. J Am Med Inform Assoc. 2011;18:544–51. https://doi.org/10.1136/amiajnl-2011-000464.CrossRefPubMedPubMedCentral

16.

Gao H, Aiello Bowles EJ, Carrel D, Buist DS. Using natural language processing to extract mammographic findings. J Biomed Inform. 2015;54:77–84.CrossRefPubMedPubMedCentral

17.

Jain NL, Friedman C. Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports. Proc AMIA Annu Fall Symp. 1997:829–33.

18.

Sevenster M, van Ommering R, Qian Y. Automatically correlating clinical findings and body locations in radiology reports using MedLEE. J Digit Imaging. 2012;25:240–9. https://doi.org/10.1007/s10278-011-9411-0.CrossRefPubMed

19.

Smitherman E, Hernandez A, Stavinoha PL, Huang R, Kernie SG, Diaz-Arrastia R, Miles DK. Predicting outcomes after pediatric traumatic brain injury by early magnetic resonance imaging lesion location and volume. J Neurotrauma. 2016 1;33(1):35–48.CrossRefPubMedPubMedCentral

20.

Liu D, Scalzo F, Starkman S, Rao NM, Hinman JD, Kim D, et al. DWI lesion patterns predict outcome in stroke patients with thrombolysis. Cerebrovasc Dis. 2015;40(5–6):279–85.CrossRefPubMed

21.

Allemani C, Minicozzi P, Berrino F, Bastiaannet E, Gavin A, Galceran J, et al. Predictions of survival up to 10 years after diagnosis for European women with breast cancer in 2000-2002. Int J Cancer. 2013 May 15;132(10):2404–12.CrossRefPubMed

22.

Hripcsak G, Austin JH, Alderson PO, Friedman C. Use of natural language processing to translate clinical information from a database of 889,921 chest radiographic reports. Radiology. 2002;224(1):157–63. https://doi.org/10.1148/radiol.2241011118.CrossRefPubMed

23.

Dreyer KJ, Kalra MK, Maher MM, Hurier AM, Asfaw BA, Schultz T, et al. Application of recently developed computer algorithm for automatic classification of unstructured radiology reports: validation study. Radiology. 2005;234(2):323–9. https://doi.org/10.1148/radiol.2341040049.CrossRefPubMed

24.

Chaudhry B, Wang J, Wu S, Maglione M, Mojica W, Roth E, et al. Systematic review: impact of health information technology on quality, efficiency, and costs of medical care. Ann Intern Med. 2006;144(10):742–52.CrossRefPubMed

25.

O’Connor SD, Silverman SG, Ip IK, Maehara CK, Khorasani R. Simple cyst-appearing renal masses at unenhanced CT: can they be presumed to be benign? Radiology. 2013;269(3):793–800. https://doi.org/10.1148/radiol.13122633.CrossRefPubMed

26.

Zopf JJ, Langer JM, Boonn WW, Kim W, Zafar HM. Development of automated detection of radiology reports citing adrenal finding. J Digit Imaging. 2012;25(1):43–9. https://doi.org/10.1007/s10278-011-9425-7.CrossRefPubMed

27.

Percha B, Nassif H, Lipson J, Burnside E, Rubin D. Automatic classification of mammography reports by BI-RADS breast tissue composition class. J Am Med Inform Assoc. 2012;19(5):913–6. https://doi.org/10.1136/amiajnl-2011-000607.CrossRefPubMedPubMedCentral

28.

Forsberg D, Sjoblom E, Sunshine JL. Detection and labeling of vertebrae in MR images using deep learning with clinical annotations as training data. J Digit Imaging. 2017;30(4):406–12. https://doi.org/10.1007/s10278-017-9945-x.CrossRefPubMedPubMedCentral

Title: The implementation of natural language processing to extract index lesions from breast magnetic resonance imaging reports
Authors: Yi Liu
Qing Liu
Chao Han
Xiaodong Zhang
Xiaoying Wang
Publication date: 01-12-2019
Publisher: BioMed Central
Keywords: Magnetic Resonance Imaging
Magnetic Resonance Imaging
Breast Cancer
Breast Cancer
Breast MRI
Published in: BMC Medical Informatics and Decision Making / Issue 1/2019
Electronic ISSN: 1472-6947
DOI: https://doi.org/10.1186/s12911-019-0997-3

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

The implementation of natural language processing to extract index lesions from breast magnetic resonance imaging reports

Abstract

Background

Methods

Results

Conclusions

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2019

Effects of a computerised guideline support tool on child healthcare professionals’ response to suspicions of child abuse and neglect: a community-based intervention trial

Staff expectations for the implementation of an electronic health record system: a qualitative study using normalisation process theory

DeepFHR: intelligent prediction of fetal Acidemia using fetal heart rate signals based on convolutional neural network

Evidence-based medicine among physicians working in selected public hospitals in eastern Ethiopia: a cross-sectional study

Methods for a similarity measure for clinical attributes based on survival data analysis

Detection of medical text semantic similarity based on convolutional neural network