nach oben

Erschienen in:

16.05.2021 | Imaging Informatics and Artificial Intelligence

Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning

verfasst von: Yuan Li, Yang Zhang, Enlong Zhang, Yongye Chen, Qizheng Wang, Ke Liu, Hon J. Yu, Huishu Yuan, Ning Lang, Min-Ying Su

Erschienen in: European Radiology | Ausgabe 12/2021

Einloggen, um Zugang zu erhalten

Abstract

Objectives

To evaluate the performance of deep learning using ResNet50 in differentiation of benign and malignant vertebral fracture on CT.

Methods

A dataset of 433 patients confirmed with 296 malignant and 137 benign fractures was retrospectively selected from our spinal CT image database. A senior radiologist performed visual reading to evaluate six imaging features, and three junior radiologists gave diagnostic prediction. A ROI was placed on the most abnormal vertebrae, and the smallest square bounding box was generated. The input channel into ResNet50 network was 3, including the slice with its two neighboring slices. The diagnostic performance was evaluated using 10-fold cross-validation. After obtaining the malignancy probability from all slices in a patient, the highest probability was assigned to that patient to give the final diagnosis, using the threshold of 0.5.

Results

Visual features such as soft tissue mass and bone destruction were highly suggestive of malignancy; the presence of a transverse fracture line was highly suggestive of a benign fracture. The reading by three radiologists with 5, 3, and 1 year of experience achieved an accuracy of 99%, 95.2%, and 92.8%, respectively. In ResNet50 analysis, the per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85%. When the slices were combined to ve per-patient diagnosis, the sensitivity, specificity, and accuracy were 0.95, 0.80, and 88%.

Conclusion

Deep learning has become an important tool for the detection of fractures on CT. In this study, ResNet50 achieved good accuracy, which can be further improved with more cases and optimized methods for future clinical implementation.

Key Points

• Deep learning using ResNet50 can yield a high accuracy for differential diagnosis of benign and malignant vertebral fracture on CT.

• The per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85% in deep learning using ResNet50 analysis.

• The slices combined with per-patient diagnostic sensitivity, specificity, and accuracy were 0.95, 0.80, and 88% in deep learning using ResNet50 analysis.

Kendler DL, Bauer DC, Davison KS et al (2016) Vertebral fractures: clinical importance and management. Am J Med 129:221. https://doi.org/10.1016/j.amjmed.2015.09.020CrossRefPubMed

Mauch JT, Carr CM, Cloft H, Diehn FE (2018) Review of the imaging features of benign osteoporotic and malignant vertebral compression fractures. AJNR Am J Neuroradiol 39:1584–1592. https://doi.org/10.3174/ajnr.A5528

Takigawa T, Tanaka M, Sugimoto Y, Tetsunaga T, Nishida K, Ozaki T (2017) Discrimination between malignant and benign vertebral fractures using magnetic resonance imaging. Asian Spine J 11:478–483. https://doi.org/10.4184/asj.2017.11.3.478

Wong CC, McGirt MJ (2013) Vertebral compression fractures: a review of current management and multimodal therapy. J Multidiscip Healthc 6:205–214. https://doi.org/10.2147/JMDH.S31659CrossRefPubMedPubMedCentral

Schwaiger BJ, Gersing AS, Baum T, Krestan CR, Kirschke JS (2016) Distinguishing benign and malignant vertebral fractures using CT and MRI. Semin Musculoskelet Radiol 20:345–352. https://doi.org/10.1055/s-0036-1592433

Chung SW, Han SS, Lee JW et al (2018) Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop 89:468–473. https://doi.org/10.1080/17453674.2018.1453714CrossRefPubMedPubMedCentral

Gan K, Xu D, Lin Y et al (2019) Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop 90:394–400. https://doi.org/10.1080/17453674.2019.1600125CrossRefPubMedPubMedCentral

Laredo JD, Lakhdari K, Bellaiche L, B Hamze, Janklewicz P, Tubiana JM (1995) Acute vertebral collapse: CT findings in benign and malignant nontraumatic cases. Radiology 194:41–48. https://doi.org/10.1148/radiology.194.1.7997579

Kubota T, Yamada K, Ito H, Kizu O, Nishimura T (2005) High-resolution imaging of the spine using multidetector-row computed tomography: differentiation between benign and malignant vertebral compression fractures. J Comput Assist Tomogr 29:712–719. https://doi.org/10.1097/01.rct.0000175500.41836.24

10.

Lv M, Zhou Z, Tang Q et al (2020) Differentiation of usual vertebral compression fractures using CT histogram analysis as quantitative biomarkers: a proof-of-principle study. Eur J Radiol 131:109264. https://doi.org/10.1016/j.ejrad.2020.109264CrossRefPubMed

11.

Yang S, Yin B, Cao W, Feng C, Fan G, He S (2020) Diagnostic accuracy of deep learning in orthopaedic fractures: a systematic review and meta-analysis. Clin Radiol 75:713–717. https://doi.org/10.1016/j.crad.2020.05.021

12.

Kalmet P, Sanduleanu S, Primakov S et al (2020) Deep learning in fracture detection: a narrative review. Acta Orthop 91:215–220. https://doi.org/10.1080/17453674.2019.1711323CrossRefPubMedPubMedCentral

13.

Olczak J, Fahlberg N, Maki A et al (2017) Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop 88:581–586. https://doi.org/10.1080/17453674.2017.1344459CrossRefPubMedPubMedCentral

14.

Kim DH, MacKinnon T (2018) Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol 73:439–445. https://doi.org/10.1016/j.crad.2017.11.015CrossRefPubMed

15.

Adams M, Chen W, Holcdorf D, McCusker MW, Dl Howe P, Gaillard F (2019) Computer vs human: deep learning versus perceptual training for the detection of neck of femur fractures. J Med Imaging Radiat Oncol 63:27–32. https://doi.org/10.1111/1754-9485.12828

16.

Badgeley MA, Zech JR, Oakden-Rayner L et al (2019) Deep learning predicts hip fracture using confounding patient and healthcare variables. NPJ Digit Med 2:31. https://doi.org/10.1038/s41746-019-0105-1CrossRefPubMedPubMedCentral

17.

Raghavendra, S UBN, Gudigar A, Rajendra Acharya U (2018) Automated system for the detection of thoracolumbar fracture using a CNN architecture. Future Generation Computer Systems: S167739X-S17321544X

18.

Pranata YD, Wang KC, Wang JC et al (2019) Deep learning and SURF for automated classification and detection of calcaneus fractures in CT images. Comput Methods Programs Biomed 171:27–37. https://doi.org/10.1016/j.cmpb.2019.02.006CrossRefPubMed

19.

Tomita N, Cheung YY, Hassanpour S (2018) Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput Biol Med 98:8–15. https://doi.org/10.1016/j.compbiomed.2018.05.011CrossRefPubMed

20.

Chu C, Belavý DL, Armbrecht G, Bansmann M, Felsenberg D, Zheng G (2015) Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method. PLoS One 10:e143327. https://doi.org/10.1371/journal.pone.0143327

21.

Lessmann N, van Ginneken B, de Jong PA, Išgum I (2019) Iterative fully convolutional neural networks for automatic vertebra segmentation and identification. Med Image Anal 53:142–155. https://doi.org/10.1016/j.media.2019.02.005

22.

Lffler MT, Sekuboyina A, Jacob A et al (2020) A vertebral segmentation dataset with fracture grading. Radiology: Artificial Intelligence. https://doi.org/10.1148/ryai.2020190138

23.

Sekuboyina A, Bayat A, Husseini M et al (2020) VerSe: A vertebrae labelling and segmentation benchmark for multi-detector CT images. https://arxiv.org/abs/2001.09193

24.

Fang Y, Li W, Chen X et al (2021) Opportunistic osteoporosis screening in multi-detector CT images using deep convolutional neural networks. Eur Radiol 31(4):1831–1842. https://doi.org/10.1007/s00330-020-07312-8CrossRefPubMed

25.

Kingma DP BJ (2015) Adam: a method for stochastic optimization. International Conference on Learning Representations: International Conference on Learning Representations, 1–13

26.

Torres C, Hammond I (2016) Computed tomography and magnetic resonance imaging in the differentiation of osteoporotic fractures from neoplastic metastatic fractures. J Clin Densitom 19:63–69. https://doi.org/10.1016/j.jocd.2015.08.008CrossRefPubMed

27.

Li Z, Guan M, Sun D, Xu Y, Li F, Xiong W (2018) A novel MRI- and CT-based scoring system to differentiate malignant from osteoporotic vertebral fractures in Chinese patients. BMC Musculoskelet Disord 19:406. https://doi.org/10.1186/s12891-018-2331-0

28.

Romeo V, Ugga L, Stanzione A, Cocozza S, Cuocolo R, Brunetti A (2019) Differential diagnosis of benign and malignant vertebral compression fractures using conventional and advanced MRI techniques. BJR Open 1:20180033. https://doi.org/10.1259/bjro.20180033

29.

Korbar B, Olofson AM, Miraflor AP et al (2017) Deep learning for classification of colorectal polyps on whole-slide images. J Pathol Inform 8:30. https://doi.org/10.4103/jpi.jpi_34_17CrossRefPubMedPubMedCentral

30.

Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117. https://doi.org/10.1016/j.neunet.2014.09.003CrossRefPubMed

31.

Lee JG, Jun S, Cho YW et al (2017) Deep learning in medical imaging: general overview. Korean J Radiol 18:570–584. https://doi.org/10.3348/kjr.2017.18.4.570CrossRefPubMedPubMedCentral

32.

LeCun Y KKFC (2010) Convolutional networks and applications in vision. International Symposium on Circuits and Systems (ISCAS 2010): 253–256

33.

Husseini M, Sekuboyina A, Loeffler M, Navarro F, Menze BH, Kirschke JS (2020) Grading loss: a fracture grade-based metric loss for vertebral fracture detection. Medical Image Computing and Computer Assisted Intervention (MICCAI 2020):733–742

34.

Wang KC, Jeanmenne A, Weber GM, Thawait SK, Carrino JA (2011) An online evidence-based decision support system for distinguishing benign from malignant vertebral compression fractures by magnetic resonance imaging feature analysis. J Digit Imaging 24:507–515. https://doi.org/10.1007/s10278-010-9316-3

35.

Bauer JS, Müller D, Ambeka A (2006) Detection of osteoporotic vertebral fractures using multidetector CT. Osteoporos Int 17(4):608–615. https://doi.org/10.1007/s00198-005-0023-8CrossRefPubMed

Titel: Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning
verfasst von: Yuan Li
Yang Zhang
Enlong Zhang
Yongye Chen
Qizheng Wang
Ke Liu
Hon J. Yu
Huishu Yuan
Ning Lang
Min-Ying Su
Publikationsdatum: 16.05.2021
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 12/2021
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-021-08014-5

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning