Skip to main content
main-content

Tipp

Weitere Kapitel dieses Buchs durch Wischen aufrufen

2018 | OriginalPaper | Buchkapitel

AutoDVT: Joint Real-Time Classification for Vein Compressibility Analysis in Deep Vein Thrombosis Ultrasound Diagnostics

verfasst von : Ryutaro Tanno, Antonios Makropoulos, Salim Arslan, Ozan Oktay, Sven Mischkewitz, Fouad Al-Noor, Jonas Oppenheimer, Ramin Mandegaran, Bernhard Kainz, Mattias P. Heinrich

Erschienen in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Verlag: Springer International Publishing

share
TEILEN

Abstract

We propose a dual-task convolutional neural network (CNN) to fully automate the real-time diagnosis of deep vein thrombosis (DVT). DVT can be reliably diagnosed through evaluation of vascular compressibility at anatomically defined landmarks in streams of ultrasound (US) images. The combined real-time evaluation of these tasks has never been achieved before. As proof-of-concept, we evaluate our approach on two selected landmarks of the femoral vein, which can be identified with high accuracy by our approach. Our CNN is able to identify if a vein fully compresses with a F1 score of more than 90% while applying manual pressure with the ultrasound probe. Fully compressible veins robustly rule out DVT and such patients do not need to be referred to further specialist examination. We have evaluated our method on 1150 5–10 s compression image sequences from 115 healthy volunteers, which results in a data set size of approximately 200k labelled images. Our method yields a theoretical inference frame rate of more than 500 fps and we thoroughly evaluate the performance of 15 possible configurations.
Literatur
1.
Zurück zum Zitat Beckman, M.G., et al.: Venous thromboembolism: a public health concern. Am. J. Prev. Med. 38(4, Supplement), S495–S501 (2010) CrossRef Beckman, M.G., et al.: Venous thromboembolism: a public health concern. Am. J. Prev. Med. 38(4, Supplement), S495–S501 (2010) CrossRef
2.
Zurück zum Zitat Stein, P.D., et al.: D-dimer for the exclusion of acute venous thrombosis and pulmonary embolism: a systematic review. Ann. Intern. Med. 140(8), 589–602 (2004) CrossRef Stein, P.D., et al.: D-dimer for the exclusion of acute venous thrombosis and pulmonary embolism: a systematic review. Ann. Intern. Med. 140(8), 589–602 (2004) CrossRef
3.
Zurück zum Zitat Schellong, S.M., et al.: Complete compression ultrasonography of the leg veins as a single test for the diagnosis of deep vein thrombosis. Thromb. Haemost. 89(2), 228–234 (2003) CrossRef Schellong, S.M., et al.: Complete compression ultrasonography of the leg veins as a single test for the diagnosis of deep vein thrombosis. Thromb. Haemost. 89(2), 228–234 (2003) CrossRef
4.
Zurück zum Zitat Guerrero, J., et al.: System for deep venous thrombosis detection using objective compression measures. IEEE Trans. Biomed. Eng. 53(5), 845–854 (2006) CrossRef Guerrero, J., et al.: System for deep venous thrombosis detection using objective compression measures. IEEE Trans. Biomed. Eng. 53(5), 845–854 (2006) CrossRef
5.
Zurück zum Zitat Friedland, N., Adam, D.: Automatic ventricular cavity boundary detection from sequential ultrasound images using simulated annealing. IEEE Trans. Med. Imaging 8(4), 344–353 (1989) CrossRef Friedland, N., Adam, D.: Automatic ventricular cavity boundary detection from sequential ultrasound images using simulated annealing. IEEE Trans. Med. Imaging 8(4), 344–353 (1989) CrossRef
6.
Zurück zum Zitat Guerrero, J., et al.: Deep venous thrombosis identification from analysis of ultrasound data. Int. J. Comput. Assist. Radiol. Surg. 10(12), 1963–1971 (2015) CrossRef Guerrero, J., et al.: Deep venous thrombosis identification from analysis of ultrasound data. Int. J. Comput. Assist. Radiol. Surg. 10(12), 1963–1971 (2015) CrossRef
7.
Zurück zum Zitat Baumgartner, C.F., et al.: SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans. Med. Imaging 36(11), 2204–2215 (2017) CrossRef Baumgartner, C.F., et al.: SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans. Med. Imaging 36(11), 2204–2215 (2017) CrossRef
10.
Zurück zum Zitat Lensing, A., et al.: A comparison of compression ultrasound with color doppler ultrasound for the diagnosis of symptomless postoperative deep vein thrombosis. Arch. Intern. Med. 157(7), 765–768 (1997) CrossRef Lensing, A., et al.: A comparison of compression ultrasound with color doppler ultrasound for the diagnosis of symptomless postoperative deep vein thrombosis. Arch. Intern. Med. 157(7), 765–768 (1997) CrossRef
11.
Zurück zum Zitat Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: International Conference on Machine Learning (ICML) (1993) Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: International Conference on Machine Learning (ICML) (1993)
12.
Zurück zum Zitat Selvaraju, R.R., et al.: Grad-Cam: visual explanations from deep networks via gradient-based localization. CoRR abs/1610.02391 v3 7(8) (2016) Selvaraju, R.R., et al.: Grad-Cam: visual explanations from deep networks via gradient-based localization. CoRR abs/1610.02391 v3 7(8) (2016)
13.
Zurück zum Zitat Crimi, A., et al.: Automatic measurement of venous pressure using B-mode ultrasound. IEEE Trans. Biomed. Eng. 63(2), 288–299 (2016) CrossRef Crimi, A., et al.: Automatic measurement of venous pressure using B-mode ultrasound. IEEE Trans. Biomed. Eng. 63(2), 288–299 (2016) CrossRef
Metadaten
Titel
AutoDVT: Joint Real-Time Classification for Vein Compressibility Analysis in Deep Vein Thrombosis Ultrasound Diagnostics
verfasst von
Ryutaro Tanno
Antonios Makropoulos
Salim Arslan
Ozan Oktay
Sven Mischkewitz
Fouad Al-Noor
Jonas Oppenheimer
Ramin Mandegaran
Bernhard Kainz
Mattias P. Heinrich
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-00934-2_100

Premium Partner