Cover Image

Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism

Detector-based spectral CT offers the possibility of obtaining spectral information from which discrete acquisitions at different energy levels can be derived, yielding so-called virtual monoenergetic images (VMI). In this study, we aimed to develop a jointly optimized deep-learning framework based...

Full description

Saved in:
Bibliographic Details
Main Authors: Fink, Matthias A. (Author) , Seibold, Constantin (Author) , Kauczor, Hans-Ulrich (Author) , Stiefelhagen, Rainer (Author) , Kleesiek, Jens Philipp (Author)
Format: Article (Journal)
Language:English
Published: 13 May 2022
In: Diagnostics
Year: 2022, Volume: 12, Issue: 5, Pages: 1-11
ISSN:2075-4418
DOI:10.3390/diagnostics12051224
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.3390/diagnostics12051224
Verlag, kostenfrei, Volltext: https://www.mdpi.com/2075-4418/12/5/1224
Get full text
Author Notes:Matthias A. Fink, Constantin Seibold, Hans-Ulrich Kauczor, Rainer Stiefelhagen and Jens Kleesiek

MARC

LEADER 00000caa a2200000 c 4500
001 1806754320
003 DE-627
005 20230912110713.0
007 cr uuu---uuuuu
008 220610s2022 xx |||||o 00| ||eng c
024 7 |a 10.3390/diagnostics12051224  |2 doi 
035 |a (DE-627)1806754320 
035 |a (DE-599)KXP1806754320 
035 |a (OCoLC)1341461348 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Fink, Matthias A.  |d 1989-  |e VerfasserIn  |0 (DE-588)1193521289  |0 (DE-627)1672256518  |4 aut 
245 1 0 |a Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism  |c Matthias A. Fink, Constantin Seibold, Hans-Ulrich Kauczor, Rainer Stiefelhagen and Jens Kleesiek 
264 1 |c 13 May 2022 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 10.06.2022 
520 |a Detector-based spectral CT offers the possibility of obtaining spectral information from which discrete acquisitions at different energy levels can be derived, yielding so-called virtual monoenergetic images (VMI). In this study, we aimed to develop a jointly optimized deep-learning framework based on dual-energy CT pulmonary angiography (DE-CTPA) data to generate synthetic monoenergetic images (SMI) for improving automatic pulmonary embolism (PE) detection in single-energy CTPA scans. For this purpose, we used two datasets: our institutional DE-CTPA dataset D1, comprising polyenergetic arterial series and the corresponding VMI at low-energy levels (40 keV) with 7892 image pairs, and a 10% subset of the 2020 RSNA Pulmonary Embolism CT Dataset D2, which consisted of 161,253 polyenergetic images with dichotomous slice-wise annotations (PE/no PE). We trained a fully convolutional encoder-decoder on D1 to generate SMI from single-energy CTPA scans of D2, which were then fed into a ResNet50 network for training of the downstream PE classification task. The quantitative results on the reconstruction ability of our framework revealed high-quality visual SMI predictions with reconstruction results of 0.984 ± 0.002 (structural similarity) and 41.706 ± 0.547 dB (peak signal-to-noise ratio). PE classification resulted in an AUC of 0.84 for our model, which achieved improved performance compared to other naïve approaches with AUCs up to 0.81. Our study stresses the role of using joint optimization strategies for deep-learning algorithms to improve automatic PE detection. The proposed pipeline may prove to be beneficial for computer-aided detection systems and could help rescue CTPA studies with suboptimal opacification of the pulmonary arteries from single-energy CT scanners. 
700 1 |a Seibold, Constantin  |d 1995-  |e VerfasserIn  |0 (DE-588)1302294458  |0 (DE-627)1859284655  |4 aut 
700 1 |a Kauczor, Hans-Ulrich  |d 1962-  |e VerfasserIn  |0 (DE-588)139267123  |0 (DE-627)70327113X  |0 (DE-576)310955327  |4 aut 
700 1 |a Stiefelhagen, Rainer  |e VerfasserIn  |0 (DE-588)124347606  |0 (DE-627)598142789  |0 (DE-576)305861131  |4 aut 
700 1 |a Kleesiek, Jens Philipp  |d 1977-  |e VerfasserIn  |0 (DE-588)132998076  |0 (DE-627)530080745  |0 (DE-576)299554465  |4 aut 
773 0 8 |i Enthalten in  |t Diagnostics  |d Basel : MDPI, 2011  |g 12(2022), 5, Artikel-ID 1224, Seite 1-11  |h Online-Ressource  |w (DE-627)718627814  |w (DE-600)2662336-5  |w (DE-576)365413917  |x 2075-4418  |7 nnas  |a Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism 
773 1 8 |g volume:12  |g year:2022  |g number:5  |g elocationid:1224  |g pages:1-11  |g extent:11  |a Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism 
856 4 0 |u https://doi.org/10.3390/diagnostics12051224  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u https://www.mdpi.com/2075-4418/12/5/1224  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20220610 
993 |a Article 
994 |a 2022 
998 |g 132998076  |a Kleesiek, Jens Philipp  |m 132998076:Kleesiek, Jens Philipp  |d 50000  |e 50000PK132998076  |k 0/50000/  |p 5  |y j 
998 |g 139267123  |a Kauczor, Hans-Ulrich  |m 139267123:Kauczor, Hans-Ulrich  |d 910000  |d 911400  |e 910000PK139267123  |e 911400PK139267123  |k 0/910000/  |k 1/910000/911400/  |p 3 
998 |g 1193521289  |a Fink, Matthias A.  |m 1193521289:Fink, Matthias A.  |d 910000  |d 911400  |e 910000PF1193521289  |e 911400PF1193521289  |k 0/910000/  |k 1/910000/911400/  |p 1  |x j 
999 |a KXP-PPN1806754320  |e 4147548458 
BIB |a Y 
SER |a journal 
JSO |a {"note":["Gesehen am 10.06.2022"],"language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"title":[{"title":"Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism","title_sort":"Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism"}],"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"recId":"718627814","disp":"Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolismDiagnostics","origin":[{"dateIssuedKey":"2011","publisherPlace":"Basel","dateIssuedDisp":"2011-","publisher":"MDPI"}],"pubHistory":["1.2011 -"],"language":["eng"],"type":{"media":"Online-Ressource","bibl":"periodical"},"note":["Gesehen am 28.05.2020"],"id":{"eki":["718627814"],"issn":["2075-4418"],"zdb":["2662336-5"]},"title":[{"title_sort":"Diagnostics","title":"Diagnostics","subtitle":"open access journal"}],"part":{"volume":"12","year":"2022","text":"12(2022), 5, Artikel-ID 1224, Seite 1-11","extent":"11","issue":"5","pages":"1-11"}}],"person":[{"display":"Fink, Matthias A.","family":"Fink","given":"Matthias A.","role":"aut"},{"display":"Seibold, Constantin","role":"aut","given":"Constantin","family":"Seibold"},{"role":"aut","given":"Hans-Ulrich","family":"Kauczor","display":"Kauczor, Hans-Ulrich"},{"display":"Stiefelhagen, Rainer","given":"Rainer","role":"aut","family":"Stiefelhagen"},{"given":"Jens Philipp","role":"aut","family":"Kleesiek","display":"Kleesiek, Jens Philipp"}],"origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"13 May 2022"}],"physDesc":[{"extent":"11 S."}],"recId":"1806754320","id":{"eki":["1806754320"],"doi":["10.3390/diagnostics12051224"]},"name":{"displayForm":["Matthias A. Fink, Constantin Seibold, Hans-Ulrich Kauczor, Rainer Stiefelhagen and Jens Kleesiek"]}} 
SRT |a FINKMATTHIJOINTLYOPT1320 

Similar Items