Calcification Detection in Intravascular Ultrasound (IVUS) Images Using Transfer Learning Based MultiSVM model
Cardiovascular disease serves as the leading cause of death worldwide. Calcification detection is considered an important factor in cardiovascular diseases. Currently, medical practitioners visually inspect the presence of calcification using intravascular ultrasound (IVUS) images. The study aims to detect the extent of calcification as belonging to class I, II as mild calcification, and class III, IV as dense calcification from IVUS images acquired at 40 MHz. To detect calcification, the features were extracted using improved AlexNet architecture and then were fed into machine learning classifiers. The experiments were carried out using 14 real IVUS pullbacks of 10 patients. Experimental results show that the combination of traditional machine learning with deep learning approaches significantly improves accuracy. The results show that support vector machines outperform all other classifiers. The proposed model is compared with two other pre-trained models GoogLeNet (98.8%), SqueezeNet (99.2%), and exhibits considerable improvement in classification accuracy (99.8%). In the future other models such as Vision Transformers could be explored with additional feature selection methods such as ReliefF, PSO, ACO, etc. to improve the overall accuracy of diagnosis.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:45 |
---|---|
Enthalten in: |
Ultrasonic imaging - 45(2023), 3 vom: 17. Mai, Seite 136-150 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Arora, Priyanka [VerfasserIn] |
---|
Links: |
---|
Themen: |
Convolutional neural network |
---|
Anmerkungen: |
Date Completed 26.04.2023 Date Revised 27.06.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1177/01617346231164574 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM355567482 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM355567482 | ||
003 | DE-627 | ||
005 | 20231226064624.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1177/01617346231164574 |2 doi | |
028 | 5 | 2 | |a pubmed24n1185.xml |
035 | |a (DE-627)NLM355567482 | ||
035 | |a (NLM)37052393 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Arora, Priyanka |e verfasserin |4 aut | |
245 | 1 | 0 | |a Calcification Detection in Intravascular Ultrasound (IVUS) Images Using Transfer Learning Based MultiSVM model |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 26.04.2023 | ||
500 | |a Date Revised 27.06.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Cardiovascular disease serves as the leading cause of death worldwide. Calcification detection is considered an important factor in cardiovascular diseases. Currently, medical practitioners visually inspect the presence of calcification using intravascular ultrasound (IVUS) images. The study aims to detect the extent of calcification as belonging to class I, II as mild calcification, and class III, IV as dense calcification from IVUS images acquired at 40 MHz. To detect calcification, the features were extracted using improved AlexNet architecture and then were fed into machine learning classifiers. The experiments were carried out using 14 real IVUS pullbacks of 10 patients. Experimental results show that the combination of traditional machine learning with deep learning approaches significantly improves accuracy. The results show that support vector machines outperform all other classifiers. The proposed model is compared with two other pre-trained models GoogLeNet (98.8%), SqueezeNet (99.2%), and exhibits considerable improvement in classification accuracy (99.8%). In the future other models such as Vision Transformers could be explored with additional feature selection methods such as ReliefF, PSO, ACO, etc. to improve the overall accuracy of diagnosis | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a convolutional neural network | |
650 | 4 | |a coronary artery calcification | |
650 | 4 | |a intravascular ultrasound | |
650 | 4 | |a pre-trained networks | |
650 | 4 | |a support vector machine | |
700 | 1 | |a Singh, Parminder |e verfasserin |4 aut | |
700 | 1 | |a Girdhar, Akshay |e verfasserin |4 aut | |
700 | 1 | |a Vijayvergiya, Rajesh |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Ultrasonic imaging |d 1993 |g 45(2023), 3 vom: 17. Mai, Seite 136-150 |w (DE-627)NLM001622978 |x 1096-0910 |7 nnns |
773 | 1 | 8 | |g volume:45 |g year:2023 |g number:3 |g day:17 |g month:05 |g pages:136-150 |
856 | 4 | 0 | |u http://dx.doi.org/10.1177/01617346231164574 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 45 |j 2023 |e 3 |b 17 |c 05 |h 136-150 |