Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays
Cardiovascular diseases are among the major health problems that are likely to benefit from promising developments in quantum machine learning for medical imaging. The chest X-ray (CXR), a widely used modality, can reveal cardiomegaly, even when performed primarily for a non-cardiological indication...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Journal of Imaging |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-433X/9/7/128 |
_version_ | 1797588774164627456 |
---|---|
author | Pierre Decoodt Tan Jun Liang Soham Bopardikar Hemavathi Santhanam Alfaxad Eyembe Begonya Garcia-Zapirain Daniel Sierra-Sosa |
author_facet | Pierre Decoodt Tan Jun Liang Soham Bopardikar Hemavathi Santhanam Alfaxad Eyembe Begonya Garcia-Zapirain Daniel Sierra-Sosa |
author_sort | Pierre Decoodt |
collection | DOAJ |
description | Cardiovascular diseases are among the major health problems that are likely to benefit from promising developments in quantum machine learning for medical imaging. The chest X-ray (CXR), a widely used modality, can reveal cardiomegaly, even when performed primarily for a non-cardiological indication. Based on pre-trained DenseNet-121, we designed hybrid classical–quantum (CQ) transfer learning models to detect cardiomegaly in CXRs. Using Qiskit and PennyLane, we integrated a parameterized quantum circuit into a classic network implemented in PyTorch. We mined the CheXpert public repository to create a balanced dataset with 2436 posteroanterior CXRs from different patients distributed between cardiomegaly and the control. Using k-fold cross-validation, the CQ models were trained using a state vector simulator. The normalized global effective dimension allowed us to compare the trainability in the CQ models run on Qiskit. For prediction, ROC AUC scores up to 0.93 and accuracies up to 0.87 were achieved for several CQ models, rivaling the classical–classical (CC) model used as a reference. A trustworthy Grad-CAM++ heatmap with a hot zone covering the heart was visualized more often with the QC option than that with the CC option (94% vs. 61%, <i>p</i> < 0.001), which may boost the rate of acceptance by health professionals. |
first_indexed | 2024-03-11T00:56:48Z |
format | Article |
id | doaj.art-7c1d66579e114e1eadeb6cd53e9607ba |
institution | Directory Open Access Journal |
issn | 2313-433X |
language | English |
last_indexed | 2024-03-11T00:56:48Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Imaging |
spelling | doaj.art-7c1d66579e114e1eadeb6cd53e9607ba2023-11-18T19:56:53ZengMDPI AGJournal of Imaging2313-433X2023-06-019712810.3390/jimaging9070128Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-raysPierre Decoodt0Tan Jun Liang1Soham Bopardikar2Hemavathi Santhanam3Alfaxad Eyembe4Begonya Garcia-Zapirain5Daniel Sierra-Sosa6Cardiologie, Centre Hospitalo-Universitaire Brugmann, Faculté de Médecine, Université Libre de Bruxelles, Place Van Gehuchten 4, 1020 Brussels, BelgiumSchool of Computer Science, Digital Health and Innovations Impact Lab, Taylor’s University, Subang Jaya 47500, Selangor, MalaysiaDepartment of Electronics and Telecommunication Engineering, College of Engineering Pune, Pune 411005, IndiaFaculty of Graduate Studies and Research, Saint Mary’s University, 923 Robie Street, Halifax, NS B3H 3C3, CanadaFaculty of Engineering, Kyoto University of Advanced Science (KUAS), Ukyo-ku, Kyoto 615-8577, JapaneVIDA Research Group, Department of Engineering, Deusto University, 48007 Bilbao, SpainComputer Science and Information Technologies Department, Hood College, 401 Rosemont Ave., Frederick, MD 21702, USACardiovascular diseases are among the major health problems that are likely to benefit from promising developments in quantum machine learning for medical imaging. The chest X-ray (CXR), a widely used modality, can reveal cardiomegaly, even when performed primarily for a non-cardiological indication. Based on pre-trained DenseNet-121, we designed hybrid classical–quantum (CQ) transfer learning models to detect cardiomegaly in CXRs. Using Qiskit and PennyLane, we integrated a parameterized quantum circuit into a classic network implemented in PyTorch. We mined the CheXpert public repository to create a balanced dataset with 2436 posteroanterior CXRs from different patients distributed between cardiomegaly and the control. Using k-fold cross-validation, the CQ models were trained using a state vector simulator. The normalized global effective dimension allowed us to compare the trainability in the CQ models run on Qiskit. For prediction, ROC AUC scores up to 0.93 and accuracies up to 0.87 were achieved for several CQ models, rivaling the classical–classical (CC) model used as a reference. A trustworthy Grad-CAM++ heatmap with a hot zone covering the heart was visualized more often with the QC option than that with the CC option (94% vs. 61%, <i>p</i> < 0.001), which may boost the rate of acceptance by health professionals.https://www.mdpi.com/2313-433X/9/7/128medical imagingchest X-raydiagnosiscardiovascular diseasesheart failurecardiomegaly |
spellingShingle | Pierre Decoodt Tan Jun Liang Soham Bopardikar Hemavathi Santhanam Alfaxad Eyembe Begonya Garcia-Zapirain Daniel Sierra-Sosa Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays Journal of Imaging medical imaging chest X-ray diagnosis cardiovascular diseases heart failure cardiomegaly |
title | Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays |
title_full | Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays |
title_fullStr | Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays |
title_full_unstemmed | Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays |
title_short | Hybrid Classical–Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays |
title_sort | hybrid classical quantum transfer learning for cardiomegaly detection in chest x rays |
topic | medical imaging chest X-ray diagnosis cardiovascular diseases heart failure cardiomegaly |
url | https://www.mdpi.com/2313-433X/9/7/128 |
work_keys_str_mv | AT pierredecoodt hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays AT tanjunliang hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays AT sohambopardikar hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays AT hemavathisanthanam hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays AT alfaxadeyembe hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays AT begonyagarciazapirain hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays AT danielsierrasosa hybridclassicalquantumtransferlearningforcardiomegalydetectioninchestxrays |