aqora

Quantum Lung Segmentation: QCU-Net Applied to Chest X-Ray Images

Haoqi He, Mingkai Huang

Lecture notes in computer scienceJan 1, 20240 citations

Hybrid quantum-classical convolutional neural networks for multiclass lung X-ray image classification

Ariiq Islam Alfajri, Tony Ibnu Sumaryada, Sitti Yani +3 more

Journal of Radiation Research and Applied SciencesJan 13, 20263 citations

Expanding the Horizon: Enabling Hybrid Quantum Transfer Learning for Long-Tailed Chest X-Ray Classification

Skylar Chan, Pranav Kulkarni, Paul Hyunsoo Yi +1 more

Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small datasets due to limited access to quantum hardware and computationally expensive simulations. To that end, we implemented a Jax-based framework that enables the simulation of medium-sized qubit architectures with significant improvements in wall-clock time over current software offerings. We evaluated the performance of our Jax-based framework in terms of efficiency and performance for hybrid quantum transfer learning for long-tailed classification across 8, 14, and 19 disease labels using large-scale CXR datasets. The Jax-based framework resulted in up to a58% and 95% speed-up compared to PyTorch and TensorFlow implementations, respectively. However, compared to CML, QML demonstrated slower convergence and an average AUROC of 0.70, 0.73, and 0.74 for the classification of 8, 14, and 19 CXR disease labels. In comparison, the CML models had an average AUROC of 0.77, 0.78, and 0.80 respectively. In conclusion, our work presents an accessible implementation of hybrid quantum transfer learning for long-tailed CXR classification with a computationally efficient Jax-based framework.Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small datasets due to limited access to quantum hardware and computationally expensive simulations. To that end, we implemented a Jax-based framework that enables the simulation of medium-sized qubit architectures with significant improvements in wall-clock time over current software offerings. We evaluated the performance of our Jax-based framework in terms of efficiency and performance for hybrid quantum transfer learning for long-tailed classification across 8, 14, and 19 disease labels using large-scale CXR datasets. The Jax-based framework resulted in up to a58% and 95% speed-up compared to PyTorch and TensorFlow implementations, respectively. However, compared to CML, QML demonstrated slower convergence and an average AUROC of 0.70, 0.73, and 0.74 for the classification of 8, 14, and 19 CXR disease labels. In comparison, the CML models had an average AUROC of 0.77, 0.78, and 0.80 respectively. In conclusion, our work presents an accessible implementation of hybrid quantum transfer learning for long-tailed CXR classification with a computationally efficient Jax-based framework.

arXiv:2405.00156IEEE International Conference on Quantum Computing and Engineering (QCE)Sep 15, 20242 citations

A classical–quantum convolutional neural network for detecting pneumonia from chest radiographs

Viraj Kulkarni, Sanjesh Pawale, Amit T Kharat

arXiv:2202.10452Neural Computing and ApplicationsApr 12, 202328 citations

Hybrid Quantum-Classical Machine Learning for Medical Image Classification under Noisy Conditions

SAI CHANDU KUNDARAPU

This research presents a hybrid quantum-classical machine learning framework for medical image classification under noisy conditions using chest X-ray images. A classical Convolutional Neural Network (CNN) model and a hybrid quantum-classical model integrating variational quantum circuits were implemented using PyTorch and PennyLane. Gaussian noise was introduced during validation to evaluate model robustness under image perturbations. Experimental results demonstrated comparable performance between the classical CNN and the hybrid quantum-classical model, highlighting the potential of Quantum Machine Learning (QML) for future healthcare AI applications. GitHub Repository:https://github.com/saichandukundarapu/quantum-covid-detectionThis research presents a hybrid quantum-classical machine learning framework for medical image classification under noisy conditions using chest X-ray images. A classical Convolutional Neural Network (CNN) model and a hybrid quantum-classical model integrating variational quantum circuits were implemented using PyTorch and PennyLane. Gaussian noise was introduced during validation to evaluate model robustness under image perturbations. Experimental results demonstrated comparable performance between the classical CNN and the hybrid quantum-classical model, highlighting the potential of Quantum Machine Learning (QML) for future healthcare AI applications. GitHub Repository:https://github.com/saichandukundarapu/quantum-covid-detection

May 11, 20260 citations

Quantum and classical machine learning for the classification of non-small-cell lung cancer patients

Siddhant Jain, Jalal Ziauddin, Paul Leonchyk +2 more

SN Applied SciencesMay 16, 202063 citations

Hybrid framework for respiratory lung diseases detection based on classical CNN and quantum classifiers from chest X-rays

Related papers

Hybrid framework for respiratory lung diseases detection based on classical CNN and quantum classifiers from chest X-rays

Related papers