ChemicalQDeviceNext Gen Neuroradiology Algorithms, Insight
Dear Healthcare Colleague, my name is Kevin Kawchak, and I am the Founder CEO of ChemicalQDevice. Today is March 17th, 2023 for "Next Generation Neuroradiology Quantum Algorithms for Brain Disorders"
In 2021, articles were published which featured 4 Qubit Quantum Algorithms run on simulators to improve classification, segmentation, and/or prediction of disease with CT medical scans. Houssein, E. H., et al. in an arXiv paper utilized a Hybrid Quantum-Classical Convolutional Neural Network to achieve improved balanced accuracy, precision, F1-measure, and AUC-ROC scores. Also, Sengupta, K., et al. in BMC Medical Informatics and Decision Making utilized a Quantum Neural Network to outperform a conventional deep learning model for a specific task. [1-2]
In 2022, Shahwar, T., et al. in Electronics published a 4 Qubit Quantum Algorithm that ran on a Pennylane simulator for binary classification of Alzheimer's Neuroimages from Kaggle. Their hybrid network included a conventional ResNet34 architecture. With addition of the quantum circuit - small improvements were made over other authors utilizing conventional DemNet or BellCNN architectures. [3-5]
In 2023, 3 publications incorporated modified 4 Qubit quantum algorithms run on simulators to improve binary or quaternary classification of neuroimages. Kim, R in arXiv published that their Hybrid Quantum-Classical Convolutional Neural Network with ResNet18 outperformed a conventional CNN. In addition, Shahwar, T. et al. in Mathematics utilized an ADNI dataset, AlexNet, with additional epochs and feature vector size improvements to slightly improve on other authors' Alzheimer's studies that utilized DemNet, and also Parkinson's studies that utilized a CNN and a 3D-CNN. [6-9]
Also in 2023, quaternary classifications with a Kaggle Brain Tumor Dataset with a 4 qubit algorithm as part of a hybrid classical-quantum network was conducted by Dong, Y., et al. in Journal of Applied Physics with average accuracy improvements of 5% versus not incorporating the quantum circuit. [10]
In summary, the 6 papers mentioned utilized a small 4 qubit quantum circuit typically run on quantum simulators as part of a hybrid network that provides a platform for now incorporating real quantum computers. Looking forward, Neuroimage quality, acquisition speed, and size reduction will likely improve due to organizations that support Quantum Sensing and Computing such as Fermilab, Harvard University, and University of Chicago. [11-16]
Leading quantum computing manufacturers such as Google, IBM, and IonQ will also improve the likelihood of commercial quantum computers that will be able to process Larger Datasets, and allow for Larger Kernel sizes. These developments are important for classifications, predictions, and other analyses in Neuroradiology. [17-19]
Quantum computers with more qubits and less noise will allow for complex quantum algorithms to run faster than being simulated on classical computers. The effective results of practical quantum computers forecasted by NSF in 2023, will be Deeper Neural Networks. Conventional Computing has already had a larger impact in this area of Machine Learning on the Medical Field. [20]
In addition, wider circuits with more qubits will open up possibilities for greater quantum entanglement, and hence exponentially more information that will likely have a large impact computing large volumes of medical images.
References are available in the comments below. Have a productive rest of your day. Smile at Intervals.
3/17/23 "Next Generation Neuroradiology Quantum Algorithms for Brain Disorders" References[1] https://arxiv.org/abs/2102.06535[2] https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01588-6[3] https://www.mdpi.com/2079-9292/11/5/721[4] https://ieeexplore.ieee.org/abstract/document/9459692[5] https://www.sciencedirect.com/science/article/abs/pii/S0003682X21000347[6] https://arxiv.org/pdf/2301.12505.pdf[7] https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0047714[8] https://link.springer.com/chapter/10.1007/978-3-319-59740-9_32[9] https://www.mdpi.com/2227-7390/11/2/376[10] https://aip.scitation.org/doi/10.1063/5.0138021[11] https://news.fnal.gov/2022/07/nyu-langone-plans-to-partner-with-fermilabs-sqms-to-advance-mri-analysis/[12] https://quantum.fnal.gov/research/quantum-sensing-and-applications/[13] https://scholar.harvard.edu/alexeibyl/molecular-qubit-control-and-single-molecule-mri[14] https://news.harvard.edu/gazette/tag/quantum-computing/[15] https://pme.uchicago.edu/news/building-better-quantum-sensors[16] https://cs.uchicago.edu/research/quantum-computing/[17] https://www.nature.com/articles/d41586-023-00536-w[18] https://www.youtube.com/watch?v=AQjKUN8PORM[19] https://ionq.com/news/networked-quantum-computers-ionq-acquires-assets-of-entangled-networks[20] https://nsf.gov/news/factsheets/Factsheet_Quantum-proof7_508.pdf
Created by Kevin Kawchak Founder CEO ChemicalQDevice2023 San Diego, CaliforniaHealthcare Innovation
In 2021, articles were published which featured 4 Qubit Quantum Algorithms run on simulators to improve classification, segmentation, and/or prediction of disease with CT medical scans. Houssein, E. H., et al. in an arXiv paper utilized a Hybrid Quantum-Classical Convolutional Neural Network to achieve improved balanced accuracy, precision, F1-measure, and AUC-ROC scores. Also, Sengupta, K., et al. in BMC Medical Informatics and Decision Making utilized a Quantum Neural Network to outperform a conventional deep learning model for a specific task. [1-2]
In 2022, Shahwar, T., et al. in Electronics published a 4 Qubit Quantum Algorithm that ran on a Pennylane simulator for binary classification of Alzheimer's Neuroimages from Kaggle. Their hybrid network included a conventional ResNet34 architecture. With addition of the quantum circuit - small improvements were made over other authors utilizing conventional DemNet or BellCNN architectures. [3-5]
In 2023, 3 publications incorporated modified 4 Qubit quantum algorithms run on simulators to improve binary or quaternary classification of neuroimages. Kim, R in arXiv published that their Hybrid Quantum-Classical Convolutional Neural Network with ResNet18 outperformed a conventional CNN. In addition, Shahwar, T. et al. in Mathematics utilized an ADNI dataset, AlexNet, with additional epochs and feature vector size improvements to slightly improve on other authors' Alzheimer's studies that utilized DemNet, and also Parkinson's studies that utilized a CNN and a 3D-CNN. [6-9]
Also in 2023, quaternary classifications with a Kaggle Brain Tumor Dataset with a 4 qubit algorithm as part of a hybrid classical-quantum network was conducted by Dong, Y., et al. in Journal of Applied Physics with average accuracy improvements of 5% versus not incorporating the quantum circuit. [10]
In summary, the 6 papers mentioned utilized a small 4 qubit quantum circuit typically run on quantum simulators as part of a hybrid network that provides a platform for now incorporating real quantum computers. Looking forward, Neuroimage quality, acquisition speed, and size reduction will likely improve due to organizations that support Quantum Sensing and Computing such as Fermilab, Harvard University, and University of Chicago. [11-16]
Leading quantum computing manufacturers such as Google, IBM, and IonQ will also improve the likelihood of commercial quantum computers that will be able to process Larger Datasets, and allow for Larger Kernel sizes. These developments are important for classifications, predictions, and other analyses in Neuroradiology. [17-19]
Quantum computers with more qubits and less noise will allow for complex quantum algorithms to run faster than being simulated on classical computers. The effective results of practical quantum computers forecasted by NSF in 2023, will be Deeper Neural Networks. Conventional Computing has already had a larger impact in this area of Machine Learning on the Medical Field. [20]
In addition, wider circuits with more qubits will open up possibilities for greater quantum entanglement, and hence exponentially more information that will likely have a large impact computing large volumes of medical images.
References are available in the comments below. Have a productive rest of your day. Smile at Intervals.
3/17/23 "Next Generation Neuroradiology Quantum Algorithms for Brain Disorders" References[1] https://arxiv.org/abs/2102.06535[2] https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01588-6[3] https://www.mdpi.com/2079-9292/11/5/721[4] https://ieeexplore.ieee.org/abstract/document/9459692[5] https://www.sciencedirect.com/science/article/abs/pii/S0003682X21000347[6] https://arxiv.org/pdf/2301.12505.pdf[7] https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0047714[8] https://link.springer.com/chapter/10.1007/978-3-319-59740-9_32[9] https://www.mdpi.com/2227-7390/11/2/376[10] https://aip.scitation.org/doi/10.1063/5.0138021[11] https://news.fnal.gov/2022/07/nyu-langone-plans-to-partner-with-fermilabs-sqms-to-advance-mri-analysis/[12] https://quantum.fnal.gov/research/quantum-sensing-and-applications/[13] https://scholar.harvard.edu/alexeibyl/molecular-qubit-control-and-single-molecule-mri[14] https://news.harvard.edu/gazette/tag/quantum-computing/[15] https://pme.uchicago.edu/news/building-better-quantum-sensors[16] https://cs.uchicago.edu/research/quantum-computing/[17] https://www.nature.com/articles/d41586-023-00536-w[18] https://www.youtube.com/watch?v=AQjKUN8PORM[19] https://ionq.com/news/networked-quantum-computers-ionq-acquires-assets-of-entangled-networks[20] https://nsf.gov/news/factsheets/Factsheet_Quantum-proof7_508.pdf
Created by Kevin Kawchak Founder CEO ChemicalQDevice2023 San Diego, CaliforniaHealthcare Innovation