ChemicalQDeviceIncorporation of New Quantum Frameworks
Dear Healthcare Colleague, my name is Kevin Kawchak, and I am the Founder CEO of ChemicalQDevice. Today is March 10th, 2023 for "Incorporation of New Quantum Frameworks into Existing QNN Neuroradiology Advancements" 
Deep Neural Networks have seen an increase in adoption for Medical Use due to conventional hardware improvements in the early 2000s. The first Deep Learning algorithm approved by FDA in 2017 was developed by Arterys Incorporated, and analyzed blood flow from DICOM-compliant MRIs. [1-2]
In recent years, emerging quantum computing techniques have seen an increase in applications utilizing MRI Brain tumor or neurodegenerative databases such as Kaggle and ADNI. The authors of these papers published quantum-classical hybrid networks that improved quaternary or binary classification of accuracies by up to 5% , than if the quantum networks were omitted. [3-6]
These preliminary neuroradiology papers utilizing quantum simulators have opened the door for additional innovations to be incorporated, especially as real hardware emerges. 
The June 2022 "Efficient Quantum Image Classification Using Single Qubit Encoding" Paper by Easom-McCaldin, P., et al. published in IEEE offers potential to further improve quantum-classical classification accuracy. By taking advantage of the rich amount of information possessed by a single quantum bit, the authors' results across three common datasets are promising for the Medical Imaging community. [7]
In addition, Scalable Quantum Convolutional Neural Networks by Baek, H., et al. in 2022 utilized algorithms running on quantum simulators that required less qubits, improved training, and allowed for the processing of larger 2D or 3D image sizes. [8-9] These new networks appear appropriate for emerging real quantum computers that are both improving in number of qubits and decreasing in system noise. [10-11] In addition, 3D Voxelized Brain PET/MRI datasets may be appropriate for Classifying Input images should these sQCNNs becomes more adopted. [12]
Lastly, the 2022 Paper titled "Projection Valued Measure-based Quantum Machine Learning for Multi-Class Classification" by Yun, W.J., et al. offers hope for scalability in QML - by utilizing the "nature of probability amplitude in quantum statistical mechanics". Compared to State of The Art methods, their PVM-based QML developments exhibited 42% better performance, assuming no more than 6 qubits were used. [13]
References are available in the comments below. Have a productive rest of your day. 
Smile at Intervals.
3/10/23 "Incorporation of New Quantum Frameworks into Existing QNN Neuroradiology Advancements" References[1] https://www.giejournal.org/article/S0016-5107(20)34466-7/fulltext[2] https://www.accessdata.fda.gov/cdrh_docs/pdf16/K163253.pdf[3] https://aip.scitation.org/doi/10.1063/5.0138021[4] https://www.mdpi.com/2079-9292/11/5/721[5] https://arxiv.org/pdf/2301.12505.pdf[6] https://www.mdpi.com/2227-7390/11/2/376[7] https://ieeexplore.ieee.org/document/9798852[8] https://arxiv.org/abs/2209.12372[9] https://arxiv.org/abs/2210.09728[10] https://www.nature.com/articles/d41586-023-00536-w[11] https://www.quantinuum.com/news/quantum-volume-reaches-5-digits-for-the-first-time-5-perspectives-on-what-it-means-for-quantum-computing[12] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4306573/[13] https://arxiv.org/abs/2210.16731
Created by Kevin Kawchak Founder CEO ChemicalQDevice2023 San Diego, CaliforniaHealthcare Innovation