量子神经网络在肺结节诊断中的应用

       量子机器学习，是机器学习和量子计算的交叉学科，主要研究利用量 子计算优势提高机器学习对大数据的处理、分析和挖掘能力，在化学和医 学医药等领域有广阔的发展前景。量子计算已经可以模拟氢化锂等小分子 的能量和特性，从而进行建模，帮助全方位的理解化学反应能量学，进而 推动化学领域的发展。在医学医药领域，肺癌是全球范围内死亡率最高的 癌症类型，肺结节是肺癌的早期症状之一，及时准确的检测和治疗肺结节， 对于有效降低肺癌患者的死亡率具有至关重要的作用。

      本文主要研究量子机器学习算法在医学领域的应用问题，研究重点是 肺结节原始 CT 图像分类任务，并采用经典的数据预处理手段，使用多种神 经网络模型进行分类。在量子领域，搭建了变分量子电路实现数据预处理 工作，提出并构建了全连接量子神经网络模型，取得了 87.5%的分类精度。 针对全连接量子神经网络在原始 CT 图像尺寸裁剪过程中特征损失过多的问 题，提出并构建了量子卷积神经网络模型，通过量子卷积过程，提取其关 键特征，并合理设置卷积核等模型参数以减少训练的时间复杂度，最终得 到了 90.36%的分类精度，优于一般的经典算法。证明了量子卷积这种随机 非线性特征有助于提高模型精度。本文重点探究量子领域的机器学习问题， 包括构建量子电路实现经典数据到量子态的高效转换，构建可以快速训练 的量子神经网络，在实验模拟等方面探究机器学习领域的量子优势。

        Quantum machine learning is an interdisciplinary subject of machine learning and quantum computing. It mainly studies using the advantages of quantum computing to improve the processing, analysis and mining ability of machine learning on big data. It has broad development prospects in chemistry, medicine and other fields. Quantum computing can now simulate the energy and properties of small molecules such as lithium hydride for modeling, helping to fully understand the energetics of chemical reactions, and thus advancing the field of chemistry. In the field of medicine and medicine, lung cancer is the type of cancer with the highest mortality rate worldwide. Lung nodules are one of the early symptoms of lung cancer. Timely and accurate detection and treatment of lung nodules play a crucial role in effectively reducing the mortality of patients with lung cancer.

        This paper mainly studies the application of quantum machine learning algorithm in the medical field, focusing on the classification task of the original CT images of pulmonary nodules, and adopts classical data preprocessing means and a variety of neural network models for classification. In the quantum field, a variable component subcircuit is built to realize data preprocessing, and a fully connected quantum neural network model is proposed and constructed, achieving a classification accuracy of 87.5%. To solve the problem of excessive feature loss in the original CT image size tailoring process of fully connected quantum neural network, a quantum convolutional neural network model is constructed. Through the quantum convolution process, key features are extracted, and model parameters such as the convolutional kernel are set reasonably to reduce the time complexity of training. Finally, the classification accuracy of 90.36% is obtained, which is better than the general classical algorithm. It is proved that the random nonlinear feature of quantum convolution is helpful to improve the accuracy of the model. This paper focuses on exploring machine learning issues in the quantum field, including the construction of quantum circuits to realize efficient conversion of classical data to quantum states, the construction of quantum neural networks that can be rapidly trained, and the exploration of quantum advantages in the field of machine learning in aspects of experimental simulation.

[1]FEYNMAN R P. Simulating physics with computers[J]. International Journal of Theoretical Physics, 1982, 21(6-7): 467-88.
[2]CAO Y, ROMERO J, OLSON J P, et al. Quantum Chemistry in the Age of Quantum Computing[J]. Chemical Reviews, 2019, 119(19): 10856-915.
[3]JOZSA R. Quantum factoring, discrete logarithms, and the hidden subgroup problem[J]. Computing in Science & Engineering, 2001, 3(2): 34-43.
[4]WILLSCH M, WILLSCH D, JIN F, et al. Benchmarking the quantum approximate optimization algorithm[J]. Quantum Information Processing, 2020, 19(7).
[5]LLOYD S, MOHSENI M, REBENTROST P. Quantum principal component analysis[J]. Nature Physics, 2014, 10(9): 631-3.
[6]REBENTROST P, MOHSENI M, LLOYD S. Quantum Support Vector Machine for Big Data Classification[J]. Physical Review Letters, 2014, 113(13).
[7]SHAHI F, REZAKHANI A T. Fidelity-based supervised and unsupervised learning for binary classification of quantum states[J]. The European Physical Journal Plus, 2021, 136(3).
[8]SAWERWAIN M, WRBLEWSKI M. Application of Quantum k-NN and Grover's Algorithms for Recommendation Big-Data System[M]. Springer International Publishing. 2019: 235-44.
[9]GIOVANNETTI V, LLOYD S, MACCONE L. Quantum Random Access Memory[J]. Physical Review Letters, 2008, 100(16).
[10]ARUNACHALAM S, GHEORGHIU V, JOCHYM-O’CONNOR T, et al. On the robustness of bucket brigade quantum RAM[J]. New Journal of Physics, 2015, 17(12): 123010.
[11]HUANG H Y, BROUGHTON M, MOHSENI M, et al. Power of data in quantum machine learning[J]. Nature Communications, 2021, 12(1).
[12]LOOMIS D, HUANG W, CHEN G S. The International Agency for Research on Cancer (IARC) evaluation of the carcinogenicity of outdoor air pollution: focus on China [J]. Chinese Journal of Cancer, 2014, 33(4): 189-96.
[13]BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries (vol 68, pg 394, 2018) [J]. Ca-a Cancer Journal for Clinicians, 2020, 70(4): 313-.
[14]WEI Y, JIA T, LIN M X, et al. Autonomous Detection of Solitary Pulmonary Nodules on CT Images for Computer-Aided Diagnosis[C]//Proceedings of the 23rd Chinese Control and Decision Conference, Mianyang, PEOPLES R CHINA, F May 23-25, 2011.
[15]DIAO L, GUO H Y, ZHOU Y, et al. BRIDGING THE GAP BETWEEN OUTPUTS: DOMAIN ADAPTATION FOR LUNG CANCER IHC SEGMENTATION[C]//Proceedings of the IEEE International Conference on Image Processing (ICIP), Electra Network, F Sep 19-22, 2021.
[16]MCWILLIAMS A, TAMMEMAGI M C, MAYO J R, et al. Probability of Cancer in Pulmonary Nodules Detected on First Screening CT [J]. New England Journal of Medicine, 2013, 369(10): 910-9.
[17]SMIRNOV E A, TIMOSHENKO D M, ANDRIANOV S N. Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks[C]//Proceedings of the 2nd AASRI Conference on Computational Intelligence and Bioinformatics (CIB), South Korea, F Dec 27-28, 2013.
[18]SHAFIQ M, GU Z Q. Deep Residual Learning for Image Recognition: A Survey [J]. Applied Sciences-Basel, 2022, 12(18).
[19]NIBALI A, HE Z, WOLLERSHEIM D. Pulmonary nodule classification with deep residual networks [J]. International Journal of Computer Assisted Radiology and Surgery, 2017, 12(10): 1799-808.
[20]ZHANG B H, QI S L, MONKAM P, et al. Ensemble Learners of Multiple Deep CNNs for Pulmonary Nodules Classification Using CT Images [J]. IEEE Access, 2019, 7: 110358-71.
[21]LIMA T J B, DE ARAIUJO F H D, DE CARVALHO A O, et al. Evaluation of data balancing techniques in 3D CNNs for the classification of pulmonary nodules in CT images[C]//Proceedings of the 25th IEEE Symposium on Computers and Communications (ISCC), Rennes, FRANCE, F Jul 07-10, 2020.
[22]ZHANG G, ZHU D, LIU X, et al. Multi-scale pulmonary nodule classification with deep feature fusion via residual network [J]. Journal of Ambient Intelligence and Humanized Computing, 2018.
[23]LV W H, WANG Y, ZHOU C S, et al. Development and validation of a clinically applicable deep learning strategy (HONORS) for pulmonary nodule classification at CT: A retrospective multicenter study [J]. Lung Cancer, 2021, 155: 78-86.
[24]SUN H T, YUAN G, YANG Y, et al. 3D Anisotropic Convolution Based Pulmonary Nodule Classification[J]. Computer Engineering and Applications, 2021, 57(10): 133-138.
[25]LEI Y M, TIAN Y K, SHAN H M, et al. Shape and margin-aware lung nodule classification in low-dose CT images via soft activation mapping [J]. Medical Image Analysis, 2020, 60.
[26]APOSTOLOPOULOS I D, PINTELAS E G, LIVIERIS I E, et al. Automatic classification of solitary pulmonary nodules in PET/CT imaging employing transfer learning techniques [J]. Medical & Biological Engineering & Computing, 2021, 59(6): 1299-310.
[27]RAGAB M, ALSHEHRI S, ALHAKAMY N A, et al. Machine Learning with Quantum Seagull Optimization Model for COVID-19 Chest X-Ray Image Classification [J]. Journal of Healthcare Engineering, 2022, 2022: 1-13.
[28]AMIN J, SHARIF M, GUL N, et al. Quantum Machine Learning Architecture for COVID-19 Classification Based on Synthetic Data Generation Using Conditional Adversarial Neural Network [J]. Cognitive Computation, 2022, 14(5): 1677-88.
[29]TONG C, LIANG B, SU Q, et al. Pulmonary Nodule Classification Based on Heterogeneous Features Learning [J]. IEEE Journal on Selected Areas in Communications, 2021, 39(2): 574-81.
[30]KUANG Y, LAN T, PENG X Q, et al. Unsupervised Multi-Discriminator Generative Adversarial Network for Lung Nodule Malignancy Classification [J]. IEEE Access, 2020, 8: 77725-34.
[31]NI Z H, PENG Y J. A serialized classification method for pulmonary nodules based on lightweight cascaded convolutional neural network-long short-term memory [J]. International Journal of Imaging Systems and Technology, 2020, 30(4): 950-62.
[32]WANG C, CHEN D L, HAO L, et al. Pulmonary Image Classification Based on Inception-v3 Transfer Learning Model [J]. IEEE Access, 2019, 7: 146533-41.
[33]XIAO N, QIANG Y, ZIA M B, et al. Ensemble classification for predicting the malignancy level of pulmonary nodules on chest computed tomography images [J]. Oncology Letters, 2020, 20(1): 401-8.
[34]YANG Y F, SUN M, IEEE. Hybrid Quantum-Classical Machine Learning for Lithography Hotspot Detection[C]//Proceedings of the 33rd Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), Saratoga Springs, NY, F May 02-05, 2022.
[35]TORRONTRGUI E, GARCIA-RIPOLL J. Universal quantum perceptron as efficient unitary approximators[J]. arXiv preprint arXiv:1801.00934, 2018.
[36]MU R H, ZENG X Q. A Review of Deep Learning Research [J]. Ksii Transactions on Internet and Information Systems, 2019, 13(4): 1738-64.
[37]ZHANG Q C, YANG L T, CHEN Z K, et al. An Adaptive Dropout Deep Computation Model for Industrial IoT Big Data Learning With Crowdsourcing to Cloud Computing [J]. IEEE Transactions on Industrial Informatics, 2019, 15(4): 2330-7.
[38]ALCHIERI L, BADALOTTI D, BONARDI P, et al. An introduction to quantum machine learning: from quantum logic to quantum deep learning [J]. Quantum Machine Intelligence, 2021, 3(2).
[39]CEREZO M, VERDON G, HUANG H Y, et al. Challenges and opportunities in quantum machine learning [J]. Nature Computational Science, 2022, 2(9): 567-76.
[40]CILIBERTO C, HERBSTER M, IALONGO A D, et al. Quantum machine learning: a classical perspective [J]. Proceedings of the Royal Society a-Mathematical Physical and Engineering Sciences, 2018, 474(2209).
[41]DUNJKO V, BRIEGEL H J.Machine learning & artificial intelligence in the quantum domain: a review of recent progress [J]. Reports on Progress in Physics, 2018, 81(7).
[42]LINNAINMAA S. Taylor expansion of the accumulated rounding error [J]. BIT, 1976, 16(2): 146-60.
[43]RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors [J]. Nature, 1986, 323(6088): 533-6.
[44]FLURIN E, MARTIN L S, HACOHEN-GOURGY S, et al. Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations [J]. Physical Review X, 2020, 10(1).
[45]FOSEL T, TIGHINEANU P, WEISS T, et al. Reinforcement Learning with Neural Networks for Quantum Feedback [J]. Physical Review X, 2018, 8(3).
[46]ZHANG T, WANG R, DING J W, et al. Face Recognition Based on Densely Connected Convolutional Networks[C]//Proceedings of the 4th IEEE International Conference on Multimedia Big Data (BigMM), Xian, PEOPLES R CHINA, F Sep 13-16, 2018.
[47]ARMATO S G, MCLENNAN G, BIDAUT L, et al. The Lung Image Database Consortium, (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans [J]. Medical Physics, 2011, 38(2): 915-31.
[48]CHEN L C, YANG Y, WANG J, et al. Attention to Scale: Scale-aware Semantic Image Segmentation[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, F Jun 27-30, 2016.
[49]SUN W Q, ZHENG B, QIAN W. Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis [J]. Computers in Biology and Medicine, 2017, 89: 530-9.
[50]WIEMKER R, ROGALLA P, ZWARTKRUIS A, et al. Computer aided lung nodule detection on high resolution CT data[C]//Proceedings of the Medical Imaging 2002 Conference, San Diego, Ca, F Feb 24-28, 2002.
[51]ARMATO S, MCLENNAN G, MCNITT-GRAY M, et al. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Public Database of CT Scans for Lung Nodule Analysis [J]. Medical Physics, 2010, 37(6): 3416-7.
[52]CHEN J, QI X B, TERVONEN O, et al. Thorax Disease Diagnosis Using Deep Convolutional Neural Network[C]//Proceedings of the 38th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC), Orlando, FL, F Aug 16-20, 2016.
[53]DIVINCENZO D P. The physical implementation of quantum computation [J]. Fortschritte Der Physik-Progress of Physics, 2000, 48(9-11): 771-83.
[54]PRESKILL J. Quantum Computing in the NISQ era and beyond[J]. Quantum, 2018, 2: 79.
[55]ARTUE F, ARYA K, BABBUSH R, et al. Quantum supremacy using a programmable superconducting processor[J]. Nature, 2019, 574(7779): 505-510.
[56]ZHONG H S, WANG H, DENG Y H, et al. Quantum computational advantage using photons[J]. Science, 2020, 370(6523): 1460-1463.
[57]QSTASZEWSKI M, GRANT E, BENEDETTI M. Structure optimization for parameterized quantum circuits[J]. Quantum, 2021, 5: 391.
[58]D Y, HU M H, LIU T, et al. Expressive power of parametrized quantum circuits[J]. Physical Review Research, 2020, 2(3): 033125.
[59]CAO Y, GUERRESCHI G, ASPURU A. Quantum neuron: an elementary building block for machine learning on quantum computers[J]. arXiv preprint arXiv:1711.11240, 2017.
[60]CEREZO M, ARRASMITH A, BABBUSH R, et al. Variational quantum algorithms[J]. arXiv preprint arXiv:2012.09265, 2020.
[61]GULRAJANI I, AHMED F, ARIJOVSKY M, et al. Improved training of wasserstein gans[J]. arXiv preprint arXiv:1704.00028, 2017.
[62]DALLAIRE P, KILLORAN N. Quantum generative adversarial networks[J]. Physical Review A, 2018, 98(1): 012324.
[63]BEER K, BONDARENKO D, FARRELLY T, et al. Training deep quantum neural networks[J]. Nature communications, 2020, 11(1): 1-6.
[64]CONG I, CHOI S, LUKIN M D. Quantum convolutional neural networks[J]. Nature Physics, 2019, 15(12): 1273-+.
[65]FRANKEN L, GEORGIEV B. Explorations in quantum neural networks with intermediate measurements[C]//Proceedings of ESANN, 2020.
[66]ZHANG K, HSIEH M H, LIU L, et al. Toward Trainability of Quantum Neural Networks[J]. arXiv preprint arXiv:2011.06258, 2020.
[67]WATABE M, SHIBA K, CHEN C C, et al. Quantum Circuit Learning with Error Backpropagation Algorithm and Experimental Implementation[J]. Quantum Reports, 2021, 3(2): 333-349.
[68]PESAH A, CEREZO M, WANG S, et al. Absence of barren plateaus in quantum convolutional neural networks[J].arXiv preprint arXiv:2011.02966, 2020.
[69]JING Y, YANG Y, WU C, et al. RGB Image Classification with Quantum Convolutional Ansaetze[J]. arXiv preprint arXiv:2107.11099, 2021.
[70]MATTERN D, MARTYNIUK D, WILLEMS H, et al. Variational Quanvolutional Neural Networks with enhanced image encoding[J]. arXiv preprint arXiv:2106.07327, 2021.
[71]ANTHIMOPOULOS M, CHRISTODOULIDIS S, EBNER L, et al. Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network[J]. IEEE Transactions on Medical Imaging, 2016, 35(5) : 1207.
[72]DENG D L. Quantum enhanced convolutional neural networks for NISQ computers[J]. Science China Physics, Mechanics & Astronomy, 2021, 64(10): 1-1.
[73]YANG C H, QI J, CHEN S Y, et al. Decentralizing feature extraction with quantum convolutional neural network for automatic speech recognition[C]//ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021: 6523-6527.
[74]GUAN J, FANG W, YING M. Robustness verification of quantum classifiers[C]// International Conference on Computer Aided Verification, 2021: 151-174.
[75]CHEN G, ZHOU R, ZHU X, et al. Quantum Convolutional Neural Network On Scale Chaology[C]//2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), 2020: 243-247.
[76]OH S, CHOI J, KIM J K, et al. Quantum Convolutional Neural Network for Resource-Efficient Image Classification: A Quantum Random Access Memory (QRAM) Approach[C]//2021 International Conference on Information Networking (ICOIN), 2021: 50-52.
[77]LIU D, RAN S J, WITTEK P, et al. Machine learning by unitary tensor network of hierarchical tree structure[J]. New Journal of Physics, 2019, 21(7): 073059.
[78]CROSS A W, BISHOP L S, SHELDON S, et al. Validating quantum computers using randomized model circuits[J]. Physical Review A, 2019, 100(3): 032328.
[79]UMER M J, AMIN J, SHARIF M, et al. An integrated framework for COVID‐19 classification based on classical and quantum transfer learning from a chest radiograph[J].Concurrency and Computation: Practice and Experience, 2021: e6434.
[80]POMARICO D, FANIZZI A, AMOROSO N, et al. A Proposal of Quantum-Inspired Machine Learning for Medical Purposes: An Application Case[J]. Mathematics, 2021, 9(4): 410.
[81]SAJIAN M, SURESHBABU S H, KAIS S. Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials[J]. arXiv preprint arXiv:2105.09488, 2021.
[82]Li J, Shen Y, Yang C. An Adversarial Generative Network for Crop Classification from Remote Sensing Timeseries Images[J]. Remote Sensing, 2020, 13(1): 65.
[83]GUO F, ZHANG P, WANG F, et al. Finite element analysis based Hopfield neural network model for solving nonlinear electromagnetic field problems[C]// International Joint Conference on Neural Networks. 1999 : 4399 – 4403 vol.6.
[84]PAJARES G, LOPEZMART INEZ C, SANCHEZLLAD O F , et al. Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach[J].Remote Sensing, 2012, 4(11) : 3571 – 3595.
[85]NIE X, QIAO H, ZHANG B. A variational model for PolSAR data speckle reduction based on the Wishart distribution[J]. IEEE Transactions on Image Processing, 2015, 24(4) : 1209.
[86]HENDERSON M, SHAKYA S, PRADHAN S, et al. Quanvolutional neural networks: powering image recognition with quantum circuits [J]. Quantum Machine Intelligence, 2020, 2(1).
[87]ZHANG T, WANG R, DING J W, et al. Face Recognition Based on Densely Connected Convolutional Networks[C]//Proceedings of the 4th IEEE International Conference on Multimedia Big Data (BigMM), Xian, PEOPLES R CHINA, F Sep 13-16, 2018.
[88]AL-SHABI M, LEE H K, TAN M. Gated-Dilated Networks for Lung Nodule Classification in CT Scans [J]. IEEE Access, 2019, 7: 178827-38.
[89]SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of Go with deep neural networks and tree search.[J]. Nature, 2016, 529(7587) : 484.
[90]SHANG F, HIROSE A. Quaternion Neural-Network-Based PolSAR Land Classification in Poincare-Sphere-Parameter Space[J]. IEEE Transactions on Geoscience & Remote Sensing, 2014,52(9) : 5693 – 5703.
[91]BARTHELEMY M, FORTUNATO S. Resolution limit in community detection[J]. Proceedings of the National Academy of Sciences of the United States of America, 2007, 104(1) : 36.
[92]ANCICHINETTI A, FORTUNATO S. Limits of modularity maximization in community detection[J]. Physical Review E Statistical Nonlinear & Soft Matter Physics, 2011, 84(2) : 066122.
[93]GONG M, MA L, ZHANG Q, et al. Community detection in networks by using multiobjective evolutionary algorithm with decomposition[J].Physica A: Statistical Mechanics and its Applications, 2012, 391(15) : 4050 – 4060.
[94]ZOU Y, ZHUANG Z, CHEN H. HW-SW partitioning based on genetic algorithm[C]// Evolutionary Computation, 2004. CEC2004. Congress on. 2004 : 628-633 Vol.1.
[95]ANG L, WANG Q. A Community Detection Algorithm Based on NSGA-II[J]. Telecommunication Computing Electronics and Control, 2016, 14(3A) : 288 – 296.
[96]ZHAO J, BASTO FERNANDES V, JIAO L, et al. Multiobjective Optimization of Classifiers by Means of 3D Convex-Hull-Based Evolutionary Algorithms[J]. Information Sciences, 2016, 367-368 : 80 – 104.
[97]ANGELINI L, BOCCALETTI S, MARINAZZO D, et al. Identification of network modules by optimization of ratio association[J]. Chaos, 2007, 17(2) : 175.
[98]ZEILER M D, KRISHNAN D, TAYLOR G W, et al. Deconvolutional networks[J], 2010, 238(6) :2528 – 2535.
[99]HUR T, KIM L, PARK D K. Quantum convolutional neural network for classical data classification[J]. arXiv preprint arXiv:2108.00661, 2021.
[100] KINGMA D, BA J. Adam: A Method for Stochastic Optimization [J]. International Conference on Learning Representations, 2014.
[101] WANG Y Z. Quantum Computation and Quantum Information [J]. Statistical Science,2012, 27(3): 373-94.
[102] FIJANY A, WILLIAMS C P. Quantum wavelet transforms: Fast algorithms and complete circuits [M]. Quantum Computing and Quantum Communications. 1999: 10-33.
[103] YAO X W, WANG H Y, LIAO Z Y, et al. Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment [J]. Physical Review X, 2017, 7(3).