بهبود کاهش نویز، تقطیع و طبقه‌بندی توده‌های سرطان توسط فیلتر تطبیقی معکوس کوانتومی، عنکبوت اجتماعی و ELM بهبود یافته

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه کامپیوتر، واحد گرگان، دانشگاه آزاداسلامی، گرگان، ایران.

2 گروه کامپیوتر، واحد فیروزکوه، دانشگاه آزاد اسلامی، فیروزکوه، ایران.

چکیده

سیستم‌های تشخیص هوشمند پزشکی امروزه به لطف هوش مصنوعی، دچار تغییرات و همچنین چالش‌هایی شده‌اند. یکی از این سیستم‌های هوشمند پزشکی، سیستم‌های تشخیص و طبقه‌بندی توده‌های سرطانی از نواحی سینه می‌باشد. تشخیص زودهنگام می‌تواند منجر به افزایش گزینه‌های درمانی شود. انواع تکنیک‌های غربالگری برای سرطان سینه مانند ماموگرافی، MRI و التراساند وجود دارد. بسته به روش تشخیص نوع توده‌های سرطانی، از هرکدام از این تصاویر استفاده ‌شده و تکنیک‌های پردازشی متفاوتی برای آنها ارائه‌شده است. این تحقیق به استفاده از مجموعه داده‌های ماموگرافی MIAS می‌پردازد و بر اساس اصول پردازش تصویر و یادگیری ماشین، سعی در تشخیص و طبقه‌بندی توده‌های خوش‌خیم، بدخیم و مشکوک را دارد. لذا به ارائه یک رویکرد تکامل‌یافته می‌پردازد، بدین‌صورت که در ابتدا عملیات پیش‌پردازش با هدف کاهش نویز و بهسازی تصویر مبتنی بر روش پیشنهادی Quantum Inverse MFT انجام می‌شود و سپس بر اساس شدت روشنایی و لبه، عملیات تقطیع تصویر با استفاده از الگوریتم عنکبوت اجتماعی صورت می‌گیرد. در ادامه عملیات استخراج ویژگی‌ها و طبقه‌بندی با هدف تشخیص نوع توده‌های سرطانی، با روش Extereme Learning Machine و مدل توسعه‌یافته آن یعنی Moore Penrose Matrix - Extereme Learning Machine  انجام می‌شود. نتایج تحقیق نشان می‌دهد که رویکرد پیشنهادی از لحاظ معیارهای ارزیابی همچون دقت، حساسیت، نرخ ویژگی‌ها و همین‌طور ROC و AUC نسبت به روش‌های پیشین دارای برتری عملکردی است.

کلیدواژه‌ها


عنوان مقاله [English]

Improved noise reduction, segmentation, and classification of cancer masses by quantum inverse-matched filter, social spider algorithm, and improved ELM

نویسندگان [English]

  • Mohsen Eftekharian 1
  • Ali Nodehi 1
  • Rasul Enayatifar 2
1 Computer Department, Gorgan Branch, Islamic Azad University, Gorgan, Iran.
2 Computer Department, Firoozkooh Branch, Islamic Azad University, Firoozkooh, Iran.
چکیده [English]

Intelligent medical diagnosis systems have been revolutionized by artificial intelligence, leading to new challenges and opportunities. One such system is the classification and diagnosis of breast cancer masses, which can benefit from early detection and increased treatment options. Various screening techniques are available for breast cancer, including mammography, MRI, and ultrasound, each requiring different images and image processing techniques depending on the type of cancer mass diagnosis. This paper focuses on using the MIAS mammography dataset to diagnose and classify benign, malignant, and suspicious masses based on image processing and machine learning techniques. To achieve this goal, a developed approach is proposed, in which preprocessing operations are performed at first to reduce noise and enhance the image based on the proposed Quantum Inverse MFT method, and then image segmentation is applied using the social spider algorithm based on brightness intensity and edge. Subsequently, feature extraction and classification operations are performed using the Extreme Learning Machine method and its developed model, i.e., Moore Penrose Matrix-Extreme Learning Machine, with the aim of diagnosing the type of cancer mass. The results show that the proposed approach has a higher accuracy rate than other methods in terms of some evaluation criteria such as accuracy, sensitivity, specificity and also ROC and AUC.

کلیدواژه‌ها [English]

  • Breast cancer
  • Diagnosis and classification
  • Social spider algorithm
  • Quantum inverse MFT
  • MPM-ELM model
[1] Nathan M. R. and Schmid P., “The emerging world of breast cancer immunotherapy”, The Breast, 37:200-206, 2018.
[2] Kavya N., Sriraam N., Usha N., Hiremath B., Suresh A., Sharath D., Venkatraman B., and Menaka M., ”Breast Cancer Lesion Detection From Cranial-Caudal View of Mammogram Images Using Statistical and Texture Features Extraction”, International Journal of Biomedical and Clinical Engineering , 9(1):16-32, 2020.
[3] Barinov L., Jairaj A., Becker M., Seymour S., Lee E., Schram A., Lane E., Goldszal A., Quigley D., and Paster L., “Impact of data presentation on physician performance utilizing artificial intelligence-based computer-aided diagnosis and decision support systems”, Digital Imaging,32(3):408-416, 2019.
[4] Keavey E., Phelan N., and Fitzpatrick P., “Clinical performance of digital mammography systems in a breast screening programme–An update”, Physica Medica, 52:179-180, 2018. 
[5] Houssami N., Bernardi D., Pellegrini M., Valentini, M., and Macaskill P., “Breast cancer detection using single-reading of breast tomosynthesis (3D-mammography) compared to double-reading of 2D-mammography, Evidence from a population-based trial”, Cancer Epidemiology, 47:94-99, 2017.
[6] Kikuchi M., Hayashida T., Watanuki R., Nakashoji A., Kawai Y., and Nagayama A., “Diagnostic system of breast ultrasound images using Convolutional Neural Network”, Cancer Research, 80(4), 2020.
[7] Ekici S. and Jawzal H., “Breast cancer diagnosis using thermography and convolutional neural networks”, Medical Hypotheses, 137, 2020.
[8] Togaçar M., Ergen B., and Comert Z., “Application of breast cancer diagnosis based on a combination of convolutional neural networks, ridge regression and linear discriminant analysis using invasive breast cancer images processed with autoencoders”, Medical Hypotheses, 135, 2020.
[9] Yektaei H., Manthouri M., and Farivar F., “Diagnosis of Breast Cancer Using Multiscale Convolutional Neural Network”, Biomedical Engineering Applications, Basis and Communications, 31(5), 2019.
[10] Rouhi R., Jafari M., Kasaei S., and Keshavarzian P., “Benign and malignant breast tumors classification based on region growing and CNN segmentation”, Expert Systems with Applications, 42:990-1002, 2015.
[11] Telegrafo M., Rella L., Stabile A., Ianora A., Angelelli G., and Moschetta M., “Effect of background parenchymal enhancement on breast cancer detection with magnetic resonance imaging”, Diagnostic and Interventional Imaging, 97:313-318, 2016.
[12] Guo R., Lu G., Qin B., and Fei B., “Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review”, Ultrasound in Medicine and Biology, 44(1):37-70, 2018.
[13] Dehghan-Khalilabad N. and Hassanpour H., “Employing image processing techniques for cancer detection using microarray images”, Computers in Biology and Medicine, 81(1):139-147, 2016.
[14] Kaymak S., Helwan A., and Uzun D., “Breast cancer image classification using artificial neural networks”, Procedia Computer Science, 120:129-131, 2016.
[15] Yassin, I. R. N., Omran S., El.Houby S. M. F., and Allam H., “Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review”, Computer Methods and Programs in Biomedicine, 156:25-45, 2018.
[16] Karabatak M., “A new classifier for breast cancer detection based on Naïve Bayesian”, Measurement, 72:32-36, 2015.
[17] Wang F., Zhang S., and Henderson L. M., “Adaptive decision-making of breast cancer mammography screening: A heuristic-based regression model”, Omega, 76:70-84, 2018.
[18] Patel B. C. and Sinha G. R., “Mammography Feature Analysis and Mass Detection in Breast Cancer Images”, International Conference on Electronic Systems, Signal Processing and Computing Technologies, January, pp. 474-478, 2014.
[19] Singh A. K. and Gupta B., “A Novel Approach for Breast Cancer Detection and Segmentation in a Mammogram. Eleventh International Multi-Conference on Information Processing”, Procedia Computer Science, 54:676-682, 2015.
[20] Tang J., Rangayyan R. M., Xu J., Naqa I. E., and Yang Y., “Computer-Aided Detection and Diagnosis of Breast Cancer with Mammography: Recent Advances”, IEEE Transactions on Information Technology in Biomedicine, 13(2):236-251, 2009.
[21] Lee Y., “Preliminary evaluation of dual-head Compton camera with Si/CZT material for breast cancer detection: Monte Carlo simulation study”, Optik, 202, October 2019. 
[22] Ullah Khan S., Islam N., Jan Z., Ud Din I., and Rodrigues J. P. C. J., “A novel deep learning based framework for the detection and classification of breast cancer using transfer learning”, Pattern Recognition Letters, 125:1-6, 2019.
[23] Kaur P., Singh G., and Kaur P., “Intellectual detection and validation of automated mammogram breast cancer images by multi-class SVM using deep learning classification”, Informatics in Medicine Unlocked, 16:100239, 2019.
[24] Martinez-Martinez F., Rupérez-Moreno M. J., Martinez-Sober M., Solves-Llorens J. A., and Martin-Guerrero J. D., “A finite element-based machine learning approach for modeling the mechanical behavior of the breast tissues under compression in real-time”, Computers in Biology and Medicine, 90:116-124, 2017.
[25] Mohebian R. M., Marateb R. H., Mansourian M., Angel Mananas M., and Mokarian F., “A Hybrid Computer-aided-diagnosis System for Prediction of Breast Cancer Recurrence (HPBCR) Using Optimized Ensemble Learning”, Computational and Structural Biotechnology Journal, 15:75-85, 2017.
[26] Panelli G., Benjamin M. R., and Derevianko A., “Applying the matched-filter technique to the search for dark matter transients with networks of quantum sensors”, EPJ Quantum Technology, 7, 2020.
[27] Mascarade P., “Quantum Image Filtering in the Frequency Domain”, IEEE Open Access, 2018.
[28]  Kannan S., Subiramaniyam N. P., Rajamanickam A. T., and Balamurugan A., “Performance Comparison Of Noise Reduction Inmammogram Images”, International Journal of Research in Engineering and Technology, 5(2):31-33, 2016.
[29] Ball J. E. and Bruce L. M., “Digital mammogram spiculated mass detection and spicule segmentation using level sets”, In Proceedings of the IEEE 29th Annual International Conference on Engineering in Medicine and Biology Society, pp. 4979–4984, August 2007.
[30] Ball J. E. and Bruce L. M., “Digital mammographic computer aided diagnosis (CAD) using adaptive level set segmentation”, In Proceedings of the IEEE 29th Annual International Conference on Engineering in Medicine and Biology Society, pp. 4973–4978, 2007.
[31] Tao Y., Freedman M. T., Makariou E., and Xuan J., “Multilevel learning-based segmentation of ill-defined and spiculated masses in mammograms”, Medical Physics, 37:5993-6002, 2010.
[32] Xu S., Liu H., and Song E., “Marker-controlled watershed for lesion segmentation in mammograms”, Digital Imaging, 24:754-763, 2011.
[33] Rahmati P., Adler A., and Hamarneh G., “Mammography segmentation with maximum likelihood active contours”, Medical Image Anal, 16:1167-1186, 2012.
[34] Abbas Q., Celebi M. E., and Garcia I. F., “Breast mass segmentation using region-based and edge-based methods in a 4-stage multiscale system”, Biomedical and Signal Process, 8:204-214, 2013.
[35] Pereira D. C., Ramos R. P., and Do Nascimento M. Z., “Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm”, Computer Methods and Programs in Biomedicine, 114:88-101, 2014.
[36] Cordeiro F. R., Santos W. P., and Silva-Filho A. G., “An adaptive semi-supervised Fuzzy GrowCut algorithm to segment masses of regions of interest of mammographic images”, Applied Soft Computing., 46:613-628, 2016.
[37] Punitha S., Amuthan A., and Suresh Joseph K., “Benign and malignant breast cancer segmentation using optimized region growing technique”, Future Computing and Informatics Journal, 3(2): 348-358, 2018. 
[38] El Adoui M., Ahmed Mahmoudi S., Amine Larhmam M., and Benjelloun M., “MRI Breast Tumor Segmentation Using Different Encoder and Decoder CNN Architectures”, MDPI Computers, 8(52):11, 2019. 
[39] Ahmed L., Iqbal M. M., Aldabbas H., Khalid S., Saleem Y., and Saeed S., “Images data practices for Semantic Segmentation of Breast Cancer using Deep Neural Network”, Journal of Ambient Intelligence and Humanized Computing, pp. 1–17, 2020.
[40] Zeiser F. A., da Costa C. A., Zonta T., Marques N. M. C., Roehe A. V., Moreno M., and da Rosa Righi R., “Segmentation of masses on mammograms using data augmentation and deep learning”, Journal of digital imaging, 33(4):858–868, 2020.
[41] Abdelhafiz D., Bi J., Ammar R., Yang C., and Nabavi S., “Convolutional neural network for automated mass segmentation in mammography”, BMC Bioinformatics, 21(S1):1–19, 2020.
[42] Salama W. M. and Aly M. H., “Deep learning in mammography images segmentation and classification: automated cnn approach”, Alexandria Engineering Journal, 60(5):4701–4709, 2021.
[43] Tsochatzidis L., Koutla P., Costaridou L., and Pratikakis I., “Integrating segmentation information into cnn for breast cancer diagnosis of mammographic masses”, Computer Methods and Programs in Biomedicine, 200:p. 105913, 2021.
[44] Devakumari D. and Punithavathi V., “Comparison Of Noise Removal Filters For Breast Cancerdetection In Mammogram Images”, International Journal of Pure and Applied Mathematics, 119(18): 3863-3874, 2018. 
[45] Dabass J., Arora S.,  Vig R., and Hanmandlu M., “CLAHE and entropy based Intuitionistic Fuzzy Method”, International Conference on Signal Processing and Integrated Networks (SPIN), 2019, doi: 10.1109/SPIN.2019.8711696.
[46] Zebari D. A., Haron H., Zeebaree S. R. M., and Zeebaree D. Q., “Enhance the Mammogram Images for Both Segmentation and Feature Extraction Using Wavelet Transform”, In 2019 International Conference on Advanced Science and Engineering (ICOASE), Duhok, Iraq, 100–05, 2019.
[47] Al-Antari M. A., Han S.-M., and Kim T.-S., “Evaluation of deep learning detection and classification towards computer-aided diagnosis of breast lesions in digital X-ray mammograms”, Computer methods and programs in biomedicine 196:105584, 2020.
[48] Shen L., He M., Shen N., Yousefi N., Wang C., and Liu G., “Optimal breast tumor diagnosis using discrete wavelet transform and deep belief network based on improved sunflower optimization method”, Biomedical Signal Processing and Control 60:101953, 2020.
[49] Arora R., Rai P. K., and Raman B., “Deep feature–based automatic classification of mammograms”, Medical and biological engineering and computing, 58(6):1199-1211, 2020.
[50] Mahmood T., Li J., Pei Y., and Akhtar F., “An Automated In-Depth Feature Learning Algorithm for Breast Abnormality Prognosis and Robust Characterization from Mammography Images Using Deep Transfer Learning”, Biology, 10, 859, 2021.
[51]  AmineNaji M., Aarika K., HabibBenlahmar E. L.,  AitAbdelouhahid R., and Debauche O., “Machine Learning Algorithms For Breast Cancer Prediction And Diagnosis”, Procedia Computer Science, 191:487-492, 2021.
[52] Resmini R., Silva L., L. Araujo L., L. Medeiros L., Muchaluat-Saade D., and Conci A., “Combining Genetic Algorithms and SVM for Breast Cancer Diagnosis Using Infrared Thermography”, sensors 21(14):4802, 2021.
[53] Chabert S., Castro J. S., Munoz L., Cox P., Riveros R., Vielma J., Huerta G., Querales M., Saavedra C., Veloz A., and Salas R., “Image Quality Assessment to Emulate Experts’ Perception in Lumbar MRI Using Machine Learning”, Applied Sciences, 11(14), 2021.
[54] آخوندی ر.، حسینی ر.، «ارایه مدل هوشمند هایبریدی فازی-تکامل ژنتیکی تفاضلی در یک سیستم خبره فازی برای پیش‌بینی خطر ابتلا به بیماری قلبی»، مجله محاسبات نرم، جلد 1، شماره 5، ص. 35-12، 1391.
[55] ویسی ه.، قایدشرف ح.، ابراهیمی م.، «بهبود کارایی الگوریتم‌های یادگیری ماشین در تشخیص بیماری‌های قلبی با بهینه‌سازی داده‌ها و ویژگی‌ها»، مجله محاسبات نرم، جلد 8، شماره 1، ص. 85-70، 1398.
[56] وثیقی ذاکر ا.، جلیلی س.، «پیش‌بینی ژن‌های بیماری با استفاده از دسته‌بند تک کلاسی ماشین بردار پشتیبان»، مجله محاسبات نرم، جلد 4، شماره 1، ص. 83-74، 1394.