نشریه علمی مهندسی پزشکی زیستی
Iranian Journal of Biomedical Engineering (IJBME)

انتخاب ویژگی‌های موثر سیگنال‌های فرکانس رادیویی اولتراسوند خام به منظور بهبود طبقه‌بندی هوشمند ضایعات پستانی با استفاده از یادگیری ماشین

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

مهسا عرب 1
علی فلاح 2
سعید رشیدی 3
مریم مهدی‌زاده دستجردی 4
نسرین احمدی‌نژاد 5

1 دانشجوی دکتری، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

2 دانشیار، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

3 استادیار، گروه مهندسی پزشکی، دانشکده‌ی علوم و فناوری‌های پزشکی، دانشگاه آزاد اسلامی، واحد علوم و تحقیقات، تهران، ایران

4 دکتری، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی امیرکبیر، تهران، ایران

5 دانشیار، مرکز تصویربرداری پزشکی-رادیولوژی، پژوهشکده‌ی سرطان، مرکز تحقیقات رادیولوژی پیشرفته‌ی تشخیصی و مداخله‌ای بیمارستان امام خمینی، دانشگاه علوم پزشکی تهران، تهران، ایران

https://doi.org/10.22041/ijbme.2024.2012148.1864
چکیده
سرطان پستان رایج‌ترین نوع سرطان در زنان است. بیش از 80% ناهنجاری‌های پستان در مراحل اولیه خوش‌خیم هستند. بنابراین تشخیص زودهنگام مهم‌ترین چالش برای درمان به موقع است. یکی از روش‌های غیرتهاجمی و زمان واقعی برای غربال‌گری سرطان پستان استفاده از سیگنال‌های فرکانس رادیویی اولتراسوند (US RF) است. این روش علاوه بر تمایز بافتی و مقرون‌ به ‌صرفه بودن، در مقایسه با روش­های دیگر نیازی به تجهیزات تکمیلی ندارد. این پژوهش با هدف ارائه‌ی رویکردی هوشمند برای طبقه‌بندی ضایعات خوش‌خیم، مشکوک و بدخیم پستان بر اساس ویژگی‌های موثر استخراج شده از سری زمانی US RF صورت گرفته است. مجموعه‌ی داده‌ی US RF ثبت شده با عنوان USRFTS شامل 170 داده‌ از ضایعات مذکور بوده که از 88 بیمار به دست آمده است. روش پیشنهادی در این تحقیق شامل چهار بخش اصلی پیش‌پردازش، استخراج ویژگی، انتخاب ویژگی و طبقه‌بندی است. در مرحله‌ی پیش‌پردازش پس از بازسازی تصاویر B-mode از سری­های زمانی US RF ثبت شده، ناحیه‌ی دارای ضایعه (ROI) در هر تصویر B-mode توسط پرتوشناس به صورت دستی انتخاب شده است. در ادامه ویژگی‌های مختلف حوزه‌های زمان و فرکانس در مرحله‌ی استخراج ویژگی از هر ROI استخراج شده و پس از آن ویژگی‌های موثر با استفاده از روش کلونی مورچه انتخاب شده است. در نهایت دادگان با استفاده از طبقه‌بندهای ماشین بردار پشتیبان (SVM)، K-نزدیک‌ترین همسایه (KNN)، درخت تصمیم (DT)، تجزیه‌ی تشخیص خطی (LDA) و هم‌چنین روش طبقه‌بندی با مرجع (RCM) مورد ارزیابی قرار گرفته است. با توجه به نتایج به دست آمده بیشینه‌ی صحت طبقه‌بندی دوکلاسه و سه‌کلاسه به ترتیب برابر با 95/94% و 33/93% ارزیابی شده است.

کلیدواژه‌ها

فرکانس رادیویی
اولتراسوند
تصاویر B-Mode
سری زمانی
طبقه‌بندی
یادگیری ماشین
ضایعات پستان

موضوعات

عنوان مقاله English

Selection of Effective Features from Raw US RF Signals to Enhance Intelligent Breast Lesion Classification using Machine Learning

نویسندگان English

Mahsa Arab 1
Ali Fallah 2
Saeid Rashidi 3
Maryam Mehdizadeh Dastjerdi 4
Nasrin Ahmadinejad 5
1 Ph.D. Candidate, Bioelectric Group, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
2 Associate Professor, Bioelectric Group, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
3 Assistant Professor, Biomedical Engineering Group, Medical Sciences and Technologies Department, Islamic Azad University, Science and Research Branch, Tehran, Iran
4 Ph.D., Bioelectric Group, Biomedical Engineering Department, Amirkabir University of Technology, Tehran, Iran
5 Associate Professor, Radiology-Medical Imaging Center, Cancer Research Institute, Imam Khomeini Hospital Advanced Diagnostic and Interventional Radiology Research Center, Medical Sciences and Technologies Department, Tehran University of Medical Sciences, Tehran, Iran
چکیده English

Breast cancer stands as the most prevalent form of cancer among women, with over 80% of early-stage breast abnormalities being benign. Timely detection is therefore crucial for prompt intervention. Ultrasound Radio Frequency (US RF) signals represent a non-invasive, and real-time screening method for breast cancer, offering advantages in tissue differentiation and cost-effectiveness without requiring additional equipment. This research aims to present an intelligent approach for the classification of benign, suspicious, and malignant breast lesions based on effective features extracted from the time series. The dataset, registered as USRFTS, comprises 170 instances recorded from 88 patients. The proposed methodology encompasses four key phases: pre-processing, feature extraction, feature selection, and classification. In the pre-processing phase, B-mode images are reconstructed from US RF time series, and a radiologist manually selects the Region of Interest (ROI) in each image. Subsequently, diverse features in the time and frequency domains are extracted from each ROI during the feature extraction stage. The ant colony method is employed for the selection of impactful features. The dataset is then subjected to evaluation using classifiers such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree (DT), Linear Discriminant Analysis (LDA), and a reference classification method (RCM). The results demonstrate a maximum classification accuracy of 94.95% for two classes and 93.33% for three classes.

کلیدواژه‌ها English

Radio Frequency
Ultrasound
B-Mode Images
Time Series
Classification
Machine Learning
Breast Lesions
  1. Tahmasebi, M. M. Dastjerdi, A. Fallah, and S. Rashidi, "Estimation of linear and nonlinear elastic parameters of prostate tumors using artificial neural networks: Estimation of linear and nonlinear elastic parameters of tumors," in 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME), Tehran, Iran, pp. 87-96, Nov 2020.
  2. C. Observatory. (2021). Population Fact Sheets of Iran 2020. Available: https://gco.iarc.fr/today/data/factsheets/populations/364-iran-islamic-republic-of-fact-sheets.pdf
  3. Uniyal et al., "Ultrasound RF time series for classification of breast lesions," IEEE Trans Med Imaging, vol. 34, no. 2, pp. 652-61, Feb 2015.
  4. M. Dastjerdi, A. Fallah, and S. Rashidi, "An iterative method for estimating nonlinear elastic constants of tumor in soft tissue from approximate displacement measurements," J. Healthc. Eng., vol. 2019, pp. 1-12, Jan 2019.
  5. M. Kolb, J. Lichy, and J. H. Newhouse, "Comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: an analysis of 27,825 patient evaluations," Radiology, vol. 225, no. 1, pp. 165-75, Oct 2002.
  6. A. Berg et al., "Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer," Jama, vol. 299, no. 18, pp. 2151-63, May 2008.
  7. Rahbar et al., "Benign versus malignant solid breast masses: US differentiation," Radiology, vol. 213, no. 3, pp. 889-94, Dec 1999.
  8. Zheng, J. F. Greenleaf, and J. J. Gisvold, "Reduction of breast biopsies with a modified self-organizing map," IEEE Trans Neural Netw, vol. 8, no. 6, pp. 1386-96, Nov 1997.
  9. Donohue, L. Huang, T. Burks, F. Forsberg, and C. Piccoli, "Tissue classification with generalized spectrum parameters," Ultrasound Med Biol, vol. 27, no. 11, pp. 1505-14, Nov 2001.
  10. Joo, Y. S. Yang, W. K. Moon, and H. C. Kim, "Computer-aided diagnosis of solid breast nodules: Use of an artificial neural network based on multiple sonographic features," IEEE Trans Med Imaging, vol. 23, no. 10, pp. 1292-300, Oct 2004.
  11. Moradi, P. Abolmaesumi, D. R. Siemens, E. E. Sauerbrei, A. H. Boag, and P. Mousavi, "Augmenting detection of prostate cancer in transrectal ultrasound images using SVM and RF time series," IEEE Trans Biomed Eng, vol. 56, no. 9, pp. 2214-24, Sep 2009.
  12. Mehdi, S. S. Mahdavi, N. Guy, C. J. Edward, S. L. Goldenberg, and E. S. Septimiu, "Ultrasound RF time series for tissue typing: First in vivo clinical results," in Proc.SPIE, Brussels, Belgium, pp. 86701I-8, Mar 2013.
  13. Moradi, P. Abolmaesumi, and P. Mousavi, "Tissue typing using ultrasound RF time series: Experiments with animal tissue samples," Med Phys, vol. 37, no. 8, pp. 4401-13, Aug 2010.
  14. Jarosik, Z. Klimonda, M. Lewandowski, and M. Byra, "Breast lesion classification based on ultrasonic radio-frequency signals using convolutional neural networks," Biocybern Biomed Eng., vol. 40, pp. 977-986, May 2020.
  15. Yan et al., "Research on diagnosis of breast cancer based on ultrasonic radio frequency signals," Nanosci Nanotechnol Lett, vol. 11, no. 8, pp. 1116-1124, Aug 2019.
  16. Qiao, Z. Fang, Y. Guo, S. Zhou, C. Chang, and Y. Wang, "Breast calcification detection based on multichannel radiofrequency signals via a unified deep learning framework," Expert Syst. Appl., vol. 168, no. 114218, pp. 1-11, Apr 2021.
  17. Taleghamar, H. Moghadas-Dastjerdi, G. J. Czarnota, and A. Sadeghi-Naini, "Characterizing intra-tumor regions on quantitative ultrasound parametric images to predict breast cancer response to chemotherapy at pre-treatment," Sci. Rep., vol. 11, no. 1, pp. 1-13, Jul 2021.
  18. Byra et al., "Joint segmentation and classification of breast masses based on ultrasound radio-frequency data and convolutional neural networks," Ultrasonics, vol. 121, no. 6, Apr 2022.
  19. R. Gare et al., "W-Net: Dense and diagnostic semantic segmentation of subcutaneous and breast tissue in ultrasound images by incorporating ultrasound RF waveform data," Med. Image Anal., vol. 76, pp. 1-14, Feb 2022.
  20. Taleghamar, S. A. Jalalifar, G. J. Czarnota, and A. Sadeghi-Naini, "Deep learning of quantitative ultrasound multi-parametric images at pre-treatment to predict breast cancer response to chemotherapy," Sci. Rep., vol. 12, no. 1, pp. 1-13, Feb 2022.
  21. Chowdhury et al., "Ultrasound classification of breast masses using a comprehensive Nakagami imaging and machine learning framework," Ultrasonics, vol. 124, no. 3, Aug 2022.
  22. Wei, B. Wang, and J. Saniie, "Faster region convolutional neural networks applied to ultrasonic images for breast lesion detection and classification," in 2020 IEEE International Conference on Electro Information Technology (EIT), Chicago, IL, USA, pp. 171-174, Jul 2020.
  23. Gómez Flores, W. C. d. A. Pereira, and A. F. C. Infantosi, "Improving classification performance of breast lesions on ultrasonography," Pattern Recognit., vol. 48, no. 4, pp. 1125-1136, Apr 2015.
  24. Warnich, I. Viljoen, and M. Kuehnast, "Breast imaging at Chris Hani Baragwanath Academic Hospital: A clinically relevant audit," SA Journal of Radiology, vol. 24, no. 1, pp. 1-11, Oct 2020.
  25. -C. Hsu and J.-C. Yu, "American college of radiology breast imaging reporting and data system ultrasound: An overview of the second edition," J. Med. Ultrasound, vol. 23, no. 3, pp. 117-119, Aug 2015.
  26. J. Feleppa et al., "Typing of prostate tissue by ultrasonic spectrum analysis," IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 43, no. 4, pp. 609-619, Jul 1996.
  27. J. Moon, M. J. Kim, J. H. Yoon, and E. K. Kim, "Follow-up interval for probably benign breast lesions on screening ultrasound in women at average risk for breast cancer with dense breasts," (in eng), Acta Radiol, vol. 59, no. 9, pp. 1045-1050, Sep 2018.
  28. Y. Chae, J. H. Cha, H. J. Shin, W. J. Choi, and H. H. Kim, "Reassessment and follow-up results of BI-RADS category 3 lesions detected on screening breast ultrasound," AJR Am J Roentgenol, vol. 206, no. 3, pp. 666-72, Mar 2016.
  29. Fatima, I. Masroor, and S. Khanani, "Probably benign solid breast lesions on ultrasound: need for biopsy reassessed," Asian Pac J Cancer Prev, vol. 19, no. 12, pp. 3467-3471, Dec 2018.
  30. Johnson and M. Frigo, "A modified split-radix FFT with fewer arithmetic operations," IEEE Trans. Signal Process., vol. 55, no. 1, pp. 111-119, Dec 2007.
  31. Li, Y. Liu, M. Zhang, G. Zhang, Z. Wang, and J. Luo, "Radiomics with attribute bagging for breast tumor classification using multimodal ultrasound images," J Ultrasound Med, vol. 39, no. 2, pp. 361-371, Aug 2020.
  32. B. Subramanya, V. Kumar, S. Mukherjee, and M. Saini, "SVM-based CAC system for B-mode kidney ultrasound images," J Digit Imaging, vol. 28, no. 4, pp. 448-58, Dec 2015.
  33. Malkov et al., "Mammographic texture and risk of breast cancer by tumor type and estrogen receptor status," Breast Cancer Res, vol. 18, no. 1, pp. 1-11, Dec 2016.
  34. M. Haralick, K. Shanmugam, and I. Dinstein, "Textural features for image classification," IEEE Trans. Syst. Man Cybern. Syst., vol. SMC-3, no. 6, pp. 610-621, Jan 1973.
  35. Pezeshki, M. Rastgarpour, A. Sharifi, and S. Yazdani, "Extraction of spiculated parts of mammogram tumors to improve accuracy of classification," Multimed. Tools Appl., vol. 78, no. 14, pp. 1-25, Feb 2019.
  36. Loizidou, G. Skouroumouni, C. Nikolaou, and C. Pitris, "An automated breast micro-calcification detection and classification technique using temporal subtraction of mammograms," IEEE Access, vol. 8, pp. 1-11, Mar 2020.
  37. A. Zebari et al., "Breast cancer detection using mammogram images with improved multi-fractal dimension approach and feature fusion," Appl. Sci., vol. 11, no. 24, pp. 1-28, Dec 2021.
  38. B. Mandelbrot, Gaussian Self-Affinity and Fractals. Harrisonburg: Springer, 2002.
  39. K. Loo, A. Samraj, and G. C. Lee, "Evaluation of methods for estimating fractal dimension in motor imagery-based brain computer interface," Discrete Dyn. Nat. Soc., vol. 2011, pp. 1-8, Jan 2011.
  40. Higuchi, "Approach to an irregular time series on the basis of the fractal theory," Phys. D: Nonlinear Phenom., vol. 31, no. 2, pp. 277-283, Jun 1988.
  41. J. Katz, "Fractals and the analysis of waveforms," Comput. Biol. Med., vol. 18, no. 3, pp. 145-156, Jan 1988.
  42. Petrosian, "Kolmogorov complexity of finite sequences and recognition of different preictal EEG patterns," in Proceedings 8th IEEE Symposium on Computer-Based Medical Systems, Lubbock, TX, USA, pp. 212-217, Jun 1995.
  43. Imani et al., "Computer-aided prostate cancer detection using ultrasound RF time series: In vivo feasibility study," IEEE Trans Med Imaging, vol. 34, no. 11, pp. 2248-57, Nov 2015.
  44. H. Aghdam, N. Ghasem-Aghaee, and M. E. Basiri, "Text feature selection using ant colony optimization," Expert Syst. Appl., vol. 36, no. 3, Part 2, pp. 6843-6853, Apr 2009.
  45. Jayaprakash and C. KeziSelvaVijila, "Feature selection using ant colony optimization (ACO) and road sign detection and recognition (RSDR) system," Cogn. Syst. Res., vol. 58, pp. 123-133, Dec 2019.
  46. Z. Dadaneh, H. Y. Markid, and A. Zakerolhosseini, "Unsupervised probabilistic feature selection using ant colony optimization," Expert Syst. Appl., vol. 53, pp. 27-42, Jul 2016.
  47. Basiri, N. Ghasem-Aghaee, and M. Hosseinzadeh Aghdam, "Using ant colony optimization-based selected features for predicting post-synaptic activity in proteins," in Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, 6th European Conference (EvoBIO), Naples, Italy, Mar 2008, vol. 4973, pp. 12-23.
  48. R. Kanan, K. Faez, and S. M. Taheri, "Feature selection using ant colony optimization (ACO): A new method and comparative study in the application of face recognition system," in Industrial Conference on Data Mining, Leipzig, Germany, pp. 63-76, Aug 2007.
  49. F. Chang, W. J. Wu, W. K. Moon, Y. H. Chou, and D. R. Chen, "Support vector machines for diagnosis of breast tumors on US images," Acad Radiol, vol. 10, no. 2, pp. 189-97, Feb 2003.
  50. Fleury and K. Marcomini, "Performance of machine learning software to classify breast lesions using BI-RADS radiomic features on ultrasound images," Eur. Radiol. Exp., vol. 3, no. 1, pp. 1-8, Dec 2019.
  51. Muhtadi, "Breast tumor classification using intratumoral quantitative ultrasound descriptors," Comput Math Methods Med, vol. 2022, pp. 1-18, Mar 2022.
  52. Kim, J. Park, J. Yi, and H. Kim, "End-to-end convolutional neural network framework for breast ultrasound analysis using multiple parametric images generated from radiofrequency signals," Appl. Sci., vol. 12, no. 10, pp. 1-17, May 2022.
  53. M. Shankar et al., "Classification of ultrasonic B-mode images of breast masses using Nakagami distribution," IEEE Trans Ultrason Ferroelectr Freq Control, vol. 48, no. 2, pp. 569-80, Mar 2001.
  54. L. Huang and D. R. Chen, "Support vector machines in sonography: Application to decision making in the diagnosis of breast cancer," Clin Imaging, vol. 29, no. 3, pp. 179-84, May-Jun 2005.
  55. Z. Dadaneh, H. Y. Markid, and A. Zakerolhosseini, "Unsupervised probabilistic feature selection using ant colony optimization," Expert Syst. Appl., vol. 53, pp. 27-42, Jul 2016.
  56. Dorigo and T. Stützle, Ant colony optimization: overview and recent advances (Handbook of Metaheuristics). 2018.
  57. Fallahzadeh, Z. Dehghani-Bidgoli, and M. Assarian, "Raman spectral feature selection using ant colony optimization for breast cancer diagnosis," Lasers Med Sci., vol. 33, no. 8, pp. 1799-1806, June 2018.
  58. Panigrahi, H. Swapnarekha, and S. Subudhi, "GACO: A genetic algorithm with ant colony optimization—based feature selection for breast cancer diagnosis," in Nature-Inspired Optimization Methodologies in Biomedical and HealthcareCham: Springer International Publishing, pp. 269-293, Nov 2022.
  59. Shunmugapriya and S. Kanmani, "A hybrid algorithm using ant and bee colony optimization for feature selection and classification (AC-ABC Hybrid)," Swarm Evol. Comput., vol. 36, pp. 27-36, Oct 2017.
نشریه علمی مهندسی پزشکی زیستی
دوره 17، شماره 2
تابستان 1402
صفحه 109-124

  • تاریخ دریافت 12 مهر 1402
  • تاریخ بازنگری 06 دی 1402
  • تاریخ پذیرش 15 دی 1402

صفحه اصلی

تماس با ما