Skip to main content

Advertisement

SpringerLink
Log in

An Automated Decision Support System to Analyze Malignancy Patterns of Breast Masses Employing Medically Relevant Features of Ultrasound Images

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

An automated computer-aided approach might aid radiologists in diagnosing breast cancer at a primary stage. This study proposes a novel decision support system to classify breast tumors into benign and malignant based on clinically important features, using ultrasound images. Nine handcrafted features, which align with the clinical markers used by radiologists, are extracted from the region of interest (ROI) of ultrasound images. To validate that these elected clinical markers have a significant impact on predicting the benign and malignant classes, ten machine learning (ML) models are experimented with resulting in test accuracies in the range of 96 to 99%. In addition, four feature selection techniques are explored where two features are eliminated according to the feature ranking score of each feature selection method. The Random Forest classifier is trained with the resultant four feature sets. Results indicate that even when eliminating only two features, the performance of the model is reduced for each feature selection technique. These experiments validate the efficiency and effectiveness of the clinically important features. To develop the decision support system, a probability density function (PDF) graph is generated for each feature in order to find a threshold range to distinguish benign and malignant tumors. Based on the threshold range of particular features, a decision support system is developed in such a way that if at least eight out of nine features are within the threshold range, the image will be denoted as true predicted. With this algorithm, a test accuracy of 99.38% and an F1 Score of 99.05% is achieved, which means that our decision support system outperforms all the previously trained ML models. Moreover, after calculating individual class-based test accuracies, for the benign class, a test accuracy of 99.31% has been attained where only three benign instances are misclassified out of 437 instances, and for the malignant class, a test accuracy of 99.52% has been attained where only one malignant instance is misclassified out of 210 instances. This system is robust, time-effective, and reliable as the radiologists’ criteria are followed and may aid specialists in making a diagnosis.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Algorithm 1
Fig. 7

Similar content being viewed by others

Data Availability

This study utilizes dataset of breast ultrasound images from Data in Brief [23]. The dataset is publicly available.

References

  1. Gouzerh F, Bessiere J-M, Ujvari B, Thomas F, Dujon AM, Dormont L. Odors and cancer: Current status and future directions. Biochimica et Biophysica Acta (BBA)-Reviews on Cancer. 2022;1877(1):188644.

  2. Ragab DA, Sharkas M, Marshall S, Ren J. Breast cancer detection using deep convolutional neural networks and support vector machines. PeerJ. 2019;7:e6201.

    Article  PubMed  PubMed Central  Google Scholar 

  3. Rafid ARH, Azam S, Montaha S, Karim A, Fahim KU, Hasan MZ. An effective ensemble machine learning approach to classify breast cancer based on feature selection and lesion segmentation using preprocessed mammograms. Biology. 2022;11(11):1654.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Giaquinto AN, Sung H, Miller KD, et al. Breast cancer statistics, 2022. CA: A Cancer Journal for Clinicians. 2022;72(6):524–41.

  5. Montaha S, Azam S, Rafid AKMRH, et al. BreastNet18: a high accuracy fine-tuned VGG16 model evaluated using ablation study for diagnosing breast cancer from enhanced mammography images. Biology. 2021;10(12):1347.

  6. Hiatt RA, Brody JG. Environmental determinants of breast cancer. Annual review of public health. 2018;39:113-33.

    Article  PubMed  Google Scholar 

  7. Kantelhardt E, Wienke A, Addissie A, Walter Bruchhausen BA, Gregor Seliger H. Breast cancer and endocrine therapy adherence in Ethiopia: Diagnosis, treatment, and breast [Internet]. Uni-halle.de. [cited 2023 Sep 10]. Available from: https://opendata.uni-halle.de/bitstream/1981185920/103673/1/Dissertation_MLU_2023_GetachewKelboreSefonias.pdf

  8. Dubey AK, Gupta U, Jain S. Breast cancer statistics and prediction methodology: a systematic review and analysis. Asian Pacific journal of cancer prevention. 2015;16(10):4237-45.

    Article  PubMed  Google Scholar 

  9. Na SP, Houserkovaa D. The role of various modalities in breast imaging. Biomed Pap Med Fac Univ Palacky Olomouc Czech Repub. 2007;151(2):209-18.

    Article  Google Scholar 

  10. Wiacek A, Oluyemi E, Myers K, Mullen L, Bell MAL. Coherence-based beamforming increases the diagnostic certainty of distinguishing fluid from solid masses in breast ultrasound exams. Ultrasound in Medicine & Biology. 2020;46(6):1380-94.

    Article  Google Scholar 

  11. Friedewald SM, Rafferty EA, Rose SL, et al. Breast cancer screening using tomosynthesis in combination with digital mammography. JAMA. 2014;311(24):2499-507.

    Article  CAS  PubMed  Google Scholar 

  12. Zeimarani B, Costa MGF, Nurani NZ, Bianco SR, Pereira WCDA, Costa Filho CFF. Breast lesion classification in ultrasound images using deep convolutional neural network. IEEE Access. 2020;8:133349-59.

    Article  Google Scholar 

  13. Masud M, Eldin Rashed AE, Hossain MS. Convolutional neural network-based models for diagnosis of breast cancer. Neural Computing and Applications. 2020:1–12.

  14. Hassanien MA, Singh VK, Puig D, Abdel-Nasser M. Predicting breast tumor malignancy using deep convnext radiomics and quality-based score pooling in ultrasound sequences. Diagnostics. 2022;12(5):1053.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Zhuang Z, Ding W, Zhuang S, et al. Tumor classification in automated breast ultrasound (ABUS) based on a modified extracting feature network. Computerized Medical Imaging and Graphics. 2021;90:101925.

    Article  PubMed  Google Scholar 

  16. Vigil N, Barry M, Amini A, et al. Dual-intended deep learning model for breast cancer diagnosis in ultrasound imaging. Cancers. 2022;14(11):2663.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Zhuang Z, Yang Z, Raj ANJ, Wei C, Jin P, Zhuang S. Breast ultrasound tumor image classification using image decomposition and fusion based on adaptive multi-model spatial feature fusion. Computer Methods and Programs in Biomedicine. 2021;208:106221.

    Article  PubMed  Google Scholar 

  18. Pourasad Y, Zarouri E, Salemizadeh Parizi M, Salih Mohammed A. Presentation of novel architecture for diagnosis and identifying breast cancer location based on ultrasound images using machine learning. Diagnostics. 2021;11(10):1870.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Yap MH, Pons G, Marti J, et al. Automated breast ultrasound lesions detection using convolutional neural networks. IEEE Journal of Biomedical and Health Informatics. 2017;22(4):1218-26.

    Article  PubMed  Google Scholar 

  20. Ayana G, Park J, Jeong J-W, Choe S-w. A novel multistage transfer learning for ultrasound breast cancer image classification. Diagnostics. 2022;12(1):135.

  21. Liao W-X, He P, Hao J, et al. Automatic identification of breast ultrasound image based on supervised block-based region segmentation algorithm and features combination migration deep learning model. IEEE Journal of Biomedical and Health Informatics. 2019;24(4):984-93.

    Article  PubMed  Google Scholar 

  22. Sapate SG, Mahajan A, Talbar SN, Sable N, Desai S, Thakur M. Radiomics based detection and characterization of suspicious lesions on full field digital mammograms. Computer Methods and Programs in Biomedicine. 2018;163:1-20.

    Article  PubMed  Google Scholar 

  23. Al-Dhabyani W, Gomaa M, Khaled H, Fahmy A. Dataset of breast ultrasound images. Data Brief 28, 104863 (2020). 2019.

    Google Scholar 

  24. Cai S, Wang H, Zhang X, et al. Superb microvascular imaging technology can improve the diagnostic efficiency of the BI-RADS system. Frontiers in Oncology. 2021;11:634752.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Huang Y, Han L, Dou H, Luo H, Yuan Z, Liu Q, et al. Two-stage CNNs for computerized BI-RADS categorization in breast ultrasound images. Biomedical Engineering Online. 2019;18(1):1-18.

    Article  ADS  CAS  Google Scholar 

  26. Dobruch-Sobczak K, Piotrzkowska-Wróblewska H, Roszkowska-Purska K, Nowicki A, Jakubowski W. Usefulness of combined BI-RADS analysis and Nakagami statistics of ultrasound echoes in the diagnosis of breast lesions. Clinical Radiology. 2017;72(4):339. e7-. e15.

  27. Srivastava V, Purwar RK. Classification of CT scan images of lungs using deep convolutional neural network with external shape-based features. Journal of Digital Imaging. 2020;33:252-61.

    Article  PubMed  Google Scholar 

  28. Liu Y, Ren L, Cao X, Tong Y. Breast tumors recognition based on edge feature extraction using support vector machine. Biomedical Signal Processing and Control. 2020;58:101825.

    Article  Google Scholar 

  29. Khan IU, Raiaan MAK, Fatema K, et al. A computer-aided diagnostic system to identify diabetic retinopathy, utilizing a modified compact convolutional transformer and low-resolution images to reduce computation time. Biomedicines. 2023;11(6):1566.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Raiaan MAK, Al Mamun A, Islam MA, Ali ME, Mukta MSH, editors. Envy prediction from users’ photos using convolutional neural networks. 2023 International Conference on Computer, Electrical & Communication Engineering (ICCECE); 2023: IEEE.

  31. Montaha S, Azam S, Rafid ARH, Hasan MZ, Karim A, Islam A. Timedistributed-cnn-lstm: A hybrid approach combining cnn and lstm to classify brain tumor on 3d mri scans performing ablation study. IEEE Access. 2022;10:60039-59.

    Article  Google Scholar 

  32. Fahad NM, Sakib S, Raiaan MAK, Mukta MSH, editors. SkinNet-8: An Efficient CNN Architecture for Classifying Skin Cancer on an Imbalanced Dataset. 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE); 2023: IEEE.

  33. Montaha S, Azam S, Rafid ARH, et al. MNet-10: A robust shallow convolutional neural network model performing ablation study on medical images assessing the effectiveness of applying optimal data augmentation technique. Frontiers in Medicine. 2022;9.

  34. Raiaan MAK, Fatema K, Khan IU, et al. A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images. IEEE Access. 2023.

Download references

Funding

This research does not include any external funding.

Author information

Authors and Affiliations

  1. Faculty of Science and Technology, Charles Darwin University, Casuarina, NT, 0909, Australia

    Sami Azam, Sidratul Montaha, Mohaimenul Azam Khan Raiaan, A. K. M. Rakibul Haque Rafid & Mirjam Jonkman

  2. Department of CSE, United International University, Dhaka, 1212, Bangladesh

    Saddam Hossain Mukta

Authors
  1. Sami Azam
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sidratul Montaha
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohaimenul Azam Khan Raiaan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. K. M. Rakibul Haque Rafid
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Saddam Hossain Mukta
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mirjam Jonkman
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Methodology: Sami Azam, Sidratul Montaha, Mohaimenul Azam Khan Raiaan; conceptualization: Sami Azam, Sidratul Montaha, Mohaimenul Azam Khan Raiaan, A.K.M. Rakibul Haque Rafid; formal analysis and investigation: Sami Azam, Sidratul Montaha, Mohaimenul Azam Khan Raiaan, A.K.M. Rakibul Haque Rafid; writing—original draft preparation: Sami Azam, Sidratul Montaha, Mohaimenul Azam Khan Raiaan; writing—review, and editing: Mirjam Jonkman, Md. Saddam Hossain Mukta; supervision: Sami Azam, Md. Saddam Hossain Mukta.

Corresponding author

Correspondence to Sami Azam.

Ethics declarations

Ethics Approval

The authors declare that no human or animal subjects have been involved in this study. Therefore, this declaration is “not applicable.”

Consent to Participate

The authors declare that no human or animal subjects have been involved in this study. Therefore, this declaration is “not applicable.”

Consent to Publish

The authors confirm that this study does not include human or animal subjects. Therefore, this declaration is “not applicable.”

Competing Interest

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Azam, S., Montaha, S., Raiaan, M.A.K. et al. An Automated Decision Support System to Analyze Malignancy Patterns of Breast Masses Employing Medically Relevant Features of Ultrasound Images. J Digit Imaging. Inform. med. 37, 45–59 (2024). https://doi.org/10.1007/s10278-023-00925-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-023-00925-7

Keywords

Search

Navigation