Explainable DCNN Decision Framework for Breast Lesion Classification from Ultrasound Images Based on Cancer Characteristics

Journal article


AlZoubi, A., Eskandari, A., Yu, H. and Du, H. 2024. Explainable DCNN Decision Framework for Breast Lesion Classification from Ultrasound Images Based on Cancer Characteristics . Bioengineering. 11 (5), pp. 1-23. https://doi.org/10.3390/bioengineering11050453
AuthorsAlZoubi, A., Eskandari, A., Yu, H. and Du, H.
Abstract

In recent years, deep convolutional neural networks (DCNNs) have shown promising performance in medical image analysis, including breast lesion classification in 2D ultrasound (US) images. Despite the outstanding performance of DCNN solutions, explaining their decisions remains an open investigation. Yet, the explainability of DCNN models has become essential for healthcare systems to accept and trust the models. This paper presents a novel framework for explaining DCNN classification decisions of lesions in ultrasound images using the saliency maps linking the DCNN decisions to known cancer characteristics in the medical domain. The proposed framework consists of three main phases. First, DCNN models for classification in ultrasound images are built. Next, selected methods for visualization are applied to obtain saliency maps on the input images of the DCNN models. In the final phase, the visualization outputs and domain-known cancer characteristics are mapped. The paper then demonstrates the use of the framework for breast lesion classification from ultrasound images. We first follow the transfer learning approach and build two DCNN models. We then analyze the visualization outputs of the trained DCNN models using the EGrad-CAM and Ablation-CAM methods. We map the DCNN model decisions of benign and malignant lesions through the visualization outputs to the characteristics such as echogenicity, calcification, shape, and margin. A retrospective dataset of 1298 US images collected from different hospitals is used to evaluate the effectiveness of the framework. The test results show that these characteristics contribute differently to the benign and malignant lesions’ decisions. Our study provides the foundation for other researchers to explain the DCNN classification decisions of other cancer types.

Keywords deep convolutional neural networks; visual explanations; saliency maps; cancer recognition; breast cancer; ultrasonography ; cancer characteristics
Year2024
JournalBioengineering
Journal citation11 (5), pp. 1-23
PublisherMDPI
ISSN2306-5354
Digital Object Identifier (DOI)https://doi.org/10.3390/bioengineering11050453
Web address (URL)https://www.mdpi.com/2306-5354/11/5/453
Publisher's version
License
File Access Level
Open
Output statusPublished
Publication dates
Online02 May 2024
Publication process dates
Deposited13 May 2024
Permalink -

https://repository.derby.ac.uk/item/q619q/explainable-dcnn-decision-framework-for-breast-lesion-classification-from-ultrasound-images-based-on-cancer-characteristics

Download files


Publisher's version
bioengineering-11-00453-1.pdf
License: CC BY 4.0
File access level: Open

  • 5
    total views
  • 1
    total downloads
  • 2
    views this month
  • 1
    downloads this month

Export as

Related outputs

Deep Recognition of Chinese Herbal Medicines Based on a Caputo Fractional Order Convolutional Neural Network
Tao Li, Jiawei Yang, Chenxi Li, Lulu Lv, Kang Liu, Zhipeng Yuan, Youyong Li, Hongqing Yu and Yu, H. 2024. Deep Recognition of Chinese Herbal Medicines Based on a Caputo Fractional Order Convolutional Neural Network. International Workshop on Internet of Things of Big Data for Healthcare. Springer. https://doi.org/10.1007/978-3-031-52216-1_4
Evaluation of Integrated XAI Frameworks for Explaining Disease Prediction Models in Healthcare
Yu, H., Adebola Alaba and Ebere Eziefuna 2024. Evaluation of Integrated XAI Frameworks for Explaining Disease Prediction Models in Healthcare. International Workshop on Internet of Things of Big Data for Healthcare. Springer. https://doi.org/10.1007/978-3-031-52216-1_2
Attention Enhanced Siamese Neural Network for Face Validation
Yu, H. 2023. Attention Enhanced Siamese Neural Network for Face Validation. Artificial Intelligence and Applications. 2 (1), pp. 21-27. https://doi.org/10.47852/bonviewAIA32021018
IoTBDH-2023: The 5th International Workshop on Internet of Things of Big Data for Healthcare
Qi, J., Yu, H., Yang, P., Yang, Y. and Pang, Z. 2023. IoTBDH-2023: The 5th International Workshop on Internet of Things of Big Data for Healthcare. 32nd ACM International Conference on Information and Knowledge Management (CIKM’23), Birmingham, UK. ACM. https://doi.org/10.1145/3583780.3615299
Automatic Bi-LSTM Architecture Search Using Bayesian Optimisation for Vehicle Activity Recognition
AlZoubi, A. and Radhakrishnan , R. 2023. Automatic Bi-LSTM Architecture Search Using Bayesian Optimisation for Vehicle Activity Recognition. in: A. Augusto de Sousa, Kurt Debattista, Alexis Paljic, Mounia Ziat, Christophe Hurter, Helen Purchase, Giovanni Maria Farinella, Petia Radeva and Kadi Bouatouch (ed.) Computer Vision, Imaging and Computer Graphics Theory and Applications New York Springer. pp. 108–134
ENAS-B: Combining ENAS with Bayesian Optimisation for Automatic Design of Optimal CNN Architectures for Breast Lesion Classification from Ultrasound Images
Ahmed, M., Du, H. and AlZoubi, A. 2023. ENAS-B: Combining ENAS with Bayesian Optimisation for Automatic Design of Optimal CNN Architectures for Breast Lesion Classification from Ultrasound Images. Ultrasonic Imaging. https://doi.org/10.1177/01617346231208709
Automatic Detection of Thyroid Nodule Characteristics From 2D Ultrasound Images
Han, D., Ibrahim, N., Lu, F., Zhu, Y., Du, H. and AlZoubi, A. 2023. Automatic Detection of Thyroid Nodule Characteristics From 2D Ultrasound Images. Ultrasonic Imaging. pp. 1-18. https://doi.org/10.1177/01617346231200804
Classification of breast lesions in ultrasound images using deep convolutional neural networks: transfer learning versus automatic architecture design
AlZoubi, A., Lu, F., Zhu, Y., Ying, T., Ahmed, M. and Du, H. 2023. Classification of breast lesions in ultrasound images using deep convolutional neural networks: transfer learning versus automatic architecture design. Medical & Biological Engineering & Computing. pp. 1-15. https://doi.org/10.1007/s11517-023-02922-y
AIMS: An Automatic Semantic Machine Learning Microservice Framework to Support Biomedical and Bioengineering Research
Yu, H., O'Neill, S. and Kermanizadeh, A. 2023. AIMS: An Automatic Semantic Machine Learning Microservice Framework to Support Biomedical and Bioengineering Research. Bioengineering. 10 (10), pp. 1-18. https://doi.org/10.3390/bioengineering10101134
Learning Disease Causality Knowledge from Web of Health Data
Yu, H. and Reiff-Marganiec, S. 2022. Learning Disease Causality Knowledge from Web of Health Data. International journal on semantic web and information systems. 18 (1), pp. 1-19. https://doi.org/10.4018/IJSWIS.297145
Experimental Disease Prediction Research on Combining Natural Language Processing and Machine Learning
Yu, H. 2020. Experimental Disease Prediction Research on Combining Natural Language Processing and Machine Learning. IEEE 7th International Conference on Computer Science and Network Technology (ICCSNT). IEEE Xplore. https://doi.org/10.1109/iccsnt47585.2019.8962507
Dynamic Causality Knowledge Graph Generation for Supporting the Chatbot Healthcare System
Yu, H. 2020. Dynamic Causality Knowledge Graph Generation for Supporting the Chatbot Healthcare System. in: Arai, Kohei, Kapoor, Supriya and Bhatia, Rahul (ed.) Proceedings of the Future Technologies Conference (FTC) 2020, Volume 3 New York Springer.
Low-Cost and Data Anonymised City Traffic Flow Data Collection to Support Intelligent Traffic System
Handscombe, J. and Yu, H. 2019. Low-Cost and Data Anonymised City Traffic Flow Data Collection to Support Intelligent Traffic System. Sensors. 19 (2), p. 347. https://doi.org/10.3390/s19020347
Semantic Lifting and Reasoning on the Personalised Activity Big Data Repository for Healthcare Research
Yu, H. and Dong, F. 2019. Semantic Lifting and Reasoning on the Personalised Activity Big Data Repository for Healthcare Research. International Journal of Web Engineering and Technology. 14 (2), pp. 103 - 121.
Mining Symptom and Disease Web Data with NLP and Open Linked Data
Yu, H. 2019. Mining Symptom and Disease Web Data with NLP and Open Linked Data. 5th World Congress on Electrical Engineering and Computer Systems and Sciences (EECSS’19) Lisbon, Portugal – August, 2019. https://doi.org/10.11159/mvml19.108
A linear logic approach to the composition of RESTful web services
Zhao, X., Liu, E., Yu, H. and Clapworthy, G.J. 2015. A linear logic approach to the composition of RESTful web services. International Journal of Web Engineering and Technology. 10 (3), pp. 245-271. https://doi.org/10.1504/ijwet.2015.072348
Socio-semantic Integration of Educational Resources - the Case of the mEducator Project
Dietze, Stefan, Kaldoudi, Eleni, Dovrolis, Nikolas, Giordano, Daniela, Spampinato, Concetto, Hendrix, Maurice, Protopsaltis, Aristidis, Taibi, v and Yu, H. 2013. Socio-semantic Integration of Educational Resources - the Case of the mEducator Project. Journal of Universal Computer Science. 19 (11), pp. 1-27. https://doi.org/10.3217/jucs-019-11-1543
Interlinking educational resources and the web of data
Dietze, S., Sanchez‐Alonso, S., Ebner, H., Yu, H., Giordano, D., Marenzi, I. and Pereira Nunes, B. 2013. Interlinking educational resources and the web of data. Program. 47 (1). https://doi.org/10.1108/00330331211296312
Using Linked Data to Annotate and Search Educational Video Resources for Supporting Distance Learning
Yu, H., Pedrinaci, C., Dietze, S. and Domingue, J. 2012. Using Linked Data to Annotate and Search Educational Video Resources for Supporting Distance Learning. IEEE Transactions on Learning Technologies. 5 (2), pp. 130-142. https://doi.org/10.1109/tlt.2012.1
An automated approach to Semantic Web Services Mediation
Dietze, S., Gugliotta, A., Domingue, J., Yu, H. and Mrissa, M. 2010. An automated approach to Semantic Web Services Mediation. Service Oriented Computing and Applications. 4, p. 261–275. https://doi.org/10.1007/s11761-010-0070-7