Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model

Shahed Hossain; Sami Azam; Sidratul Montaha; Asif Karim; Sadia Sultana Chowa; Chaity Mondol; Md Zahid Hasan; Mirjam Jonkman

doi:10.1016/j.heliyon.2023.e21369

Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model

Heliyon. 2023 Oct 21;9(11):e21369. doi: 10.1016/j.heliyon.2023.e21369. eCollection 2023 Nov.

Authors

Shahed Hossain¹, Sami Azam², Sidratul Montaha³, Asif Karim², Sadia Sultana Chowa¹, Chaity Mondol¹, Md Zahid Hasan¹, Mirjam Jonkman²

Affiliations

¹ Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka, 1341, Bangladesh.
² Faculty of Science and Technology, Charles Darwin University, Casuarina, 0909, NT, Australia.
³ Department of Computer Science, University of Calgary, Calgary, AB, T2N 1N4, Canada.

Abstract

Introduction: Breast cancer stands as the second most deadly form of cancer among women worldwide. Early diagnosis and treatment can significantly mitigate mortality rates.

Purpose: The study aims to classify breast ultrasound images into benign and malignant tumors. This approach involves segmenting the breast's region of interest (ROI) employing an optimized UNet architecture and classifying the ROIs through an optimized shallow CNN model utilizing an ablation study.

Method: Several image processing techniques are utilized to improve image quality by removing text, artifacts, and speckle noise, and statistical analysis is done to check the enhanced image quality is satisfactory. With the processed dataset, the segmentation of breast tumor ROI is carried out, optimizing the UNet model through an ablation study where the architectural configuration and hyperparameters are altered. After obtaining the tumor ROIs from the fine-tuned UNet model (RKO-UNet), an optimized CNN model is employed to classify the tumor into benign and malignant classes. To enhance the CNN model's performance, an ablation study is conducted, coupled with the integration of an attention unit. The model's performance is further assessed by classifying breast cancer with mammogram images.

Result: The proposed classification model (RKONet-13) results in an accuracy of 98.41 %. The performance of the proposed model is further compared with five transfer learning models for both pre-segmented and post-segmented datasets. K-fold cross-validation is done to assess the proposed RKONet-13 model's performance stability. Furthermore, the performance of the proposed model is compared with previous literature, where the proposed model outperforms existing methods, demonstrating its effectiveness in breast cancer diagnosis. Lastly, the model demonstrates its robustness for breast cancer classification, delivering an exceptional performance of 96.21 % on a mammogram dataset.

Conclusion: The efficacy of this study relies on image pre-processing, segmentation with hybrid attention UNet, and classification with fine-tuned robust CNN model. This comprehensive approach aims to determine an effective technique for detecting breast cancer within ultrasound images.

Keywords: Channel self attention; Deep learning; Hybrid attention module; Image preprocessing; Image segmentation; Spatial self attention.