Improving Breast Cancer Detection and Diagnosis Through Semantic Segmentation Using the Unet3+ Deep Learning Framework

Overview

Journal Biomedicines

Specialty Biomedical Engineering

Date 2023 Jun 28

PMID 37371631

Authors

Taukir Alam

Wei-Chung Shia

Fang-Rong Hsu

Taimoor Hassan

Affiliations

Soon will be listed here.

Abstract

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide a more accurate and objective diagnosis of breast cancer, leading to improved patient outcomes.

Citing Articles

Multi-attention Mechanism for Enhanced Pseudo-3D Prostate Zonal Segmentation.

Krishnan C, Onuoha E, Hung A, Sung K, Kim H J Imaging Inform Med. 2025; .

PMID: 40021566 DOI: 10.1007/s10278-025-01401-0.

Extracting Knowledge from Machine Learning Models to Diagnose Breast Cancer.

Martinez-Ramirez J, Carmona C, Ramirez-Exposito M, Martinez-Martos J Life (Basel). 2025; 15(2).

PMID: 40003620 PMC: 11856414. DOI: 10.3390/life15020211.

Segmentation of ADPKD Computed Tomography Images with Deep Learning Approach for Predicting Total Kidney Volume.

Sheng T, Onthoni D, Gupta P, Lee T, Sahoo P Biomedicines. 2025; 13(2).

PMID: 40002677 PMC: 11852143. DOI: 10.3390/biomedicines13020263.

Innovative breast cancer detection using a segmentation-guided ensemble classification framework.

Bala P, Palani U Biomed Eng Lett. 2025; 15(1):179-191.

PMID: 39781047 PMC: 11704121. DOI: 10.1007/s13534-024-00435-7.

Multi-scale feature fusion of deep convolutional neural networks on cancerous tumor detection and classification using biomedical images.

Prakash U, Iniyan S, Dutta A, Alsubai S, Naga Ramesh J, Mohanty S Sci Rep. 2025; 15(1):1105.

PMID: 39774273 PMC: 11707024. DOI: 10.1038/s41598-024-84949-1.

References

Wang L . Early Diagnosis of Breast Cancer. Sensors (Basel). 2017; 17(7). PMC: 5539491. DOI: 10.3390/s17071572. View

Michael E, Ma H, Li H, Kulwa F, Li J . Breast Cancer Segmentation Methods: Current Status and Future Potentials. Biomed Res Int. 2021; 2021:9962109. PMC: 8321730. DOI: 10.1155/2021/9962109. View

Lu H, She Y, Tie J, Xu S . Half-UNet: A Simplified U-Net Architecture for Medical Image Segmentation. Front Neuroinform. 2022; 16:911679. PMC: 9218935. DOI: 10.3389/fninf.2022.911679. View

Bartolotta T, Taibbi A, Picone D, Anastasi A, Midiri M, Lagalla R . Detection of liver metastases in cancer patients with geographic fatty infiltration of the liver: the added value of contrast-enhanced sonography. Ultrasonography. 2017; 36(2):160-169. PMC: 5381848. DOI: 10.14366/usg.16041. View

Larbi A, Fourneret B, Lukas C, Baron M, Molinari N, Taourel P . Prevalence and topographic distribution of spinal inflammation on MR imaging in patients recently diagnosed with axial spondyloarthritis. Diagn Interv Imaging. 2016; 98(4):347-353. DOI: 10.1016/j.diii.2016.10.005. View

Zhang S, Liao M, Wang J, Zhu Y, Zhang Y, Zhang J . Fully automatic tumor segmentation of breast ultrasound images with deep learning. J Appl Clin Med Phys. 2022; 24(1):e13863. PMC: 9859996. DOI: 10.1002/acm2.13863. View

Hsieh Y, Hsu F, Dai S, Huang H, Chen D, Shia W . Incorporating the Breast Imaging Reporting and Data System Lexicon with a Fully Convolutional Network for Malignancy Detection on Breast Ultrasound. Diagnostics (Basel). 2022; 12(1). PMC: 8774546. DOI: 10.3390/diagnostics12010066. View

Zhou Z, Siddiquee M, Tajbakhsh N, Liang J . UNet++: A Nested U-Net Architecture for Medical Image Segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2020; 11045:3-11. PMC: 7329239. DOI: 10.1007/978-3-030-00889-5_1. View

Pereira D, Ramos R, do Nascimento M . Segmentation and detection of breast cancer in mammograms combining wavelet analysis and genetic algorithm. Comput Methods Programs Biomed. 2014; 114(1):88-101. DOI: 10.1016/j.cmpb.2014.01.014. View

10.

Li X, Chen H, Qi X, Dou Q, Fu C, Heng P . H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes. IEEE Trans Med Imaging. 2018; 37(12):2663-2674. DOI: 10.1109/TMI.2018.2845918. View

11.

Schoemaker M, Jones M, Wright L, Griffin J, McFadden E, Ashworth A . Psychological stress, adverse life events and breast cancer incidence: a cohort investigation in 106,000 women in the United Kingdom. Breast Cancer Res. 2016; 18(1):72. PMC: 4946095. DOI: 10.1186/s13058-016-0733-1. View

12.

Shia W, Lin L, Chen D . Classification of malignant tumours in breast ultrasound using unsupervised machine learning approaches. Sci Rep. 2021; 11(1):1418. PMC: 7809485. DOI: 10.1038/s41598-021-81008-x. View

13.

Hai J, Qiao K, Chen J, Tan H, Xu J, Zeng L . Fully Convolutional DenseNet with Multiscale Context for Automated Breast Tumor Segmentation. J Healthc Eng. 2019; 2019:8415485. PMC: 6350548. DOI: 10.1155/2019/8415485. View

14.

Chen Z, Strange H, Oliver A, R E Denton E, Boggis C, Zwiggelaar R . Topological modeling and classification of mammographic microcalcification clusters. IEEE Trans Biomed Eng. 2014; 62(4):1203-14. DOI: 10.1109/TBME.2014.2385102. View

15.

Irfan R, Almazroi A, Rauf H, Damasevicius R, Nasr E, Abdelgawad A . Dilated Semantic Segmentation for Breast Ultrasonic Lesion Detection Using Parallel Feature Fusion. Diagnostics (Basel). 2021; 11(7). PMC: 8304124. DOI: 10.3390/diagnostics11071212. View

16.

Guo Y, Duan X, Wang C, Guo H . Segmentation and recognition of breast ultrasound images based on an expanded U-Net. PLoS One. 2021; 16(6):e0253202. PMC: 8205136. DOI: 10.1371/journal.pone.0253202. View

17.

Rezk E, Awan Z, Islam F, Jaoua A, Maadeed S, Zhang N . Conceptual data sampling for breast cancer histology image classification. Comput Biol Med. 2017; 89:59-67. DOI: 10.1016/j.compbiomed.2017.07.018. View

18.

Varela C, Tahoces P, Mendez A, Souto M, Vidal J . Computerized detection of breast masses in digitized mammograms. Comput Biol Med. 2006; 37(2):214-26. DOI: 10.1016/j.compbiomed.2005.12.006. View

19.

Yin X, Sun L, Fu Y, Lu R, Zhang Y . U-Net-Based Medical Image Segmentation. J Healthc Eng. 2022; 2022:4189781. PMC: 9033381. DOI: 10.1155/2022/4189781. View

20.

Avci H, Karakaya J . A Novel Medical Image Enhancement Algorithm for Breast Cancer Detection on Mammography Images Using Machine Learning. Diagnostics (Basel). 2023; 13(3). PMC: 9914723. DOI: 10.3390/diagnostics13030348. View