{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T05:20:36Z","timestamp":1791868836272,"version":"4.3.4"},"reference-count":53,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Early detection of breast cancer commonly relies on imaging technologies such as ultrasound, mammography and MRI. Among these, breast ultrasound is widely used by radiologists to identify and assess lesions. In this study, we developed image segmentation techniques and multiclass classification artificial intelligence (AI) tools based on pretrained models to segment lesions and detect breast cancer. The proposed workflow includes both the development of segmentation models and development of a series of classification models to classify ultrasound images as normal, benign or malignant. The pretrained models were trained and evaluated on the Breast Ultrasound Images (BUSI) dataset, a publicly available collection of grayscale breast ultrasound images with corresponding expert-annotated masks. For segmentation, images and ground-truth masks were used to pretrained encoder (ResNet18, EfficientNet-B0 and MobileNetV2)\u2013decoder (U-Net, U-Net++ and DeepLabV3) models, including the DeepLabV3 architecture integrated with a Frequency-Domain Feature Enhancement Module (FEM). The proposed FEM improves spatial and spectral feature representations using Discrete Fourier Transform (DFT), GroupNorm, dropout regularization and adaptive fusion. For classification, each image was assigned a label (normal, benign or malignant). Optuna, an open-source software framework, was used for hyperparameter optimization and for the testing of various pretrained models to determine the best encoder\u2013decoder segmentation architecture. Five different pretrained models (ResNet18, DenseNet121, InceptionV3, MobielNetV3 and GoogleNet) were optimized for multiclass classification. DeepLabV3 outperformed other segmentation architectures, with consistent performance across training, validation and test images, with Dice Similarity Coefficient (DSC, a metric describing the overlap between predicted and true lesion regions) values of 0.87, 0.80 and 0.83 on training, validation and test sets, respectively. ResNet18:DeepLabV3 achieved an Intersection over Union (IoU) score of 0.78 during training, while ResNet18:U-Net++ achieved the best Dice coefficient (0.83) and IoU (0.71) and area under the curve (AUC, 0.91) scores on the test (unseen) dataset when compared to other models. However, the proposed Resnet18: FrequencyAwareDeepLabV3 (FADeepLabV3) achieved a DSC of 0.85 and an IoU of 0.72 on the test dataset, demonstrating improvements over standard DeepLabV3. Notably, the frequency-domain enhancement substantially improved the AUC from 0.90 to 0.98, indicating enhanced prediction confidence and clinical reliability. For classification, ResNet18 produced an F1 score\u2014a measure combining precision and recall\u2014of 0.95 and an accuracy of 0.90 on the training dataset, while InceptionV3 performed best on the test dataset, with an F1 score of 0.75 and accuracy of 0.83. We demonstrate a comprehensive approach to automate the segmentation and multiclass classification of breast cancer ultrasound images into benign, malignant or normal transfer learning models on an imbalanced ultrasound image dataset.<\/jats:p>","DOI":"10.3390\/s25247557","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T14:04:40Z","timestamp":1765548280000},"page":"7557","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning for Tumor Segmentation and Multiclass Classification in Breast Ultrasound Images Using Pretrained Models"],"prefix":"10.3390","volume":"25","author":[{"given":"K. E.","family":"ArunKumar","sequence":"first","affiliation":[{"name":"School of Agriculture and Food Systems, Davis College of Agriculture and Natural Resources, West Virginia University, Morgantown, WV 26506, USA"},{"name":"West Virginia Agricultural and Forestry Experiment Station, Morgantown, WV 26506, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7419-6358","authenticated-orcid":false,"given":"Matthew E.","family":"Wilson","sequence":"additional","affiliation":[{"name":"School of Agriculture and Food Systems, Davis College of Agriculture and Natural Resources, West Virginia University, Morgantown, WV 26506, USA"},{"name":"West Virginia Agricultural and Forestry Experiment Station, Morgantown, WV 26506, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6928-0570","authenticated-orcid":false,"given":"Nathan E.","family":"Blake","sequence":"additional","affiliation":[{"name":"School of Agriculture and Food Systems, Davis College of Agriculture and Natural Resources, West Virginia University, Morgantown, WV 26506, USA"},{"name":"West Virginia Agricultural and Forestry Experiment Station, Morgantown, WV 26506, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1259-1078","authenticated-orcid":false,"given":"Tylor J.","family":"Yost","sequence":"additional","affiliation":[{"name":"School of Agriculture and Food Systems, Davis College of Agriculture and Natural Resources, West Virginia University, Morgantown, WV 26506, USA"},{"name":"West Virginia Agricultural and Forestry Experiment Station, Morgantown, WV 26506, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Walker","sequence":"additional","affiliation":[{"name":"Office of Statistics and Data Analytics, Davis College of Agriculture and Natural Resources, West Virginia University, Morgantown, WV 26506, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,12]]},"reference":[{"key":"ref_1","unstructured":"American Cancer Society (2024, May 05). Breast Cancer Facts & Figures 2024. Available online: https:\/\/www.cancer.org\/content\/dam\/cancer-org\/research\/cancer-facts-and-statistics\/breast-cancer-facts-and-figures\/2024\/breast-cancer-facts-and-figures-2024.pdf."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.clinimag.2023.05.007","article-title":"Emerging uses of artificial intelligence in breast and axillary ultrasound","volume":"100","author":"Trepanier","year":"2023","journal-title":"Clin. Imaging"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1142\/S0219519410003277","article-title":"Breast imaging systems: A review and comparative study","volume":"10","author":"Sree","year":"2010","journal-title":"J. Mech. Med. Biol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1148\/radiol.13121606","article-title":"Breast ultrasonography: State of the art","volume":"268","author":"Hooley","year":"2013","journal-title":"Radiology"},{"key":"ref_5","first-page":"127","article-title":"Artificial intelligence in cancer imaging: Clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA A Cancer J. Clin."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xian, M., Cheng, H.D., Shareef, B., Ding, J., Xu, F., Huang, K., Zhang, B., Ning, C., and Wang, Y. (2022). BUSIS: A benchmark for breast ultrasound image segmentation. Healthcare, 10.","DOI":"10.3390\/healthcare10040729"},{"key":"ref_7","unstructured":"Kayalibay, B., Jensen, G., and van der Smagt, P. (2017). CNN-based segmentation of medical imaging data. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2983","DOI":"10.1016\/j.patcog.2015.04.019","article-title":"CRF learning with CNN features for image segmentation","volume":"48","author":"Liu","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_9","first-page":"566","article-title":"Performance analysis of deep learning CNN models for disease detection in plants using image segmentation","volume":"7","author":"Sharma","year":"2020","journal-title":"Inf. Process. Agric."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Soulami, K.B., Kaabouch, N., Saidi, M.N., and Tamtaoui, A. (2021). Breast cancer: One-stage automated detection, segmentation, and classification of digital mammograms using UNet model based-semantic segmentation. Biomed. Signal Process. Control., 66.","DOI":"10.1016\/j.bspc.2021.102481"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/s12282-018-0857-5","article-title":"An overview of mammographic density and its association with breast cancer","volume":"25","author":"Nazari","year":"2018","journal-title":"Breast Cancer"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Badawy, S.M., Mohamed, A.E., Hefnawy, A.A., Zidan, H.E., GadAllah, M.T., and El-Banby, G.M. (2021). Automatic semantic segmentation of breast tumors in ultrasound images based on combining fuzzy logic and deep learning\u2014A feasibility study. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0251899"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"He, Q., Yang, Q., and Xie, M. (2023). HCTNet: A hybrid CNN-transformer network for breast ultrasound image segmentation. Comput. Biol. Med., 155.","DOI":"10.1016\/j.compbiomed.2023.106629"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Guo, Y., Duan, X., Wang, C., and Guo, H. (2021). Segmentation and recognition of breast ultrasound images based on an expanded U-Net. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0253202"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nastase, I.A., Moldovanu, S., and Moraru, L. (2024). Deep learning-based segmentation of breast masses using convolutional neural networks. J. Phys. Conf. Ser., 2701.","DOI":"10.1088\/1742-6596\/2701\/1\/012005"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhao, G., Lin, Y., Lu, Y., Chen, Z., and Guo, W. (2025). Lightweight bilateral network for Mura detection on micro-OLED displays. Measurement, 255.","DOI":"10.1016\/j.measurement.2025.117937"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yu, X., Liang, X., Zhou, Z., Zhang, B., and Xue, H. (2024). Deep soft threshold feature separation network for infrared handprint identity recognition and time estimation. Infrared Phys. Technol., 138.","DOI":"10.1016\/j.infrared.2024.105223"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., and Li, X. (2021, January 10\u201317). FcaNet: Frequency Channel Attention Networks. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"ref_20","first-page":"980","article-title":"Global filter networks for image classification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"46037","DOI":"10.1007\/s11042-023-17411-5","article-title":"Semantic segmentation of breast cancer images using DenseNet with proposed PSPNet","volume":"83","author":"Samudrala","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Uysal, F., and K\u00f6se, M.M. (2022). Classification of breast cancer ultrasound images with deep learning-based models. Eng. Proc., 31.","DOI":"10.3390\/ASEC2022-13791"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zakareya, S., Izadkhah, H., and Karimpour, J. (2023). A new deep-learning-based model for breast cancer diagnosis from medical images. Diagnostics, 13.","DOI":"10.3390\/diagnostics13111944"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., and Xu, D. (2022, January 3\u20138). Unetr: Transformers for 3d medical image segmentation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 2022, Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Said, Y., Alsheikhy, A.A., Shawly, T., and Lahza, H. (2023). Medical images segmentation for lung cancer diagnosis based on deep learning architectures. Diagnostics, 13.","DOI":"10.3390\/diagnostics13030546"},{"key":"ref_26","unstructured":"Xing, R. (2025). FreqU-FNet: Frequency-Aware U-Net for imbalanced medical image segmentation. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Fu, J., Yu, Y., and Wang, L. (2025). FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation. arXiv.","DOI":"10.1109\/JSTARS.2025.3583558"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Al-Dhabyani, W., Gomaa, M., Khaled, H., and Fahmy, A. (2020). Dataset of breast ultrasound images. Data Brief, 28.","DOI":"10.1016\/j.dib.2019.104863"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Huang, Q., Huang, Y., Luo, Y., Yuan, F., and Li, X. (2020). Segmentation of breast ultrasound image with semantic classification of superpixels. Med. Image Anal., 61.","DOI":"10.1016\/j.media.2020.101657"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"10076","DOI":"10.1109\/TPAMI.2024.3435571","article-title":"Medical image segmentation review: The success of U-Net","volume":"46","author":"Azad","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015, Proceedings of the 18th International Conference, Munich, Germany. Part III.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_32","unstructured":"Tai, X.C., Liu, H., Chan, R.H., and Li, L. (2024). A mathematical explanation of UNet. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","article-title":"UNet++: Redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_34","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., and Tu, Z. (2014). Deeply supervised nets. arXiv."},{"key":"ref_35","first-page":"3","article-title":"Unet++: A nested U-Net architecture for medical image segmentation","volume":"11045","author":"Stoyanov","year":"2018","journal-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Proceedings of the 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018; Granada, Spain, 20 September 2018"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Pedrayes, O.D., Lema, D.G., Garc\u00eda, D.F., Usamentiaga, R., and Alonso, \u00c1. (2021). Evaluation of semantic segmentation methods for land use with spectral imaging using Sentinel-2 and PNOA imagery. Remote Sens., 13.","DOI":"10.3390\/rs13122292"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Chen, L.C. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_38","unstructured":"Dumoulin, V., and Visin, F. (2016). A guide to convolution arithmetic for deep learning. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1109\/TASSP.1987.1165220","article-title":"Real-valued fast Fourier transform algorithms","volume":"35","author":"Sorensen","year":"1987","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_42","unstructured":"Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"113599","DOI":"10.1109\/ACCESS.2021.3105112","article-title":"Circular fruit and vegetable classification based on optimized GoogLeNet","volume":"9","author":"Yuesheng","year":"2021","journal-title":"IEEE Access"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"146533","DOI":"10.1109\/ACCESS.2019.2946000","article-title":"Pulmonary image classification based on inception-v3 transfer learning model","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Meena, G., Mohbey, K.K., and Kumar, S. (2023). Sentiment analysis on images using convolutional neural networks-based Inception-V3 transfer learning approach. Int. J. Inf. Manag. Data Insights, 3.","DOI":"10.1016\/j.jjimei.2023.100174"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision 2019, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Bello, A., Ng, S.C., and Leung, M.F. (2024). Skin Cancer Classification Using Fine-Tuned Transfer Learning of DENSENET-121. Appl. Sci., 14.","DOI":"10.3390\/app14177707"},{"key":"ref_48","unstructured":"Ross, T.Y., and Doll\u00e1r, G.K. (2017, January 21\u201326). Focal loss for dense object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, HI, USA."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2019, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Almajalid, R., Shan, J., Du, Y., and Zhang, M. (2018, January 17\u201320). Development of a deep-learning-based method for breast ultrasound image segmentation. Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) 2018, Orlando, FL, USA.","DOI":"10.1109\/ICMLA.2018.00179"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Byra, M., Jarosik, P., Szubert, A., Galperin, M., Ojeda-Fournier, H., Olson, L., O\u2019Boyle, M., Comstock, C., and Andre, M. (2020). Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network. Biomed. Signal Process. Control., 61.","DOI":"10.1016\/j.bspc.2020.102027"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Badawy, S.M., Mohamed, A.E., Hefnawy, A.A., Zidan, H.E., GadAllah, M.T., and El-Banby, G.M. (2021, January 13\u201315). Classification of Breast Ultrasound Images Based on Convolutional Neural Networks-A Comparative Study. Proceedings of the 2021 International Telecommunications Conference (ITC-Egypt), Alexandria, Egypt.","DOI":"10.1109\/ITC-Egypt52936.2021.9513972"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Yan, J. (2023). Study for Performance of MobileNetV1 and MobileNetV2 Based on Breast Cancer. arXiv.","DOI":"10.54097\/hset.v39i.6340"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/24\/7557\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T11:02:22Z","timestamp":1765882942000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/24\/7557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":53,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["s25247557"],"URL":"https:\/\/doi.org\/10.3390\/s25247557","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,12]]}}}