Rethinking Breast Cancer Diagnosis through Deep Learning Based Image Recognition

Kwak, Deawon; Choi, Jiwoo; Lee, Sung‐Jin

doi:10.3390/s23042307

Cited by 12 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semi-automatic and automatic segmentation not only simplify the process but also improve repeatability. In recent years, deep learning has emerged as a powerful alternative for supervised segmentation [30][31][32] . DeepLabv3_resnet50 utilizes a self-attention encoder model structure and combines it with ResNet-50 as a feature extractor 33 .…”

Section: Discussionmentioning

confidence: 99%

Radiomics analysis based on semi-automatic image segmentation of ultrasound for preoperative evaluation of Mammotome-assisted minimally invasive resection

Huang,

Zhu,

et al. 2024

Preprint

View full text Add to dashboard Cite

Previous radiomics studies still relied on manual delineation. DeepLabv3_resnet50 and FCN_resnet50 are deep neural networks commonly used for semantic segmentation in recent years. This study evaluated the effects of two different networks for semi-automatic segmentation of ultrasound images, and established an ensemble model. Purpose Performing a preoperative assessment prior to Mammotome-assisted minimally invasive resection to aid physicians in guiding more precise individualized treatments, our research aims to develop an ultrasound-based semi-automatic segmentation ensemble learning model for preoperative assessment Methods From November 2018 to November 2023, we retrospectively collected preoperative ultrasound images from 733 patients and randomly assigned them to two cohorts in an 8:2 ratio: a training cohort and a testing cohort. Among these, 230 patients without breast tumors were also randomly divided into training and testing cohorts following the same 8:2 ratio. We then selected DeepLabv3_resnet50 and FCN_resnet50 models for semi-automatic image segmentation. Radiomic features and deep transfer learning features were extracted from both semi-automatic segmentation outcomes to construct radiomic models, deep learning models, and deep learning radiomic models. An ensemble learning strategy was employed to integrate the deep learning radiomic models from both pathways with clinical models. The predictive performance was evaluated using receiver operating characteristic curves and decision curve analysis. Results The semi-automatic segmentation model, DeepLabv3_resnet50, achieved a peak global accuracy of 99.4% and an average Dice coefficient of 92.0% at its best epoch. On the other hand, the FCN_resnet50 model exhibited a peak global accuracy of 99.5% and an average Dice coefficient of 93.7% at its best epoch.In the task of predicting tumor and non-tumor patients, the stacking model ultimately demonstrated an AUC of 0.890 in the training cohort (with a sensitivity of 0.844 and a specificity of 0.815) and an AUC of 0.780 in the testing cohort (with a sensitivity of 0.713 and a specificity of 0.739).In the task of predicting adenosis and other lesion types, the stacking model achieved an AUC of 0.890 in the training cohort (with a sensitivity of 0.613 and a specificity of 0.859) and an AUC of 0.771 in the testing cohort (with a sensitivity of 0.759 and a specificity of 0.765). Conclusion Our study has established an ensemble learning model grounded in semi-automatic segmentation techniques. This model accurately distinguishes between tumor and non-tumor patients preoperatively, as well as discriminates adenosis from other lesion types among the non-tumor cohort, thus providing valuable insights for individualized treatment planning.

show abstract

Section: Discussionmentioning

confidence: 99%

Radiomics analysis based on semi-automatic image segmentation of ultrasound for preoperative evaluation of Mammotome-assisted minimally invasive resection

Huang,

Zhu,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The multi-layer perceptron (MLP), deep learning (DL), support vector machine (SVM), and ensemble-based classifier were all outperformed by this suggested approach, with margins of 7.23%, 6.62%, 5.39%, and 3.45%, respectively. Kwak et al [17] used DL methods for medical image identification in their study to dive into the field of breast cancer detection. Their in-depth investigation included a variety of medical imaging modalities, including histology, ultrasonography, and X-ray (Mammography) pictures.…”

Section: Related Workmentioning

confidence: 99%

Detection of Breast Cancer in Mammogram Images Using Multi Attention Feature Extraction with Hybrid RSA Based AlexNet

Bommagani,

Challageri,

Naik

et al. 2024

IJCMEM

View full text Add to dashboard Cite

Breast tumors have become one of the most frequent illnesses among women, with 287,850 new cases projected to be discovered in 2022. Of those, 43,250 women passed away from this malignancy. The mortality rate for cancer might be decreased through early detection. Despite this, employing mammography photographs to manually identify this kind of cancer is a challenging process that always demands an expert. In the literature, a number of AI-based (Artificial Intelligence) strategies have been proposed. However, they still deal with issues including irrelevant feature extraction, inadequate training models, and similarities between cancerous and non-cancerous areas. In order to identify breast cancer, this research suggested an SMO-MAFNet-Hybrid Alexnet model. The images in this study were first preprocessed to get rid of noise. After that, the multi-attention fusion network (MAFNet) is used to extract features. The Spider Monkey Optimization (SMO) method is utilized in this work to optimize the learning rate in MAFNet. Following feature extraction, classification is done using the AlexNet model. In this work, hybrid optimization, namely Ant Colony Optimization-Reptile Search Algorithm (ACO-RSA), is applied to fine-tune the hyperparameters in AlexNet classification. The suggested method was tested using the CBIS-DDSM (Curated breast imaging subset of Digital Database for Screening Mammography) dataset and demonstrated an accuracy of 98%, outperforming previous models.

show abstract

“…Both the layers saved from the feature extractor and the newly added classifier need to be retrained. The purpose of fine-tuning is to increase the specificity of the previously trained model for the current task at hand [ 34 ].…”

Section: Preliminariesmentioning

confidence: 99%

Breast Cancer Classification Using Synthesized Deep Learning Model with Metaheuristic Optimization Algorithm

Thirumalaisamy,

Thangavilou,

Rajadurai

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Breast cancer is the second leading cause of mortality among women. Early and accurate detection plays a crucial role in lowering its mortality rate. Timely detection and classification of breast cancer enable the most effective treatment. Convolutional neural networks (CNNs) have significantly improved the accuracy of tumor detection and classification in medical imaging compared to traditional methods. This study proposes a comprehensive classification technique for identifying breast cancer, utilizing a synthesized CNN, an enhanced optimization algorithm, and transfer learning. The primary goal is to assist radiologists in rapidly identifying anomalies. To overcome inherent limitations, we modified the Ant Colony Optimization (ACO) technique with opposition-based learning (OBL). The Enhanced Ant Colony Optimization (EACO) methodology was then employed to determine the optimal hyperparameter values for the CNN architecture. Our proposed framework combines the Residual Network-101 (ResNet101) CNN architecture with the EACO algorithm, resulting in a new model dubbed EACO–ResNet101. Experimental analysis was conducted on the MIAS and DDSM (CBIS-DDSM) mammographic datasets. Compared to conventional methods, our proposed model achieved an impressive accuracy of 98.63%, sensitivity of 98.76%, and specificity of 98.89% on the CBIS-DDSM dataset. On the MIAS dataset, the proposed model achieved a classification accuracy of 99.15%, a sensitivity of 97.86%, and a specificity of 98.88%. These results demonstrate the superiority of the proposed EACO–ResNet101 over current methodologies.

show abstract

Rethinking Breast Cancer Diagnosis through Deep Learning Based Image Recognition

Cited by 12 publications

References 35 publications

Radiomics analysis based on semi-automatic image segmentation of ultrasound for preoperative evaluation of Mammotome-assisted minimally invasive resection

Radiomics analysis based on semi-automatic image segmentation of ultrasound for preoperative evaluation of Mammotome-assisted minimally invasive resection

Detection of Breast Cancer in Mammogram Images Using Multi Attention Feature Extraction with Hybrid RSA Based AlexNet

Breast Cancer Classification Using Synthesized Deep Learning Model with Metaheuristic Optimization Algorithm

Contact Info

Product

Resources

About