Dilawar Shah, Mohammad Asmat Ullah Khan, Mohammad Abrar
Breast cancer imaging is paramount to quickly detecting and accurately evaluating the disease. The scarcity of annotated mammogram data presents a significant obstacle when building deep learning models that can produce reliable outcomes. This paper proposes a novel approach that utilizes deep convolutional generative adversarial networks (DCGANs) to effectively tackle the issue of limited data availability. The main goal is to produce synthetic mammograms that accurately reproduce the intrinsic patterns observed in real data, enhancing the current dataset. The proposed synthesis method is supported by thorough experimentation, demonstrating its ability to reproduce diverse viewpoints of the breast accurately. A mean similarity assessment with a standard deviation was performed to evaluate the credibility of the synthesized images and establish the clinical significance of the data obtained. A thorough evaluation of the uniformity within each class was conducted, and any deviations from each class’s mean values were measured. Including outlier removal using a specified threshold is a crucial process element. This procedure improves the accuracy level of each image cluster and strengthens the synthetic dataset’s general dependability. The visualization of the class clustering results highlights the alignment between the produced images and the inherent distribution of the data. After removing outliers, distinct and consistent clusters of homogeneous data points were observed. The proposed similarity assessment demonstrates noteworthy effectiveness, eliminating redundant and dissimilar images from all classes. Specifically, there are 505 instances in the normal class, 495 instances in the benign class, and 490 instances in the malignant class out of 600 synthetic mammograms for each class. To check the further validity of the proposed model, human experts visually inspected and validated synthetic images. This highlights the effectiveness of our methodology in identifying substantial outliers.
{"title":"Reliable Breast Cancer Diagnosis with Deep Learning: DCGAN-Driven Mammogram Synthesis and Validity Assessment","authors":"Dilawar Shah, Mohammad Asmat Ullah Khan, Mohammad Abrar","doi":"10.1155/2024/1122109","DOIUrl":"https://doi.org/10.1155/2024/1122109","url":null,"abstract":"Breast cancer imaging is paramount to quickly detecting and accurately evaluating the disease. The scarcity of annotated mammogram data presents a significant obstacle when building deep learning models that can produce reliable outcomes. This paper proposes a novel approach that utilizes deep convolutional generative adversarial networks (DCGANs) to effectively tackle the issue of limited data availability. The main goal is to produce synthetic mammograms that accurately reproduce the intrinsic patterns observed in real data, enhancing the current dataset. The proposed synthesis method is supported by thorough experimentation, demonstrating its ability to reproduce diverse viewpoints of the breast accurately. A mean similarity assessment with a standard deviation was performed to evaluate the credibility of the synthesized images and establish the clinical significance of the data obtained. A thorough evaluation of the uniformity within each class was conducted, and any deviations from each class’s mean values were measured. Including outlier removal using a specified threshold is a crucial process element. This procedure improves the accuracy level of each image cluster and strengthens the synthetic dataset’s general dependability. The visualization of the class clustering results highlights the alignment between the produced images and the inherent distribution of the data. After removing outliers, distinct and consistent clusters of homogeneous data points were observed. The proposed similarity assessment demonstrates noteworthy effectiveness, eliminating redundant and dissimilar images from all classes. Specifically, there are 505 instances in the normal class, 495 instances in the benign class, and 490 instances in the malignant class out of 600 synthetic mammograms for each class. To check the further validity of the proposed model, human experts visually inspected and validated synthetic images. This highlights the effectiveness of our methodology in identifying substantial outliers.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"65 2","pages":"1122109:1-1122109:13"},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140449540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yatong Chang, Wenjian Luo, Xin Lin, Zhen Song, C. Coello
{"title":"Biparty multiobjective optimal power flow: The problem definition and an evolutionary approach","authors":"Yatong Chang, Wenjian Luo, Xin Lin, Zhen Song, C. Coello","doi":"10.2139/ssrn.4381246","DOIUrl":"https://doi.org/10.2139/ssrn.4381246","url":null,"abstract":"","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"9 1","pages":"110688"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74693673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yusuf Fatihu Hamza, M. F. Hamza, A. Rababah, Salisu Ibrahim
There are substantial methods of degree reduction in the literature. Existing methods share some common limitations, such as lack of geometric continuity, complex computations, and one-degree reduction at a time. In this paper, an approximate geometric multidegree reduction algorithm of Wang–Ball curves is proposed. G 0 -, G 1 -, and G 2 -continuity conditions are applied in the degree reduction process to preserve the boundary control points. The general equation for high-order (G2 and above) multidegree reduction algorithms is nonlinear, and the solutions of these nonlinear systems are quite expensive. In this paper, C 1 -continuity conditions are imposed besides the G 2 -continuity conditions. While some existing methods only achieve the multidegree reduction by repeating the one-degree reduction method recursively, our proposed method achieves multidegree reduction at once. The distance between the original curve and the degree-reduced curve is measured with the L 2 -norm. Numerical example and figures are presented to state the adequacy of the algorithm. The proposed method not only outperforms the existing method of degree reduction of Wang–Ball curves but also guarantees geometric continuity conditions at the boundary points, which is very important in CAD and geometric modeling.
{"title":"Geometric Degree Reduction of Wang-Ball Curves","authors":"Yusuf Fatihu Hamza, M. F. Hamza, A. Rababah, Salisu Ibrahim","doi":"10.1155/2023/5483111","DOIUrl":"https://doi.org/10.1155/2023/5483111","url":null,"abstract":"There are substantial methods of degree reduction in the literature. Existing methods share some common limitations, such as lack of geometric continuity, complex computations, and one-degree reduction at a time. In this paper, an approximate geometric multidegree reduction algorithm of Wang–Ball curves is proposed. \u0000 \u0000 \u0000 \u0000 G\u0000 \u0000 \u0000 0\u0000 \u0000 \u0000 \u0000 -, \u0000 \u0000 \u0000 \u0000 G\u0000 \u0000 \u0000 1\u0000 \u0000 \u0000 \u0000 -, and \u0000 \u0000 \u0000 \u0000 G\u0000 \u0000 \u0000 2\u0000 \u0000 \u0000 \u0000 -continuity conditions are applied in the degree reduction process to preserve the boundary control points. The general equation for high-order (G2 and above) multidegree reduction algorithms is nonlinear, and the solutions of these nonlinear systems are quite expensive. In this paper, \u0000 \u0000 \u0000 \u0000 C\u0000 \u0000 \u0000 1\u0000 \u0000 \u0000 \u0000 -continuity conditions are imposed besides the \u0000 \u0000 \u0000 \u0000 G\u0000 \u0000 \u0000 2\u0000 \u0000 \u0000 \u0000 -continuity conditions. While some existing methods only achieve the multidegree reduction by repeating the one-degree reduction method recursively, our proposed method achieves multidegree reduction at once. The distance between the original curve and the degree-reduced curve is measured with the \u0000 \u0000 \u0000 \u0000 L\u0000 \u0000 \u0000 2\u0000 \u0000 \u0000 \u0000 -norm. Numerical example and figures are presented to state the adequacy of the algorithm. The proposed method not only outperforms the existing method of degree reduction of Wang–Ball curves but also guarantees geometric continuity conditions at the boundary points, which is very important in CAD and geometric modeling.","PeriodicalId":8218,"journal":{"name":"Appl. Comput. Intell. Soft Comput.","volume":"17 7 1","pages":"5483111:1-5483111:10"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88628805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：