Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer
Breast cancer is a serious health concern for women in both developed and developing countries, and early diagnosis is crucial for an effective treatment. One possible approach of detection is by observing abnormal surface temperatures of the breast. To study the thermal behavior of the human breast...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | Results in Applied Mathematics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590037423000304 |
| _version_ | 1797727678327947264 |
|---|---|
| author | Danang A. Pratama Maharani A. Bakar Nur Fadhilah Ibrahim Ruwaidiah Idris Norizan Mohamed |
| author_facet | Danang A. Pratama Maharani A. Bakar Nur Fadhilah Ibrahim Ruwaidiah Idris Norizan Mohamed |
| author_sort | Danang A. Pratama |
| collection | DOAJ |
| description | Breast cancer is a serious health concern for women in both developed and developing countries, and early diagnosis is crucial for an effective treatment. One possible approach of detection is by observing abnormal surface temperatures of the breast. To study the thermal behavior of the human breast, this research paper employs the two-dimensional heat equation’s partial differential equation (PDE). In fact, we propose a method called r-PINN-Adam, which uses Physics-Informed Neural Networks (PINN) with a restarting strategy to solve the PDE thermal analysis. PINN is a method that incorporates physical law in each dataset to solve PDE problems, while Adam is used to update the weights of the ANN and minimize the loss function. The restarting process monitors the progress of the loss values, and if no improvement is made, the process is restarted with the best weights as the initial input to the next cycle. This approach ensures that the method finds the smallest value of the loss function, and it is also more efficient as no time is wasted on iterations that do not significantly improve the results. The PDE thermal analysis was solved for normal and tumorous breasts to study the temperature behavior surrounding the cancer. The proposed r-PINN-Adam method was compared to the basic PINN and other optimizers in terms of accuracy and efficiency. The numerical results indicated that our proposed method yields competitive results compared to state-of-the-art methods, while significantly reducing computational time. |
| first_indexed | 2024-03-12T11:03:02Z |
| format | Article |
| id | doaj.art-f4c9c4621e42401d91259dcc70ef409c |
| institution | Directory Open Access Journal |
| issn | 2590-0374 |
| language | English |
| last_indexed | 2024-03-12T11:03:02Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Applied Mathematics |
| spelling | doaj.art-f4c9c4621e42401d91259dcc70ef409c2023-09-02T04:32:15ZengElsevierResults in Applied Mathematics2590-03742023-08-0119100384Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancerDanang A. Pratama0Maharani A. Bakar1Nur Fadhilah Ibrahim2Ruwaidiah Idris3Norizan Mohamed4Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, MalaysiaSpecial Interest Group Modelling and Data Analytics, Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, Malaysia; Corresponding author.Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, MalaysiaFaculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, Malaysia; Special Interest Group Modelling and Data Analytics, Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, MalaysiaFaculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Nerus, Terengganu, 21030, MalaysiaBreast cancer is a serious health concern for women in both developed and developing countries, and early diagnosis is crucial for an effective treatment. One possible approach of detection is by observing abnormal surface temperatures of the breast. To study the thermal behavior of the human breast, this research paper employs the two-dimensional heat equation’s partial differential equation (PDE). In fact, we propose a method called r-PINN-Adam, which uses Physics-Informed Neural Networks (PINN) with a restarting strategy to solve the PDE thermal analysis. PINN is a method that incorporates physical law in each dataset to solve PDE problems, while Adam is used to update the weights of the ANN and minimize the loss function. The restarting process monitors the progress of the loss values, and if no improvement is made, the process is restarted with the best weights as the initial input to the next cycle. This approach ensures that the method finds the smallest value of the loss function, and it is also more efficient as no time is wasted on iterations that do not significantly improve the results. The PDE thermal analysis was solved for normal and tumorous breasts to study the temperature behavior surrounding the cancer. The proposed r-PINN-Adam method was compared to the basic PINN and other optimizers in terms of accuracy and efficiency. The numerical results indicated that our proposed method yields competitive results compared to state-of-the-art methods, while significantly reducing computational time.http://www.sciencedirect.com/science/article/pii/S2590037423000304Breast cancerPINNAdamRestartingPDE thermal analysis |
| spellingShingle | Danang A. Pratama Maharani A. Bakar Nur Fadhilah Ibrahim Ruwaidiah Idris Norizan Mohamed Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer Results in Applied Mathematics Breast cancer PINN Adam Restarting PDE thermal analysis |
| title | Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer |
| title_full | Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer |
| title_fullStr | Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer |
| title_full_unstemmed | Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer |
| title_short | Physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer |
| title_sort | physical restriction neural networks with restarting strategy for solving mathematical model of thermal heat equation for early diagnose breast cancer |
| topic | Breast cancer PINN Adam Restarting PDE thermal analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2590037423000304 |
| work_keys_str_mv | AT danangapratama physicalrestrictionneuralnetworkswithrestartingstrategyforsolvingmathematicalmodelofthermalheatequationforearlydiagnosebreastcancer AT maharaniabakar physicalrestrictionneuralnetworkswithrestartingstrategyforsolvingmathematicalmodelofthermalheatequationforearlydiagnosebreastcancer AT nurfadhilahibrahim physicalrestrictionneuralnetworkswithrestartingstrategyforsolvingmathematicalmodelofthermalheatequationforearlydiagnosebreastcancer AT ruwaidiahidris physicalrestrictionneuralnetworkswithrestartingstrategyforsolvingmathematicalmodelofthermalheatequationforearlydiagnosebreastcancer AT norizanmohamed physicalrestrictionneuralnetworkswithrestartingstrategyforsolvingmathematicalmodelofthermalheatequationforearlydiagnosebreastcancer |