Chapter 6 Artificial intelligence in breast cancer management
-
Abstract
Breast cancer is a substantial cause of cancer-related mortality among women worldwide. Timely and accurate diagnosis is essential, and clinical results can be significantly improved. The emergence of artificial intelligence (AI) has brought about a new period, particularly in the field of image analysis, which has paved the way for significant progress in the detection of breast cancer and the development of personalised treatment plans. AI plays a crucial role in the diagnostic workflow for patients with breast cancer, including several aspects, such as screening, diagnosis, staging, biomarker evaluation, prognostication, and predicting therapy response. Imaging detection is a primary method employed in clinical practice to screen, diagnose, and evaluate the effectiveness of treatment. It allows for the visualisation of changes in both the size and texture of tumours before and after treatment. The excessive quantity of images, resulting in a difficult duty for radiologists and a slow reporting timeframe, indicates the necessity for computer-aided detection approaches and systems. The fundamental challenges in breast cancer screening and imaging diagnosis arise from the presence of complex and variable image features, the diverse quality of pictures, and the inconsistent interpretation by different radiologists and medical institutions. Utilising imaging-based AI to help in tumour diagnosis is an optimal approach for enhancing the efficiency and accuracy of imaging diagnosis. Through the process of analysing visual data and developing algorithmic models, AI has the capability to automatically identify, separate, and diagnose tumour lesions. This technology holds great potential for future applications. Furthermore, the implementation of advanced diagnostic methods would ultimately lead to greater patient treatment. This chapter extensively examined the various uses of AI in the field of breast cancer care, emphasising its potential to bring about significant changes.
Abstract
Breast cancer is a substantial cause of cancer-related mortality among women worldwide. Timely and accurate diagnosis is essential, and clinical results can be significantly improved. The emergence of artificial intelligence (AI) has brought about a new period, particularly in the field of image analysis, which has paved the way for significant progress in the detection of breast cancer and the development of personalised treatment plans. AI plays a crucial role in the diagnostic workflow for patients with breast cancer, including several aspects, such as screening, diagnosis, staging, biomarker evaluation, prognostication, and predicting therapy response. Imaging detection is a primary method employed in clinical practice to screen, diagnose, and evaluate the effectiveness of treatment. It allows for the visualisation of changes in both the size and texture of tumours before and after treatment. The excessive quantity of images, resulting in a difficult duty for radiologists and a slow reporting timeframe, indicates the necessity for computer-aided detection approaches and systems. The fundamental challenges in breast cancer screening and imaging diagnosis arise from the presence of complex and variable image features, the diverse quality of pictures, and the inconsistent interpretation by different radiologists and medical institutions. Utilising imaging-based AI to help in tumour diagnosis is an optimal approach for enhancing the efficiency and accuracy of imaging diagnosis. Through the process of analysing visual data and developing algorithmic models, AI has the capability to automatically identify, separate, and diagnose tumour lesions. This technology holds great potential for future applications. Furthermore, the implementation of advanced diagnostic methods would ultimately lead to greater patient treatment. This chapter extensively examined the various uses of AI in the field of breast cancer care, emphasising its potential to bring about significant changes.
Chapters in this book
- Frontmatter I
- Preface V
- Foreword VII
- Contents IX
- About the authors XVII
- Chapter 1 Artificial intelligence in cancer treatment and management 1
- Chapter 2 AI-based approaches to cancer drug discovery 27
- Chapter 3 Integrating AI and digital twin technology in cancer therapy 47
- Chapter 4 AI for enhanced cancer detection and diagnosis 63
- Chapter 5 AI-guided surgical interventions for cancer and tumor removal 99
- Chapter 6 Artificial intelligence in breast cancer management 121
- Chapter 7 AI innovations in colorectal cancer detection and treatment 143
- Chapter 8 AI applications in brain cancer therapy 165
- Chapter 9 Leveraging AI for liver cancer diagnosis and treatment 191
- Chapter 10 AI-driven advances in lung cancer care 213
- Chapter 11 Artificial intelligence in prostate cancer detection and management 243
- Chapter 12 AI solutions for skin cancer diagnosis and treatment 265
- Index 345
- De Gruyter Series on the Applications of Mathematics in Engineering and Information Sciences
Chapters in this book
- Frontmatter I
- Preface V
- Foreword VII
- Contents IX
- About the authors XVII
- Chapter 1 Artificial intelligence in cancer treatment and management 1
- Chapter 2 AI-based approaches to cancer drug discovery 27
- Chapter 3 Integrating AI and digital twin technology in cancer therapy 47
- Chapter 4 AI for enhanced cancer detection and diagnosis 63
- Chapter 5 AI-guided surgical interventions for cancer and tumor removal 99
- Chapter 6 Artificial intelligence in breast cancer management 121
- Chapter 7 AI innovations in colorectal cancer detection and treatment 143
- Chapter 8 AI applications in brain cancer therapy 165
- Chapter 9 Leveraging AI for liver cancer diagnosis and treatment 191
- Chapter 10 AI-driven advances in lung cancer care 213
- Chapter 11 Artificial intelligence in prostate cancer detection and management 243
- Chapter 12 AI solutions for skin cancer diagnosis and treatment 265
- Index 345
- De Gruyter Series on the Applications of Mathematics in Engineering and Information Sciences
