Breast cancer, a prevalent and potentially fatal disease, underscores the need for early and accurate detection to improve patient outcomes. Traditional histopathological examination, the current gold standard for diagnosis, faces limitations like subjectivity and low efficiency. In response, this research seeks to revolutionize breast cancer diagnostics by using deep learning techniques to classify invasive and noninvasive breast cancer types from histopathological images. Non-invasive cancers, like DCIS and LCIS, are confined to milk ducts or lobules, while invasive cancers spread to surrounding tissue and make up 70% of cases, often leading to poorer outcomes. The proposed AI model aims to enhance diagnostic accuracy and efficiency, surpassing manual methods, and providing a scalable solution for diverse healthcare settings. By automating image analysis, the model seeks to democratize cancer screening, making it accessible in underserved populations and adaptable to different resources and equipment. Ultimately, this research aims to advance breast cancer detection, improve patient care, and contribute to better treatment outcomes globally.
Breast cancer, a widespread and potentially fatal illness, emphasizes the urgent requirement for early and precise detection to enhance patient outcomes. The current diagnostic framework, characterized by manual histopathological examination, exhibits inherent drawbacks such as subjectivity and limited throughput. In response, our research aims to transform breast cancer diagnostics by leveraging advanced computational techniques, particularly deep learning. Breast cancer can be classified into two main subtypes: invasive and noninvasive. Noninvasive breast cancer, often termed in situ breast cancer, is characterized by abnormal cells confined within the milk ducts (ductal carcinoma in situ or DCIS) or lobules (lobular carcinoma in situ or LCIS) without invading surrounding tissues. This type is considered an early stage and typically not life-threatening on its own. Invasive breast cancers are those that spread from the original site (either the milk ducts or the lobules) into the surrounding breast tissue. These constitute approximately 70% of all breast cancer cases and generally have a poorer prognosis compared to the in-situ subtypes. Medical imaging of breasts can be acquired through various techniques, such as MRI scans, mammography, ultrasound, thermography, computed tomography scans, and histopathology. Among these approaches, the histopathology test serves as the gold standard for the clinical diagnosis of cancer. The proposed AI model aims to streamline and enhance the analysis of histopathological images for the classification of invasive and noninvasive breast cancer, surpassing conventional methods and providing a reliable means of identifying cancerous regions. This promises to significantly improve the accuracy and efficiency of breast cancer diagnostics, meeting the urgent need for dependable and scalable solutions. By automating the complex process of breast cancer histopathological image analysis, our goal is to democratize screening, making it more accessible and reaching underserved populations. Moreover, our model goes beyond technological innovation; it addresses broader issues of accessibility and scalability, particularly in low-income settings. The research's focus on domain adaptation is crucial, ensuring the model's accuracy and reliability across various health facilities. This involves accommodating differences in resources, equipment, and demographic factors, making it a versatile and adaptable solution for diverse contexts. In summary, our research not only aims to advance the technological frontier in breast cancer diagnostics but also seeks to drive a transformative change in accessibility, efficiency, and reliability. By developing an AI model that tackles the specific challenges of traditional methods, we aim to make a meaningful impact on breast cancer screening, ultimately leading to early detection, tailored treatment, and improved outcomes for patients worldwide.
Study Type
OBSERVATIONAL
Enrollment
500
Biopsy: This intervention involves the collection of breast tissue samples through a biopsy procedure. These samples are obtained from women undergoing investigation for unusual cell growth and are analyzed to detect potential abnormalities, including benign, in situ, or invasive cancerous changes. Mastectomy: This intervention refers to the surgical removal of breast tissue, typically performed to treat or prevent the spread of breast cancer. It may involve the removal of part or all of the breast and is considered in cases of invasive breast cancer or high-risk noninvasive breast cancer. Histopathology: This intervention focuses on the microscopic examination of breast tissue samples collected through biopsy or mastectomy. Histopathological analysis is conducted to assess cellular abnormalities, determine the presence of cancer, and classify the tissue as benign, in situ, or invasive, providing the basis for diagnosis and treatment decisions.
National Institute of Cancer Research & Hospital (NICRH)
Dhaka, Bangladesh
RECRUITINGAccuracy of Deep Learning Model in Classifying Breast Tissue as Normal Benign, In Situ, or Invasive.
The primary outcome of this study is the diagnostic accuracy of the deep learning model in classifying histopathological images from breast biopsies into three categories: benign, in situ (noninvasive), and invasive breast cancer. Accuracy will be measured by comparing the model's predictions to the ground truth diagnoses determined by expert pathologists.
Time frame: Measured at the time of histopathological image analysis (within 1 week of biopsy or mastectomy).
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.