Using Artificial Intelligence (AI) in breast cancer treatment
The American cancer society simply defines breast cancer as cancer that affects the breast. It occurs when abnormal or old cells in your body don’t die as they should and instead the body continues to produce more cells. Cancer cells have the ability to push out normal cells as they grow out of control. This in turn makes it difficult for your body to function properly.
According to the world health organization (WHO) breast cancer affects over 2.26 million people in 2020 alone and the report by the National Cancer Institute, breast cancer is now the most diagnosed cancer in the United States, with an estimated total of two hundred and eighty-one thousand, (281,000) diagnoses and about Forty-three, thousand, (43,000) deaths in both men and women.
The Institute also predicted that as a direct result of the pandemic, about 10,000 additional deaths from breast and colorectal cancers will occur over the next ten years, making it more crucial than ever for women and men (though in the minority) to take care of their breast health.
If breast cancer is detected in time, it can be successfully treated. As a result, having suitable procedures for detecting the earliest signs of breast cancer is critical.
Artificial Intelligence (AI) technology complements health professionals’ abilities and heralds a new era in which routine and time-consuming jobs in healthcare can be mechanized and done (wholly or partially) by AI systems. In the fight against diseases, the use of AI to assure quality delivery is critical, and there is little doubt that the next decade will see an increasing number of AI applications in healthcare. Machine learning applications in digital pathology for breast cancer, including diagnostic and prognostic applications, will not only supplement but also increase breast pathologists’ diagnosis accuracy.
For many years, computer-assisted diagnosis (CAD) has been widely utilized in radiography, and it was the first program to be approved for clinical use in breast cancer diagnosis. This application is most commonly used to detect breast cancer on mammography and pulmonary nodules on chest CT 3. Mammography is one of the most significant early detection procedures for breast cancer, although it is ineffective in dense breasts, hence ultrasound or diagnostic sonography techniques are recommended instead. Since small malignant tumours can pass radiographic radiation, thermography can be more effective in diagnosing smaller cancerous masses. Traditional feature engineering based on domain expertise was used in these systems, while recent approaches use machine learning to uncover latent characteristics in imaging data.
Role Of AI In Early Detection Of Breast Cancer
1. Imaging Techniques
Breast cancer can be detected and diagnosed using a variety of imaging techniques, the most common of which are mammography, ultrasound, and thermography.
Breast cancer can be detected and diagnosed using a variety of imaging techniques, the most common of which are mammography, ultrasound, and thermography.
Digital breast tomosynthesis (DBT) – often known as 3D mammography – is becoming more used as a screening and diagnostic tool for early-stage breast cancer. DBT delivers enormous data sets consisting of hundreds of images, offering radiologists with higher clarity and depth than typical 2D mammograms, which only produce four images to evaluate. In contrast, reviewing and interpreting each breast exam takes substantially more time.
iCAD, a global medical technology pioneer that provides revolutionary cancer diagnosis and therapy solutions, recently unveiled ProFound AI, its newest solution for DBT.
ProFound AI has been shown to increase cancer detection rates by 8% on average and reduce unnecessary patient recall rates by 7% on average. The new method is also capable of detecting cancerous soft-tissue densities and calcifications. It also gives radiologists scoring information based on the enormous dataset of clinical images used to train the algorithm, which represents the program’s confidence that a certain finding or case is malignant.
Other Types Of Imaging In Breast Cancer Detection Include:
1. Magnetic Resonance Imaging (MRI) is a type of imaging that uses magnets to produce images (MRI) Low-energy radio waves and strong magnets are used to obtain precise pictures of structures within the breast. Its sensitivity ranges from 75 to 100%. The capacity to detect breast cancers that often elude clinical, mammography and ultrasound detection is its principal advantage. Some of the drawbacks of MRI include its high cost and inability to standardize the exam. Unnecessary breast biopsies due to inability to distinguish between malignant and benign lesions.
2. Diffusion-Weighted Imaging is a non-radioactive imaging technology that uses water molecule diffusion to generate contrast. It has an 83% Sensitivity. The failure to detect high water content malignant lesions due to high apparent diffusion coefficients is a key drawback of this imaging.
3. Positron Emission Tomography conjugated with computed Tomography (PETCT), Combines nuclear medicine technique and computed tomography resulting in highly detailed images. It is non-invasive. It provides diagnostic benefits twice (elevated activity within the body detected by PET scan and intricate images of tissues and organs discovered by CT scan). The disadvantage of this approach is its high cost and difficulty to detect cancers smaller than 8mm.
Role of AI In Breast Cancer Treatment
i. Machine learning and deep learning aids in anticancer drug development: Scientists are utilizing machine learning to construct and create reverse synthesis pathways for compounds, which is speeding up drug discovery. The entire process of developing a new medicine generates a large amount of data. Machine learning provides a fantastic opportunity for us to evaluate chemical data and generate conclusions that can aid in drug development. Although deep learning’s application in drug response prediction has just recently been examined, these types of models offer unique qualities that may make them more suitable for complicated tasks such as simulating drug reactions based on biological and chemical data.
ii. AI can be used to forecast anticancer drug action or to aid in the discovery of anticancer drugs. Different malignancies and medications may react in different ways, and data from high-throughput screening processes frequently demonstrate a link between cancer cell genetic diversity and therapeutic activity. In the fight against cancer medication resistance, artificial intelligence plays a key role. By learning and analyzing data on large drug-resistant cancers, AI can swiftly comprehend how cancer cells grow resistant to cancer treatments, which can assist improve medication development and drug use.
ii. AI can be used to forecast anticancer drug action or to aid in the discovery of anticancer drugs. Different malignancies and medications may react in different ways, and data from high-throughput screening processes frequently demonstrate a link between cancer cell genetic diversity and therapeutic activity. In the fight against cancer medication resistance, artificial intelligence plays a key role. By learning and analyzing data on large drug-resistant cancers, AI can swiftly comprehend how cancer cells grow resistant to cancer treatments, which can assist improve medication development and drug use.
Enjoyed this post? Never miss out on any of our future posts by following us»
