Cancer is the deadliest disease of all, no matter what type of malignancy it is. Only in 2018, about 9.6 million people have died due to cancer worldwide. Though the cancer death rate has decreased by 27% in the US in the last 25 years, still new stats are not satisfactory.
With the diagnosis of more than 1.7 million new cancer cases and more than 606,000 expected cancer deaths in 2019, advancements in cancer diagnostic methods and treatment options are need of the time.
All researchers and oncologists agree on the fact that early detection of cancer increases the patient's chances of survival tremendously. Unfortunately, most of the cancer patients are diagnosed in the final stages of the disease. In later stages, the tumor has spread excessively leaving no better treatment options for either stopping the metastasis or complete removal of cancer. Recently, Artificial intelligence and deep learning have shown major significance in solving this issue.
Artificial intelligence and machine learning have long been there, hugely affecting our everyday lives by bringing major changes in communication, transportation, and media. Now the researchers have shown a keen interest in using advancements in the field of AI to improve diagnosis, management, and better therapeutic options of various diseases, especially cancer.
The application of artificial intelligence for the betterment of healthcare is booming with each passing day. With new technological advancements in algorithms and improvements in hardware, machine learning and artificial intelligence can learn and analyze an enormous amount of data.
As a vast amount of data of cancer diagnosed patients and those who got various treatments has collected over the years, so it is possible that using this database the artificial intelligence will help in the early diagnosis of cancer.
Using Artificial Intelligence as a Diagnostic Tool
The diagnostic skills of highly sophisticated software have been tested and compared with the traditional diagnostic tools and experts, and found very helpful in diagnosis as well as prognosis of the disease.
A team of researchers from Beth Israel Deaconess Medical Center of Harvard Medical School led by Dr. Andrew Beck showed that analysis of data through deep-learning had decreased the error rate in breast cancer diagnosis by 85%.
Dr. Beck said,
"The goal was to build a computational system to assist in the identification of metastatic areas of cancer in lymph nodes," and the results were astonishing as they successfully diagnosed cancer accurately 92% of the time. With more improvements in the algorithm, researchers achieved 97% accuracy in the results.
Overjoyed with the results, Dr. Beck hoped for further implications of artificial intelligence in oncology saying,
"The implications of this work are large, suggesting that in the future we'll see more examples of AI being used with traditional pathology to make diagnoses more accurate, standardized and predictive,"
Machine-learning algorithms also tested for the diagnosis of melanoma by the researchers of Stanford University. Apart from checking the diagnostic skills of the tool, the researchers also compared these results with certified dermatologists. And artificial intelligence can classify skin cancer as accurately as the dermatologists.
Similarly, researchers tested the commercially available tool for the detection of colorectal cancer, ColonFlag (in Europe) or LGI Flag (in the US), and found that the machine-learning algorithm identified
"individuals with tenfold higher risk of undiagnosed colorectal cancer at curable stages (0/I/II)".
Google is also working on developing an "Augmented Reality Microscope" which can enhance the functioning of existing light microscope "using low-cost, readily-available components, and without the need for whole slide digital versions of the tissue being analyzed." However, the new approach utilizing artificial intelligence would be able to generate results quicker than the manual microscope.
In another study, Adam Yala and his colleagues at the Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology designed an algorithm to analyze the tissue density of the breast. Denser the glandular and fibrous breast tissues are, the higher are the chances of breast cancer development. Traditionally, doctors used the Gail model to find out the risk of malignancy in breast. And more recently, the Gail model was incorporated with the Tyrer-Cuzick (TC) mode to evaluate breast density.
Yala and his team tested and compared the diagnostic abilities of both TC model and convolutional neural network (new algorithm) in analyzing the mammogram images and for the correct prediction of breast cancer. After examining an enormous amount of data of breast cancer patients, the researchers concluded," Deep learning models that use full-field mammograms yield substantially improved risk discrimination compared with the Tyrer-Cuzick (version 8) model".
Chinese researchers used artificial intelligence and machine-learning accurate segmentation of brain tumors. Tumor segmentation is essential for the diagnosis of brain tumor and evaluation of surgical options. Generally, surgeons perform personalized tumor segmentations manually, but its results are not reliable. The seep learning network provided accurate, reliable, and efficient results.
Recently, researchers from the Viterbi School of Engineering at the University of Southern California trained a machine-learning algorithm to differentiate between benign and malignant tumors in breast cancer. They used synthetic data instead of real data to train the algorithm. The results were fascinating, as the lead researcher Prof. Assad Oberai said, "We had about an 80% accuracy rate. Next, we continue to refine the algorithm by using more real-world images as inputs."
Solid Tumor Solutions is SOPHiA GENETICS's (a Swiss company) approved cancer test kit that analyzes DNA samples of patients on an AI platform. This test can accurately detect mutations/ alterations in 42 genes that are linked with solid cancers. This cancer diagnostic kit is assisting doctors in more than 920 hospitals all around the world.
Using Artificial Intelligence in Precision Medicine
Artificial intelligence can have an immense impact on precision medicine. Precision medicine or personalized medicine is a subjective medicinal approach that allows doctors to select the most beneficial treatment option for the patient. The treatment is based on the patient's molecular signature, disease history, and present health condition.
Although the idea of personalized medicine is not the latest, the excessive advances in the field of medical science and technology are helping in speeding up research in this field.
Artificial Intelligence is making remarkable applications in the processes of drug discovery, identification of disease pathways, designing of new drugs, validation of the drugs, discovering disease similarities, discovering new biomarkers, finding molecular mechanisms of pharmacological effects, analyzing the most responsive group of patients for a particular treatment and several others alike.
In 2016, Pfizer Inc. partnered with IBM Watson, which is a deep learning platform that uses extensive medical literature, analyze this medical record, and generate insightful treatment options. Both companies intended to discover immune-oncology therapies and discover new drugs. Mikael Dolsten, President of Pfizer Worldwide Research & Development, hoped for significant benefits in the field of drug discovery and its applications for cancer patients saying,
"With the incredible volume of data and literature available in this complex field, we believe that tapping into advanced technologies can help our scientific experts more rapidly identify novel combinations of immune-modulating agents. We are hopeful that by leveraging Watson's cognitive capabilities in our drug discovery efforts, we will be able to bring promising new immuno-oncology therapeutics to patients more quickly."
A UK based company, Exscientia is the world's leading drug discovery company that explores different dimensions of artificial intelligence to design new drugs. This is the first company that has surpassed conventional drug designing approaches and automated the process. GSK and Sanofi have partnered with Exscientia to find out cancer targets and to develop specific drugs against these targets.
Overall, researchers are taking benefits of artificial intelligence in every dimension of precision medicine, cancer diagnosis, and evaluating the best treatment options for cancer patients. Though excellent results are coming, still, extensive research is needed to improve the results further.