Detecting cancer through medical imaging
August 5, 2015
By Hamada Al-Absi
According to estimates from the International Agency for Research on Cancer, there were 14.1 million new cancer cases worldwide in 2012. Of this, eight million occurred in developing countries, which consists of about 82% of the world’s population. In Malaysia, 21,773 cancer cases are registered each year while about 10,000 cases are unregistered, according to the National Cancer Registry.
Besides a change in diet and lifestyle, healthcare practitioners also suggest annual medical check-ups so as to ensure one is in good health. It is also a means to detect any form of cancer in its early stages so as to administer the appropriate treatment. In some cases, however, medical imaging may be recommended for further analysis of one’s condition. You may have come across such terms as CT scan, MRI or X-ray. Very simply, they refer to medical imaging, the technique and process to create a visual representation of the interior of the body for clinical analysis and medical intervention.
In fact, medical imaging has transformed modern healthcare as we know it today. Every day around the world, it is a tool medical practitioners turn to for the diagnoses and treatment of ailments. Undoubtedly, this method of looking into the body has saved countless lives. If not for medical imaging, many lives may have been lost. With early diagnoses through the images obtained, better and more targeted treatment can be applied.
Until a few decades ago, this process was dominated by X-ray radiography to detect changes in tissue density that may result from abnormalities in cell function, possibly due to cancer. But more recently, as a result of improvements in computer technology, digital techniques were introduced. Powerful diagnostic tomographic modalities were made available to clinicians, namely X-ray computed tomography (CT), magnetic resonance imaging (MRI) and nuclear medicine techniques such as single photon emission computed tomography (SPECT) and positron emission tomography (PET).
Diagnostic radiology techniques such as CT and conventional MRI detect structural or anatomical abnormalities whereas nuclear medicine techniques, in particular PET, and to some extent advanced MRI techniques, have the ability to detect cancer based on molecular and biochemical processes within the tumour tissue. Advances in hardware and software have enabled the realization of clinically feasible via using two or more imaging techniques together (multimodality) in which both the structure and the behaviour of the cancer can be determined. For example, PET can be combined with CT to produce PET-CT images. And, PET can be combined with MRI to produce PET-MRI, thereby providing a comprehensive view of the cancer.
The images produced are examined by radiologists for diagnosis and to determine if there are signs of cancer. However, in some cases it has been reported that radiologists, especially those who are less experienced, face difficulties in identifying subtle and small cancerous cells. To resolve this issue, Computer Aided Detection (CAD) systems have been introduced to assist radiologists with the analysis of medical images.
The CAD system relies on intelligent computer algorithms, or formulae, which are designed and developed to evaluate medical images and detect abnormalities i.e. breast cancer. Computer scientists have been working on the development of CAD systems for the past four decades or more and the results are a boon to radiologists as well as patients. As a complementary tool to radiologists, the system has proven itself in identifying abnormal cells in regions of the human body that the naked eye could not pick up.
The evaluation of the system’s success is measured through its accuracy rate in detecting the abnormal regions in the organ, and speed (i.e. how fast it takes to analyse and show the abnormal regions). These two key measurements continue to improve with research, and new technologies and advanced algorithms are being developed.
Radiologists, with the assistance of CAD systems, are contributing tremendously to the battle against cancer with its early detection capability. It has thus played a role in increasing the success rate of treatments and reducing the number of cancer deaths.
Hamada Al-Absi is a lecturer and researcher at the Faculty of Engineering, Computing and Science at Swinburne University of Technology Sarawak Campus. He is contactable at email@example.com