For India to champion research in radiology, very strong organisational structure and clear strategies are essential at the institutional and policy levels
By Raelene Kambli
We all know that research in the field of radiology and imaging sciences has generated several critical technologies. Many spectacular advances in medical sciences and diagnostics that we see today have been centred around radiology. For example, technologies such as magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, mammography and nuclear medicine that are now omnipresent and are a very critical components of the medical decision making process in healthcare have sharpened modern techniques to identify diseases such as cancer.
However, for all the advances and developments so far in imaging technology, radiology research in India has many a times come under criticism in its efforts to assess the effectiveness and appropriate use of advanced technologies. Take for instance, the integration of digital technologies such as artificial intelligence (AI) and machine learning with imaging technology. Worldwide radiologists are indulging in research utilising AI and machine-learning to seek discoveries that can provide novel methodologies for the detection and treatment of complex human diseases. AI in the west has already made a foothold to optimise radiologists’ workflow, facilitate quantitative radiology, and assist in discovering genomic markers. But in India very few companies seem to crack the code for such integration and many remain clueless of the positive spin-offs of AI in radiology. So, what keeps radiologists in India away from research? How can we build a research culture in the future? And how can research really deliver value in India?
Significance and scope
To understand this aspect it is important to know if the true value of research in radiology is well understood. We spoke to some practising radiologists from across the country to understand their point of view and here is what they have to say.
Ascertaining the significance of research, Dr Bhavin Jankharia, Chief Radiologist, Picture This by Jankharia, says, “It is only through research that we can advance the subject. This includes both basic research with animal experiments to study different molecules, contrast media or disease processes as well as human studies, whether they are randomised double blind-controlled trials or whether they are observational studios. The scope in India is huge. We have barely scratched the surface in India. For example, in oncology, apart from diagnosis, radiology helps with biopsies and treatment, as well as developing new molecules that can be used to manage these tumours better, as with the field of theranostics where nuclear medicine substances are used to treat prostate cancer, etc.”
As Dr Raju Kalindini, CEO and Medical Director at Apollo Radiology International, Apollo Hospitals puts it, imaging science is a multi-disciplinary field concerning generation, modification, analysis, and interpretation of diagnostic medical images. Therefore, research in radiology is also multi-disciplinary in nature and can occur in the fields of computer science, biomedical, mathematics and clinical research. But he feels that research has not been the top priority so far. “As we move more and more towards personalised and precision medicine, the role of accurate and early diagnosis becomes even more critical. Hence, advances in many fields of medicine are directly dependant on research in imaging. The highly varied nature of functioning of radiology departments in India that include diagnostic centres, academic institutions, private hospitals, diagnostic and clinics make research quite difficult. For example, in most diagnostic centres which perform a large share of imaging in India, there is a fractured clinical chain with little scope for the clinico-radiological partnerships required for research. However, a lot of high-quality clinical research does happen in the premier academic institutions and Indian authors have been contributing in more noticeable numbers to radiology literature,” he informs.
Dr Bhavin Vakil, MD Radiology, Bhatia Hospital Mumbai on Radiology and Imaging Science, begs to differ on this stance. He straight away cites examples of compelling research happening within the sector. “Modern research is seeking discoveries to contribute to advances in the treatment of diseases such as cancer and Alzheimer’s disease. In India too, AI has already entered into commercial diagnostics with some organisations deploying Google’s Deep Learning application to identify diabetic retinopathy in patients. There are some start-ups that focus on AI-powered diagnostic tools to counter tobacco-related deaths in India. There are initiatives on deep learning applications for tumour segmentation as well. Likewise, there is an ample amount of other research too in the field of imaging science in India,” he shares.
Adding to this, Dr Vakil points out, “In countries like India where the doctor-patient ratio is reported to be 1:921, deep learning algorithms are being currently used to help radiologists assess cases faster. There are organisations that create algorithms that will make diagnosis for a radiologist quick, easy and accurate. In this, sophisticated AI-enabled decision support tool is used to run standalone or additional information systems. In some places, AI is already being used to detect early stage cancer symptoms, more accurately than conventional methods. Machine-learning models and neural networks can help AI detect such anomalies in a fraction of the time taken by doctors. This is especially crucial in the Indian market, given the size of the population and the lack of intensive diagnostics in many remote areas. Interventional radiology is also seeing continuous advances with aspects like the clinical gene therapy which is rapidly developing and promising.”
So what are the areas that show more potential in India?
AI, nano technology sees more traction
According to a paper published during the Radiological Society of North America Congress, imaging research laboratories in the most advanced nations are rapidly creating machine learning systems that achieve expert human performance using open-source methods and tools. These AI systems are being developed to improve medical image reconstruction, noise reduction, quality assurance, triage, segmentation, computer-aided detection, computer-aided classification and radiogenomics.
India too is following suit and exploring country-specific research, informs Dr Sikandar Shaikh, Consultant PET-CT and Radiology, Yashoda Hospitals, Adjunct Asst Prof, Dept of Biomedical Engg, Asst Prof, Dept of Radiology, Shadan Medical College, Hyderabad, “The biggest research hot cake is AI followed by multi/single randomised trials and efficacy of various modalities going on in various other specialities where radiology is involved. For example the various cancer drug trials. The other research trials are in the field of imaging efficacy in radiology instruments, comparison in various radiology modalities like MR vs PET in various disease diagnosis, molecular imaging technology for diagnosis of disease and therapeutic aspects of disease. Nano technology is one of the promising area for research. The diagnostic and therapeutic aspects are also involved in nano technology.”
Dr Shaikh believes, molecular imaging, nano imaging and robotic imaging have the most potential for research and advancements in coming years. “These are novel modalities to diagnose diseases at the molecular level. The therapeutic option of drug delivery systems by nanotechnology and robotic technology are very promising with very high results in years to come,” he feels.
“Today’s radiology research is rightly focussed on advances in the diagnosis and treatment of challenging diseases including cancer, tuberculosis and Alzheimer’s disease.
adiologists have long struggled with the quantitative and qualitative challenges associated with imaging of these pathologies. The potential of machine learning and AI to radically enhance the scope of imaging in these diseases by its ability to interpret highly complex image patterns at a rapid pace and well beyond the normal human limitations is extremely exciting and can transform the role of imaging in these diseases,” adds Dr Kalindini.
Scope for radio genomics
Just as AI and machine learning applications have seen traction, the other area of interest is genomics and experts hint specific to the scope for further developments in the field of radiogenomics. As per some report from the Pubmed, radiological and clinical phenotyping has found an enhanced role in guiding and interpreting genetic test results. “Genomics and imaging research show great promise for precision medicine to better understand diseases,” opines Dr Kalindini.
“The term radio genomics is popularly used to describe the growing field of study at this cross-section of imaging-based molecular phenotyping and genetic assays derived from biopsy. Studying this area has taken researchers into a new frontier of disease diagnosis, risk stratification, therapy assessment and prognostic medicine,” expresses Dr Vakil.
Need for fostering clinical research
Well, integration of various digital tools in radiology has seen some success but very little is spoken about radiology and clinical trials. Nevertheless, the need for more clinical research is felt deeply by radiologists across the country. “Clinical trials allow the development, registration and finally access new treatments to patients. Imaging can support the drug development process by providing non-invasive assessment of drug action and disease response for the treatment. Even though size measurement criteria are still the most widely used imaging-based assessment, functional imaging techniques are progressively being used in early phase trials to study the initial effects of drug action on characteristics of tumour biology,” Dr Kalindini further states.
Adding to this, Dr Jankharia speaks of some trials that are already existing. “The imaging aspect has relevance in relation to the new patient benefit. The trails for example already included are the efficacy of anti-cancer drugs after treatment by the new novel drugs. The various trails are also mostly in relation to the diagnosis, treatment response and follow-up of treatment response. Without this, we cannot conclude our efficiency of the drugs and response to treatment where imaging again will be a benchmark for the status of the disease,” he asserts.
Dr Vakil expounds further, “Imaging techniques are being rapidly used in oncological clinical trials to provide evidence for decision making. The conventional morphological imaging techniques and standardised response criteria based on tumour size measurements are used increasingly for defining key endpoints. Non-invasive imaging using computed tomography (CT), magnetic resonance imaging (MRI) and fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT plays a seminal role in generating primary, secondary and exploratory study endpoints. In later stages of oncological drug development, imaging forms the basis of robust response and progression criteria to interrogate the drug in a large number of clinical trial subjects.”
While there is some good work happening in silos, experts feel that there is not much backing from the institutions, govt, etc. Dr Jankharia is quiet abrasive while he speaks of Indians and their sense of attitude towards research. He says, “We just don’t have it in us to do good research.” But the others, dissent this accusation. Most experts believe that the challenge at hand is multi-faceted.
“The challenges that modern radiology research face is several including increasing workload and the shortage of qualified labour. There is also a growing demand to keep up with quality standards and to document proper performance. Digitisation is another challenge for radiology. Although experts agree that AI and big data analytics will not replace radiologists any time soon, there is still some concern,” shares Dr Vakil.
Similarly, Dr Kalindini points out that the pursuit of conducting research as a radiologist is challenging especially in India because most of the radiologists have limited time built-in for research due to increasing clinical demands. “The varying ecosystems of radiological practice, as discussed earlier, is also a major barrier. Successful research in radiology requires an integrated multi-disciplinary team approach which is not possible in set ups like diagnostic centres,” he adds.
As rightly indicated by Dr Kalindini, undertaking research of the highest quality involves multitude of factors which can create a far reaching impact. Ensuring access to funding, career progression for researchers, increasing clinical engagement and improving the research infrastructure can really help boost research activities in future.