The field of medicine is currently witnessing a major paradigm shift in the design principles of many computer-based tools that are being used in the clinic. There is great debate about the speed with which newer deep learning methods will be implemented in clinical healthcare practice with speculations for the time needed to fully automate clinical tasks ranging from a few years to decades. Regardless of whether machine- or human-based aids are leveraged, healthcare needs such aids. Improving performance has become vital to its future.
Artificial intelligence (AI), particularly deep learning algorithms, have demonstrated remarkable success in the field of healthcare and image-recognition tasks. Healthcare practice historically has been dependent on trained physicians who visually assess the medical images for detection, characterisation and monitoring of diseases. At the same time there is a relative paucity of trained expert physicians compared to the patient density and the disease burden in our country. We believe, AI has the potential to bridge this gap to a large extent. In the current era of AI, there is a paradigm shift where AI methods have the potential to automatically recognising complex patterns in imaging data and provide quantitative, rather than qualitative, assessments of radiographic characteristics.
With seamless integration of the AI component within the healthcare workflow, there is great potential to increase efficiency, reduce errors and turn-around-times by automating the mundane repetitive tasks which the physicians perform. Rather, their expertise can be augmented and supplemented by providing trained radiologists and pathologists with pre-screened images and identified features, enhancing their work outputs. Hence, considerable efforts need to be put to plan and strategically design, allocate funds and implement the technological advances related to AI in medical imaging. Almost all image-based healthcare tasks are dependent upon the quantification and assessment of radiographic and pathologic characteristics from their images.
The adoption of AI in the healthcare sector especially in the public sector, can have far-reaching implications in terms of augmenting accessibility to healthcare services through early detection, diagnostic, decision making, treatment planning and monitoring, and is expected to see an exponential increase in the next few years. It has the potential to augment the care physicians and other healthcare workers provide and should be seen as ‘Augmented and Assistive Intelligence’ rather than ‘Alternative Intelligence’. The time is ripe for developing countries like India to join the race to lead the AI revolution, which is still in the making. Strategic positioning, ethical considerations and joint public private sector collaborations will ensure smooth transition and implementation of AI in healthcare especially healthcare.
Recognising the potential of AI to transform India’s economy, the Government of India authorised ‘NITI (National Institution for transforming India) Aayog’ to address the national strategy on artificial intelligence and other emerging technologies. In pursuit of the above, NITI Aayog has collaborated with several leading AI technology companies to implement AI projects in critical areas such as agriculture and health. AI-based Radiomics project supported by NITI Aayog in collaboration with Tata Memorial Centre Imaging Biobank (figure 1): (Machine learning and Artificial Intelligence Database (MAD), Tumor Radiomics Atlas Project (TRAP) for Cancer and Human Cancer Pathology Atlas) is currently underway under the leadership of Dr Sudeep Gupta with principal investigators being Dr Abhishek Mahajan, Associate Professor, Radiology and Dr Swapnil Rane, Assistant Professor, Pathology. This project will allow the generation of imaging biomarkers for use in research studies, support biological validation of existing and novel imaging biomarkers and in the long run, provide an unprecedented opportunity to improve decision-support in cancer treatment at low cost.
The TMC Imaging Biobank for Cancer will be one of the most ambitious and exciting health research opportunities in recent years for TMC in collaboration with GoI and will provide wide range of opportunities across the nation. It will provide an unprecedented level of information to help scientists and oncologist working on cancer biology to develop and validate AI algorithms. This will be an organised database of medical images and associated imaging biomarkers (healthcare and beyond) shared among researchers within and outside the country and linked to other biorepositories.- Express Healthcare