Key Trends for Diagnostic Imaging in 2018 and Beyond

The imaging diagnostic industry will witness many disruptive trends in the next few years as the society demands better, faster and inexpensive diagnosis. The industry is expected to witness the following key trends in 2018.

1. Value based radiology outcomes –  Though, there have been many debates about Value based radiology for many years, the imminent programs like Merit-based Incentive Payment System (MIPS) being implemented in the USA starting 2019 has forced the stakeholders to consider new strategies for radiology implementation. This was clearly evident at the RSNA 2017. This is part of a major Patient-centric healthcare reform, wherein the service providers are held accountable for the outcome including diagnostic performance, quality of diagnosis, service and adherence to safety standards.

2. Better integration of Information systems – Availability of holistic picture of the patient’s health at the point-of-care plays a great part in the quality of diagnosis. An integrated workflow approach combining the image viewing capability of PACS and non-image clinical data available in the EHR system would add to the effectiveness of outcomes greatly. Incompatible workflows and data models between various departments of the hospital are a major hurdle which has to be sorted out. The upcoming MIPS program has ‘Meaningful use of EHRs’ as one of the performance categories to assess the composite performance score of the Radiologists.

The rising activity around VNA is another indicator of the need for providing seamless exchange of patient information. It has the potential to become the future of image delivery as well.

3. Artificial Intelligence – Artificial Intelligence (AI) created considerable excitement in RSNA 2017 Yes…the question of ‘will Radiologist be replaced by a machine?’ is still in the air! One thing is certain though; AI can definitely augment the efforts of Radiologists. It can support the ‘normal’ diagnosis, while leaving the ‘exceptions’ to the Radiologists’ discretion. Deep Learning has already made inroads into a number of clinical applications. The first FDA approval for a machine learning application in early 2017 (Arterys) is a major leap for AI and deep learning in healthcare industry.

4. 3D printing – 3D printed models of internal organs are now gaining clinical acceptance. They are primarily used to aid diagnosis and also in complex surgical procedures. Models are now increasingly being used to plan radiotherapy.  The models are used now in clinical education and also to improve patient engagement. The acceptance of stereo-lithography file format by CT and MR device manufacturers have helped create 3D models of the organs and allow interaction with real world objects such as stents. With desktop 3D printers becoming relatively inexpensive, the adoption of this technology in the imaging world is only bound to increase.