Innovations in Medical Imaging – From Images to Informatics

Unlike the innovations of the past, medical imaging advances may have less to do with the image acquisition itself, and instead be more about the cutting-edge technologies from other industries propelling it forward. Frost & Sullivan has identified five avenues along which innovation is likely to occur.

Over the last 25 years, the medical imaging industry has undergone tremendous change—in the process transforming the health care industry itself. The changes have been dramatic: from analog to digital systems; from invasive to non-invasive imaging; and from pixelated, black-and-white, two-dimensional images to color-rich, three-dimensional imaging. As impactful as this has been, Frost & Sullivan believes that the medical imaging industry will truly transform in the next decade.

Unlike the innovations of the past, medical imaging advances may have less to do with the image acquisition itself, and instead be more about the cutting-edge technologies from other industries propelling it forward. Frost & Sullivan has identified five avenues along which innovation is likely to occur.

Mobile Imaging

Nearly every imaging modality—ultrasound, magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET)—has a mobile read-out. A physician may view medical images on a smartphone or a tablet computer. While a number of these mobile viewers are regulated as being for reference purposes only, a pipeline of products are awaiting U.S. Food and Drug Administration (FDA) approval. This will provide physicians and patients with a greater degree of mobility and make image sharing and remote consultations easier.

Imaging systems themselves are becoming mobile. This is seen most clearly in ultrasound imaging with the advent of pocket devices. The ultrasound transducer is connected to a specially made smartphone or a portable console, making it a great value addition in emergency rooms and at the patient bedside, where conventional, cart-based systems may not be readily available. In 2008, MIT Technology Review carried a profile of the world’s first pocket ultrasound device: Siemens’ Acuson. Since then, the pocket device market has exploded into a multibillion-dollar industry. All major ultrasound manufacturers (GE, Siemens, Fujifilm Sonosite, Toshiba, Samsung Medison and Philips) have a portable variant in their product portfolios, while at least half-dozen companies manufacture only portable devices.

Key opinion leaders and clinical researchers have suggested that ultrasound devices, which provide real-time, high-definition visualizations, could replace stethoscopes as physicians’ primary examination tool.

Big Data in Health Care

Declining medical imaging prices and a greater dependence on high-resolution images and videos for diagnosis have resulted in a medical data explosion. Frost & Sullivan estimates that by 2020, the volume of data generated and archived in the United States alone will exceed 2,500 petabytes (1 petabyte equals 1 million gigabytes). This necessitates a radically different approach to handling data, which conventionally relies on monolithic data archives.

A Big Data-based medical imaging stack would include both structured and unstructured images, requiring interaction with a variety of vendors and solution providers that handle various aspects of data capture, storage, management, analysis, reporting and decision support. The market is dominated by data companies IBM, McKesson, Lexmark and Dell, and healthcare companies such as GE, Philips and Siemens.

Imaging Informatics

The next logical avenue for innovation would be to make use of the petabytes of data being generated every day. To make sense of the vast and diverse data types—images, text, video, and reference databases—is no mean (or manual) feat. This is where Big Data analytics platforms such as Hadoop and NoSQL, and artificial intelligence tools come into play.

Instead of subjecting diagnosticians to a deluge of data—and conversely subjecting complex data to a poor laboratory technician—advanced algorithms can help in the analysis and interpretation of medical images. Computer-aided diagnosis is already popular in clinical practices; this could evolve into a computer-only diagnosis. It is possible that machine learning algorithms will take over the task of interpreting images, comparing test results with reference standards and the patient’s own past records, and presenting radiologists with outcomes. In essence, radiologists will cease looking at medical imaging, basing their clinical decisions solely on information supplied by advanced algorithms.

Hybrid Imaging

As the name indicates, hybrid imaging is the fusion of two or more imaging modalities in clinical practice. By doing this, the challenges associated with the individual modalities can be addressed, and the fused imaging platform produces a more powerful diagnostic imaging platform for clinicians. The fusion of PET and CT was an instant success, as evident from the rapid market growth. Other hybrid systems, such as ultrasound/MRI, MRI/angiography, and single photon emission computed tomography (SPECT)/CT, all bring new capabilities and strengths to diagnosis.

The fusion of nuclear imaging techniques such as PET and SPECT showcase, for the first time, in vivo molecular processes in the larger context of anatomical imaging. While PET/CT and SPECT/CT have become mainstays of the imaging world, PET/MRI is still in its infancy. Its premium pricing (a PET/MR system costs between $3.5 million and $5.5 million) and complex installation have limited adoption to high-end clinical settings and research institutions.

The Road Ahead

Apart from these trends, several more innovations are knocking at the door of medical imaging, but haven’t quite got in yet. There has been promise in the use of augmented reality and advanced visualization platforms for image displays, digital integration of medical imaging systems in order to make communicate with each other, and in automating the work stream. When all—or even a portion of these—become a reality, the value addition to diagnoses would be tremendous. Hospitals would witness more efficient use of imaging resources, patients and radiologists would experience lowered radiation exposure, and all stakeholders would enjoy the benefits of reduced costs and improved clinical outcomes.

Copyright © 2017 Frost & Sullivan