Summary: This post summarizes the course learning about the recent technological developments involving the Healthcare, focussing on Imaging and Signal processing (Reading time: ~8 minutes)
- Innovations in the physical Healthcare infrastructure
- Beyond the physical tool landscape, the Digital influence depends upon the balance between Healthcare professional’s interaction needed v/s Technological innovations base
- Imaging and Signal processing as a fundamental enabler of Healthcare
- But more importantly, the digitization brings transformational capabilities via AI/ML tools
- Engineering advances have yielded impressive tools for imaging
- Clinical imaging v/s research imaging
- Chemical Tools for Biomolecular Imaging
- Currently, imaging is evolving rapidly in three distinct biomedical areas: (i) imaging molecular biomarkers (ii) Single Cell Imaging (iii) Imaging in Drug Therapy
For an entrepreneur looking to develop digital solutions in Healthcare, it is essential to understand the extent of dependency on the interaction required from the Healthcare professional (or provider) against technological innovations underlying any solution being developed.
The Healthcare sector is a complex interface of tools, technologies, and highly specialized (and regulated) professional experts. The most important aspect is that the professional expert administering any significant Healthcare service is usually not conversant with the technological aspects. The acquisition of medical knowledge to become a Healthcare professional is enormous, leaving little room for gaining further expertise in any other complementary areas.
Innovations in the physical Healthcare infrastructure:
The current tool landscape of Health care is based on illness protocols and hence gets into the intimate personal space of patients, both physical and mental. In the face of disease, one gets helpless and must trust Healthcare establishments with no alternative.
The basic probing and diagnostic investigation space of Healthcare will need to be physical. In addition, the processes like emergency care, radiological examinations, or surgical procedures will need physical intervention.
In these areas, digital transformation will play a supporting role, like better tool designing, tracking performance and outcomes, or processing the data outputs. However, this space might be transformed by more fundamental innovations. For example, 3D printing might enable printing custom-designed bio-compatible parts, reducing costs. Quantum microscopy might provide hi-definition vision at the micro-level as the Hubble telescope did at a macro level. Quantum computing may enable probabilistic molecule modeling leading to a reduction of the cost of drug discovery to a fraction of today’s prices. Or consider microscopic robots traversing our innards and providing real-time feedback.
These may look like tall claims, but so were the many science fictions or James Bond movies in the second half of the 20th century. Some of the above ideas might become real constructs embedded in our Healthcare system within this generation.
Beyond the physical tool landscape, the Digital influence depends upon the balance between Healthcare professional’s interaction needed v/s Technological innovations base:
Higher the technological innovation needed, the longer the path for adaptation to Healthcare. Significant time will be required by the regulators looking for enough reliability or by the medical professionals needing time to get comfortable with new technology. Tolerance for adaptation stage errors is understandably very low.
Digital tools like developing hospital websites or physician locators with low need for Healthcare professional interaction are low-hanging fruits. On the other hand, video consultations or remote imaging reviews will need higher medical expertise and depend on complex tech innovations.
Health care services like lab result reporting and online pharmacies fall in the middle; even in these areas, digital innovations have capabilities to reduce errors and resultant costs.
Imaging and Signal processing as a fundamental enabler of Healthcare
Perhaps the most direct impact is from the Imaging and signal processing transformation.
Almost every Healthcare tool reports back with either an Image or some medical condition status in real-time. Simpler biomarkers like weight and blood test readings provide point-in-time references. Most other higher diagnostic information will result from radiology investigation, biopsies, or continuous status monitoring like ECGs. The increase in capability to store and process large volumes of data has created the immense potential to transform this space.
At a minimum, the digital conversion of these images and signals facilitates easy and simultaneous access to multiple stakeholders. Furthermore, as the medical protocols need feedback evidence of effectiveness over a large group of treatments, the digitization unlocks a higher level of effectiveness.
Pattern recognition capabilities at the minute level beyond intuitive human cognitive sense are increasingly becoming accessible at a commercial scale. In the last decade, significant developments have taken place in imaging infrastructure and data analysis capabilities.
Automated image classification may not disrupt medicine as much as the invention of the roentgenogram (X-ray) did. Still, the roles of radiologists, dermatologists, pathologists, and cardiologists will likely change as AI-enabled diagnostic imaging improves and expands.
Consider some of these developments (source: Advancing biomedical imaging (pnas.org) ):
- Image recognition techniques can differentiate among competing diagnoses, assist in screening patients, and guide clinicians in radiotherapy and surgery planning (Matheson, 2018).
- Diagnostic image recognition can differentiate between benign and malignant melanomas, diagnose retinopathy, identify cartilage lesions within the knee joint (Liu et al., 2018), detect lesion-specific ischemia, and predict node status after positive biopsy for breast cancer.
- Histopathologic diagnosis has seen similar gains in cancer classification from tissue, universal microorganism detection from sequencing data, and analysis of a single drop of body fluid to find evidence of bacteria, viruses, or proteins that could indicate an illness (Best, 2017).
- Detecting abnormal brain structures is much more challenging than detecting a broken bone or a fracture. Multimodal image recognition analysis has discovered novel impairments not visible from a single view of the brain (e.g., structural MRI versus functional MRI) (Plis et al., 2018).
AI is also being applied to moving images. Gait analysis is now being performed with greater accuracy by AI using video and sensor data. The uses are to detect Parkinson’s disease, to improve geriatric care, for sports rehabilitation, and in other areas (Prakash et al., 2018). AI can also enhance video-assisted surgery, for example, by detecting colon polyps in real-time (Urban et al., 2018)
Engineering advances have yielded impressive tools for imaging:
The special feature article, Advancing biomedical Imaging by Ralph Weissleder and Matthias Nahrendorf [link], provides a good summary of developments that have taken place in the recent decade.
Engineering sciences have miniaturized detectors, enhanced system design, increased speed, sensitivity, and resolution, accelerated computational analysis, and developed methods to minimize applied energy’s side effects. Additionally, chemical engineering has produced advanced imaging probes (nanomaterials, labeled small and large molecules, and fluorescent proteins) to improve tissue, cell, and molecular specificity.
Clinical imaging v/s research imaging
It is interesting to note that the clinical imaging systems in Healthcare and research imaging techniques somewhat differ in approaches.
Clinical Imaging Systems: X-Ray has evolved into sophisticated 3-D computed tomography (CT) scans that can detect millimeter-sized pulmonary nodules. The evolution has also produced complementary information because the energy-matter interaction generates different highly informative contrast mechanisms (e.g., magnetic relaxivity, susceptibility, diffusion, temperature, elasticity, electrical impedance, radiation absorption, scattering, and fluorescence).
Research Imaging. Compared to clinical imaging, the research imaging are often based on confocal or multiphoton scopes with long working distance objectives, special lasers, and unique motion compensation techniques.
The discovery of fluorescent proteins, for which the Nobel prize was awarded in 2008 (Shimomura, Chalfie, and Tsien), allowed researchers to visualize a broad range of specific proteins or cells for the first time. In one stunning example, individual neurons with over 100 distinct colors were marked and subsequently traced to reconstruct entire connectome brain maps.
Chemical Tools for Biomolecular Imaging:
Many imaging agents have been developed over the last decade [Molecular Imaging and Contrast Agent Database (MICAD)]. Nanoparticles are particularly promising; they tend to accumulate in innate immunocytes, which are often “first responders” in pathologic processes; they circulate longer and are not immediately cleared renally and can be targeted to specific organs, cells, or proteins. Magnetic nanoparticles, detected by magnetic resonance imaging (MRI), are perhaps the best-studied nanoparticle type.
Currently, imaging is evolving rapidly in three distinct biomedical areas:
(i) Imaging Molecular and CellularBiomarkers
In vivo imaging of molecular and cellular biomarkers is most helpful in studying organs not readily biopsied (such as the brain), finding early cancers, and mapping disease severity and location.
Imaging Receptors. Receptors have expanded our knowledge of human biology and improved treatments for numerous conditions. For example, receptor imaging has been used to study the dopamine reward pathway in people with attention deficit hyperactivity disorder (ADHD). Tumor receptors play an important role in carcinogenesis and tumor growth.
Imaging Physiology. Using a sensitive contrast agent that informs on vascular (blood carrying veins) parameters like density, permeability, etc. often reveals disease processes. A stunning demonstration detects certain leukocytes’ capacity to crawl along the endothelial surface of small vessels, sometimes even against blood flow. The imaging tool had the sensitivity and resolution to follow cell group interactions distinguished by specific reporter genes discovered this patrolling behavior.
(ii) Single Cell Imaging
In vivo imaging of molecular and cellular biomarkers is most helpful in studying organs not readily biopsied (such as the brain), finding early cancers, and mapping disease severity and location. Emerging multiplexed imaging and cytometry approaches will likely play an important role in defining new imaging targets.
Immune Cell Imaging.
New mouse models with bright fluorescence reporter genes show that macrophages (specialized cells involved in detecting and destroying bacteria and other harmful organisms) are much more widely distributed than previously thought. These macrophages have projecting dendrites that facilitate sensing, and these cells display remarkable dynamics and effector functions. Similar networks exist in many other healthy and diseased organs, and imaging facilitates exploration of these networks’ functions in normal and diseased tissues, especially in cancer, myocardial infarction, type 1 diabetes, and autoimmune diseases.
Translating these insights from mouse to man would likely be impossible
without imaging, which, unlike biopsies, can noninvasively sample the entire human body.
Stem Cell Imaging: Microscopy in a living organism (in vivo) can follow individual fluorescently tagged hematopoietic stem cells and report on their propensity to divide or migrate as a function of their localization in the hematopoietic niche and as a function of disease. Hematopoietic stem cells are responsible for replenishing our pool of blood cells throughout life.
Brain Mapping: Structure-function relationships in the brain are the least understood. In vivo functional MRI (fMRI) and diffusion tensor imaging provide insight into specific brain area functions and interconnections. But, understanding how the brain works needs cellular and subcellular resolution relying on microscopic techniques.
Cellular connectomes track axons with micrometer resolution over long distances through large volumes of the brain and spinal cord. CLARITY
ex vivo processing replaces optically dense lipids in cellular membranes with a 3D hydrogel that is cross-linked to proteins and preserves the tissue structure. The procedure increases light penetration depth by at least an order of magnitude and enables imaging of large portions of the mouse brain at cellular resolution. The Brainbow method provides cell-specific coding of ∼100 hues through a combination of three to four fluorescent proteins per neuron.
When combined, CLARITY and Brainbow may be able to simultaneously visualize a multitude of neuronal circuits in their entirety. Together
with functional imaging of firing neurons with calcium and voltage reporters, these approaches demonstrated that brain imaging is at the forefront of imaging technology development and contributes to deciphering how the central nervous system works.
(iii) Imaging in Drug Therapy
Imaging has the potential to play a leading role in the routine use of therapeutics, particularly in oncology, where drug resistance develops over time, and targeted therapies can be extremely expensive.
In the research setting, intravital microscopy has been used to study new drugs’ pharmacokinetics and pharmacodynamics. Advances like fluorescent companion imaging drugs and immobilization techniques allow orthotopic imaging (implantation of tumor cell lines or patient-derived cell xenografts into animal tumor models) to get detailed insight into when and why drugs fail.
More importantly, until now, most research has been performed in cell culture rather than at the cellular level in vivo, leaving unanswered questions regarding delivery to target cells and whether or not the assumed mechanism of drug action occurs in vivo. Recent in vivo imaging of an anticancer drug’s cellular pharmacokinetic properties and cytotoxic activity is a powerful strategy for explaining drug resistance mechanisms in heterogeneous tumors.
These innovations lead to extraordinary opportunities to develop imaging capabilities. The Healthcare system will have access to new types of measurements and can access our cellular and/or subcellular/molecular levels in-vivo; live access to our internal workings will be a game-changer.
I currently work full-time at Swiss Re, Bengaluru. The blogs and articles on this website www.balajos.com are the personal posts of myself, Balachandra Joshi, and only contain my personal views, thoughts, and opinions. It is not endorsed by Swiss Re (or any of my formal employers), nor does it constitute any official communication of Swiss Re.
Also, please note that the opinions, views, comprehensions, impressions, deductions, etc., are my takes on the vast resources I am lucky to have encountered. No individuals or entities, including the Indian Institute of Science and NSE Talent Sprint who have shown me where to research, or the actuarial professional bodies that provide me continuous professional growth support, are responsible for any of these views; and these musings do not by any stretch of imagination represent their official stands; and they may not subscribe/support/confirm any of these views and hence can be held liable in any vicarious way. All the information in the public space is shared to share the knowledge without any commercial advantages.