Medical Image Analysis Software – Part One

Medical imaging technology comes in a variety of applications that benefit both patients and physicians. Medical imaging software is helping doctors make better and more prompt diagnoses of patients. This article begins by explaining some of the more current forms of medical imaging software and some of the possible applications for medical imaging analysis software.

The article will end with a summary of some of the legal issues that developers and practitioners need to consider such as when these devices might be considered medical devices that need to be approved by the US Food and Drug Administration. Any form of digital technology that collects electronic information also needs to comply with the Health Insurance Portability and Accountability Act (HIPAA).

How is medical imaging analysis software affecting healthcare?

There are some traditional uses already for medical imaging. Many doctors refer patients to facilities that conduct computed tomography (CT), magnetic resonance imaging (MRI), thermography, or echocardiography scans. According to Demigos (a developer of healthcare products), new solutions are leveraging machine learning (ML), deep learning, and big data analytics in order to:

• Identify the precise part of a person’s body that needs treatment – to help prevent or reduce damaging healthy tissues.
• “Find pathologies even in images that don’t reveal any visible abnormalities.”
• Allow doctors to focus on the most severe by “sifting through hundreds of scans, flagging images with abnormalities, and prioritizing them based on complexity.”
• Validating a medical diagnosis.
• Monitor the progression of a disease by comparing images made at different times.
• “Streamline communication and image data sharing between various decision-makers.”

“These technologies can help reduce clinical errors, avoid unnecessary procedures, reduce radiation exposure, facilitate early diagnostics and thus increase recovery/survival rates, accelerate the image examination workflow, and minimize hospital stays.”

What are some of the new trends in medical image analysis software?

Some of the new imaging analysis trends for radiology software (a prime uses of medical imaging analysis software) according to Demigos includes:

• The use of artificial intelligence (AI). AI can analyze large amounts of imaging data to “see” results that the human eye can’t. AI software can also help automate the use of diagnostic images, reduce the need for invasive diagnostic tests, and help reduce the number of diagnoses that are incorrect or missed.
• 3D imaging. While 2-dimensional is still the norm, in part because 2D imaging is less expensive, 3D imaging does have advantages.

“For example, in breast imaging, digital tomosynthesis (3D mammography) has already become the “gold standard”. Since both cancer tissue and fibroglandular (the milk glands and ducts in breasts) appear white on a mammogram, they can overlap on a 2D image, which might prevent a healthcare provider from identifying the abnormality in time. On the contrary, tomosynthesis allows viewing an area of interest from different angles. Thus, 3D imaging increases the accuracy of anomaly detection, especially when combined with AI, which is able to process high volumes of data.”

As CT, MRI, and X-ray scanners are developing 3D capabilities, the demand for software that can analyze the 3D scans from these devices will grow.

• Cloud computing. As medical imaging devices develop, the amount of data/information in the images increases so much that the information has to be secured for future analysis – in places that can handle huge amounts of data. For this reason, some health care providers are using cloud computing to store their images. Cloud computing does facilitate the sharing of image data (subject to HIPAA compliance and any other compliance issues) which is useful in the age of COVID.
• Integrated software. According to Demigos, integrated technology use for medical imaging analysis is expanding greatly.

“A single toolkit designed for a host of radiology operations (such as image acquisition, processing, analysis, and management) and a centralized healthcare data storage with live access to multiple users is a much more convenient and cost-effective option than a variety of standalone tools. That’s why if you are planning to develop medical image analysis software, be sure that it seamlessly integrates with your other radiology tools.”

What types of medical practices can benefit from medical imaging?

Virtually every health practice profession can benefit from medical image analysis software – such as:

• Cardiology. Demigos states that advanced algorithms are being used by one software developer to “automate routine tasks in a cardiac analysis workflow, including 2D visualization, 3D and 4D reconstruction, semi-quantitative perfusion, quantitative delayed enhancement, and tissue characterization.”
• Orthopedics. Some machine learning software uses helps when patients who have a fracture by “automatically aligning bone parts, thus avoiding minor segment misalignment typical of manual reconstruction.” The images can be used for surgeries and implant design. Medical imaging analysis can also help to detect osteosarcoma, a type of bone tumor.
• Dentistry. Getting good images of a patient’s teeth can be very difficult because teeth have different sizes and positions. Medical image analysis software helps dentists make a proper diagnosis. Imaging software can also be used for implants, dental prostheses, and other applications.
• Neurology. AI software can help clinicians detect various disorders such as the early signs of Alzheimer’s or epilepsy.
• Breast oncology. “AI models have proven to be capable of identifying tumors that are otherwise impossible to detect. Meanwhile, according to NCBI, deep-learning models are capable of performing at the same level as radiologists in terms of diagnosis accuracy during breast cancer screening.”

Other medical practices that are using more developed medical imaging include various skin disorders, obstetrics and gynecology, urology, and nephrology.

Medical imaging software is being used by doctors, hospitals, diagnostic facilities, surgical centers, and research centers.

What are the key components of medical image analysis software?

Some of the key features of medical imaging software include enhanced image quality, image segmentation, quantification, 2d visualization, and 3D reconstruction.

Some of the additional uses for medical imaging software include helping health care providers:

• Track images and share related information on-the-go
• Archive images
• Manipulate images
• Manage images within an unbroken medical admin routine.

Newer medical technology is now accessible through a patient’s smartphone or portable wearing devices. Some of these devices use sensors. With a smartphone/device doctors (with the use of the imaging software) may be able to determine if a patient may have:

• Melanoma (the most aggressive form of skin cancer, and which is often curable if detected early).
• Pressure ulcers/bedsores
• Various types of wounds

Doctors should then examine the patient in person.

Medical image analysis software includes software analysis through the use of less complex 2D slices to 3D models that help “analyze a clinical case in a few simple steps and introduced in the diagnostic medical imaging and 3D simulation software that can interact with the patients’ 3D model created by importing CT/CBCT/MR in DICOM format.”

4D imaging is the next stage of medical imaging that has many applications such as radiation therapy. There are many different technical formats.

What are some of the key healthcare compliance issues for medical imaging software?

Any business that is developing new medical imaging technology or modifying current technology should consult with experienced health care lawyers about what federal and state compliance requirements apply to the software. Some of the issues developers and the medical practices who use and recommend imaging software should consider include:

• HIPAA compliance. HIPAA is a federal law that regulates the sharing of electronic medical information. Medical imaging software involves the collection of electronic patient information and sharing of that information – especially if AI is being used to analyze all the information. For this reason, understanding which entities are bound by HIPAA, the consequences for violating HIPAA, and the ways for coming into compliance with HIPAA are critical. The penalties for HIPAA violations can be millions of dollars. Generally, entities that are required to comply with HIPAA must comply with HIPAA’s privacy rule and HIPAA’s security rule.
• FDA compliance. FDA has oversight over medical devices and many AI applications including some for diagnostics.
  • Medical devices. Skilled healthcare compliance lawyers review whether a medical imaging software product is a device. Generally, the Food, Drug, and Cosmetic Act defines a medical device as:
    • An instrument, apparatus, implement, machine, contrivance, implant, in vitro reagent, or other similar or related article, including a component part, or accessory which is:
      • recognized in the official National Formulary, or the United States Pharmacopoeia, or any supplement to them,
      • intended for use in the diagnosis of disease or other conditions, or in the cure, mitigation, treatment, or prevention of disease, in man or other animals, or
      • intended to affect the structure or any function of the body of man or other animals, and which does not achieve its primary intended purposes through chemical action within or on the body of man or other animals and

which does not achieve its primary intended purposes through chemical action within or on the body of man or other animals and which is not dependent upon being metabolized for the achievement of its primary intended purposes. The term “device” does not include software functions excluded pursuant to section 520(o). [The Cures Act further defines what software functions such as administrative support of a healthcare facility are excluded].

FDA suggests that developers define the intended use and indications for the product.

Skilled health care compliance lawyers will also help developers determine if an appropriate product classification exists for the product.

• • Regulation of artificial intelligence and machine learning medical devices.

“Traditionally, the FDA reviews medical devices through an appropriate premarket pathway, such as premarket clearance (510(k)), De Novo classification, or premarket approval. The FDA may also review and clear modifications to medical devices, including software as a medical device, depending on the significance or risk posed to patients of that modification.”

Because medical device regulation was not designed for adaptive AI and machine learning technologies, the FDA “anticipates that many of these artificial intelligence and machine learning-driven software changes to a device may need a premarket review.”

• The unauthorized practice of medicine. Developers and doctors who use medical imaging software should review with a skilled health care compliance lawyer whether the software might be considered as providing medical advice in violation of the California Business and Professions Code.

While these products can help with better patient diagnoses and better use of a doctor’s time, the products do create different health care compliance issues. Developers of medical imaging software need to review HIPAA compliance requirements, FDA oversight of medical devices, FDA oversight of specific software applications, and the unauthorized practice of medicine – before the developers begin the development or marketing of any products.

The manufacturers of medical imaging software and the doctors who recommend and use the software should contact Cohen Healthcare Law Group, PC to review the federal and state regulations that govern these new digital technology devices. Our experienced healthcare attorneys advise medical product companies and medical practices about healthcare compliance laws and regulations.