Innovation, Detection, and Healing: The Role of AI in Breast Cancer Treatment
Imagine a world where you can detect issues early and can use that information to make changes that are beneficial for everyone? What if that was possible now? Thanks to Ken Ferry, the CEO of iCAD, there is no need to wonder. Ken and his team have developed innovative technology that detects cancer at an early stage and offers therapy solutions that provide non-invasive treatment for patients.
Tamara: Can you share a story that inspired you to get involved in AI?
Ken: What inspires and excites me the most about AI is the fact that this innovative technology has the ability to protect and preserve life through the collaboration between technology and medical science. According to Breastcancer.org, about one in eight U.S. women will develop invasive breast cancer during her lifetime. Two-thirds of women with breast cancer have the potential to be saved through early detection and progressive treatments. Innovative technologies using AI — such as what iCAD offers — play a tremendous role in this early detection and can have a direct impact on patients’ lives.
Tamara: Describe your company and the AI products/services you offer.
Ken: iCAD delivers innovative cancer detection and radiation therapy solutions and services that enable clinicians to find and treat cancers earlier while enhancing patient care. iCAD offers a comprehensive range of computer aided detection (CAD) and workflow solutions to support rapid and accurate detection of breast and colorectal cancers. iCAD’s Xoft® Axxent® Electronic Brachytherapy (eBx®) System® is a painless, non-invasive technology that delivers high dose rate, low energy radiation, which targets cancer while minimizing exposure to surrounding healthy tissue. The Xoft System is FDA cleared and CE marked for use anywhere in the body, including treatment of non-melanoma skin cancer, early-stage breast cancer and gynecological cancers. The comprehensive iCAD technology platforms include advanced hardware and software as well as management services designed to support cancer detection and radiation therapy treatments.tomosynthesis, breast density and 2D mammography. These innovative breast cancer solutions offer clinicians a wide range of tools for disease detection and analysis that enhance workflow and improve overall efficiency. Our suite of solutions supports healthcare facilities worldwide in providing quality breast care to their patients.
iCAD was the first to market with PowerLook Tomo Detection, an FDA-approved radiologist workflow solution built on the latest advances in pattern recognition and Machine and Deep Learning. The solution was designed to optimize breast tomosynthesis reading efficiency, streamline workflow and support cancer detection without compromising reading performance or increasing recalls. We have trained our algorithm to rapidly scan each plane in the tomosynthesis volume, identifying suspicious soft tissue densities (masses, architectural distortions and asymmetries). These soft tissue densities are extracted from the planes and naturally blended onto a synthetic 2D image. The detected regions on the enhanced synthetic 2D image are linked to the appropriate tomosynthesis planes, creating an efficient and effective navigation tool for radiologists to decrease reading time (by an average of 29.2 percent) and improve reader experience. Unlike traditional 2D cancer detection solutions, PowerLook Tomo Detection is designed to be used concurrently throughout study interpretation and has proven to be of huge value to radiologists.
Tamara: How do you see the AI industry evolving in the future?
Ken: As it relates to AI in healthcare specifically, I believe that providers who utilize and fully understand the unique capabilities of AI solutions will perform above the rest, especially as the industry continues to turn to a value-based care model. As a whole, AI is going to become more and more popular in the future and will have even more impacts on businesses and consumers alike.
Tamara: What is the biggest challenge facing the industry today in your opinion?
Ken: The biggest challenge will be addressing and helping people overcome their initial fears and concerns about AI. Within the healthcare industry, for example, many providers (especially radiologists) fear being replaced by this technology. However, radiologists have more job duties and responsibilities than what they are utilizing AI for, and I believe that AI solutions are simply a productivity enhancer to their workflow. Embracing the technology — which ultimately supports a patient’s outcome — is the benefit.
Another concern or challenge among some healthcare providers and professionals is related to AI’s data collection and accuracy, as we are keenly aware that AI is only as good as the data it collects. Not to mention, AI must be implemented correctly in order to reach its full potential. The concern here is that since AI is built on deep learning, a technique in which computers learn through example and work to better understand and process complex forms of data, there is no real way to determine its inner workings — so providers have to rely on trust. Some providers on the other side of the fence, however, argue that AI is actually much faster and more accurate than humans.
Tamara: How do you see your products/services evolving going forward?
Ken: At iCAD, we intend to continue to develop innovative solutions to support imaging modalities through AI. Backed by our expertise and investments over the last half a decade in AI, we believe we can extend our solutions beyond breast health into a number of other areas in the imaging space over the coming years.
Tamara: What is your favorite AI movie and why?
Ken: The Terminator. It’s a great reminder of how AI has been around for years, we just never truly focused on it or paid attention to it fully.
Tamara: What type of advice would you give readers about AI?
Ken: While there is much more to be understood about AI in healthcare and medical imaging, I want readers to understand that AI is no doubt fundamentally changing the way businesses operate. In the healthcare industry, it has a huge impact on how radiologists and other healthcare providers do their jobs. I would like to see people overcome their fears and concerns associated with AI, be open-minded and truly understand how it can be of real assistance. If implemented correctly, AI can reach it’s true potential.
Tamara: How does AI, particularly your product/service, bring goodness to the world? Can you explain how you help people?
Ken: Our AI solution — PowerLook Tomo Detection — brings good to the world by serving as an effective tool radiologists’ can use to help detect more breast cancers earlier. By reducing the reading time of radiologists, patient results are available more quickly, providing breast cancer patients with an opportunity to seek treatment and learn next steps for their diagnosis sooner. Better yet, our AI tool is the first and only FDA approved concurrent-read cancer detection solution for DBT, demonstrating our commitment to supporting faster, more confident detection of breast cancer.
Tamara: What is the funniest or most interesting story that occurred to you during your company’s evolution?
Ken: When I first came to iCAD, we had a 2D mammo algorithm solution in the market. During this time, we decided to develop a new, better 2D algorithm. After years of development time and millions of dollars later using a similar development approach as with the first algorithm, we found that the new product was not in fact better, so we scraped it and went back to the original. Today, we have dramatically changed our development approach using machine and deep learning. As a result, we have developed an outstanding AI based product and are well on our way to developing a follow-on solution with even more capability. This is some progress in light of iCAD being the only company that is FDA cleared for these types of breast cancer detection solutions today.
Tamara: What are the 3–5 things that most excite you about AI? Why? (industry specific)
Ken: 1) The potential — AI has the potential to truly change businesses, industries and people’s lives as a whole.
2) The cost benefits of AI — AI solutions, such as what our company offers, should aid in bringing down the costs of healthcare due to higher productivity. With this technology radiologists can detect cancer sooner, meaning patients costs will be reduced and this significantly impacts their treatment options.
3) AI continuously gets smarter — AI can be updated and changed so that the algorithms become smarter and smarter each and every day. It’s a continuous process of gathering data to see what works and what doesn’t and then updating the product or solution to make it better.
Tamara: What are the 3–5 things that you worry about with AI? Why? (industry specific)
Ken: 1) The ‘impersonators’ — A lot of companies claim they are in the business, but there are ultimately a lot of good looking websites without any commercially available products behind them. I think this could be controlled by having the FDA continue to set a high bar in testing and the regulatory process.
2) Market adoption — In order for companies to implement our solutions, we must be able to prove to them that the data we can provide is relevant. We must be able to prove AI is valuable so that customers adopt and implement our technology.
3) The misconceptions — As I discussed before, there are a lot of misconceptions about AI and its capabilities. I hope that the benefits soon outweigh the fears and challenges and that AI lives up to its expectations.
Tamara: Over the next three years, name at least one thing that we can expect in the future related to AI?
Ken: I think we can expect that many will begin to believe — even the naysayers — that AI is smarter than we think. In healthcare, with AI we are able to find more cancers even quicker with our solutions. It’s not that radiologists aren’t able to detect cancers, it’s just that this innovative technology allows radiologists to focus more on the entire process of providing superior patient care. With this technology and its continued developments utilizing deep learning, we can specialize in gaining and reading massive data — something that humans just simply do not have enough time to do.