Oncology Imaging: Pursuing Precision
By Joshua Miller
Radiology Today
Vol. 25 No. 3 P. 6
What is precision medicine?
Precision medicine commonly integrates advanced diagnostic tools, such as molecular and genetic testing, with advanced imaging techniques to provide precise disease diagnoses and delineate their unique characteristics. The mantra of precision medicine is “right patient, right treatment, right time.” Researchers and clinicians seek to create individualized treatment strategies for patients, including the selection of the most suitable medications, mitigating adverse effects, and enhancing patient outcomes. Its impact has been particularly noteworthy in the field of oncology, where targeted therapies have demonstrated significant success. Medical imaging is integral to cancer research and the development of new therapies. Imaging techniques are used to evaluate the effectiveness of experimental treatments in clinical trials and to monitor the progression of cancer in preclinical models.
Without precision medicine, oncologists must rely on standard treatments that are designed to work for the average patient but may not be effective for every individual. This can result in treatments that do not effectively target the specific genetic or molecular characteristics of a patient’s cancer, leading to poor treatment outcomes. This is what was initially seen in the population of lung cancer patients treated with Iressa (gefitinib) until precision medicine in the form of genetic biomarkers enabled a successful comeback story for the treatment.
Initial Breakthrough
Iressa, also known as gefitinib, developed and produced by Astra- Zeneca, is designed to treat nonsmall cell lung cancer (NSCLC). The drug initially received FDA approval in 2003, but its presence on the US market was temporarily suspended in 2012 due to inconclusive results in a clinical trial, which suggested it might not outperform the standard of care at the time. When a drug that represents hundreds of millions of dollars of research and development investment from a biopharmaceutical company and an unquantifiable amount of hope for oncologists, their patients, and their families is removed from the market, it causes major disappointment and setbacks. For many drugs, such an event is the end of the line. However, for Iressa, the outcome was different.
The true breakthrough for Iressa emerged when it was identified that the drug exhibited remarkable efficacy in treating tumors driven by mutations in the genes encoding for an epidermal growth factor receptor (EGFR). This pivotal insight led to a more refined approach: Astra- Zeneca designed a carefully targeted clinical trial protocol, using CT scans performed every six weeks and the Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1) to assess the tumors, that exclusively administered Iressa to patients with EGFR mutations. Iressa was granted Orphan Drug Designation by the FDA specifically for the treatment of EGFR mutation-positive NSCLC. In July 2015, Iressa was reapproved by the FDA for first-line treatment in metastatic NSCLC patients possessing EGFR mutations.
Enabling oncologists to tailor treatments to individual genetic profiles optimizes therapeutic outcomes and spares patients without EGFR mutations from inappropriate treatment. Iressa’s tumultuous but ultimately successful journey underscores the invaluable contribution of precision medicine in revolutionizing cancer therapy and saving lives by providing targeted and effective treatments to those who need them the most.
Chasing Efficacy
RECIST 1.1 constitutes a fundamental tool in the field of oncology, particularly in the evaluation of novel cancer treatments during clinical trials. These guidelines, produced by the National Cancer Institute, offer a standardized approach to assessing the efficacy of treatments. RECIST 1.1 relies heavily on medical imaging techniques such as CT and MRI to provide objective and reproducible tumor size and response measurements.
The value of imaging within the RECIST 1.1 framework cannot be overstated. It allows for precise and consistent evaluation of tumor burden, response, and progression, ensuring that outcomes are measured uniformly across diverse patient populations and clinical studies. Furthermore, RECIST 1.1’s reliance on imaging allows for early identification of therapeutic effects or the lack thereof, enabling timely decisions in developing and refining oncology treatments. This systematic approach enhances the scientific rigor of clinical trials and accelerates the translation of promising therapies into clinical practice, ultimately benefiting patients and advancing the field of oncology. The convergence of RECIST 1.1 and imaging techniques underscores their pivotal role in the relentless pursuit of effective cancer treatments.
AI Potential
AI-driven algorithms can greatly enhance the accuracy and efficiency of tumor detection and characterization. They excel in identifying subtle nuances within medical images, enabling early cancer diagnosis and precise staging, which is crucial for tailoring treatments effectively. Additionally, machine learning can analyze vast datasets at remarkable speeds, facilitating the rapid processing of medical images and expediting diagnosis, ultimately improving patient outcomes.
However, the development and deployment of AI and machine learning in medical imaging for precision oncology necessitates careful consideration of several vital factors. Ensuring data quality and diversity is paramount, as AI models heavily depend on robust, representative datasets for training. Furthermore, the ethical and regulatory dimensions of AI in health care must be addressed. Safeguarding patient privacy, transparency in algorithm decision-making, and adherence to stringent regulatory standards are essential for responsible integration into clinical practice. Additionally, effective collaboration between multidisciplinary teams comprising clinicians, radiologists, data scientists, and engineers is pivotal to aligning technological advancements with clinical needs and workflows. This interdisciplinary approach ensures that AI-driven solutions are accurate and seamlessly integrated into the health care ecosystem.
Looking Ahead
In the dynamic landscape of precision oncology, the convergence of cutting-edge technology and unwavering commitment to improving patient care is forging a path toward brighter horizons. A steadfast commitment to patient privacy and the transparent integration of AI into clinical workflows are essential to ensure these groundbreaking technologies serve as a force for good. Moreover, the collaborative spirit among clinicians, data scientists, and engineers is the linchpin of success, as interdisciplinary efforts enable us to harness the full potential of these transformative tools.
Every patient’s journey is unique, and the world of precision oncology strives to reflect this. By leveraging advanced medical imaging and AI-powered innovation, we can help enhance the lives of people affected by cancer. The medical community continues to deepen its understanding of this complex disease, and this knowledge means we could be standing on the cusp of a new era in oncology—one defined by personalized care, treatment breakthroughs, and, above all, a dedication to improving the quality of life for every patient.
— Joshua Miller is the CEO of Gradient Health.
References
1. Howard P. Why the FDA rejected a drug that helps cure lung cancer – and what we can do to fix it. Forbes website. https://www.forbes.com/sites/theapothecary/2015/11/06/attacking-the-21st-century-cures-act/?sh=520dc8d11ffc. Published November 6, 2015.
2. Eisenhauer EA, Therasse P, Bogaerts J, et al. New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer. 2009;45(2):228-247.
3. Ruchalski K, Braschi-Amirfarzan M, Douek M, et al. A primer on RECIST 1.1 for oncologic imaging in clinical drug trials. Radiol Imaging Cancer. 2021;3(3):e210008.
4. Nishino M. Tumor response assessment for precision cancer therapy: response evaluation criteria in solid tumors and beyond. Am Soc Clin Oncol Educ Book. 2018;38:1019-1029.
