The saying, “treat the patient, not the X-ray,” captures a core challenge we face in spine practice: Clinical symptoms and imaging findings often do not align, making it crucial to approach imaging with a structured framework. This lesson was evident when we treated two patients with strikingly different presentations. The first was a 35-year-old woman whose MRI report identified severe scoliosis and spinal stenosis. Yet, she was totally asymptomatic, with little to no back pain and high functional capacity. In contrast, a similarly aged patient at our practice has had debilitating, chronic back pain for years, but with only moderate spinal stenosis reported on MRI. These contrasting cases highlight a key question: How do we best use and interpret imaging to inform care when clinical and radiological data diverge?
Reflecting on these cases, it is clear that magnetic resonance imaging has transformed how we evaluate spinal stenosis. In my early years of practice, radiology reports often described findings in qualitative terms: “mild narrowing,” “severe foraminal compromise,” or even “variable stenosis.” These phrases were helpful, but they were also imprecise. After all, what is the boundary between “mild” and “moderate” stenosis, and are such metrics consistently reproducible between and within patients? Eventually, structured MRI classification systems for spinal stenosis emerged, offering a more standardized language.
Building on these advances
Standardized MRI classifications, such as the Schizas grading system for lumbar central canal stenosis and structured grading systems for foraminal narrowing, brought much-needed consistency to reporting. Instead of vague descriptors, we now assess the morphology of the dural sac, the presence or absence of cerebrospinal fluid around nerve roots, and whether there is nerve root collapse or deformation. In the cervical spine, grading incorporates cord deformity and even signal change. These systems improve interobserver reliability and create a shared vocabulary between radiologists, surgeons, and physiatrists. More critically, they provide a much-needed framework that shapes clinical reasoning, surgical decision-making, and even our conversations with patients. For instance, when confronted with an imaging report, patients often ask, “What will happen if I do nothing about this?” or “Would I benefit from surgery?” Providing accurate, evidence-based answers to these questions is greatly facilitated by the standardized reporting of imaging findings.
These frameworks impact daily decision-making in meaningful ways
For instance, a cord signal change in the cervical spine raises concern for the progression of myelopathy. High-grade foraminal collapse with concordant radiculopathy supports decompression. Structured grading also correlates more reliably with operative findings than vague terminology and provides a baseline for monitoring disease progression. In the non-surgical realm, these classifications influence interventional strategies. Targeted epidural injections, selective nerve root blocks, and minimally invasive procedures rely on accurate anatomical localization. Knowing whether stenosis is central, lateral recess, or foraminal helps refine technique and set realistic expectations. Therefore, there is an undeniable need for universal implementation of standardized grading.
Despite this apparent need, in daily clinical practice, standardized classifications are not universally used, and reports remain radiologist-dependent, with significant variability. Perhaps this is a result of the tedious nature of applying standardized classifications, which may prove too time-consuming for busy radiologists facing ever-increasing imaging volumes.
To address this variation
The emergence of artificial intelligence in imaging analysis provides a potential path forward. Automated measurements of canal diameter, dural sac area, and foraminal narrowing promise increased efficiency and reduced variability. At present, several artificial intelligence algorithms for spinal imaging are under active development, and early validation studies have demonstrated promising accuracy in quantifying spinal canal compromise and grading stenosis. However, most existing tools remain in the research or pilot stage, and their widespread adoption in clinical practice remains limited. Regulatory approval and multi-center validation are ongoing for many proposed systems, and only a handful of artificial intelligence-driven reporting tools are currently available to clinicians at scale. Algorithms may soon provide standardized and structured grading of findings or even directly predict surgical outcomes based on imaging patterns. This emerging technology offers hope of extracting more value and information from each imaging study, thereby better informing both the patient and the treating physician.
Ultimately, medicine has always wrestled with the tension between objective data and subjective experience. MRI classification systems represent our desire to quantify and categorize. They reflect the scientific impulse to measure what we see. And artificial intelligence can help us implement these classifications more universally across imaging studies.
Perhaps the most valuable role of MRI classification, however, is not in assigning a number or letter, but in focusing clinical thinking and informing patient care. The main argument is that standardized classification systems serve as cognitive tools: They force us to ask essential questions about central versus foraminal issues, cord signal change, nerve root collapse, and symptom correlation. They organize complexity, reduce ambiguity, and provide a foundation for meaningful discussions between physician and patient. Ultimately, clear, standardized imaging interpretation guides better, more individualized decision-making and improved patient outcomes.
Purab Patel is a medical student.
Francisco M. Torres is an interventional physiatrist specializing in diagnosing and treating patients with spine-related pain syndromes. He is certified by the American Board of Physical Medicine and Rehabilitation and the American Board of Pain Medicine and can be reached at Florida Spine Institute and Wellness.
Dr. Torres was born in Spain and grew up in Puerto Rico. He graduated from the University of Puerto Rico School of Medicine. Dr. Torres performed his physical medicine and rehabilitation residency at the Veterans Administration Hospital in San Juan before completing a musculoskeletal fellowship at Louisiana State University Medical Center in New Orleans. He served three years as a clinical instructor of medicine and assistant professor at LSU before joining Florida Spine Institute in Clearwater, Florida, where he is the medical director of the Wellness Program.
Dr. Torres is an interventional physiatrist specializing in diagnosing and treating patients with spine-related pain syndromes. He is certified by the American Board of Physical Medicine and Rehabilitation and the American Board of Pain Medicine. He is a prolific writer and primarily interested in preventative medicine. He works with all of his patients to promote overall wellness.
