Background/Objectives: To characterize the degenerative vocabulary of 500 consecutive lumbar MRI reports using a transparent, reproducible text extraction pipeline; to quantify which descriptors distinguish included from excluded reports and which factors predict text-derived severity; and to specify a reproducible image analysis pipeline whose formal validation against radiologist Pfirrmann grading is defined as the next step. Methods: We analyzed 500 lumbar MRI reports (386 patients; December 2018–November 2025), extracting morphological and severity keywords, segmental levels (L1–L2 to L5–S1), Modic mentions, and a custom text-derived ordinal severity (0–3). Keyword prevalence differences were tested with the Fisher exact test under Benjamini–Hochberg false discovery rate control, with 95% confidence intervals (CIs) for all odds ratios (ORs) and risk differences; predictors of severity were examined by ordinal logistic regression. Robustness to within-patient clustering was assessed with patient-clustered robust estimation and one-report-per-patient analyses. A MATLAB pipeline derived per-disc candidate imaging features (predicted Pfirrmann grade, normalized disc height, T2 signal index, quality control) across 316 studies. Results: In total, 385/500 reports (77.0%) met the inclusion criteria. The structured morphological keyword field was missing in 49.4% of records, varying by year (58.6% in 2020, 68.7% in 2023, 41.9% in 2024, 33.5% in 2025), indicating systematic reporting drift. Bulge was the dominant descriptor (53.8%); L4–L5 and L5–S1 dominated level mentions. After correction, bulge (OR 6.70, 95% CI 3.86–11.65), mild (5.08, 2.39–10.78), dehydration (9.82, 2.36–40.87) and central (8.63, 2.07–36.01) were enriched among the included reports. All four remained significant in clustering-aware sensitivity analyses. Older age independently predicted higher severity (OR 1.36 per 10 years, 95% CI 1.19–1.56). The image pipeline produced per-disc candidate biomarkers across 316 studies. Conclusions: Free-text lumbar MRI reports encode a recognizable but heterogeneous degenerative vocabulary, sufficient for cohort construction yet inconsistent for quantitative grading; the text-derived severity is a noisy proxy. The reproducible image analysis pipeline yields candidate biomarkers whose formal validation against an adjudicated radiologist Pfirrmann reference standard is the explicit, pre-specified next step.

Background/Purpose: To characterize the degenerative vocabulary of 500 consecutive lumbar MRI reports using a transparent, reproducible text-extraction pipeline; to quantify which descriptors distinguish included from excluded reports and which factors predict text-derived severity; and to specify a reproducible image-analysis pipeline whose formal validation against radiologist Pfirrmann grading is defined as the next step. Methods: We analyzed 500 lumbar MRI reports (386 patients; December 2018–November 2025), extracting morphological and severity keywords, segmental levels (L1–L2 to L5–S1), Modic mentions, and a custom text-derived ordinal severity (0–3). Keyword-prevalence differences were tested with the Fisher exact test under Benjamini–Hochberg false-discovery-rate control, with 95% confidence intervals (CIs) for all odds ratios (ORs) and risk differences; predictors of severity were examined by ordinal logistic regression. A MATLAB pipeline derived per-disc candidate imaging features (predicted Pfirrmann grade, normalized disc height, T2 signal index, quality control) across 316 studies. Results: 385/500 reports (77.0%) met inclusion criteria. The structured morphological-keyword field was missing in 49.4% of records, declining across years (58.6% in 2020 to 33.5% in 2025), indicating systematic reporting drift. Bulge was the dominant descriptor (53.8%); L4–L5 and L5–S1 dominated level mentions. After correction, bulge (OR 6.70, 95% CI 3.86–11.65), mild (5.08, 2.39–10.78), dehydration (9.82, 2.36–40.87) and central (8.63, 2.07–36.01) were enriched among included reports. Older age independently predicted higher severity (OR 1.48 per 10 years, 95% CI 1.29–1.70). The image pipeline produced per-disc candidate biomarkers across 316 studies. Conclusions: Free-text lumbar MRI reports encode a recognizable but heterogeneous degenerative vocabulary, sufficient for cohort construction yet inconsistent for quantitative grading; the text-derived severity is a noisy proxy. The reproducible image-analysis pipeline yields candidate biomarkers whose formal validation against an adjudicated radiologist Pfirrmann reference standard is the explicit, pre-specified next step.

Purpose: To characterize the documented spectrum of degenerative lumbar spine disease across 500 consecutive magnetic resonance imaging (MRI) radiology reports using a transparent, reproducible text-extraction pipeline, to quantify which descriptors distinguish reports retained for degenerative analysis from those excluded, and to develop a reproducible image-based assessment pipeline that derives per-disc imaging features for benchmarking against radiologist Pfirrmann grading. Methods: We analyzed 500 lumbar MRI reports (386 unique patients; December 2018 to November 2025). Reports were screened against degenerative-disease eligibility criteria. From each report we extracted morphological and severity keywords, explicit segmental level mentions (L1–L2 to L5–S1), Modic-change mentions, and an ordinal degeneration severity (0–3) derived by a published rule set. Field completeness was quantified. Differences in keyword prevalence between included and excluded reports were tested with the Fisher exact test, with Benjamini–Hochberg control of the false discovery rate (FDR). A complementary MATLAB image-processing pipeline was executed across 316 studies to derive per-disc imaging features (predicted Pfirrmann grade, normalized disc height, T2 signal index, severity and quality control) for benchmarking against radiologist Pfirrmann grading. Results: 385 of 500 reports (77.0%) met inclusion criteria; exclusions were predominantly trauma/fracture (58/115) and prior surgery (38/115). Narrative fields were complete, but the structured morphological-keyword field was missing in 49.4% of records. Disc bulge was the dominant descriptor (53.8%), followed by mild (27.5%), stenosis (18.7%) and severe (16.4%). The lower segments L4–L5 (27.0%) and L5–S1 (28.4%) dominated level mentions. After FDR correction, bulge, mild, dehydration and central were significantly enriched among included reports (all q < 0.05). Derived severity was broadly balanced (report-level: 28.0% none, 30.2% mild, 19.8% moderate, 22.0% severe). Conclusions: Free-text lumbar MRI reports encode a recognizable but heterogeneous degenerative vocabulary that is sufficient for cohort construction yet inconsistent for quantitative grading. The text-derived severity is reasonable but should be regarded as a noisy proxy; we therefore developed and executed a reproducible image-based assessment pipeline, deriving per-disc features and quality control across 316 studies; benchmarking these outputs against an adjudicated Pfirrmann gold standard is the immediate next step toward clinically defensible, image-based phenotyping.