Mode
Text Size
Log in / Sign up

Review of MRI radiomic features aids Alzheimer's disease classification and progression modeling in 382 participantsMRI Scan Finds Alzheimer's Signs Before Memory Loss Starts

AI-generated summary of the cited source, checked by automated accuracy review. How we work

Key Takeaway
Consider MRI radiomic features from precuneus and fusiform gyrus for robust Alzheimer's disease classification and progression modeling.

This publication is a review of an observational study involving 382 participants, including 134 cognitively normal, 149 with mild cognitive impairment, and 99 with Alzheimer's disease. The analysis focused on MRI-derived radiomic features from the precuneus and fusiform gyrus to classify disease stages and model progression. Follow-up occurred at four time points: 0, 6, 12, and 24 months. Secondary outcomes included gray matter volume and cortical thickness measurements.

Key synthesized findings indicate significant reductions in gray matter volume and cortical thickness in Alzheimer's disease patients compared to cognitively normal and mild cognitive impairment groups, with a Padj < 0.001. Random forest classifiers achieved training accuracies of 98.21% (AD vs. CN), 96.98% (AD vs. MCI), and 99.31% (MCI vs. CN). Prognostic modeling showed the highest predictive performance in the left fusiform gyrus, with correlation coefficients of r = 0.97 for GMV and r = 0.93 for CT. Time-series models outperformed linear regression in most cases.

The authors highlight that these regions represent promising non-invasive biomarkers for early diagnosis and longitudinal monitoring. However, because the source is an observational study, causal relationships cannot be established. No adverse events or safety data were reported. The practice relevance lies in the potential for using these specific radiomic features to enhance diagnostic accuracy and track disease trajectory, pending further validation.

Why catching signs early changes everything

Alzheimer's disease affects millions of families worldwide. It slowly steals memories, personality, and independence. Doctors often wait until symptoms appear to start testing. By then, damage is already done deep inside the brain.

Waiting for symptoms means missing the best time to help. Early action can slow decline and improve quality of life. Families need answers sooner than the current tests allow.

The secret spots inside your brain

For years, we relied on memory tests to find Alzheimer's. These only work after problems show up in daily life. But here is the twist. Scientists found tiny shape changes in the brain first.

They looked at two specific brain zones. One is deep in the center. The other is on the side. These areas shrink before memory loss becomes obvious.

Think of the brain like a garden. Usually, we wait for the flowers to wilt. Now, we check the soil for dry spots. This study looked at the soil before the plants died.

What the numbers really mean for you

Researchers scanned 382 people over two years. Some had normal memory. Some had mild trouble. Others had full Alzheimer's disease. They used advanced software to read the MRI pictures.

The computer guessed the disease stage with near perfect accuracy. It told apart healthy brains from sick ones 98 percent of the time. It also predicted how fast the disease would grow.

One brain area worked better than the rest. The left side of the brain showed the clearest signs. This helps doctors know who needs help first.

This does not mean you can get this test tomorrow.

Why we cannot rush to use this

Experts say this is a huge step forward. It turns a blurry picture into clear data. It helps doctors plan care much sooner. But it is not a magic crystal ball.

You cannot book this scan at a clinic yet. It is a research tool right now. If you worry about memory, talk to your doctor. They have standard tests you can use today.

Why we cannot rush to use this

This study was small and preliminary. It has not passed full peer review yet. Results might change with more people. We need to see if it works for everyone.

More trials will test this on larger groups. Approval takes years of safety checks. But the path looks very promising.

Scientists will now test this on thousands of people. They want to see if it works for different ages and backgrounds. This ensures the tool is fair for everyone.

If successful, this could become a standard check-up. It might help doctors start treatment years earlier. For now, it remains a powerful signal of what is possible.

Study Details

Sample sizen = 382
EvidenceLevel 5
PublishedApr 2026
View Original Abstract ↓
Background Alzheimer's disease (AD) is characterized by progressive neurodegeneration, with early structural changes detectable in specific brain regions. This study explores the diagnostic and prognostic utility of MRI-derived radiomic features from the precuneus and fusiform gyrus for identifying and tracking AD progression. Methods T1-weighted MRI scans from 382 participants; 134 cognitively normal (CN), 149 with mild cognitive impairment (MCI), and 99 with AD were analyzed across four time points (0, 6, 12, and 24 months). Using the FreeSurfer automated pipeline, nine radiomic features were extracted bilaterally from the precuneus and fusiform gyrus. Statistical comparisons were conducted using the Mann-Whitney U test with Benjamini-Hochberg correction. Diagnostic classification was performed using random forest models, while disease progression was modeled using multiple linear regression and ARIMA-based time-series approaches. Results Significant reductions in gray matter volume (GMV) and cortical thickness (CT) were observed in AD patients compared to CN and MCI groups (Padj < 0.001). Random forest classifiers achieved high training accuracies: 98.21% (AD vs. CN), 96.98% (AD vs. MCI), and 99.31% (MCI vs. CN). Prognostic modeling showed the highest predictive performance in the left fusiform gyrus (GMV: r = 0.97, CT: r = 0.93), followed by the left precuneus, right fusiform, and right precuneus. Time-series models outperformed linear regression in most cases, reinforcing temporal consistency in radiomic progression. Conclusion Radiomic features from the precuneus and fusiform gyrus enable robust classification of AD stages and accurate modeling of disease progression. These regions represent promising non-invasive biomarkers for early diagnosis and longitudinal monitoring of Alzheimer's disease.
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.