Cortical Dysplasia Teaching Pathology to a Machine
Bibliographic record
Abstract
Many patients with epilepsy do not achieve adequate pharmacologic control of their seizures and must consider surgical options. Many such patients undergo temporal lobectomy and experience a marked reduction in the frequency and severity of their seizures. However, many are less fortunate. One suspected factor for the latter group is the limited ability of clinical imaging to delineate subtle epileptogenic abnormalities, leading to subtotal resection of lesional tissue. A long range goal in this field is to increase the sensitivity and specificity of detecting such abnormalities by “training” MRI with pathology, feature analysis and machine learning. A key component of this is the ability to segment histopathology to facilitate its mapping to co-registered MRI. A foundational step in this process is to determine whether or not algorithms are capable of detecting the architectural abnormalities in cortical dysplasia on the basis of these segmentations. In brief, reliable semi-automated segmentations were developed to extract a number of features including neuron size, clustering, eccentricity, field-fraction and polarity. Feature analyses using t-Distributed Stochastic Neighbor Embedding (t-SNE) plots demonstrate a non-random association between selected features and diagnostic categories. These results indicate that automated algorithms are capable of distinguishing dysplastic from normal cortex on the basis of semi-automated segmentations. Learning Objectives Describe the value of segmentation in image analysis Define the role of feature analysis such as t-SNE in high dimensionality histopathology data
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".