Opening the Black Box: Utilizing Everyday Textures as Concept-Based Explanations for Deep Learning Model Prediction of Glioma Biomarker Status
Bibliographic record
Abstract
This thesis aims to bridge the gap between artificial intelligence (AI) model prediction and human comprehension of higher-level concepts in brain cancer imaging.Using magnetic resonance images of gliomas, four deep learning models were trained to differentiate between tumours with "wildtype" and "mutated" forms of the isocitrate dehydrogenase (IDH) biomarker, a key indicator of tumour aggressiveness.Each convolutional neural network model, developed based on the ResNet50 architecture, was evaluated using 5-fold cross-validation.We employed the Testing with Concept Activation Vectors framework to assess the impact of 'everyday' texture concepts on model decisionmaking.Scores from 0 to 1 were generated for 47 concepts across three layers of each model for both forms of IDH.This work provides a preliminary evaluation of how conceptbased explanations may elucidate the internal mechanisms of black-box neural networks in a medical context, a crucial step towards ensuring end-user trust and deploying AI models in clinical settings.
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 | 0.002 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
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".