Computer Aided Deep Learning Based Assessment of Stroke From Brain Radiological CT Images
Bibliographic record
Abstract
The aim of the study is to detect the abnormal area(s) from brain CTs of stroke patients using Image Processing and to accurately evaluate the stroke changes in brain tissues among patients with Deep Learning models in MATLAB 2019b interface. 1000 patients (500 stroke suspected, 500 healthy participants) were chosen between 25 and 75 age ranges from TOBB ETU and Yıldırım Beyazıt University Hospitals according to the ethics committee certificate. For this study, for increasing the accuracy and eliminating the redundancy, from the image data of the patients, only lateral and 4th ventricle CT images were used. Firstly, these images were processed via Image Processing methods (Image Acquisition, Preprocessing, Thresholding, Segmentation, Morphological Operations etc.). After these methods, the resulted lateral ventricle image was split into 6 specific areas and 4th ventricle image was split into 14 specific areas like automated computerized Alberta Stroke Scoring, respectively. For 1000 images, totally 20x1000=20000 pieces of CT subimages were obtained with the specific class names (as healthy and stroke) and were used as the input of Artificial Intelligence (AI) and Deep Learning (DL) models (optimized ANN with Levenberg-Marquardt method and CNN). This approach can give an important chance to the doctors for supporting their results with a decision support system, speeding up the diagnosis time and also decreasing the possible rate of misdiagnosis.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".