Hybrid Vision Transformer and ResNet18 Framework for Multiclass Kidney Disease Detection from CT Scans
Bibliographic record
Abstract
A hybrid Vision Transformer (ViT) and ResNet18 architecture is used in this work to propose a high-performance automated classification model for kidney disease diagnosis. The CT-KIDNEY DATASET: cyst, normal, stone, tumour which comprises 12,446 lossless JPEG images obtained from DICOM scans in hospitals in Dhaka, Bangladesh, was used to train the model. Both axial and coronal images from contrast-enhanced and non-contrast CT examinations are included in the collection. The task involves four diagnostic categories: normal, cyst, tumor, and stone that represent the most common kidney conditions. The proposed model combines a Transformer encoder to capture long-range dependencies and a ResNet18 backbone for convolutional feature extraction, leveraging both local spatial characteristics and global contextual information. The hybrid model’s robustness and diagnostic efficacy were demonstrated by its remarkable accuracy of 99.84% on a held-out test set, as well as excellent scores on key evaluation metrics, including F1 score, AUC, and Matthews Correlation Coefficient (MCC). This study provides a dependable tool to assist radiologists in accurately distinguishing among the four kidney disease classes, highlighting the promise of integrating CNN and Transformer-based architectures for medical image analysis.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".