Transforming CT imaging with deep learning: Noise reduction, artifact management, and clinical applications – A comprehensive review
Bibliographic record
Abstract
Deep Learning Reconstruction (DLR) is emerging as a significant advancement in Computed Tomography (CT) imaging by addressing crucial issues such as noise reduction, artifact suppression, and dose optimization. Traditional CT reconstruction methods, namely Filtered Back Projection (FBP) and the relatively newer Iterative Reconstruction (IR), have limitations in preserving image quality as radiation doses are lowered. While FBP allows for rapid image generation, it is highly prone to image noise, often requiring higher radiation doses to maintain diagnostic quality. In contrast, IR employs iterative refinement techniques to reduce noise and enhance image quality, but this can lead to unnatural textures that undermine diagnostic confidence especially at lower doses. DLR has shown potential for clinical applications across various imaging subspecialties, such as neuro, thoracic, abdominopelvic, cardiovascular, and pediatric imaging. DLR improves lesion detection, increases soft-tissue Contrast-to-noise, and supports lower-dose protocols, which are particularly important for pediatric patients. Compared to IR, DLR retains more fine anatomical details while effectively reducing artifacts such as beam hardening and motion distortions. However, DLR also faces challenges related to model interpretability, dataset diversity, and computational resource requirements. Addressing these issues through adaptive learning models, explainable AI frameworks, and cross-institutional data sharing will be essential for broader adoption. As DLR continues to advance, its integration with AI-driven diagnostic tools and multi-modality imaging may contribute to advancing the future of CT imaging, enhancing both diagnostic accuracy and patient safety.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".