Pith. sign in

REVIEW 7 cited by

CTLformer: A Hybrid Denoising Model Combining Convolutional Layers and Self-Attention for Enhanced CT Image Reconstruction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.12203 v1 pith:HUJQCCHC submitted 2025-05-18 eess.IV cs.CV

classification eess.IVcs.CV
keywords denoisingattentionctlformerldctmechanismnoiseimageconvolutional
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Low-dose CT (LDCT) images are often accompanied by significant noise, which negatively impacts image quality and subsequent diagnostic accuracy. To address the challenges of multi-scale feature fusion and diverse noise distribution patterns in LDCT denoising, this paper introduces an innovative model, CTLformer, which combines convolutional structures with transformer architecture. Two key innovations are proposed: a multi-scale attention mechanism and a dynamic attention control mechanism. The multi-scale attention mechanism, implemented through the Token2Token mechanism and self-attention interaction modules, effectively captures both fine details and global structures at different scales, enhancing relevant features and suppressing noise. The dynamic attention control mechanism adapts the attention distribution based on the noise characteristics of the input image, focusing on high-noise regions while preserving details in low-noise areas, thereby enhancing robustness and improving denoising performance. Furthermore, CTLformer integrates convolutional layers for efficient feature extraction and uses overlapping inference to mitigate boundary artifacts, further strengthening its denoising capability. Experimental results on the 2016 National Institutes of Health AAPM Mayo Clinic LDCT Challenge dataset demonstrate that CTLformer significantly outperforms existing methods in both denoising performance and model efficiency, greatly improving the quality of LDCT images. The proposed CTLformer not only provides an efficient solution for LDCT denoising but also shows broad potential in medical image analysis, especially for clinical applications dealing with complex noise patterns.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs

    cs.LG 2025-07 reject novelty 3.0 of 10

    A meta-learned prompt-tuning method for cold-start LLM recommendations reports better Hit@10 and nDCG@10 on MovieLens-1M, but with no code, no error bars, and no shown results for Amazon or Recbole.

  2. Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems

    cs.LG 2025-06 reject novelty 3.0 of 10

    A hybrid GNN-LLM recommender with FPGA, DeepSpeed, and LoRA reportedly reaches NDCG@10 of 0.75 at 40-60ms latency while cutting training time by 66%, but the supporting artifacts are absent.

  3. LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP

    cs.CL 2025-07 reject novelty 2.0 of 10

    A small synthetic study reports that Bio_ClinicalBERT embeddings with Random Forest classify CVD risk in about 20 hand-written symptom texts, but the claims of MIMIC-III and CARDIO-NLP evaluation are unsupported.

  4. Research on Model Parallelism and Data Parallelism Optimization Methods in Large Language Model-Based Recommendation Systems

    cs.DC 2025-06 reject novelty 2.0 of 10

    A hybrid model-plus-data parallel scheme is reported to boost training throughput and GPU utilization for LLM-based recommenders, but the supporting experiments are not reproducible from the paper.

  5. Deep Learning Model Acceleration and Optimization Strategies for Real-Time Recommendation Systems

    cs.IR 2025-06 reject novelty 2.0 of 10

    A standard combination of model compression and serving optimization gives 2.4x throughput on a GPU benchmark, but the headline claims of <30% latency and preserved accuracy are not supported by the paper's own data.

  6. Research on Personalized Financial Product Recommendation by Integrating Large Language Models and Graph Neural Networks

    cs.IR 2025-06 reject novelty 2.0 of 10

    A hybrid LLM-plus-GNN recommender is claimed to beat collaborative filtering, LLM-only, and GNN-only baselines on financial product ranking, with NDCG@10 of 0.372.

  7. LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion

    cs.CL 2025-05 reject novelty 2.0 of 10

    An LLM copywriting pipeline combining fine-tuning, vector search, and weighted reranking reportedly lifts CTR by 12.5% and CVR by 8.3%, but the evidence is unverifiable and internally inconsistent.

Pith tools