Virtual-Eyes: Quantitative Validation of a Lung CT Quality-Control Pipeline for Foundation-Model Cancer Risk Prediction

• URL: http://arxiv.org/abs/2512.24294v1
• Date: Tue, 30 Dec 2025 15:34:18 GMT
• Title: Virtual-Eyes: Quantitative Validation of a Lung CT Quality-Control Pipeline for Foundation-Model Cancer Risk Prediction
• Abstract summary: Preprocessing is rarely quantified in deep-learning pipelines for low-dose lung cancer screening.<n>We develop VirtualEyes, a 16-bit CT quality-control pipeline, and measure its impact on generalist foundation models versus specialist models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust preprocessing is rarely quantified in deep-learning pipelines for low-dose CT (LDCT) lung cancer screening. We develop and validate Virtual-Eyes, a clinically motivated 16-bit CT quality-control pipeline, and measure its differential impact on generalist foundation models versus specialist models. Virtual-Eyes enforces strict 512x512 in-plane resolution, rejects short or non-diagnostic series, and extracts a contiguous lung block using Hounsfield-unit filtering and bilateral lung-coverage scoring while preserving the native 16-bit grid. Using 765 NLST patients (182 cancer, 583 non-cancer), we compute slice-level embeddings from RAD-DINO and Merlin with frozen encoders and train leakage-free patient-level MLP heads; we also evaluate Sybil and a 2D ResNet-18 baseline under Raw versus Virtual-Eyes inputs without backbone retraining. Virtual-Eyes improves RAD-DINO slice-level AUC from 0.576 to 0.610 and patient-level AUC from 0.646 to 0.683 (mean pooling) and from 0.619 to 0.735 (max pooling), with improved calibration (Brier score 0.188 to 0.112). In contrast, Sybil and ResNet-18 degrade under Virtual-Eyes (Sybil AUC 0.886 to 0.837; ResNet-18 AUC 0.571 to 0.596) with evidence of context dependence and shortcut learning, and Merlin shows limited transferability (AUC approximately 0.507 to 0.567) regardless of preprocessing. These results demonstrate that anatomically targeted QC can stabilize and improve generalist foundation-model workflows but may disrupt specialist models adapted to raw clinical context.

Related papers

• Distilling Photon-Counting CT into Routine Chest CT through Clinically Validated Degradation Modeling [51.330452704464925]
  We train a latent diffusion model on 1,046 PCCTs and 405,379 EICTs from 145 hospitals.<n>We construct a large-scale dataset of over 17,316 publicly available EICTs enhanced to PCCT-like quality.<n>Our results suggest emerging imaging advances can be systematically distilled into routine EICT using limited high-quality scans as reference.
  arXiv  Detail & Related papers  (2026-04-08T17:47:35Z)
• CT-to-X-ray Distillation Under Tiny Paired Cohorts: An Evidence-Bounded Reproducible Pilot Study [11.316541559874864]
  This study is not a validated CT-to-X-ray architecture, but a reproducible and evidence-bounded pilot protocol that makes the exact task definition, failure modes, ranking instability, and the minimum requirements for future credible CT-to-X-ray transfer claims explicit.
  arXiv  Detail & Related papers  (2026-03-31T02:25:33Z)
• Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation [64.42236775544579]
  Cone beam computed tomography (CBCT)-guided puncture has become an established approach for diagnosing and treating thoracic tumours.<n>DeepPriorCBCT is a three-stage deep learning framework that achieves diagnostic-grade reconstruction using only one-sixth of the conventional radiation dose.
  arXiv  Detail & Related papers  (2025-11-30T12:45:02Z)
• Click, Predict, Trust: Clinician-in-the-Loop AI Segmentation for Lung Cancer CT-Based Prognosis within the Knowledge-to-Action Framework [0.7340285482623061]
  Lung cancer remains the leading cause of cancer mortality, with CT imaging central to screening, prognosis, and treatment.<n>Deep learning (DL) offers automation but faces barriers to clinical adoption.<n>This study develops a clinician-in-the-loop DL pipeline to enhance, prognostic accuracy, and clinical trust.
  arXiv  Detail & Related papers  (2025-10-19T23:02:43Z)
• A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler [49.03919553747297]
  We propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries.<n>No prior studies have explored AI-driven cerebrovascular segmentation using Transcranial Color-coded Doppler (TCCD)<n>The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels.
  arXiv  Detail & Related papers  (2025-08-19T14:41:22Z)
• ViT-2SPN: Vision Transformer-based Dual-Stream Self-Supervised Pretraining Networks for Retinal OCT Classification [0.10241134756773226]
  Vision Transformer-based Dual-Stream Self-Supervised Pretraining Network (ViT-2SPN) is a novel framework designed to enhance feature extraction and improve diagnostic accuracy.<n>ViT-2SPN employs a three-stage workflow: Supervised Pretraining, Self-Supervised Pretraining, and Supervised Fine-Tuning.<n>ViT-2SPN achieves a mean AUC of 0.93, accuracy of 0.77, precision of 0.81, recall of 0.75, and an F1 score of 0.76, outperforming existing SSP-based methods.
  arXiv  Detail & Related papers  (2025-01-28T19:41:38Z)
• BeyondCT: A deep learning model for predicting pulmonary function from chest CT scans [2.602923751641061]
  The BeyondCT model was developed to predict forced vital capacity (FVC) and forced expiratory volume in one second (FEV1) from non-contrasted inspiratory chest CT scans. The model showed robust performance in predicting lung function from non-contrast inspiratory chest CT scans.
  arXiv  Detail & Related papers  (2024-08-10T22:28:02Z)
• Rapid quantification of COVID-19 pneumonia burden from computed tomography with convolutional LSTM networks [1.0072268949897432]
  We propose a new fully automated deep learning framework for rapid quantification and differentiation between lung lesions in COVID-19 pneumonia. The performance of the method was evaluated on CT data sets from 197 patients with positive reverse transcription polymerase chain reaction test result for SARS-CoV-2.
  arXiv  Detail & Related papers  (2021-03-31T22:09:14Z)
• COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 from Chest CT Images Through Bigger, More Diverse Learning [70.92379567261304]
  We introduce COVID-Net CT-2, enhanced deep neural networks for COVID-19 detection from chest CT images. We leverage explainability to investigate the decision-making behaviour of COVID-Net CT-2. Results are promising and suggest the strong potential of deep neural networks as an effective tool for computer-aided COVID-19 assessment.
  arXiv  Detail & Related papers  (2021-01-19T03:04:09Z)
• FLANNEL: Focal Loss Based Neural Network Ensemble for COVID-19 Detection [61.04937460198252]
  We construct the X-ray imaging data from 2874 patients with four classes: normal, bacterial pneumonia, non-COVID-19 viral pneumonia, and COVID-19. To identify COVID-19, we propose a Focal Loss Based Neural Ensemble Network (FLANNEL) FLANNEL consistently outperforms baseline models on COVID-19 identification task in all metrics.
  arXiv  Detail & Related papers  (2020-10-30T03:17:31Z)
• An Efficient Mixture of Deep and Machine Learning Models for COVID-19 and Tuberculosis Detection Using X-Ray Images in Resource Limited Settings [2.408714894793063]
  Clinicians in the frontline need to assess quickly whether a patient with symptoms indeed has COVID-19 or not. The difficulty of this task is exacerbated in low resource settings that may not have access to biotechnology tests. We propose the extraction of deep features (DF) from chest X-ray images and their subsequent classification using machine learning methods.
  arXiv  Detail & Related papers  (2020-07-16T09:49:49Z)
• Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning [57.00601760750389]
  We present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge severity of COVID-19 lung infections that can be used for escalation or de-escalation of care.
  arXiv  Detail & Related papers  (2020-05-24T23:13:16Z)
• Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT [48.785596536318884]
  The proposed method takes as input a non-contrasted chest CT and segments the lesions, lungs, and lobes in three dimensions. The method outputs two combined measures of the severity of lung and lobe involvement, quantifying both the extent of COVID-19 abnormalities and presence of high opacities. Evaluation of the algorithm is reported on CTs of 200 participants (100 COVID-19 confirmed patients and 100 healthy controls) from institutions from Canada, Europe and the United States.
  arXiv  Detail & Related papers  (2020-04-02T21:49:14Z)
• Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images [54.919022945740515]
  The aim of this study is to realize automatic severity assessment (non-severe or severe) of COVID-19 based on chest CT images. A random forest (RF) model is trained to assess the severity (non-severe or severe) based on quantitative features. Several quantitative features, which have the potential to reflect the severity of COVID-19, were revealed.
  arXiv  Detail & Related papers  (2020-03-26T15:49:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.