30 May 2024 in EBioMedicine
Chest X-rays (CXR) are essential for diagnosing a variety of conditions, but when used on new populations, model generalizability issues limit their efficacy. Generative AI, particularly denoising diffusion probabilistic models (DDPMs), offers a promising approach to generating synthetic images, enhancing dataset diversity. This study investigates the impact of synthetic data supplementation on the performance and generalizability of medical imaging research. The study employed DDPMs to create synthetic CXRs conditioned on demographic and pathological characteristics from the CheXpert dataset. These synthetic images were used to supplement training datasets for pathology classifiers, with the aim of improving their performance. The evaluation involved three datasets (CheXpert, MIMIC-CXR, and Emory Chest X-ray) and various experiments, including supplementing real data with synthetic data, training with purely synthetic data, and mixing synthetic data with external datasets. Performance was assessed using the area under the receiver operating curve (AUROC). Adding synthetic data to real datasets resulted in a notable increase in AUROC values (up to 0.02 in internal and external test sets with 1000% supplementation, p-value <0.01 in all instances). When classifiers were trained exclusively on synthetic data, they achieved performance levels comparable to those trained on real data with 200%-300% data supplementation. The combination of real and synthetic data from different sources demonstrated enhanced model generalizability, increasing model AUROC from 0.76 to 0.80 on the internal test set (p-value <0.01). Synthetic data supplementation significantly improves the performance and generalizability of pathology classifiers in medical imaging. Dr. Gichoya is a 2022 Robert Wood Johnson Foundation Harold Amos Medical Faculty Development Program and declares support from RSNA Health Disparities grant (#EIHD2204), Lacuna Fund (#67), Gordon and Betty Moore Foundation, NIH (NIBIB) MIDRC grant under contracts 75N92020C00008 and 75N92020C00021, and NHLBI Award Number R01HL167811.
9 March 2026 in European Heart Journal
Background and Aims: Women are underdiagnosed and undertreated for cardiovascular disease (CVD). Automatic quantification of breast arterial calcification (BAC) on screening mammography can identify women at risk for CVD. This study aimed to determine whether artificial intelligence–based automatic quantification of BAC from screening mammograms predicts CVD and mortality beyond PREVENT scores in a large, racially diverse, multi-institutional population. Methods: This retrospective cohort study included 123 762 women from two healthcare systems who had screening mammograms. Breast arterial calcification was quantified using a transformer-based neural network for segmentation. Breast arterial calcification severity was categorized as zero (0 mm2), mild (>0–10 mm2), moderate (>10–25 mm2), and severe (>25 mm2). Kaplan–Meier analysis, Cox proportional hazards, and Fine–Gray competing event models were used to examine the association between BAC and major adverse cardiovascular events (MACE). Results: Breast arterial calcification was detected in 16.1% (internal cohort) and 20.6% (external cohort) of women and provided significant prognostic value incremental to the PREVENT score. In PREVENT adjusted models, a clear dose–response was observed. Compared with zero BAC, mild [internal: hazard ratio (HR) 1.32, 95% confidence interval (CI) 1.10–1.59; external: HR 1.28, 95% CI 1.17–1.39], moderate (internal: HR 1.75, 95% CI 1.23–2.50; external: HR 1.79, 95% CI 1.55–2.06), and severe BAC (internal: HR 3.29, 95% CI 2.15–5.05; external: HR 2.80, 95% CI 2.36–3.32) were all prognostic for any MACE. Each 1 mm2 increase in BAC conferred an additional 2%–3% risk for MACE (P < .001). Conclusions: Automatically quantified BAC is an independent predictor of MACE and mortality, adding prognostic value to the PREVENT score. This approach may provide an opportunistic cardiovascular risk assessment during routine mammography screening without additional radiation exposure to guide earlier and more effective preventive care for women.
29 April 2021 in IEEE Access
Assessment of disease burden and drug efficacy is achieved preclinically using high resolution micro computed tomography (CT). However, micro-CT is not applicable to clinical human imaging due to operating at high dose. In addition, the technology differences between micro-CT and standard clinical CT prevent direct translation of preclinical applications. The current proof-of-concept study presents spectral photon-counting CT as a clinically translatable, molecular imaging tool by assessing contrast uptake in an ex-vivo mouse model of pulmonary tuberculosis (TB). Iodine, a common contrast used in clinical CT imaging, was introduced into a murine model of TB. The excised mouse lungs were imaged using a standard micro-CT subsystem (SuperArgus) and the contrast enhanced TB lesions quantified. The same lungs were imaged using a spectral photoncounting CT system (MARS small-bore scanner). Iodine and soft tissues (water and lipid) were materially separated, and iodine uptake quantified. The volume of the TB infection quantified by spectral CT and micro-CT was found to be 2.96 mm 3 and 2.83 mm 3 , respectively. This proof-of-concept study showed that spectral photon-counting CT could be used as a predictive preclinical imaging tool for the purpose of facilitating drug discovery and development. Also, as this imaging modality is available for human trials, all applications are translatable to human imaging. In conclusion, spectral photon-counting CT could accelerate a deeper understanding of infectious lung diseases using targeted pharmaceuticals and intrinsic markers, and ultimately improve the efficacy of therapies by measuring drug delivery and response to treatment in animal models and later in humans.
1 March 2026 in Radiology: Artificial Intelligence
CSChiratidzo Rudado Sanyika
Chiratidzo Rudado Sanyika
+3
Large language model–generated labels can introduce systematic bias in artificial intelligence binary classification model performance evaluation, with disease prevalence critically determining whether sensitivity or specificity is most affected.
10 March 2026 in Journal of Imaging Informatics in Medicine
4 August 2026 in eClinicalMedicine