EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Autoencoder–Based Anomaly Detection Reveals Clinical–Radiologic Heterogeneity in Pulmonary Fibrosis

Constantin Ghimuș, Călin Gheorghe Buzea iD, Alin Horațiu Nedelcu iD, Vlad Florin Oiegar iD, Ancuța Lupu iD, Răzvan Tudor Tepordei iD, Simona Alice Partene Vicoleanu, Ana Maria Dumitrescu, Manuela Ursaru, Gabriel Statescu, Emil Anton iD, Vasile Valeriu Lupu iD und 1 weitere

Medical Sciences · 2026

DOI: 10.3390/medsci14010076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Sciences, 2026. Verfasst von Constantin Ghimuș und 12 weiteren Autor:innen. Beteiligte Einrichtung: Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania. Hauptthemen laut MEDLINE: Pulmonary Fibrosis. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Pulmonary fibrosis (PF) and post-infectious fibrotic lung disease are characterized by marked heterogeneity in radiologic patterns, physiologic impairment, and clinical presentation. Conventional analytic approaches often fail to capture non-linear and multimodal relationships between structural imaging findings and functional limitation. Integrating imaging-derived representations with clinical and functional data using artificial intelligence (AI) may provide a more comprehensive characterization of disease heterogeneity.

Objectives

The objective of this study was to develop and evaluate a multimodal AI framework combining imaging-derived embeddings and structured clinical data to identify atypical clinical–radiologic profiles in patients with pulmonary fibrosis using unsupervised anomaly detection.

Methods

A retrospective cohort of 41 patients with radiologically confirmed pulmonary fibrosis or post-infectious fibrotic lung disease was analyzed. Deep imaging embeddings were extracted from baseline thoracic CT examinations using a pretrained convolutional neural network and integrated with standardized clinical and functional variables. A multimodal variational autoencoder (VAE) was trained in an unsupervised manner to learn the distribution of typical patient profiles. Patient-specific anomaly scores were derived from reconstruction error plus latent regularization (β·KL divergence). Associations between anomaly scores, disease severity, and clinical markers were assessed using Spearman rank correlation.

Results

Anomaly scores were right-skewed (median 26.91, IQR 22.87–32.11; range 19.75–46.18). Patients above the 85th percentile (anomaly score ≥ 33.85) comprised 7/41 (17.1%) of the cohort and occurred across all clinician-assigned severity categories (mild 3, moderate 1, severe 3). Anomaly scores overlapped substantially across severity groups, with similar medians (mild 26.47, moderate 28.55, severe 28.23). Correlations with conventional severity markers were weak and non-significant, including DLCO (% predicted; ρ = −0.25, p = 0.115) and FEV1 (% predicted; ρ = −0.22, p = 0.165), a pattern consistent with anomaly scores reflecting multimodal deviation rather than severity alone, while acknowledging the exploratory nature of the analysis. Highly anomalous patients frequently exhibited discordant clinical–radiologic profiles, including preserved functional capacity despite marked imaging-derived deviation or disproportionate physiological impairment relative to imaging patterns.

Conclusions

This proof-of-concept study demonstrates that multimodal VAE-based anomaly detection integrating imaging-derived embeddings with clinical data can quantify clinical–radiologic heterogeneity in pulmonary fibrosis beyond conventional severity stratification. Unsupervised anomaly detection provides a complementary framework for identifying atypical multimodal profiles and supporting individualized phenotyping and hypothesis generation in fibrotic lung disease. Given the modest cohort size, these findings should be interpreted as illustrative and hypothesis-generating rather than generalizable.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pulmonary FibrosisHumansAutoencoderFemaleRetrospective StudiesMaleTomography, X-Ray ComputedMiddle AgedAgedConvolutional Neural Networks

Stichwörter der Autor:innen

CT imaginganomaly detectionautoencoderdeep learningmultimodal AIpost-infectious fibrosispulmonary fibrosisvariational autoencoder

Autor:innen und Institutionen

  • Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.
  • National Institute of Research and Development for Technical Physics, IFT Iași, 700050 Iasi, Romania.
  • Clinical Emergency Hospital "Prof. Dr. Nicolae Oblu" Iași, 700309 Iasi, Romania.
  • Radiology Clinic, Recovery Hospital, 700661 Iasi, Romania.
  • Radiology Clinic, "Sf Spiridon" County Clinical Emergency Hospital, 700111 Iasi, Romania.

ORCID-Profile: Călin Gheorghe Buzea, Alin Horațiu Nedelcu, Vlad Florin Oiegar, Ancuța Lupu, Răzvan Tudor Tepordei, Emil Anton, Vasile Valeriu Lupu, Paraschiva Postolache

Zitieren

APA

Ghimuș, C., Buzea, C. G., Nedelcu, A. H., Oiegar, V. F., Lupu, A., Tepordei, R. T., Vicoleanu, S. A. P., Dumitrescu, A. M., Ursaru, M., Statescu, G., Anton, E., Lupu, V. V., & Postolache, P. (2026). Multimodal Autoencoder–Based Anomaly Detection Reveals Clinical–Radiologic Heterogeneity in Pulmonary Fibrosis. Medical Sciences. https://doi.org/10.3390/medsci14010076

Vancouver

Ghimuș C, Buzea CG, Nedelcu AH, Oiegar VF, Lupu A, Tepordei RT, et al. Multimodal Autoencoder–Based Anomaly Detection Reveals Clinical–Radiologic Heterogeneity in Pulmonary Fibrosis. Medical Sciences. 2026. doi:10.3390/medsci14010076

BibTeX
@article{Ghimu2026,
  author = {Ghimuș, Constantin and Buzea, Călin Gheorghe and Nedelcu, Alin Horațiu and Oiegar, Vlad Florin and Lupu, Ancuța and Tepordei, Răzvan Tudor and Vicoleanu, Simona Alice Partene and Dumitrescu, Ana Maria and Ursaru, Manuela and Statescu, Gabriel and Anton, Emil and Lupu, Vasile Valeriu and Postolache, Paraschiva},
  title = {Multimodal Autoencoder–Based Anomaly Detection Reveals Clinical–Radiologic Heterogeneity in Pulmonary Fibrosis},
  journal = {Medical Sciences},
  year = {2026},
  doi = {10.3390/medsci14010076}
}
Kostenlos starten →