EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Explainable AI to identify radiographic features of pulmonary edema

Viacheslav V Danilov iD, Anton O Makoveev iD, Alex Proutski, Irina Ryndova, Alex Karpovsky, Yuriy Gankin iD

Radiology Advances · 2024

DOI: 10.1093/radadv/umae003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology Advances, 2024. Verfasst von Viacheslav V Danilov und 5 weiteren Autor:innen. Beteiligte Einrichtung: Pompeu Fabra University, Barcelona, 08018, Spain. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Quantori and Kanda Software.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Pulmonary edema is a leading cause for requiring hospitalization in patients with congestive heart failure. Assessing the severity of this condition with radiological imaging becomes paramount in determining the optimal course of patient care.

Purpose

This study aimed to develop a deep learning methodology for the identification of radiographic features associated with pulmonary edema. Materials and Methods This retrospective study used a dataset from the Medical Information Mart for Intensive Care database comprising 1000 chest radiograph images from 741 patients with suspected pulmonary edema. The images were annotated by an experienced radiologist, who labeled radiographic manifestations of cephalization, Kerley lines, pleural effusion, bat wings, and infiltrate features of edema. The proposed methodology involves 2 consecutive stages: lung segmentation and edema feature localization. The segmentation stage is implemented using an ensemble of 3 networks. In the subsequent localization stage, we evaluated 8 object detection networks, assessing their performance with average precision (AP) and mean AP.

Results

Effusion, infiltrate, and bat wing features were best detected by the Side-Aware Boundary Localization (SABL) network with corresponding APs of 0.599, 0.395, and 0.926, respectively. Furthermore, SABL achieved the highest overall mean AP of 0.568. The Cascade Region Proposal Network network attained the highest AP of 0.417 for Kerley lines and the Probabilistic Anchor Assignment network achieved the highest AP of 0.533 for cephalization.

Conclusion

The proposed methodology, with the application of SABL, Cascade Region Proposal Network, and Probabilistic Anchor Assignment detection networks, is accurate and efficient in localizing and identifying pulmonary edema features and is therefore a promising diagnostic candidate for interpretable severity assessment of pulmonary edema.

Schlagwörter

Stichwörter der Autor:innen

chest X-ray analysisexplainable AIinterpretabilitylung segmentationpulmonary edema diagnosisradiographic feature detection

Autor:innen und Institutionen

  • Pompeu Fabra University, Barcelona, 08018, Spain.
  • Quantori, Cambridge, MA, 02142, United States.
  • Kanda Software, Newton, MA, 02464, United States.

ORCID-Profile: Viacheslav V Danilov, Anton O Makoveev, Yuriy Gankin

Förderung

  • Quantori and Kanda Software

Zitieren

APA

Danilov, V. V., Makoveev, A. O., Proutski, A., Ryndova, I., Karpovsky, A., & Gankin, Y. (2024). Explainable AI to identify radiographic features of pulmonary edema. Radiology Advances. https://doi.org/10.1093/radadv/umae003

Vancouver

Danilov VV, Makoveev AO, Proutski A, Ryndova I, Karpovsky A, Gankin Y. Explainable AI to identify radiographic features of pulmonary edema. Radiology Advances. 2024. doi:10.1093/radadv/umae003

BibTeX
@article{Danilov2024,
  author = {Danilov, Viacheslav V and Makoveev, Anton O and Proutski, Alex and Ryndova, Irina and Karpovsky, Alex and Gankin, Yuriy},
  title = {Explainable AI to identify radiographic features of pulmonary edema},
  journal = {Radiology Advances},
  year = {2024},
  doi = {10.1093/radadv/umae003}
}
Kostenlos starten →