Texture‐based speciation of otitis media‐related bacterial biofilms from optical coherence tomography images using supervised classification

• Published in: Journal of biophotonics Vol. 17; no. 10; pp. e202400075 - n/a
• Main Authors: Zaki, Farzana R., Monroy, Guillermo L., Shi, Jindou, Sudhir, Kavya, Boppart, Stephen A.
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01.10.2024; Wiley Subscription Services, Inc
• Subjects: Bacteria; Biofilms; Chronic infection; gray‐level co‐occurrence matrix; Humans; Image Processing, Computer-Assisted - methods; In vivo methods and tests; Learning algorithms; Machine learning; Medical imaging; Middle ear; Optical Coherence Tomography; Otitis media; Otitis Media - diagnostic imaging; Otitis Media - microbiology; raincloud plots; random forest; Recurrent infection; SHAP; Speciation; Supervised Machine Learning; Support vector machines; SVM; Texture; texture feature; Tomography, Optical Coherence; XGBoost; SHAP; optical coherence tomography; otitis media; XGBoost; raincloud plots; texture feature; SVM; random forest; biofilms; gray‐level co‐occurrence matrix
• ISSN: 1864-063X; 1864-0648; 1864-0648
• DOI: 10.1002/jbio.202400075

Otitis media (OM), a highly prevalent inflammatory middle‐ear disease in children worldwide, is commonly caused by an infection, and can lead to antibiotic‐resistant bacterial biofilms in recurrent/chronic OM cases. A biofilm related to OM typically contains one or multiple bacterial species. OCT has been used clinically to visualize the presence of bacterial biofilms in the middle ear. This study used OCT to compare microstructural image texture features from bacterial biofilms. The proposed method applied supervised machine‐learning‐based frameworks (SVM, random forest, and XGBoost) to classify multiple species bacterial biofilms from in vitro cultures and clinically‐obtained in vivo images from human subjects. Our findings show that optimized SVM‐RBF and XGBoost classifiers achieved more than 95% of AUC, detecting each biofilm class. These results demonstrate the potential for differentiating OM‐causing bacterial biofilms through texture analysis of OCT images and a machine‐learning framework, offering valuable insights for real‐time in vivo characterization of ear infections. Otitis media (OM) is an inflammatory middle‐ear infection in children that can lead to antibiotic‐resistant bacterial biofilms in recurrent or chronic cases. Optical coherence tomography (OCT) is used clinically to visualize these biofilms. This study used OCT to compare texture features from primary bacterial biofilms, employing machine‐learning frameworks (SVM, random forest, XGBoost). Optimized SVM‐RBF and XGBoost classifiers achieved over 95% AUC. These results demonstrate the potential for differentiating OM‐causing biofilms with OCT and offer insights for real‐time in vivo characterization.