Automated delineation of orbital abscess depicted on CT scan using deep learning

Abstract

Objectives: To develop and validate a deep learning algorithm to automatically detect and segment an orbital abscess depicted on computed tomography (CT). Methods: We retrospectively collected orbital CT scans acquired on 67 pediatric subjects with a confirmed orbital abscess in the setting of infectious orbital cellulitis. A context-aware convolutional neural network (CA-CNN) was developed and trained to automatically segment orbital abscess. To reduce the requirement for a large dataset, transfer learning was used by leveraging a pre-trained model for CT-based lung segmentation. An ophthalmologist manually delineated orbital abscesses depicted on the CT images. The classical U-Net and the CA-CNN models with and without transfer learning were trained and tested on the collected dataset using the 10-fold cross-validation method. Dice coefficient, Jaccard index, and Hausdorff distance were used as performance metrics to assess the agreement between the computerized and manual segmentations. Results: The context-aware U-Net with transfer learning achieved an average Dice coefficient and Jaccard index of 0.78 AE 0.12 and 0.65 AE 0.13, which were consistently higher than the classical U-Net or the context-aware U-Net without transfer learning (P < 0.01). The average differences of the abscess between the computerized results and the experts in terms of volume and Hausdorff distance were 0.10 AE 0.11 mL and 1.94 AE 1.21 mm, respectively. The context-aware U-Net detected all orbital abscess without false positives. Conclusions:The deep learning solution demonstrated promising performance in detecting and segmenting orbital abscesses on CT images in strong agreement with a human observer.

Treatment planning for photodynamic therapy of abscess cavities using patient-specific optical properties measured prior to illumination

“…This motivates utilization of CT imaging immediately prior to PDT, in order to capture accurate abscess morphology. This could be facilitated by real-time abscess segmentation, which has been demonstrated for orbital abscesses 39 .…”

Effective encoder-decoder neural network for segmentation of orbital tissue in computed tomography images of Graves’ orbitopathy patients

“…Several studies have attempted to segment and measure various orbital component areas and volumes using artificial intelligence in orbital CT images ( Table 4 ) [ 13 , 14 , 37 – 41 ]. However, the model best suited for semantic orbital tissue segmentation in GO patients’ CT images remains unknown.…”

Orbital and eyelid diseases: The next breakthrough in artificial intelligence?

“…Brown et al (2020) used a UNet-like CNN to segment orbital septal fat from orbital MRI images, and the results showed that AI segmentation was consistent with manual segmentation. Fu et al (2021) trained and evaluated a context-aware CNN (CA-CNN) to segment orbital abscess regions from CT images of patients with orbital cellulitis, with the AI results being similar to those obtained by medical experts.…”