Toward reliable calcification detection: calibration of uncertainty in object detection from coronary optical coherence tomography images

Abstract

Significance: Optical coherence tomography (OCT) has become increasingly essential in assisting the treatment of coronary artery disease (CAD). However, unidentified calcified regions within a narrowed artery could impair the outcome of the treatment. Fast and objective identification is paramount to automatically procuring accurate readings on calcifications within the artery.

Aim: We aim to rapidly identify calcification in coronary OCT images using a bounding box and reduce the prediction bias in automated prediction models.

Approach: We first adopt a deep learning-based object detection model to rapidly draw the calcified region from coronary OCT images using a bounding box. We measure the uncertainty of predictions based on the expected calibration errors, thus assessing the certainty level of detection results. To calibrate confidence scores of predictions, we implement dependent logistic calibration using each detection result's confidence and center coordinates.

Results: We implemented an object detection module to draw the boundary of the calcified region at a rate of 140 frames per second. With the calibrated confidence score of each prediction, we lower the uncertainty of predictions in calcification detection and eliminate the estimation bias from various object detection methods. The calibrated confidence of prediction results in a confidence error of $\sim 0.13$ , suggesting that the confidence calibration on calcification detection could provide a more trustworthy result.

Conclusions: Given the rapid detection and effective calibration of the proposed work, we expect that it can assist in clinical evaluation of treating the CAD during the imaging-guided procedure.

Keywords: calibration; coronary artery disease; deep learning; optical coherence tomography.

Fig. 1

Flowchart of the proposed work. Scale bar: $500\mu \mathrm{m}$.

Fig. 2

Schematic of YOLO object detector and calibration.

Fig. 3

Example of (a) ground-truth label, (b) corresponding histology, and object detection results from (c) Faster RCNN, (d) SSD, and (e) YOLO. Scale bar: $500\mu \mathrm{m}$.

Fig. 4

Object detection results of deep learning models with a threshold of 0.4 in precision, recall, and $f\text{-}1$ score. The gray bars are the results of Faster RCNN, the blue bars are the results of the SSD, and the green bars are the results of YOLO.

Fig. 5

Example result: (a) ground-truth label, (b) corresponding histology, and confidence calibration results of (c) Faster RCNN, (d) SSD, and (e) YOLO. Scale bar: $500\mu \mathrm{m}$.