Audiogram Detection AI Trained Using Size-Fixed Frame and Bounding-Boxes

Abstract Audiograms are used to diagnose auditory diseases and are depicted in a standardized manner using mostly identical threshold signs. This study proposes a novel method for detecting and standardizing audiometric thresholds using artificial intelligence, specifically DETR and YOLO models. We introduce a size-fixed rectangular frame and size-fixed bounding-box strategy tailored to the standardized characteristics of audiogram symbols, while comparing performance between YOLOv5 and DETR. The method comprises two main phases: training and detection. In the training phase, a dataset of audiograms is prepared by extracting frame rectangles from original audiogram images and resizing them to 416 × 416 pixels. Air-conduction and bone-conduction threshold signs are annotated using a fixed bounding-box size with the labelImg software. A DETR/YOLO model is then trained on this annotated dataset, leveraging transfer learning from a pre-trained model to enhance efficiency and accuracy. In the detection phase, the trained DETR/YOLO model is applied to original audiogram images. Frame rectangles are extracted and resized to 416 × 416 pixels before being subjected to inference. The error detection rate was as low as 0.3%, representing an 11-fold improvement over the conventional model. The predicted threshold signs are mapped to their relative positions, converted into standardized formats, redrawn as a standardized audiogram, and evaluated using Intraclass Correlation Coefficient (ICC). Compared to the existing YOLOv5 model, the ICC3 (single fixed rater model) of the YOLOv5 model of this method was improved from 0.89 to 1.00. This method highly advances automated audiogram interpretation, paving the way for scalable and standardized audiological assessments.