Self-CephaloNet: A Two-stage Novel Framework using Operational Neural Network for Cephalometric Analysis

TL;DR

This paper introduces Self-CephaloNet, a novel two-stage deep learning framework utilizing operational neural networks for efficient and accurate cephalometric landmark detection, outperforming previous methods on multiple datasets.

Contribution

The study presents a new end-to-end cascaded deep learning model with a self-bottleneck in HRNetV2, achieving benchmark performance in cephalometric landmark detection.

Findings

70.95% success rate within 2mm in initial detection

82.25% success rate after second stage

75.95% success rate on external dataset

Abstract

Cephalometric analysis is essential for the diagnosis and treatment planning of orthodontics. In lateral cephalograms, however, the manual detection of anatomical landmarks is a time-consuming procedure. Deep learning solutions hold the potential to address the time constraints associated with certain tasks; however, concerns regarding their performance have been observed. To address this critical issue, we proposed an end-to-end cascaded deep learning framework (Self-CepahloNet) for the task, which demonstrated benchmark performance over the ISBI 2015 dataset in predicting 19 dental landmarks. Due to their adaptive nodal capabilities, Self-ONN (self-operational neural networks) demonstrate superior learning performance for complex feature spaces over conventional convolutional neural networks. To leverage this attribute, we introduced a novel self-bottleneck in the HRNetV2 (High Resolution Network) backbone, which has exhibited benchmark performance on the ISBI 2015 dataset for the dental landmark detection task. Our first-stage results surpassed previous studies, showcasing the efficacy of our singular end-to-end deep learning model, which achieved a remarkable 70.95% success rate in detecting cephalometric landmarks within a 2mm range for the Test1 and Test2 datasets. Moreover, the second stage significantly improved overall performance, yielding an impressive 82.25% average success rate for the datasets above within the same 2mm distance. Furthermore, external validation was conducted using the PKU cephalogram dataset. Our model demonstrated a commendable success rate of 75.95% within the 2mm range.