Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus

Abstract

Purpose Paranasal anomalies are commonly discovered during routine radiological screenings and can present with a wide range of morphological features. This diversity can make it difficult for convolutional neural networks (CNNs) to accurately classify these anomalies, especially when working with limited datasets. Additionally, current approaches to paranasal anomaly classification are constrained to identifying a single anomaly at a time. These challenges necessitate the need for further research and development in this area. Methods We investigate the feasibility of using a 3D convolutional neural network (CNN) to classify healthy maxillary sinuses (MS) and MS with polyps or cysts. The task of accurately localizing the relevant MS volume within larger head and neck Magnetic Resonance Imaging (MRI) scans can be difficult, but we develop a strategy which includes the use of a novel sampling technique that not only effectively localizes the relevant MS volume, but also increases the size of the training dataset and improves classification results. Additionally, we employ a Multiple Instance Ensembling (MIE) prediction method to further boost classification performance. Results With sampling and MIE, we observe that there is consistent improvement in classification performance of all 3D ResNet and 3D DenseNet architecture with an average AUPRC percentage increase of 21.86 ± 11.92% and 4.27 ± 5.04% by sampling and 28.86 ± 12.80% and 9.85 ± 4.02% by sampling and MIE, respectively. Conclusion Sampling and MIE can be effective techniques to improve the generalizability of CNNs for paranasal anomaly classification. We demonstrate the feasibility of classifying anomalies in the MS. We propose a data enlarging strategy through sampling alongside a novel MIE strategy that proves to be beneficial for paranasal anomaly classification in the MS.

Dynamic Navigation Protocol for Direct Sinus Lift and Simultaneous Implant Placement: A Case Report

“…This study was conducted at the Department of Implantology, Saveetha Dental College and Hospital, Chennai, India. The following criteria were followed to include the patient for working under dynamic navigation: patients eligible for inclusion were as follows: (A) patients desiring posterior maxillary implants with 4-6 mm residual alveolar ridge height (indicating the need for direct SFE); (B) individuals with maximum mouth opening (40 mm) for Physiodispenser handpiece drill orientation; (C) for whom a preoperative digital visual implant plan was prepared; and (D) people in good health without any systemic diseases that are contraindicated for implant placement [ 8 ].…”

“…Dynamic navigation in dental implantology can help overcome complications associated with direct sinus lift procedures. Dynamic navigation is a relatively new technology increasingly used in dental implantology to improve accuracy and safety during surgical procedures, including direct sinus lift procedures [ 2 , 8 ]. This technology uses real-time imaging and computer-guided navigation to allow for the precise and predictable placement of dental implants [ 9 ].…”

Comparative Evaluation of Accuracy of Adjacent Parallel Implant Placements Between Dynamic Navigation and Static Guide: A Prospective Study

“…Patients requiring dental implant placements must have a streamlined appointment. Several other factors can play a major role in the success of the implant, such as anatomical limitations in the maxilla, bone density, wound healing, and crestal bone loss in the long run [1][2][3][4].…”