パノラマX線写真における第三大臼歯埋伏の分類および検出のためのデュアルフレームワーク
Zohaib Khurshid1, Mousa Haney Alsleem1, Fahad Ahmed Aljubairah1
1Department of Prosthodontics and Dental Implantology, College of Dentistry, King Faisal University, Al-Ahsa, Saudi Arabia.
International dental journal
|February 8, 2026
まとめ
本研究では、埋伏した下顎第三大臼歯を分析するための高度なAIフレームワークを紹介し、外科的計画を改善し、神経損傷のリスクを低減します。新しいモデルは、臨床使用において高い精度と効率を提供します。
科学分野:
- 口腔および顎顔面外科学;放射線学における人工知能;医用画像における深層学習
背景:
- 埋伏した下顎第三大臼歯の外科的抜歯は、下顎歯槽神経損傷のリスクを伴い、正確な術前評価が必要です。現在、歯科放射線学におけるAIは、二項分類、クラス不均衡、および標準化された評価の欠如によって制限されており、臨床応用を妨げています。
研究 の 目的:
- 埋伏した下顎第三大臼歯の包括的かつ自動化された分析のための2つの独立した深層学習フレームワークを開発および評価すること。第三大臼歯手術の術前評価の精度と効率を向上させること。
主な方法:
- マルチヘッド自己注意を備えた変更YOLOv10およびYOLOv11nアーキテクチャを使用したエンドツーエンドオブジェクト検出パイプライン。従来の機械学習アルゴリズムによって分類されるResNet50およびInceptionNetV3からのディープ特徴を利用した特徴ベースの分類アプローチ。
主要な成果:
- ResNet50特徴を備えたFine KNN分類器は、97.56%の精度と96.10%のF1スコアを達成しました。YOLOv11nオブジェクト検出は、計算複雑性が低いながらも、88.9%(mAP@0.5)の平均精度を示しました。マルチヘッド自己注意とGANベースの拡張は、検出性能を6.4% mAP向上させました。
結論:
- 提案されたAIフレームワークは、高い診断性能と計算効率を備えた、第三大臼歯埋伏の正確で自動化されたマルチクラス評価を提供します。この研究は、信頼性の高いF1スコア評価、リアルタイム検出、および改善された術前リスク層別化を通じて、AI支援外科計画を強化します。
関連する概念動画
Molar Mass
87.0K
The identity of a substance is defined not only by the types of atoms or ions it contains but by the quantity of each type of atom or ion. For example, water, H2O, and hydrogen peroxide, H2O2, are alike in that their respective molecules are composed of hydrogen and oxygen atoms. However, because a hydrogen peroxide molecule contains two oxygen atoms, as opposed to the water molecule, which has only one, the two substances exhibit very different properties.
87.0K
Applications of the Ideal Gas Law: Molar Mass, Density, and Volume
63.5K
The volume occupied by one mole of a substance is its molar volume. The ideal gas law, PV = nRT, suggests that the volume of a given quantity of gas and the number of moles in a given volume of gas vary with changes in pressure and temperature. At standard temperature and pressure, or STP (273.15 K and 1 atm), one mole of an ideal gas (regardless of its identity) has a volume of about 22.4 L — this is referred to as the standard molar volume.
63.5K
Impact of Groups on Groups
258
Social psychologists analyze how groups influence one another, shaping social structures and interactions through both cooperation and competition. These dynamics manifest in various ways, ranging from economic partnerships to intergroup conflicts that shape societal structures and perceptions.Cooperation and Competition in Intergroup RelationsIntergroup relationships vary across contexts, sometimes fostering cooperation and mutual benefit while at other times leading to conflict and...
258
Force Classification
2.4K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.4K
Classification of Neurotransmitters
5.3K
Neurotransmitters play a crucial role in the communication between neurons in the autonomic nervous system. Neurons in the autonomic nervous system can be cholinergic or adrenergic depending on the neurotransmitters synthesized. Cholinergic neurons use acetylcholine as their primary neurotransmitter. This includes all the preganglionic fibers of the sympathetic and pre- and postganglionic fibers of the parasympathetic nervous systems. In addition, neurons of the somatic nervous system also use...
5.3K
Classification of Leukocytes
6.0K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
6.0K


