arXiv:2512.08323v1 Announce Type: new 
Abstract: Teeth landmark detection is a critical task in modern clinical orthodontics. Their precise identification enables advanced diagnostics, facilitates personalized treatment strategies, and supports more effective monitoring of treatment progress in clinical dentistry. However, several significant challenges may arise due to the intricate geometry of individual teeth and the substantial variations observed across different individuals. To address these complexities, the development of advanced techniques, especially through the application of deep learning, is essential for the precise and reliable detection of 3D tooth landmarks. In this context, the 3DTeethLand challenge was held in collaboration with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) in 2024, calling for algorithms focused on teeth landmark detection from intraoral 3D scans. This challenge introduced the first publicly available dataset for 3D teeth landmark detection, offering a valuable resource to assess the state-of-the-art methods in this task and encourage the community to provide methodological contributions towards the resolution of their problem with significant clinical implications.

تم الإعلان عن تحدي 3DTeethLand بالتعاون مع المؤتمر الدولي حول الحوسبة الطبية والتدخل المدعوم بالكمبيوتر (MICCAI) 2024، والذي يركز على اكتشاف المعالم السنية من المسح ثلاثي الأبعاد داخل الفم. تهدف هذه المبادرة إلى تحسين دقة التشخيصات التقويمية ومراقبة العلاج من خلال استخدام تقنيات التعلم العميق المتقدمة لمواجهة تعقيدات هندسة الأسنان الفردية.

Se anunció el desafío 3DTeethLand en colaboración con la Conferencia Internacional sobre Computación Médica e Intervención Asistida por Computadora (MICCAI) 2024, centrado en la detección de puntos de referencia dentales a partir de escaneos 3D intraorales. Esta iniciativa tiene como objetivo mejorar la precisión de los diagnósticos ortodónticos y el monitoreo del tratamiento mediante el uso de técnicas avanzadas de aprendizaje profundo para abordar las complejidades de la geometría dental individual.

Le défi 3DTeethLand a été annoncé en collaboration avec la Conférence Internationale sur l'Informatique Médicale et l'Intervention Assistée par Ordinateur (MICCAI) 2024, axé sur la détection des repères dentaires à partir de scans 3D intra-oraux. Cette initiative vise à améliorer la précision des diagnostics orthodontiques et du suivi des traitements en utilisant des techniques avancées d'apprentissage profond pour relever les complexités des géométries dentaires individuelles.

The 3DTeethLand challenge was announced in collaboration with the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2024, focusing on the detection of dental landmarks from intraoral 3D scans. This initiative aims to enhance the precision of orthodontic diagnostics and treatment monitoring by leveraging advanced deep learning techniques to address the complexities of individual tooth geometries.

Detecting Dental Landmarks from Intraoral 3D Scans: the 3DTeethLand challenge

arXiv:2512.06206v1 Announce Type: cross 
Abstract: We present the design and results of the MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024, which focuses on federated learning (FL) for glioma sub-region segmentation in multi-parametric MRI and evaluates new weight aggregation methods aimed at improving robustness and efficiency. Six participating teams were evaluated using a standardized FL setup and a multi-institutional dataset derived from the BraTS glioma benchmark, consisting of 1,251 training cases, 219 validation cases, and 570 hidden test cases with segmentations for enhancing tumor (ET), tumor core (TC), and whole tumor (WT). Teams were ranked using a cumulative scoring system that considered both segmentation performance, measured by Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95), and communication efficiency assessed through the convergence score. A PID-controller-based method achieved the top overall ranking, obtaining mean DSC values of 0.733, 0.761, and 0.751 for ET, TC, and WT, respectively, with corresponding HD95 values of 33.922 mm, 33.623 mm, and 32.309 mm, while also demonstrating the highest communication efficiency with a convergence score of 0.764. These findings advance the state of federated learning for medical imaging, surpassing top-performing methods from previous challenge iterations and highlighting PID controllers as effective mechanisms for stabilizing and optimizing weight aggregation in FL. The challenge code is available at https://github.com/FeTS-AI/Challenge.

تم الإعلان عن تحدي MICCAI لتجزئة الأورام الفيدرالية (FeTS) 2024، الذي يركز على التعلم الفيدرالي لتجزئة المناطق الفرعية للورم الدبقي في التصوير بالرنين المغناطيسي متعدد المعلمات. تم تقييم ستة فرق باستخدام إعداد موحد ومجموعة بيانات من معيار glioma BraTS، والتي تضمنت 1,251 حالة تدريب و570 حالة اختبار مخفية. تم تصنيف الفرق بناءً على أداء التجزئة وكفاءة الاتصال، حيث حققت طريقة قائمة على وحدة تحكم PID أعلى درجة.

Se ha anunciado el Desafío de Segmentación Tumoral Federada (FeTS) 2024 de MICCAI, que se centra en el aprendizaje federado para la segmentación de subregiones de glioma en IRM multiparamétrica. El desafío evaluó a seis equipos utilizando una configuración estandarizada y un conjunto de datos del benchmark de gliomas BraTS, que incluía 1,251 casos de entrenamiento y 570 casos de prueba ocultos. Los equipos fueron clasificados según el rendimiento de segmentación y la eficiencia de comunicación, destacando un método basado en controlador PID que logró la mejor puntuación.

Le défi MICCAI de segmentation tumorale fédérée (FeTS) 2024 a été annoncé, se concentrant sur l'apprentissage fédéré pour la segmentation des sous-régions de gliome dans l'IRM multiparamétrique. Le défi a évalué six équipes utilisant une configuration standardisée et un ensemble de données du benchmark gliome BraTS, comprenant 1 251 cas d'entraînement et 570 cas de test cachés. Les équipes ont été classées en fonction de la performance de segmentation et de l'efficacité de communication, une méthode basée sur un contrôleur PID ayant obtenu le meilleur score.

The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024 has been announced, focusing on federated learning for glioma sub-region segmentation in multi-parametric MRI. The challenge evaluated six teams using a standardized setup and a dataset from the BraTS glioma benchmark, which included 1,251 training cases and 570 hidden test cases. Teams were ranked based on segmentation performance and communication efficiency, with a PID-controller-based method achieving the top score.

Detecting Dental Landmarks from Intraoral 3D Scans: the 3DTeethLand challenge

Was this article worth reading? Share it

WasItAI

Attentive AI

Deptho.ai