arXiv:2510.23442v1 Announce Type: new 
Abstract: Identifying high-quality and easily accessible annotated samples poses a notable challenge in medical image analysis. Transfer learning techniques, leveraging pre-training data, offer a flexible solution to this issue. However, the impact of fine-tuning diminishes when the dataset exhibits an irregular distribution between classes. This paper introduces a novel deep convolutional neural network, named Curriculum Learning and Progressive Self-supervised Training (CURVETE). CURVETE addresses challenges related to limited samples, enhances model generalisability, and improves overall classification performance. It achieves this by employing a curriculum learning strategy based on the granularity of sample decomposition during the training of generic unlabelled samples. Moreover, CURVETE address the challenge of irregular class distribution by incorporating a class decomposition approach in the downstream task. The proposed method undergoes evaluation on three distinct medical image datasets: brain tumour, digital knee x-ray, and Mini-DDSM datasets. We investigate the classification performance using a generic self-supervised sample decomposition approach with and without the curriculum learning component in training the pretext task. Experimental results demonstrate that the CURVETE model achieves superior performance on test sets with an accuracy of 96.60% on the brain tumour dataset, 75.60% on the digital knee x-ray dataset, and 93.35% on the Mini-DDSM dataset using the baseline ResNet-50. Furthermore, with the baseline DenseNet-121, it achieved accuracies of 95.77%, 80.36%, and 93.22% on the brain tumour, digital knee x-ray, and Mini-DDSM datasets, respectively, outperforming other training strategies.

تقدم ورقة جديدة CURVETE، وهو شبكة عصبية تلافيفية عميقة مصممة لتحسين تصنيف الصور الطبية. تتناول هذه الطريقة المبتكرة التحدي المتمثل في الحصول على عينات مشروحة عالية الجودة من خلال استخدام التعلم بالنقل والتدريب الذاتي المراقب التدريجي. كما تعالج المشكلة الشائعة المتمثلة في عدم التوازن بين الفئات في مجموعات البيانات، مما يجعلها تقدمًا كبيرًا في هذا المجال. هذا التطور مهم لأنه قد يؤدي إلى تشخيصات أكثر دقة ونتائج أفضل للمرضى في التصوير الطبي.

Un nuevo artículo presenta CURVETE, una red neuronal convolucional profunda diseñada para mejorar la clasificación de imágenes médicas. Este enfoque innovador aborda el desafío de obtener muestras anotadas de alta calidad utilizando el aprendizaje por transferencia y el entrenamiento auto-supervisado progresivo. Se ocupa del problema común del desequilibrio entre clases en los conjuntos de datos, lo que representa un avance significativo en el campo. Este desarrollo es crucial, ya que podría conducir a diagnósticos más precisos y mejores resultados para los pacientes en la imagenología médica.

Un nouvel article présente CURVETE, un réseau de neurones convolutifs profonds conçu pour améliorer la classification des images médicales. Cette approche innovante s'attaque au défi d'obtenir des échantillons annotés de haute qualité en utilisant l'apprentissage par transfert et l'apprentissage auto-supervisé progressif. Elle aborde le problème courant du déséquilibre entre les classes dans les ensembles de données, ce qui en fait une avancée significative dans le domaine. Ce développement est crucial car il pourrait conduire à des diagnostics plus précis et à de meilleurs résultats pour les patients en imagerie médicale.

A new paper introduces CURVETE, a deep convolutional neural network designed to enhance medical image classification. This innovative approach tackles the challenge of obtaining high-quality annotated samples by utilizing transfer learning and progressive self-supervised training. It addresses the common issue of class imbalance in datasets, making it a significant advancement in the field. This development is crucial as it could lead to more accurate diagnoses and better patient outcomes in medical imaging.

CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification

Was this article worth reading? Share it

Cogent

MyCVBot

q32 CV Match