Alexander Rakhlin

ColocAI quantifies co-localization between mass spectrometry images using AI, outperforming existing methods and providing insights into 10,273 molecules from public datasets.

This paper presents a deep learning approach for automatic segmentation of robotic instruments in surgery videos, achieving state-of-the-art results for both binary and multi-class segmentation tasks.

This paper develops a deep learning approach for automated pediatric bone age assessment using radiological hand images and shows it outperforms existing methods.

This paper develops a deep learning model for diabetic retinopathy detection using CNNs, achieving high sensitivity and AUC on test data, surpassing optometrist performance.

This paper develops deep convolutional neural networks for detecting and localizing angiodysplasia lesions in gastrointestinal images, achieving state-of-the-art results.

This paper develops a deep convolutional neural network approach for breast cancer histology image classification, achieving high accuracy in both 4-class and 2-class tasks.