Rate My Professor Lasse Lensu

Lasse Lensu is a Professor of Machine Vision and Data Analysis at LUT University, Lappeenranta, Finland, affiliated with the Department of Computational Engineering and the Computer Vision and Pattern Recognition Laboratory. He earned his Doctor of Science in Technology (D.Sc. Tech.) degree in computer science and engineering from the Department of Information Technology at LUT University in 2002. Throughout his career at LUT, Lensu has focused his research on machine vision, computer vision, pattern recognition, machine learning, data analysis, artificial intelligence, and signal processing. His work spans diverse applications, including medical image analysis for diabetic retinopathy detection, retinal blood vessel segmentation, energy forecasting, automated plankton imaging, bubble detection in industrial processes, and explainable artificial intelligence. Lensu has played a pivotal role in technology transfer, contributing to the development of five spin-off companies originating from LUT University technologies.

Lensu's scholarly contributions are substantial, with over 3,473 citations on Google Scholar. He is renowned for creating benchmark databases that have become standards in the field, such as the DIARETDB1 diabetic retinopathy database and evaluation protocol (2007, British Machine Vision Conference, 1,269 citations) and DIARETDB0: evaluation database and methodology for diabetic retinopathy algorithms (2006, Machine Vision and Pattern Recognition Research Group, 451 citations). Other key publications include 'Assessing the performance of deep learning models for multivariate probabilistic energy forecasting' (Applied Energy, 2021, 123 citations), 'Deep Bayesian baseline for segmenting diabetic retinopathy lesions: Advances and challenges' (Computers in Biology and Medicine, 2021, 58 citations), 'Comparison of bubble detectors and size distribution estimators' (Pattern Recognition Letters, 2018, 65 citations), 'Survey of automatic plankton image recognition: challenges, existing solutions and future perspectives' (Artificial Intelligence Review, 2024, 61 citations), and 'Performance comparison of publicly available retinal blood vessel segmentation methods' (Computerized Medical Imaging and Graphics, 2017, 59 citations). These works have advanced computer-aided diagnosis in ophthalmology, probabilistic forecasting in energy systems, and automated analysis in marine and industrial imaging, demonstrating his broad influence in computational engineering and applied AI.