Tomas Iešmantas is an associate professor at the KTU Faculty of Mathematics and Natural Sciences, a member of the COST activity “Novel tools for test evaluation and disease prevalence estimation” committee. COST activity is a cooperation network initiated by researchers and innovators working in a certain field of science or technology development (innovation).
Deep Learning for Multiple Sclerosis (DeepMS)
During this project, a representative sample of MRI scans of MS patients obtained, and it has been used construct an artificial intelligence-based system for the assessment fo lesions multiple sclerosis patients. Such a system enable faster and more accurate diagnosis of multiple sclerosis and assessment of its stage and development over time. To achieve these goals, deep learning methods was used, and additionally, capsule neural network will be developed in order to gain more accuracy.
During the project, the researcher, together with other team members, will aim to develop an innovative method for predicting and early warning of cerebral vasospasms (CV) and delayed cerebral ischemia (DCI) after spontaneous aneurysmal subarachnoid hemorrhage, to conduct clinical trials of this method, and to develop a software tool for predicting CV and DCI. Project partners: Lithuanian University of Health Sciences, VŠĮ Vilniaus universiteto ligoninės Santaros klinikos.
Risk reduction rationale through inspection
Coordinator – VTT (Finland), 2015-2016. T. Iešmantas’ duties in the project: researcher, executor.
R&D of Cell Nucleus Detection Model Based on Artificial Intelligence (DItect)
The researcher led the R&D of Cell Nucleus Detection Model Based on Artificial Intelligence (DItect) project. The project team aimed to develop the model based on the artificial intelligence used to detect cell nucleus in fluorescence images. Scientists focused on images containing noise, touching and partially overlapping nuclei, and possible observed under different lighting conditions.
| No. | Title | Authors | Year |
| 1. | Enhancing multi-tissue and multi-scale cell nuclei segmentation with deep metric learning. | Tomas Iešmantas, Agnė Paulauskaitė-Tarasevičienė, Kristina Šutienė | 2020 |
| 2. | Deep learning-based detection of overlapping cells. | Agnė Paulauskaitė-Tarasevičienė, Kristina Šutienė, Justas Valotka, Vidas Raudonis, Tomas Iešmantas | 2019 |
| 3. | Exploiting information of fusion component tests for failure rate estimation: Divertor Inner Vertical Target component study case | Danilo Nicola Dongiovanni, Tomas Iešmantas, Pierre Gavila, Tonio Pinna | 2018 |
| 4. | Convolutional neural networks for early seizure alert system | Tomas Iešmantas, Robertas Alzbutas | 2017 |
