Nils Gessert

About

Nils Gessert is a leading researcher at the intersection of deep learning and medical robotics, with a primary focus on vision-based force estimation and surgical data science. His pioneering work addresses the critical challenge of providing haptic feedback during robot-assisted minimally invasive interventions by estimating interaction forces directly from imaging data. Gessert’s major contributions include developing novel 3D and 4D convolutional neural network architectures that learn force information from volumetric Optical Coherence Tomography (OCT) data and raw spectral OCT signals, bypassing the need for external force sensors. His most influential work, “A deep learning approach for pose estimation from volumetric OCT data” (2018), has garnered 35 citations, while his subsequent studies on spatio-temporal deep learning for force estimation have accumulated over 50 citations collectively. Notably, his 2019 study on force estimation from OCT volumes using 3D CNNs directly addresses the friction and integration challenges that plague traditional sensor-based approaches. Gessert’s research demonstrates remarkable translational potential, offering a pathway to safer, more intuitive surgical robotics through purely vision-based tactile sensing.

Research Focus

Key Achievements

Top Papers

1. 1
   A deep learning approach for pose estimation from volumetric OCT data

   35 citations · 2018
2. 2
   Deep learning with 4D spatio-temporal data representations for OCT-based force estimation

   27 citations · 2020
3. 3
   Force estimation from OCT volumes using 3D CNNs

   19 citations · 2019
4. 4
   Needle tip force estimation by deep learning from raw spectral OCT data

   5 citations · 2020
5. 5
   Generalization of spatio-temporal deep learning for vision-based force estimation

   2 citations · 2020
6. 6
   Towards Deep Learning-Based EEG Electrode Detection Using Automatically Generated Labels

   2 citations · 2019

Key Collaborators

Contact & Links