Nils Porsche

Nils Porsche

Researcher

HS Flensburg

Hello,
I am a AI researcher at Flensburg University of Applied Sciences where I contribute to the CLE project; an optical Biopsy of Sinonasal Tumors using Confocal Laser Endomicroscopy. The project focuses on:
– Automatic detection of malignancy in CLE images
– Optimization of clinical evaluation parameters
– Virtual CLE-assisted endoscopy

My research interests include self-supervised learning and few-shot learning. I am particularly focused on how machine learning models can acquire robust and transferable representations from limited or unlabeled data, enabling generalization in low-data regimes.

I also investigate related fields such as foundation models and Low-Rank Adaptation (LoRA), with a particular focus on building scalable and data-efficient AI systems.

Publications

2026

  • Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation

    Sweta Banerjee, Viktoria Weiss, Taryn A. Donovan, Rutger H. J. Fick, Thomas Conrad, Jonas Ammeling, Nils Porsche, Robert Klopfleisch, Christopher Kaltenecker, Katharina Breininger, Marc Aubreville and Christof A Bertram

    Machine Learning for Biomedical Imaging doi

  • Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures

    Sweta Banerjee, Alireza Teimoury, Nils Porsche, Alexandra K Stoll, Viktoria Weiss, Niklas Hargarter, Jonas Ammeling, Thomas Conrad, Christoph Stroblberger, Christopher Kaltnecker, Robert Klopfleisch, Christof A Bertram, Katharina Breininger and Marc Aubreville

    MICCAI Workshop on Computational Pathology with Multimodal Data (COMPAYL)

  • Enabling Fast and Mobile Histopathology Image Annotation through Swipeable Interfaces SWAN

    Sweta Banerjee, Timo Gosch, Sara Hester, Viktoria Weiss, Thomas Conrad, Taryn A. Donovan, Nils Porsche, Jonas Ammeling, Christoph Stroblberger, Robert Klopfleisch, Christopher Kaltenecker, Christof A. Bertram, Katharina Breininger and Marc Aubreville

    Bildverarbeitung für die Medizin 2026 doi link

  • Feasibility of confocal laser endomicroscopy as an optical biopsy method for SCC on the auricle : an exploratory study

    Flurin Müller-Diesing, Matti Sievert, Bharat Akhanda Panuganti, Marc Aubreville, Nils Porsche, Stephan Hackenberg, Manuel Stöth, Agmal Scherzad, Jasper Meyer, Markus Wirth and Miguel Goncalves

    Oral and Maxillofacial Surgery doi link

  • Filtering Scheme for Confocal Laser Endomicroscopy (CLE)-video Sequences for Self-supervised Learning

    Nils Porsche, Flurin Müller-Diesing, Sweta Banerjee, Miguel Goncalves and Marc Aubreville

    Bildverarbeitung für die Medizin 2026 doi link

  • Investigation of Factors Contributing to Domain Generalization in Single-Shot Autofocus

    Niklas Hargarter, Jonas Ammeling, Nils Porsche, Sweta Banerjee, F Maria Schabel, Christof A Bertram, Annina Neumann and Marc Aubreville

    MICCAI Workshop on Computational Pathology with Multimodal Data (COMPAYL) link

  • Optical biopsy of nasal cavity cancer with confocal laser endomicroscopy – a pilot study

    Flurin Müller-Diesing, Matti Sievert, Bharat Akhanda Panuganti, Marc Aubreville, Nils Porsche, Stephan Hackenberg, Manuel Stöth, Agmal Scherzad, Markus Wirth, Philipp Winnand and Miguel Goncalves

    European Archives of Oto-Rhino-Laryngology doi link

  • Reporting Transparency in Veterinary Pathology Deep Learning: A Systematic Review of Reproducibility-Critical Details

    Sweta Banerjee, Christof A. Bertram, Viktoria Weiss, Jonas Ammeling, Thomas Conrad, Nils Porsche, Robert Klopfleisch, Christoph Stoblberger, Christopher Kaltenecker, Katharina Breininger and Marc Aubreville

    Veterinary Pathology doi

  • RetroScope: An Open Framework for Motorizing and Digitizing Vintage Microscopes

    Marvin Carstensen, Nils Porsche, Justin Carstensen, Niklas Hargarter, Simon Olberding and Marc Aubreville

    MICCAI Workshop on Computational Pathology with Multimodal Data (COMPAYL) link

← Back to the research group