Marc Aubreville1, Maike Stoeve2, Nicolai Oetter3, Miguel Goncalves4, Christian Knipfer5, Helmut Neumann6, Christopher Bohr7, Florian Stelzle3, Andreas Maier2. 1. Pattern Recognition Lab, Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. marc.aubreville@fau.de. 2. Pattern Recognition Lab, Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. 3. Department of Oral and Maxillofacial Surgery, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. 4. Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. 5. Department of Oral and Maxillofacial Surgery, University Medical Center Hamburg-Eppendorf, Universität Hamburg, Hamburg, Germany. 6. First Department of Internal Medicine, University Hospital Mainz, Johannes Gutenberg-Universität Mainz, Mainz, Germany. 7. Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital, Universität Regensburg, Regensburg, Germany.
Abstract
PURPOSE: Probe-based confocal laser endomicroscopy (pCLE) is a subcellular in vivo imaging technique capable of producing images that enable diagnosis of malign structural modifications in epithelial tissue. Images acquired with pCLE are, however, often tainted by significant artifacts that impair diagnosis. This is especially detrimental for automated image analysis, which is why said images are often excluded from recognition pipelines. METHODS: We present an approach for the automatic detection of motion artifacts in pCLE images and apply this methodology to a data set of 15 thousand images of epithelial tissue acquired in the oral cavity and the vocal folds. The approach is based on transfer learning from intermediate endpoints within a pre-trained Inception v3 network with tailored preprocessing. For detection within the non-rectangular pCLE images, we perform pooling within the activation maps of the network and evaluate this at different network depths. RESULTS: We achieved area under the ROC curve values of 0.92 with the proposed method, compared to 0.80 for the best feature-based machine learning approach. Our overall accuracy with the presented approach is 94.8%. CONCLUSION: Over traditional machine learning approaches with state-of-the-art features, we achieved significantly improved overall performance.
PURPOSE: Probe-based confocal laser endomicroscopy (pCLE) is a subcellular in vivo imaging technique capable of producing images that enable diagnosis of malign structural modifications in epithelial tissue. Images acquired with pCLE are, however, often tainted by significant artifacts that impair diagnosis. This is especially detrimental for automated image analysis, which is why said images are often excluded from recognition pipelines. METHODS: We present an approach for the automatic detection of motion artifacts in pCLE images and apply this methodology to a data set of 15 thousand images of epithelial tissue acquired in the oral cavity and the vocal folds. The approach is based on transfer learning from intermediate endpoints within a pre-trained Inception v3 network with tailored preprocessing. For detection within the non-rectangular pCLE images, we perform pooling within the activation maps of the network and evaluate this at different network depths. RESULTS: We achieved area under the ROC curve values of 0.92 with the proposed method, compared to 0.80 for the best feature-based machine learning approach. Our overall accuracy with the presented approach is 94.8%. CONCLUSION: Over traditional machine learning approaches with state-of-the-art features, we achieved significantly improved overall performance.
Authors: Nils Gessert; Marcel Bengs; Lukas Wittig; Daniel Drömann; Tobias Keck; Alexander Schlaefer; David B Ellebrecht Journal: Int J Comput Assist Radiol Surg Date: 2019-05-25 Impact factor: 2.924
Authors: Lei Tian; Brady Hunt; Muyinatu A Lediju Bell; Ji Yi; Jason T Smith; Marien Ochoa; Xavier Intes; Nicholas J Durr Journal: Lasers Surg Med Date: 2021-05-20
Authors: Shan Guleria; Tilak U Shah; J Vincent Pulido; Matthew Fasullo; Lubaina Ehsan; Robert Lippman; Rasoul Sali; Pritesh Mutha; Lin Cheng; Donald E Brown; Sana Syed Journal: Sci Rep Date: 2021-03-03 Impact factor: 4.379
Authors: Do Han Kim; Somashekar G Krishna; Emmanuel Coronel; Paul T Kröner; Herbert C Wolfsen; Michael B Wallace; Juan E Corral Journal: Clin Endosc Date: 2021-11-29
Authors: Matti Sievert; Florian Stelzle; Marc Aubreville; Sarina K Mueller; Markus Eckstein; Nicolai Oetter; Andreas Maier; Konstantinos Mantsopoulos; Heinrich Iro; Miguel Goncalves Journal: Eur Arch Otorhinolaryngol Date: 2021-02-13 Impact factor: 2.503
Authors: Andreas Ziebart; Denis Stadniczuk; Veronika Roos; Miriam Ratliff; Andreas von Deimling; Daniel Hänggi; Frederik Enders Journal: Front Oncol Date: 2021-05-11 Impact factor: 6.244