Abstract: Deep-learning on Lossily Compressed Pathology Images

Digital whole slide imaging (WSI) systems allow scanning complete probes at microscopic resolutions, making image compression inevitable to reduce storage costs. While lossy image compression is readily incorporated in proprietary file formats as well as the open DICOM format for WSI, its impact on deep-learning algorithms is largely unknown.We compare the performance of several deep learning classification architectures on different datasets using a wide range and different combinations of compression ratios during training and inference.We use ImageNet pre-trained models, which is commonly applied in computational pathology. With this work, we present a quantitative assessment on the effects of repeated lossy JPEG compression for ImageNet pre-trained models.We showadverse effects for a classification task, when certain quality factors are combined during training and inference. This work was published on the International Workshop on Medical Optical Imaging and Virtual Microscopy Image Analysis [1].

Authors and Affiliations

1. Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany

   Maximilian Fischer, Peter Neher, Michael Götz, Shuhan Xiao, Silvia Dias Almeida, Marco Nolden & Klaus Maier-Hein

2. German Cancer Consortium (DKTK), partner site Heidelberg, Heidelberg, Germany

   Maximilian Fischer & Peter Neher

3. Clinic of Diagnostics and Interventional Radiology, Ulm University Medical Centre, Ulm, Germany

   Michael Götz

4. Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany

   Shuhan Xiao & Klaus Maier-Hein

5. Medical Faculty, Heidelberg University, Heidelberg, Germany

   Silvia Dias Almeida & Klaus Maier-Hein

6. School of Medicine, Institute of Pathology, Technical University of Munich, Munich, Germany

   Peter Schüffler & Alexander Muckenhuber

7. Department of Diagnostic and Interventional Radiology, TU Munich, Munich, Germany

   Rickmer Braren

8. Institute for AI in Medicine (IKIM), University Medicine Essen, Essen, Germany

   Jens Kleesiek

9. German Cancer Consortium (DKTK), partner site Essen, Essen, Germany

   Jens Kleesiek

10. Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany

    Marco Nolden & Klaus Maier-Hein

11. National Center for Tumor Diseases (NCT), Heidelberg, Germany

    Peter Neher & Klaus Maier-Hein

Corresponding author

Correspondence to Maximilian Fischer .

Editors and Affiliations

1. Peter L. Reichertz Institut für Medizinische, Informatik der TU Braunschweig und der Medizinischen Hochschule Hannover, Braunschweig, Niedersachsen, Deutschland

   Thomas M. Deserno

2. Institut für Medizinische Informatik, Universität zu Lübeck, Lübeck, Schleswig-Holstein, Deutschland

   Heinz Handels

3. Lehrstuhl für Mustererkennung, Friedrich-Alexander-Universität, Erlangen, Bayern, Deutschland

   Andreas Maier

4. Medical Image Computing, E230, Deutsches Krebsforschungszentrum (DKFZ), Heidelberg, Baden-Württemberg, Deutschland

   Klaus Maier-Hein

5. Fakultät für Informatik und Mathematik, Ostbayerische Technische Hochschule Regensburg, Regensburg, Deutschland

   Christoph Palm

6. Institut für Medizinische Informatik, Charité – Universitätsmedizin Berlin, Berlin, Berlin, Deutschland

   Thomas Tolxdorff

Reprints and permissions

© 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature

Policies and ethics