Timezone: »

Streaming Convolutional Attention Models
Stephan Dooper · Geert Litjens · Johannes Pinckaers

Recent developments have shown multiple ways to tackle whole-slide image clas- sification with weak labels, a challenging task due to memory constraints. A recent example is Clustering-constrained Attention Multiple instance learning (CLAM), which encodes whole-slide images (WSI) into a smaller set of features. The down- side of this approach is that the encoder uses ImageNet pre-trained weights for feature extraction, which might result in suboptimal features for downstream clas- sification tasks. In this study we propose to train the CLAM model end-to-end using streaming stochastic gradient descent, which can train deep neural networks at near static memory cost regardless of image input size. This way the encoder can learn task-specific feature representations of whole-slide images. We show that it is possible to train with images of 65536 × 65536 at 0.5µm, and obtain improved results for public datasets of metastasis detection in breast cancer.

Author Information

Stephan Dooper (Radboud University Medical Center)
Geert Litjens (Radboud University Nijmegen Medical Center)

Geert Litjens studied Biomedical Engineering at Eindhoven University of Technology. Subsequently, he completed his PhD in the Diagnostic Image Analysis Group. He worked with Henkjan Huisman on Computer-aided detection of prostate cancer. He spent 2015 as a postdoctoral researcher at the National Center for Tumor Diseases in Heidelberg, Germany on an Alexander von Humboldt Society Postdoctoral Fellowship. He is currently an Assistant Professor in Computational Pathology at the Department of Pathology. His research focus is applying machine learning to solve important questions in oncology: - How to improve efficiency and accuracy through automation of diagnostics? - How to quantify (un)known biomarkers for cancer progression and treatment success using machine learning For more details on his research group: https://www.computationalpathologygroup.eu/

Johannes Pinckaers (Radboud University Medical Center)

Hans Pinckaers is a PhD candidate in the Computational Pathology group of the Department of Pathology of the Radboud University Medical Center in Nijmegen. He studied Medicine at Leiden University Medical Center for which he obtained his MD in 2016. After his graduation he worked one year as a Pathology resident. In 2017, Hans joined the Diagnostic Image Analysis Group where he works under the supervision of Geert Litjens and Jeroen van der Laak on deep learning for improved prognostics in prostate cancer.

More from the Same Authors

  • 2019 : Coffee Break + Poster Session II »
    Niki Parmar · Haraldur Hallgrimsson · Christian Kames · Arijit Patra · Abdullah-Al-Zubaer Imran · Junlin Yang · David Zimmerer · Arunava Chakravarty · Lawrence Schobs · Alexej Gossmann · TUNG-I CHEN · Tarun Dutt · Li Yao · Octavio Eleazar Martinez Manzanera · Johannes Pinckaers · Mehmet Ufuk Dalmis · Deepak Gupta · Nandinee Haq · David Ruhe · Jevgenij Gamper · Alfredo De Goyeneche Macaya · Jonathan Tamir · Byunghwan Jeon · SUBBAREDDY OOTA · Reinhard Heckel · Pamela Douglas · Oleksii Sidorov · Ke Wang · Melanie Garcia · Ravi Soni · Ankita Shukla