Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge

no code implementations • 11 May 2023 • Aneeq Zia, Kiran Bhattacharyya, Xi Liu, Max Berniker, Ziheng Wang, Rogerio Nespolo, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Bo Liu, David Austin, Yiheng Wang, Michal Futrega, Jean-Francois Puget, Zhenqiang Li, Yoichi Sato, Ryo Fujii, Ryo Hachiuma, Mana Masuda, Hideo Saito, An Wang, Mengya Xu, Mobarakol Islam, Long Bai, Winnie Pang, Hongliang Ren, Chinedu Nwoye, Luca Sestini, Nicolas Padoy, Maximilian Nielsen, Samuel Schüttler, Thilo Sentker, Hümeyra Husseini, Ivo Baltruschat, Rüdiger Schmitz, René Werner, Aleksandr Matsun, Mugariya Farooq, Numan Saaed, Jose Renato Restom Viera, Mohammad Yaqub, Neil Getty, Fangfang Xia, Zixuan Zhao, Xiaotian Duan, Xing Yao, Ange Lou, Hao Yang, Jintong Han, Jack Noble, Jie Ying Wu, Tamer Abdulbaki Alshirbaji, Nour Aldeen Jalal, Herag Arabian, Ning Ding, Knut Moeller, Weiliang Chen, Quan He, Muhammad Bilal, Taofeek Akinosho, Adnan Qayyum, Massimo Caputo, Hunaid Vohra, Michael Loizou, Anuoluwapo Ajayi, Ilhem Berrou, Faatihah Niyi-Odumosu, Lena Maier-Hein, Danail Stoyanov, Stefanie Speidel, Anthony Jarc

Unfortunately, obtaining the annotations needed to train machine learning models to identify and localize surgical tools is a difficult task.

Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class

1 code implementation • 11 Apr 2023 • Maximilian Nielsen, Laura Wenderoth, Thilo Sentker, René Werner

Exploiting the learned image representation, we achieve state-of-the-art classification performance for all three imaging modalities and data sets with only a fraction of between 1% and 10% of the available labeled data and about 100 labeled samples per class.

Image Classification Medical Image Classification

Skin Lesion Classification Using Ensembles of Multi-Resolution EfficientNets with Meta Data

1 code implementation • 9 Oct 2019 • Nils Gessert, Maximilian Nielsen, Mohsin Shaikh, René Werner, Alexander Schlaefer

On the official test set our method is ranked first for both tasks with a balanced accuracy of 63. 6% for task 1 and 63. 4% for task 2.

General Classification Lesion Classification +2

Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture

1 code implementation • 24 Sep 2019 • Rüdiger Schmitz, Frederic Madesta, Maximilian Nielsen, Jenny Krause, René Werner, Thomas Rösch

The findings demonstrate the potential of the presented family of human-inspired, end-to-end trainable, multi-scale multi-encoder FCNs to improve deep histopathologic diagnosis by extensive integration of largely different spatial scales.

Image Segmentation Semantic Segmentation +1

3d-SMRnet: Achieving a new quality of MPI system matrix recovery by deep learning

1 code implementation • 8 May 2019 • Ivo Matteo Baltruschat, Patryk Szwargulski, Florian Griese, Mirco Grosser, René Werner, Tobias Knopp

In this work, we propose a novel framework with a 3d-System Matrix Recovery Network and demonstrate it to recover a 3d system matrix with a subsampling factor of 64 in less than one minute and to outperform CS in terms of system matrix quality, reconstructed image quality, and processing time.

Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting

1 code implementation • 7 May 2019 • Nils Gessert, Thilo Sentker, Frederic Madesta, Rüdiger Schmitz, Helge Kniep, Ivo Baltruschat, René Werner, Alexander Schlaefer

The first problem is the effective use of high-resolution images with pretrained standard architectures for image classification.

General Classification Image Classification +2

Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting

2 code implementations • 5 Aug 2018 • Nils Gessert, Thilo Sentker, Frederic Madesta, Rüdiger Schmitz, Helge Kniep, Ivo Baltruschat, René Werner, Alexander Schlaefer

We identify heavy class imbalance as a key problem for this challenge and consider multiple balancing approaches such as loss weighting and balanced batch sampling.

Meta-Learning