Robust deep learning-based semantic organ segmentation in hyperspectral images

  title={Robust deep learning-based semantic organ segmentation in hyperspectral images},
  author={Silvia Seidlitz and Jan Sellner and Jan Odenthal and Berkin {\"O}zdemir and Alexander Studier-Fischer and Samuel Kn{\"o}dler and Leonardo A. Ayala and Tim J. Adler and Hannes G Kenngott and Minu Dietlinde Tizabi and Martin Wagner and Felix Nickel and Beat Peter M{\"u}ller-Stich and Lena Maier-Hein},
  journal={Medical image analysis},

Spectral imaging enables contrast agent-free real-time ischemia monitoring in laparoscopic surgery

The proposed MSI-based method does not require the injection of a contrast agent and is repeatable if the wrong segment has been clamped, and could thus evolve as an important tool for fast, efficient, reliable and safe functional imaging in minimally invasive surgery.

A comprehensive survey on recent deep learning-based methods applied to surgical data

A systematic review of recent machine learning-based approaches including surgical tool localisation, segmentation, tracking and 3D scene perception is presented and rational behind clinical integration of these approaches is provided.

Die Chirurgie

Claire Chalopin · Felix Nickel · Annekatrin Pfahl · Hannes Köhler · Marianne Maktabi · René Thieme · Robert Sucher · Boris Jansen-Winkeln · Alexander Studier-Fischer · Silvia Seidlitz · Lena

Deep Learning Based Image Processing for Robot Assisted Surgery: A Systematic Literature Survey

The study reveals that Convolutional Neural Network is most widely adopted architecture, whereas, the JIGSAWS is most employed dataset in RAS, and suggests fusing kinematic data along with image data, which produces better accuracy and precision.

Künstliche Intelligenz und hyperspektrale Bildgebung zur bildgestützten Assistenz in der minimal-invasiven Chirurgie

Intraoperative Bildgebung unterstützt Chirurgen bei minimal-invasiven Eingriffen. Die hyperspektrale Bildgebung („hyperspectral imaging“, HSI) ist ein nichtinvasives und kontaktloses optisches



Tumor Semantic Segmentation in Hyperspectral Images using Deep Learning

This work proposes using channels selection with U-Net deep neural network for tumor segmentation in hyperspectral images and achieves better results than pixel-level spectral and structural approaches in a clinical data set with tongue squamous cell carcinoma.

Tongue Tumor Detection in Hyperspectral Images Using Deep Learning Semantic Segmentation

This is the first work using deep learning semantic segmentation for tumor detection in HSI data using channel selection, and accounting for more spatial tissue context, and global comparison between the prediction map, and the annotation per sample.

Manifold Embedding and Semantic Segmentation for Intraoperative Guidance With Hyperspectral Brain Imaging

A novel dimensionality reduction scheme and a new processing pipeline are introduced to obtain a detailed tumor classification map for intra-operative margin definition during brain surgery.

Efficient Deep Auto-Encoder Learning for the Classification of Hyperspectral Images

  • Atif MugheesL. Tao
  • Environmental Science, Computer Science
    2016 International Conference on Virtual Reality and Visualization (ICVRV)
  • 2016
Experimental results with widely-used hyperspectral data confirms that the new spectral and spatial classification approach is able to improve results significantly in terms of classification accuracies.

CRF learning with CNN features for hyperspectral image segmentation

This paper attempts to combine the properties of CNN and Conditional Random Field, using a mean-field approximation algorithm for CRF inference and formulated with Gaussian pairwise potentials as Recurrent Neural Network.

A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification

The experimental results obtained with three public HSI datasets show that the SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods.

Spectral organ fingerprints for intraoperative tissue classification with hyperspectral imaging

It is concluded that automatic tissue discrimination based on HSI data is feasible and could thus aid in intraoperative decision making and pave the way for context-aware computer-assisted surgery systems and autonomous robotics.

Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations

This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor.

In-Vivo Hyperspectral Human Brain Image Database for Brain Cancer Detection

The methodology followed to generate the first hyperspectral database of in-vivo human brain tissues is presented and reveals that the system works more efficiently in the spectral range between 450 and 900 nm.