Physiological Parameter Estimation from Multispectral Images Unleashed

Wirkert, Sebastian J.; Vemuri, Anant; Kenngott, Hannes; Moccia, Sara; Götz, Michael; Mayer, Benjamin F. B.; Maier‐Hein, Klaus H.; Elson, Daniel S.; Maier-Hein, Lena

doi:10.1007/978-3-319-66179-7_16

Cited by 29 publications

(47 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure that networks initially trained on simplified simulated images can output accurate estimates when provided real images, networks may have to be modified with transfer training, taking advantage of datasets of real images. 36 , 48 , 49 Looking beyond the complexity of the tissue models, there are other more fundamental challenges that will make the application to living tissue nontrivial. In order to train a network using a supervised learning approach with in vivo data (or even to validate any technique for estimating

in vivo ), the corresponding ground truth

distribution must be available.…”

Section: Resultsmentioning

confidence: 99%

Toward accurate quantitative photoacoustic imaging: learning vascular blood oxygen saturation in three dimensions

2020

View full text Add to dashboard Cite

Significance: Two-dimensional (2-D) fully convolutional neural networks have been shown capable of producing maps of sO 2 from 2-D simulated images of simple tissue models. However, their potential to produce accurate estimates in vivo is uncertain as they are limited by the 2-D nature of the training data when the problem is inherently three-dimensional (3-D), and they have not been tested with realistic images. Aim: To demonstrate the capability of deep neural networks to process whole 3-D images and output 3-D maps of vascular sO 2 from realistic tissue models/images. Approach: Two separate fully convolutional neural networks were trained to produce 3-D maps of vascular blood oxygen saturation and vessel positions from multiwavelength simulated images of tissue models. Results: The mean of the absolute difference between the true mean vessel sO 2 and the network output for 40 examples was 4.4% and the standard deviation was 4.5%. Conclusions: 3-D fully convolutional networks were shown capable of producing accurate sO 2 maps using the full extent of spatial information contained within 3-D images generated under conditions mimicking real imaging scenarios. We demonstrate that networks can cope with some of the confounding effects present in real images such as limited-view artifacts and have the potential to produce accurate estimates in vivo.

show abstract

in vivo ), the corresponding ground truth

distribution must be available.…”

Section: Resultsmentioning

confidence: 99%

Toward accurate quantitative photoacoustic imaging: learning vascular blood oxygen saturation in three dimensions

2020

View full text Add to dashboard Cite

show abstract

“…However, the use of these technologies is still underrepresented in the medical field with few examples (e.g. [32,92]).…”

Section: Discussionmentioning

confidence: 99%

Supervised CNN Strategies for Optical Image Segmentation and Classification in Interventional Medicine

Moccia

Romeo

Migliorelli

et al. 2020

Intelligent Systems Reference Library

Self Cite

View full text Add to dashboard Cite

The analysis of interventional images is a topic of high interest for the medical-image analysis community. Such an analysis may provide interventionalmedicine professionals with both decision support and context awareness, with the final goal of improving patient safety. The aim of this chapter is to give an overview of some of the most recent approaches (up to 2018) in the field, with a focus on Convolutional Neural Networks (CNNs) for both segmentation and classification tasks. For each approach, summary tables are presented reporting the used dataset, involved anatomical region and achieved performance. Benefits and disadvantages of each approach are highlighted and discussed. Available datasets for algorithm training and testing and commonly used performance metrics are summarized to offer a source of information for researchers that are approaching the field of interventionalimage analysis. The advancements in deep learning for medical-image analysis are involving more and more the interventional-medicine field. However, these advancements are undeniably slower than in other fields (e.g. preoperative-image analysis) and considerable work still needs to be done in order to provide clinicians with all possible support during interventional-medicine procedures.

show abstract

“…We further assume that we have access to a data set T = T train ∪ T validation ∪ T test composed of tuples (x, y), with y = f (x). Typically T can be generated by means of Monte Carlo simulation, as in [13,29,30] assuming the (virtual) hardware setup H. Finally, we represent the regressor r as an invertible neural network, as detailed in Section 2.2.…”

Section: Methodsmentioning

confidence: 99%

“…We apply Monte Carlo methods to generate tuples of physiological parameters x and corresponding pixel-wise measurements y = f (x). The method is based on previous work [30] and briefly revisited here.…”

Section: Data Generation For Performance Assessmentmentioning

confidence: 99%

Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose: Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral reflectance measurements to underlying tissue parameters, such as oxygenation. Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be illposed. Methods: We present a novel approach to the assessment of optical imaging modalities, which is sensitive to the different types of uncertainties that may occur when inferring tissue parameters. Based on the concept of invertible neural networks, our framework goes beyond point estimates and maps each multispectral measurement to a full posterior probability distribution which is capable of representing ambiguity in the solution via multiple modes. Performance metrics for a hardware setup can then be computed from the characteristics of the posteriors. Results: Application of the assessment framework to the specific use case of camera selection for physiological parameter estimation yields the following insights: (1) Estimation of tissue oxygenation from multispectral images is a well-posed problem, while (2) blood volume fraction may not be recovered without ambiguity. (3) In general, ambiguity may be reduced by increasing the number of spectral bands in the camera. Conclusion: Our method could help to optimize optical camera design in an application-specific manner.

show abstract

Physiological Parameter Estimation from Multispectral Images Unleashed

Cited by 29 publications

References 10 publications

Toward accurate quantitative photoacoustic imaging: learning vascular blood oxygen saturation in three dimensions

Toward accurate quantitative photoacoustic imaging: learning vascular blood oxygen saturation in three dimensions

Supervised CNN Strategies for Optical Image Segmentation and Classification in Interventional Medicine

Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks

Contact Info

Product

Resources

About