Classification and evaluation strategies of auto‐segmentation approaches for PET: Report of AAPM task group No. 211

@article{Hatt2017ClassificationAE,
  title={Classification and evaluation strategies of auto‐segmentation approaches for PET: Report of AAPM task group No. 211},
  author={Mathieu Hatt and John Aldo Lee and C. Ross Schmidtlein and Issam El Naqa and Curtis Caldwell and Elisabetta De Bernardi and Wei Lu and Shiva K. Das and Xavier Geets and Vincent Gr{\'e}goire and Robert Jeraj and Michael P. MacManus and Osama R. Mawlawi and Ursula Nestle and Andrei Pugachev and Heiko Sch{\"o}der and Tony Shepherd and Emiliano Spezi and Dimitris Visvikis and Habib Zaidi and Assen S Kirov},
  journal={Medical Physics},
  year={2017},
  volume={44},
  pages={e1–e42}
}
Purpose The purpose of this educational report is to provide an overview of the present state‐of‐the‐art PET auto‐segmentation (PET‐AS) algorithms and their respective validation, with an emphasis on providing the user with help in understanding the challenges and pitfalls associated with selecting and implementing a PET‐AS algorithm for a particular application. Approach A brief description of the different types of PET‐AS algorithms is provided using a classification based on method… 

Figures and Tables from this paper

Toward a standard for the evaluation of PET‐Auto‐Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation

PETASset provides a platform that allows standardizing the evaluation and comparison of different PET‐AS methods on a wide range of PET datasets and examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state‐of‐the art.

The first MICCAI challenge on PET tumor segmentation

PET segmentation of bulky tumors: Strategies and workflows to improve inter-observer variability

None of the methods led to good results in all cases, but use of either the gradient or the Select-the-best workflow did outperform the other strategies tested and may be a good candidate for fast and reliable labeling of bulky and heterogeneous tumors.

Radiomics in PET/CT: Current Status and Future AI-Based Evolutions.

The field of radiomics applied to the field of PET/CT imaging has made striking advances over the last few years and it is expected advances will continue at a rapid pace.

Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET

Two semi-automatic artificial intelligence (AI)-based segmentation methods based on a textural feature segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis are compared and are considered good candidates for PET tumor segmentation.

Repeatability of Two Artificial Intelligence Approaches for Tumor Segmentation in PET

Two artificial intelligence (AI) based segmentation methods based on a textural feature segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis are compared and provided better repeatability than conventional segmentation approaches.

Advanced automated PET image segmentation in radiation therapy

This research resulted in the development of a new training dataset and demonstrated that ATLAAS can be used as a basis for adaptive radiotherapy and trained on imaging datasets outside of the original training cohort, and improved the MTV segmentation of a machine-learned PET-AS methodology.

Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: a critical review.

  • M. ShererD. Lin E. Gillespie
  • Medicine
    Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
  • 2021
...

References

SHOWING 1-10 OF 336 REFERENCES

Toward a standard for the evaluation of PET‐Auto‐Segmentation methods following the recommendations of AAPM task group No. 211: Requirements and implementation

PETASset provides a platform that allows standardizing the evaluation and comparison of different PET‐AS methods on a wide range of PET datasets and examples of agreement limits were provided to show how the software could be used to evaluate a new algorithm against the existing state‐of‐the art.

Impact of consensus contours from multiple PET segmentation methods on the accuracy of functional volume delineation

This study showed that combining different PET segmentation methods by the use of a consensus algorithm offers robustness against the variable performance of individual segmentations methods and this approach would therefore be useful in radiation oncology.

Evaluation of PET volume segmentation methods: comparisons with expert manual delineations

Five methods for [18F]-fluorodeoxyglucose PET image segmentation were evaluated on non-Hodgkin’s lymphoma lesions by comparing them with manual delineations performed by a panel of experts to establish a reliable evaluation tool.

Characterization of PET/CT images using texture analysis: the past, the present… any future?

Critical insights into the recent development of texture analysis for quantifying the heterogeneity in PET/CT images are provided, issues and challenges are identified, and a list of correct formulae for usual features and recommendations regarding implementation are provided.

ATLAAS: an automatic decision tree-based learning algorithm for advanced image segmentation in positron emission tomography

ATLAAS is an advanced automatic image segmentation algorithm based on decision tree predictive modelling, trained to automatically select and apply the best PET-AS method, according to the tumour characteristics, when the true contour is unknown.

Pathology-validated PET image data sets and their role in PET segmentation

The specimen handling techniques aimed at achieving higher geometrical accuracy of the pathology-derived “ground truth” of the PET image data sets with pathology validation are focused on.

Semiautomated segmentation of head and neck cancers in 18F-FDG PET scans: A just-enough-interaction approach

The proposed semiautomated segmentation method was found to be significantly faster and resulted in significantly higher intra- and interoperator segmentation agreement when compared to the manual segmentation approach.

Standards for PET Image Acquisition and Quantitative Data Analysis

An overview of recommendations and guidelines for quantitative 18F-FDG PET studies in oncology is provided, with special attention given to the rationale underlying certain recommendations and to some of the differences in various guidelines.

PET functional volume delineation: a robustness and repeatability study

The use of advanced image segmentation algorithms may not only allow high accuracy as previously demonstrated, but also provide a robust and repeatable tool to aid physicians as an initial guess in determining functional volumes in PET.

Comparative study with new accuracy metrics for target volume contouring in PET image guided radiation therapy.

This paper compares the largest cohort to date of established, emerging and proposed PET contouring methods, in terms of accuracy and variability, and emphasise spatial accuracy and present a new metric that addresses the lack of unique ground truth.
...