Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search Article Swipe

MAKE IMPACT

Dazhou Guo , Dakai Jin , Zhuotun Zhu , Tsung‐Ying Ho , Adam P. Harrison , Chun-Hung Chao , Jing Xiao , Alan Yuille , Chien‐Yu Lin , Le Lü · YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2004.08426

OAR segmentation is a critical step in radiotherapy of head and neck (H&N) cancer, where inconsistencies across radiation oncologists and prohibitive labor costs motivate automated approaches. However, leading methods using standard fully convolutional network workflows that are challenged when the number of OARs becomes large, e.g. > 40. For such scenarios, insights can be gained from the stratification approaches seen in manual clinical OAR delineation. This is the goal of our work, where we introduce stratified organ at risk segmentation (SOARS), an approach that stratifies OARs into anchor, mid-level, and small & hard (S&H) categories. SOARS stratifies across two dimensions. The first dimension is that distinct processing pipelines are used for each OAR category. In particular, inspired by clinical practices, anchor OARs are used to guide the mid-level and S&H categories. The second dimension is that distinct network architectures are used to manage the significant contrast, size, and anatomy variations between different OARs. We use differentiable neural architecture search (NAS), allowing the network to choose among 2D, 3D or Pseudo-3D convolutions. Extensive 4-fold cross-validation on 142 H&N cancer patients with 42 manually labeled OARs, the most comprehensive OAR dataset to date, demonstrates that both pipeline- and NAS-stratification significantly improves quantitative performance over the state-of-the-art (from 69.52% to 73.68% in absolute Dice scores). Thus, SOARS provides a powerful and principled means to manage the highly complex segmentation space of OARs.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2004.08426

PDF

https://arxiv.org/pdf/2004.08426

OA Status

green

Cited By

14

References

49

Related Works

10

OpenAlex ID

https://openalex.org/W3017362563

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3017362563

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2004.08426

Digital Object Identifier

Title

Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2020

Year of publication

Publication date

2020-04-17

Full publication date if available

Authors

Dazhou Guo, Dakai Jin, Zhuotun Zhu, Tsung‐Ying Ho, Adam P. Harrison, Chun-Hung Chao, Jing Xiao, Alan Yuille, Chien‐Yu Lin, Le Lü

List of authors in order

Landing page

https://arxiv.org/abs/2004.08426

Publisher landing page

PDF URL

https://arxiv.org/pdf/2004.08426

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2004.08426

Direct OA link when available

Concepts

Segmentation, Computer science, Pipeline (software), Artificial intelligence, Dimension (graph theory), Dice, Head and neck, Convolutional neural network, Artificial neural network, Stratification (seeds), Head and neck cancer, Workflow, Risk stratification, Medical physics, Medicine, Radiation therapy, Radiology, Mathematics, Statistics, Surgery, Biology, Internal medicine, Pure mathematics, Germination, Dormancy, Botany, Seed dormancy, Programming language, Database

Top concepts (fields/topics) attached by OpenAlex

Cited by

14

Total citation count in OpenAlex

Citations by year (recent)

2023: 1, 2022: 2, 2021: 8, 2020: 3

Per-year citation counts (last 5 years)

References (count)

49

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload