Organ at Risk Segmentation for Head and Neck Cancer Using Stratified Learning and Neural Architecture Search
Dazhou Guo,Dakai Jin,Zhuotun Zhu,Tsung-Ying Ho,Adam P. Harrison,Chun-Hung Chao,Jing Xiao,Le Lu +7 more
- pp 4223-4232
Reads0
Chats0
TLDR
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.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
TL;DR: This survey summarizes the current progress on integrating medical domain knowledge into deep learning models for various tasks, such as disease diagnosis, lesion, organ and abnormality detection, lesions and organ segmentation, and systematically categorizes different kinds of medical domainknowledge that have been utilized and their corresponding integrating methods.
Journal ArticleDOI
Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study
Stanislav Nikolov,Sam Blackwell,Alexei Zverovitch,R. Mendes,Michelle Livne,Jeffrey De Fauw,Yojan Patel,Clemens Meyer,Harry Askham,Bernadino Romera-Paredes,Christopher Kelly,Alan Karthikesalingam,Carlton Chu,Dawn Carnell,Cheng Boon,Derek D'Souza,S. Moinuddin,Bethany Garie,Yasmin McQuinlan,Sarah Ireland,Kiarna Hampton,Krystle Fuller,Hugh Montgomery,Geraint Rees,Mustafa Suleyman,Trevor Back,Cían Owen Hughes,Joseph R. Ledsam,Olaf Ronneberger +28 more
TL;DR: In this article, a 3D U-Net architecture was used to segment head and neck organs at risk commonly segmented in clinical practice, and the model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practices and segmentations created by experienced radiographers.
Posted Content
AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
Jun Ma,Yao Zhang,Song Gu,Cheng Zhu,Cheng Ge,Yichi Zhang,Xingle An,Congcong Wang,Qiyuan Wang,Xin Liu,Shucheng Cao,Qi Zhang,Shangqing Liu,Yunpeng Wang,Yuhui Li,Jian He,Xiaoping Yang +16 more
TL;DR: A large and diverse abdominal CT organ segmentation dataset with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases is presented and a simple and effective method is developed for each benchmark, which can be used as out-of-the-box methods and strong baselines.
Journal ArticleDOI
Anam-Net: Anamorphic Depth Embedding-Based Lightweight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images
Naveen Paluru,Aveen Dayal,Havard Bjorke Jenssen,Tomas Sakinis,Linga Reddy Cenkeramaddi,Jaya Prakash,Phaneendra K. Yalavarthy +6 more
TL;DR: Paluru et al. as discussed by the authors proposed anamorphic depth embedding-based lightweight CNN, called Anam-Net, to segment anomalies in COVID-19 chest CT images, which has 7.8 times fewer parameters compared to the state-of-the-art UNet (or its variants), making it lightweight capable of providing inferences in mobile or resource constraint (point of care) platforms.
Posted Content
Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Lingxi Xie,Xin Chen,Kaifeng Bi,Longhui Wei,Yuhui Xu,Zhengsu Chen,Lanfei Wang,An Xiao,Jianlong Chang,Xiaopeng Zhang,Qi Tian +10 more
TL;DR: A literature review on the application of NAS to computer vision problems is provided and existing approaches are summarized into several categories according to their efforts in bridging the gap.
References
More filters
Proceedings ArticleDOI
Mask R-CNN
TL;DR: This work presents a conceptually simple, flexible, and general framework for object instance segmentation, which extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Journal ArticleDOI
Active shape models—their training and application
TL;DR: This work describes a method for building models by learning patterns of variability from a training set of correctly annotated images that can be used for image search in an iterative refinement algorithm analogous to that employed by Active Contour Models (Snakes).
Journal ArticleDOI
Active appearance models
Abstract: We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training set. We construct an efficient iterative matching algorithm by learning the relationship between perturbations in the model parameters and the induced image errors.
Book ChapterDOI
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Özgün Çiçek,Ahmed Abdulkadir,Ahmed Abdulkadir,Soeren S. Lienkamp,Thomas Brox,Olaf Ronneberger,Olaf Ronneberger +6 more
TL;DR: In this paper, the authors propose a network for volumetric segmentation that learns from sparsely annotated volumetrized images, which is trained end-to-end from scratch, i.e., no pre-trained network is required.