Prior Guided Deep Difference Meta-Learner for Fast Adaptation to Stylized Segmentation

• URL: http://arxiv.org/abs/2211.10588v1
• Date: Sat, 19 Nov 2022 05:06:16 GMT
• Title: Prior Guided Deep Difference Meta-Learner for Fast Adaptation to Stylized Segmentation
• Authors: Anjali Balagopal, Dan Nguyen, Ti Bai, Michael Dohopolski, Mu-Han Lin, Steve Jiang
• Abstract summary: A Prior-guided DDL network learns the systematic difference between the model and the final contours approved by clinicians for an initial group of patients. The model is independent of practice styles and anatomical structures. It can be deployed for clinical use to adapt to new practice styles and new anatomical structures without further training.
• Score: 1.1091582432763736
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: When a pre-trained general auto-segmentation model is deployed at a new institution, a support framework in the proposed Prior-guided DDL network will learn the systematic difference between the model predictions and the final contours revised and approved by clinicians for an initial group of patients. The learned style feature differences are concatenated with the new patients (query) features and then decoded to get the style-adapted segmentations. The model is independent of practice styles and anatomical structures. It meta-learns with simulated style differences and does not need to be exposed to any real clinical stylized structures during training. Once trained on the simulated data, it can be deployed for clinical use to adapt to new practice styles and new anatomical structures without further training. To show the proof of concept, we tested the Prior-guided DDL network on six different practice style variations for three different anatomical structures. Pre-trained segmentation models were adapted from post-operative clinical target volume (CTV) segmentation to segment CTVstyle1, CTVstyle2, and CTVstyle3, from parotid gland segmentation to segment Parotidsuperficial, and from rectum segmentation to segment Rectumsuperior and Rectumposterior. The mode performance was quantified with Dice Similarity Coefficient (DSC). With adaptation based on only the first three patients, the average DSCs were improved from 78.6, 71.9, 63.0, 52.2, 46.3 and 69.6 to 84.4, 77.8, 73.0, 77.8, 70.5, 68.1, for CTVstyle1, CTVstyle2, and CTVstyle3, Parotidsuperficial, Rectumsuperior, and Rectumposterior, respectively, showing the great potential of the Priorguided DDL network for a fast and effortless adaptation to new practice styles

Related papers

• Sequence-aware Pre-training for Echocardiography Probe Guidance [66.35766658717205]
  Cardiac ultrasound faces two major challenges: (1) the inherently complex structure of the heart, and (2) significant individual variations. Previous works have only learned the population-averaged 2D and 3D structures of the heart rather than personalized cardiac structural features. We propose a sequence-aware self-supervised pre-training method to learn personalized 2D and 3D cardiac structural features.
  arXiv  Detail & Related papers  (2024-08-27T12:55:54Z)
• Anatomy-guided Pathology Segmentation [56.883822515800205]
  We develop a generalist segmentation model that combines anatomical and pathological information, aiming to enhance the segmentation accuracy of pathological features. Our Anatomy-Pathology Exchange (APEx) training utilizes a query-based segmentation transformer which decodes a joint feature space into query-representations for human anatomy. In doing so, we are able to report the best results across the board on FDG-PET-CT and Chest X-Ray pathology segmentation tasks with a margin of up to 3.3% as compared to strong baseline methods.
  arXiv  Detail & Related papers  (2024-07-08T11:44:15Z)
• Tissue Classification During Needle Insertion Using Self-Supervised Contrastive Learning and Optical Coherence Tomography [53.38589633687604]
  We propose a deep neural network that classifies the tissues from the phase and intensity data of complex OCT signals acquired at the needle tip. We show that with 10% of the training set, our proposed pretraining strategy helps the model achieve an F1 score of 0.84 whereas the model achieves an F1 score of 0.60 without it.
  arXiv  Detail & Related papers  (2023-04-26T14:11:04Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Anatomy-guided domain adaptation for 3D in-bed human pose estimation [62.3463429269385]
  3D human pose estimation is a key component of clinical monitoring systems. We present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method consistently outperforms various state-of-the-art domain adaptation methods.
  arXiv  Detail & Related papers  (2022-11-22T11:34:51Z)
• Prompt Tuning for Parameter-efficient Medical Image Segmentation [79.09285179181225]
  We propose and investigate several contributions to achieve a parameter-efficient but effective adaptation for semantic segmentation on two medical imaging datasets. We pre-train this architecture with a dedicated dense self-supervision scheme based on assignments to online generated prototypes. We demonstrate that the resulting neural network model is able to attenuate the gap between fully fine-tuned and parameter-efficiently adapted models.
  arXiv  Detail & Related papers  (2022-11-16T21:55:05Z)
• PSA-Net: Deep Learning based Physician Style-Aware Segmentation Network for Post-Operative Prostate Cancer Clinical Target Volume [5.90921279461999]
  This study tries to determine if physician styles are consistent and learnable, if there is an impact of physician styles on treatment outcome and toxicity. A concept called physician style-aware (PSA) segmentation is proposed which is an encoder-multidecoder network trained with perceptual loss.
  arXiv  Detail & Related papers  (2021-02-15T22:42:52Z)
• 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management [21.788423806147378]
  We exploit the feasibility to distinguish pancreatic ductal adenocarcinoma (PDAC) from the nine other nonPDAC masses using multi-phase CT imaging. We propose a holistic segmentation-mesh-classification network (SMCN) to provide patient-level diagnosis.
  arXiv  Detail & Related papers  (2020-12-08T19:38:01Z)
• Contour Transformer Network for One-shot Segmentation of Anatomical Structures [26.599337546171732]
  We present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. On segmentation tasks of four different anatomies, we demonstrate that our one-shot learning method significantly outperforms non-learning-based methods. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved to surpass the fully supervised methods.
  arXiv  Detail & Related papers  (2020-12-02T19:42:18Z)
• Learning to Segment Anatomical Structures Accurately from One Exemplar [34.287877547953194]
  Methods that permit to produce accurate anatomical structure segmentation without using a large amount of fully annotated training images are highly desirable. We propose Contour Transformer Network (CTN), a one-shot anatomy segmentor including a naturally built-in human-in-the-loop mechanism. We demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning approaches.
  arXiv  Detail & Related papers  (2020-07-06T20:27:38Z)
• Convolutional Neural Networks based automated segmentation and labelling of the lumbar spine X-ray [0.0]
  The aim of this study is to investigate the segmentation accuracies of different segmentation networks trained on 730 manually annotated lateral lumbar spine X-rays. Instance segmentation networks were compared to semantic segmentation networks.
  arXiv  Detail & Related papers  (2020-04-04T20:15:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.