Label-free segmentation from cardiac ultrasound using self-supervised learning

• URL: http://arxiv.org/abs/2210.04979v2
• Date: Tue, 24 Oct 2023 19:16:45 GMT
• Title: Label-free segmentation from cardiac ultrasound using self-supervised learning
• Authors: Danielle L. Ferreira, Zaynaf Salaymang, Rima Arnaout
• Abstract summary: We built a pipeline for self-supervised (no manual labels) segmentation using computer vision, clinical domain knowledge, and deep learning. We trained on 450 echocardiograms (93,000 images) and tested on 8,393 echocardiograms (4,476,266 images; mean 61 years, 51% female), using the resulting segmentations to calculate biometrics. Our results demonstrate a manual-label free, clinically valid, and highly scalable method for segmentation from ultrasound.
• Score: 0.6906005491572401
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Segmentation and measurement of cardiac chambers is critical in cardiac ultrasound but is laborious and poorly reproducible. Neural networks can assist, but supervised approaches require the same laborious manual annotations. We built a pipeline for self-supervised (no manual labels) segmentation combining computer vision, clinical domain knowledge, and deep learning. We trained on 450 echocardiograms (93,000 images) and tested on 8,393 echocardiograms (4,476,266 images; mean 61 years, 51% female), using the resulting segmentations to calculate biometrics. We also tested against external images from an additional 10,030 patients with available manual tracings of the left ventricle. r2 between clinically measured and pipeline-predicted measurements were similar to reported inter-clinician variation and comparable to supervised learning across several different measurements (r2 0.56-0.84). Average accuracy for detecting abnormal chamber size and function was 0.85 (range 0.71-0.97) compared to clinical measurements. A subset of test echocardiograms (n=553) had corresponding cardiac MRIs, where MRI is the gold standard. Correlation between pipeline and MRI measurements was similar to that between clinical echocardiogram and MRI. Finally, the pipeline accurately segments the left ventricle with an average Dice score of 0.89 (95% CI [0.89]) in the external, manually labeled dataset. Our results demonstrate a manual-label free, clinically valid, and highly scalable method for segmentation from ultrasound, a noisy but globally important imaging modality.

Related papers

• SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms [60.35639972035727]
  The lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. Dice scores reached up to 0.838 $pm$ 0.066 and 0.716 $pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $pm$ 0.15.
  arXiv  Detail & Related papers  (2024-11-14T17:06:00Z)
• TotalSegmentator MRI: Sequence-Independent Segmentation of 59 Anatomical Structures in MR images [62.53931644063323]
  In this study we extended the capabilities of TotalSegmentator to MR images. We trained an nnU-Net segmentation algorithm on this dataset and calculated similarity coefficients (Dice) to evaluate the model's performance. The model significantly outperformed two other publicly available segmentation models (Dice score 0.824 versus 0.762; p0.001 and 0.762 versus 0.542; p)
  arXiv  Detail & Related papers  (2024-05-29T20:15:54Z)
• Large-Scale Multi-Center CT and MRI Segmentation of Pancreas with Deep Learning [20.043497517241992]
  Automated volumetric segmentation of the pancreas is needed for diagnosis and follow-up of pancreatic diseases. We developed PanSegNet, combining the strengths of nnUNet and a Transformer network with a new linear attention module enabling volumetric computation. For segmentation accuracy, we achieved Dice coefficients of 88.3% (std: 7.2%, at case level) with CT, 85.0% (std: 7.9%, at case level) with T1W MRI, and 86.3% (std: 6.4%) with T2W MRI.
  arXiv  Detail & Related papers  (2024-05-20T20:37:27Z)
• CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers [66.15847237150909]
  We introduce a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images. The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism. We validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms.
  arXiv  Detail & Related papers  (2024-03-21T15:13:36Z)
• Deep Learning Pipeline for Preprocessing and Segmenting Cardiac Magnetic Resonance of Single Ventricle Patients from an Image Registry [1.1094040761152786]
  The data was used to train and evaluate a pipeline containing three deep-learning models. The pipeline's performance was assessed on the Dice and IoU score between the automated and reference standard manual segmentation.
  arXiv  Detail & Related papers  (2023-03-21T08:37:15Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• A New Semi-Automated Algorithm for Volumetric Segmentation of the Left Ventricle in Temporal 3D Echocardiography Sequences [1.3466792104272818]
  delineation of the left ventricle is challenging due to the presence of speckle noise and the low signal-to-noise ratio. We propose a semi-automated segmentation algorithm for the delineation of the left ventricle in temporal 3D echocardiography sequences.
  arXiv  Detail & Related papers  (2021-09-02T17:55:56Z)
• Fully Automated Mitral Inflow Doppler Analysis Using Deep Learning [0.0]
  We present a fully automated workflow which leverages deep learning to label MI Doppler images acquired in an echo study. We trained a variety of convolutional neural networks (CNN) models on 5544 images of 140 patients for predicting 24 image classes including MI Doppler images.
  arXiv  Detail & Related papers  (2020-11-24T22:27:14Z)
• Identification of Ischemic Heart Disease by using machine learning technique based on parameters measuring Heart Rate Variability [50.591267188664666]
  In this study, 18 non-invasive features (age, gender, left ventricular ejection fraction and 15 obtained from HRV) of 243 subjects were used to train and validate a series of several ANN. The best result was obtained using 7 input parameters and 7 hidden nodes with an accuracy of 98.9% and 82% for the training and validation dataset.
  arXiv  Detail & Related papers  (2020-10-29T19:14:41Z)
• Segmentation of the Myocardium on Late-Gadolinium Enhanced MRI based on 2.5 D Residual Squeeze and Excitation Deep Learning Model [55.09533240649176]
  The aim of this work is to develop an accurate automatic segmentation method based on deep learning models for the myocardial borders on LGE-MRI. A total number of 320 exams (with a mean number of 6 slices per exam) were used for training and 28 exams used for testing. The performance analysis of the proposed ensemble model in the basal and middle slices was similar as compared to intra-observer study and slightly lower at apical slices.
  arXiv  Detail & Related papers  (2020-05-27T20:44:38Z)
• How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning? [2.330464988780586]
  Planning the optimal time of intervention for pulmonary valve replacement surgery in patients with the congenital heart disease Tetralogy of Fallot (TOF) is mainly based on ventricular volume and function according to current guidelines. In several grand challenges in the last years, U-Net architectures have shown impressive results on the provided data. However, in clinical practice, data sets are more diverse considering individual pathologies and image properties derived from different scanner properties.
  arXiv  Detail & Related papers  (2020-02-10T08:50:51Z)

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.