Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis

• URL: http://arxiv.org/abs/2403.06024v1
• Date: Sat, 9 Mar 2024 22:23:45 GMT
• Title: Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis
• Authors: Zhe Huang, Xiaowei Yu, Benjamin S. Wessler and Michael C. Hughes
• Abstract summary: We introduce Semi-supervised Multimodal Multiple-Instance Learning (SMMIL), a new deep learning framework for automatic interpretation for structural heart diseases. SMMIL can combine information from two input modalities, spectral Dopplers and 2D cineloops, to produce a study-level AS diagnosis.
• Score: 6.356639194509079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated interpretation of ultrasound imaging of the heart (echocardiograms) could improve the detection and treatment of aortic stenosis (AS), a deadly heart disease. However, existing deep learning pipelines for assessing AS from echocardiograms have two key limitations. First, most methods rely on limited 2D cineloops, thereby ignoring widely available Doppler imaging that contains important complementary information about pressure gradients and blood flow abnormalities associated with AS. Second, obtaining labeled data is difficult. There are often far more unlabeled echocardiogram recordings available, but these remain underutilized by existing methods. To overcome these limitations, we introduce Semi-supervised Multimodal Multiple-Instance Learning (SMMIL), a new deep learning framework for automatic interpretation for structural heart diseases like AS. When deployed, SMMIL can combine information from two input modalities, spectral Dopplers and 2D cineloops, to produce a study-level AS diagnosis. During training, SMMIL can combine a smaller labeled set and an abundant unlabeled set of both modalities to improve its classifier. Experiments demonstrate that SMMIL outperforms recent alternatives at 3-level AS severity classification as well as several clinically relevant AS detection tasks.

Related papers

• Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple Clinical Annotation [25.459627476201646]
  We suggest using simple aspect ratio annotations directly from ultrasound clinical diagnoses for automated nodule segmentation. An asymmetric learning framework is developed by extending the aspect ratio annotations with two types of pseudo labels. Experiments on two clinically collected ultrasound datasets (thyroid and breast) demonstrate the superior performance of our proposed method.
  arXiv  Detail & Related papers  (2024-04-23T09:07:04Z)
• Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning [5.201499435914216]
  Aortic stenosis (AS) is a degenerative valve condition that causes substantial morbidity and mortality. Previous approaches to AS detection yield insufficient accuracy due to relying on inflexible averages across images. We contribute a new end-to-end MIL approach with two key methodological innovations.
  arXiv  Detail & Related papers  (2023-05-25T18:22:12Z)
• MMA-RNN: A Multi-level Multi-task Attention-based Recurrent Neural Network for Discrimination and Localization of Atrial Fibrillation [1.8037893225125925]
  This paper proposes the Multi-level Multi-task Attention-based Recurrent Neural Network for three-class discrimination on patients and localization of the exact timing of AF episodes. The model is designed as an end-to-end framework to enhance information interaction and reduce error accumulation.
  arXiv  Detail & Related papers  (2023-02-07T19:59:55Z)
• Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation [0.8200989595956418]
  Deep learning models are not trusted in the clinical routine due to failing silently on out-of-distribution data. We propose a lightweight OOD detection method that leverages the Mahalanobis distance in the feature space. We validate our method across four chest CT distribution shifts and two magnetic resonance imaging applications.
  arXiv  Detail & Related papers  (2022-08-05T15:05:23Z)
• Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning [62.13520959168732]
  We propose a semi-supervised learning framework for instrument segmentation in 3D US. To achieve the SSL learning, a Dual-UNet is proposed to segment the instrument. Our proposed method achieves Dice score of about 68.6%-69.1% and the inference time of about 1 sec. per volume.
  arXiv  Detail & Related papers  (2021-07-30T07:59:45Z)
• Self-Supervised Multi-Modal Alignment for Whole Body Medical Imaging [70.52819168140113]
  We use a dataset of over 20,000 subjects from the UK Biobank with both whole body Dixon technique magnetic resonance (MR) scans and also dual-energy x-ray absorptiometry (DXA) scans. We introduce a multi-modal image-matching contrastive framework, that is able to learn to match different-modality scans of the same subject with high accuracy. Without any adaption, we show that the correspondences learnt during this contrastive training step can be used to perform automatic cross-modal scan registration.
  arXiv  Detail & Related papers  (2021-07-14T12:35:05Z)
• Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity [77.78624443410216]
  We propose improved FDAM algorithms for detecting heterogeneous chest data. A result of this paper is that the communication of the proposed algorithm is strongly independent of the number of machines and also independent of the accuracy level. Experiments have demonstrated the effectiveness of our FDAM algorithm on benchmark datasets and on medical chest Xray images from different organizations.
  arXiv  Detail & Related papers  (2021-02-09T04:05:19Z)
• Semi-Supervised Active Learning for COVID-19 Lung Ultrasound Multi-symptom Classification [13.878896181984262]
  We propose a novel semi-supervised Two-Stream Active Learning (TSAL) method to model complicated features and reduce labeling costs. On this basis, a multi-symptom multi-label (MSML) classification network is proposed to learn discriminative features of lung symptoms. A novel lung US dataset named COVID19-LUSMS is built, currently containing 71 clinical patients with 6,836 images sampled from 678 videos.
  arXiv  Detail & Related papers  (2020-09-09T10:45:34Z)
• Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet [74.22397862400177]
  We propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation. With the detected catheter, patch-based Dual-UNet is applied to segment the catheter in 3D volumetric data.
  arXiv  Detail & Related papers  (2020-06-25T21:10:04Z)
• Detecting Parkinsonian Tremor from IMU Data Collected In-The-Wild using Deep Multiple-Instance Learning [59.74684475991192]
  Parkinson's Disease (PD) is a slowly evolving neuro-logical disease that affects about 1% of the population above 60 years old. PD symptoms include tremor, rigidity and braykinesia. We present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device.
  arXiv  Detail & Related papers  (2020-05-06T09:02:30Z)
• Detecting Pancreatic Ductal Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble [77.5625174267105]
  Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers among the population. Multiple phases provide more information than single phase, but they are unaligned and inhomogeneous in texture. We suggest an ensemble of all these alignments as a promising way to boost the performance of PDAC detection.
  arXiv  Detail & Related papers  (2020-03-18T19:06:27Z)

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.