Self-Supervised Radiograph Anatomical Region Classification -- How Clean Is Your Real-World Data?
- URL: http://arxiv.org/abs/2412.15967v1
- Date: Fri, 20 Dec 2024 15:07:55 GMT
- Title: Self-Supervised Radiograph Anatomical Region Classification -- How Clean Is Your Real-World Data?
- Authors: Simon Langer, Jessica Ritter, Rickmer Braren, Daniel Rueckert, Paul Hager,
- Abstract summary: We show the effectiveness of self-supervised methods in assigning one of 14 anatomical region classes in our in-house dataset of 48,434 skeletal radiographs.<n>We achieve a strong linear evaluation accuracy of 96.6% with a single model and 97.7% using an ensemble approach.
- Score: 10.5757425746568
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Modern deep learning-based clinical imaging workflows rely on accurate labels of the examined anatomical region. Knowing the anatomical region is required to select applicable downstream models and to effectively generate cohorts of high quality data for future medical and machine learning research efforts. However, this information may not be available in externally sourced data or generally contain data entry errors. To address this problem, we show the effectiveness of self-supervised methods such as SimCLR and BYOL as well as supervised contrastive deep learning methods in assigning one of 14 anatomical region classes in our in-house dataset of 48,434 skeletal radiographs. We achieve a strong linear evaluation accuracy of 96.6% with a single model and 97.7% using an ensemble approach. Furthermore, only a few labeled instances (1% of the training set) suffice to achieve an accuracy of 92.2%, enabling usage in low-label and thus low-resource scenarios. Our model can be used to correct data entry mistakes: a follow-up analysis of the test set errors of our best-performing single model by an expert radiologist identified 35% incorrect labels and 11% out-of-domain images. When accounted for, the radiograph anatomical region labelling performance increased -- without and with an ensemble, respectively -- to a theoretical accuracy of 98.0% and 98.8%.
Related papers
- A Clinician-Friendly Platform for Ophthalmic Image Analysis Without Technical Barriers [51.45596445363302]
GlobeReady is a clinician-friendly AI platform that enables ocular disease diagnosis without retraining/fine-tuning or technical expertise.
It achieves high accuracy across imaging modalities: 93.9-98.5% for an 11-category fundus photo dataset and 87.2-92.7% for a 15-category OCT dataset.
It addresses domain shifts across centers and populations, reaching an average accuracy of 88.9% across five centers in China, 86.3% in Vietnam, and 90.2% in the UK.
arXiv Detail & Related papers (2025-04-22T14:17:22Z) - Congenital Heart Disease Classification Using Phonocardiograms: A Scalable Screening Tool for Diverse Environments [34.10187730651477]
Congenital heart disease (CHD) is a critical condition that demands early detection.
This study presents a deep learning model designed to detect CHD using phonocardiogram (PCG) signals.
We evaluated our model on several datasets, including the primary dataset from Bangladesh.
arXiv Detail & Related papers (2025-03-28T05:47:44Z) - Artificial Intelligence-Driven Prognostic Classification of COVID-19 Using Chest X-rays: A Deep Learning Approach [0.0]
This study presents a high-accuracy deep learning model for classifying COVID-19 severity (Mild, Moderate, and Severe) using Chest X-ray images.
Our model achieved an average accuracy of 97%, with specificity of 99%, sensitivity of 87%, and an F1-score of 93.11%.
These results demonstrate the model's potential for real-world clinical applications.
arXiv Detail & Related papers (2025-03-17T15:27:21Z) - Refining Tuberculosis Detection in CXR Imaging: Addressing Bias in Deep Neural Networks via Interpretability [1.9936075659851882]
We argue that the reliability of deep learning models is limited, even if they can be shown to obtain perfect classification accuracy on the test data.
We show that pre-training a deep neural network on a large-scale proxy task, as well as using mixed objective optimization network (MOON), can improve the alignment of decision foundations between models and experts.
arXiv Detail & Related papers (2024-07-19T06:41:31Z) - Generative models improve fairness of medical classifiers under
distribution shifts [49.10233060774818]
We show that learning realistic augmentations automatically from data is possible in a label-efficient manner using generative models.
We demonstrate that these learned augmentations can surpass ones by making models more robust and statistically fair in- and out-of-distribution.
arXiv Detail & Related papers (2023-04-18T18:15:38Z) - Sparse Dynamical Features generation, application to Parkinson's Disease
diagnosis [0.0]
We propose a new approach inspired by the functioning of the brain that uses the dynamics, frequency and temporal content of EEGs to extract new demarcating features of the disease.
The method was evaluated on a publicly available dataset containing EEG signals recorded during a 3-oddball auditory task involving N = 50 subjects, of whom 25 suffer from PD.
arXiv Detail & Related papers (2022-10-20T22:39:29Z) - Learning to diagnose common thorax diseases on chest radiographs from
radiology reports in Vietnamese [0.33598755777055367]
We propose a data collecting and annotation pipeline that extracts information from Vietnamese radiology reports to provide accurate labels for chest X-ray (CXR) images.
This can benefit Vietnamese radiologists and clinicians by annotating data that closely match their endemic diagnosis categories which may vary from country to country.
arXiv Detail & Related papers (2022-09-11T06:06:03Z) - 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) - Variational Knowledge Distillation for Disease Classification in Chest
X-Rays [102.04931207504173]
We propose itvariational knowledge distillation (VKD), which is a new probabilistic inference framework for disease classification based on X-rays.
We demonstrate the effectiveness of our method on three public benchmark datasets with paired X-ray images and EHRs.
arXiv Detail & Related papers (2021-03-19T14:13:56Z) - Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for
Thoracic Disease Identification [83.6017225363714]
deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance.
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
arXiv Detail & Related papers (2021-02-26T02:29:30Z) - A Real-World Demonstration of Machine Learning Generalizability:
Intracranial Hemorrhage Detection on Head CT [5.517017976008718]
The purpose of this study was to demonstrate that ML model generalizability is achievable in medical imaging.
An ML model was trained using 21,784 scans from the RSNA Intracranial Hemorrhage CT dataset.
On external validation, the model demonstrated an AUC of 95.4%, sensitivity of 91.3%, and specificity of 94.1%.
arXiv Detail & Related papers (2021-02-09T15:05:48Z) - Chest x-ray automated triage: a semiologic approach designed for
clinical implementation, exploiting different types of labels through a
combination of four Deep Learning architectures [83.48996461770017]
This work presents a Deep Learning method based on the late fusion of different convolutional architectures.
We built four training datasets combining images from public chest x-ray datasets and our institutional archive.
We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool.
arXiv Detail & Related papers (2020-12-23T14:38:35Z) - Self-Training with Improved Regularization for Sample-Efficient Chest
X-Ray Classification [80.00316465793702]
We present a deep learning framework that enables robust modeling in challenging scenarios.
Our results show that using 85% lesser labeled data, we can build predictive models that match the performance of classifiers trained in a large-scale data setting.
arXiv Detail & Related papers (2020-05-03T02:36:00Z)
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.