A Review of Predictive and Contrastive Self-supervised Learning for Medical Images

Wang, W.; Ahn, Euijoon; Feng, David Dagan; Kim, Jinman

doi:10.1007/s11633-022-1406-4

Cited by 11 publications

(2 citation statements)

References 194 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intrinsic Dimension Estimation is the process of determining a minimum number of dimensions required to represent data accurately and it also shows the complexity of the dataset. This study encompasses various datasets and models highlighting the complex nature of radiological data and its influence on deep learning model performance [21].…”

Section: Literature Surveymentioning

confidence: 99%

Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models

BS,

Buchupalli,

Gottimukkula

et al. 2024

Preprint

View full text Add to dashboard Cite

The musculoskeletal radiograph (MURA) dataset, which is the largest bone x-ray dataset is an important resource for training and testing the machine learning model, as it has been specifically analyzed and well-classified by specially trained radiologists. Four CNN architectures have separately trained and evaluated the dataset ( DenseNet201 GoogLeNet, ResNet50, and Inception-ResNet-V2). The results of the algorithms showed variation in recall and accuracy. In addition, multiple-architecture ensemble models performed better than single models, highlighting the benefits of ensembling techniques to improve prediction accuracy. Combining multiple deep learning models reduces the risk of overfitting, increases predictive stability, improves accuracy, and optimizes the dataset. The integration of several models considers dataset robustness and uncertainty reduction. This ensembling process enables the development of accurate diagnostic tools for upper limb bone-related problems using the MURA dataset and other radiographic datasets. This work shows the use of ensemble methodologies, optimization of architecture, and various techniques, such as using data augmentation and demonstrating the ability of CNN to generalize musculoskeletal diseases. The results of this work can contribute to the creation of more effective diagnostic tools for the healthcare industry.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models

BS,

Buchupalli,

Gottimukkula

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Supervised learning and contrastive learning represent distinct methodologies, with supervised learning focusing on mapping inputs to outputs using labeled data for tasks like image classification, and contrastive learning emphasizing the learning of data representations by distinguishing similar from dissimilar data points, useful in scenarios with limited labeled data [17]. Supervised contrastive learning, a novel approach by Google Research [18], merges these techniques by using labeled data to enhance representation learning.…”

Section: Introductionmentioning

confidence: 99%

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Alzahrani

2024

Preprint

View full text Add to dashboard Cite

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

show abstract

Conductive hydrogels‐based self‐sensing soft robot state perception and trajectory tracking

Ma,

Han,

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

Soft robots face significant challenges in proprioceptive sensing and precise control due to their highly deformable and compliant nature. This paper addresses these challenges by developing a conductive hydrogel sensor and integrating it into a soft robot for bending angle measurement and motion control. A quantitative mapping between the hydrogel resistance and the robot's bending gesture is formulated. Furthermore, a nonlinear differentiator is proposed to estimate the angular velocity for closed‐loop control, eliminating the reliance on conventional sensors. Meanwhile, a controller is designed to track both structural and nonstructural trajectories. The proposed approach integrates advanced soft sensing materials and intelligent control algorithms, significantly improving the proprioception and motion accuracy of soft robots. This work bridges the gap between novel material design and practical control applications, opening up new possibilities for soft robots to perform delicate tasks in various fields. The experimental results demonstrate the effectiveness of the proposed sensing and control approach in achieving precise and robust motion control of the soft robot.

show abstract

A Review of Predictive and Contrastive Self-supervised Learning for Medical Images

Cited by 11 publications

References 194 publications

Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models

Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

Conductive hydrogels‐based self‐sensing soft robot state perception and trajectory tracking

Contact Info

Product

Resources

About