C. Paul Bonnington

A multimodal vision foundation model for clinical dermatology

Siyuan Yan, Zhen Tao Yu, Clare Primiero, Cristina Vico‐Alonso et autres

Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks such as skin cancer diagnosis from dermoscopic images, they struggle to meet …

au, at, it, es (code pays fourni par la source)

Author Correction: Hierarchical skin lesion image classification with prototypical decision tree

Zhen Tao Yu, Toan Dinh Nguyen, Lie Ju, Yaniv Gal et autres

This correction pertains to attribution in the “Class Distance Guided Prototype Learning” section, ensuring proper recognition of the work from Landrieu et al. [38], as we adapt it for addressing hierarchical skin tree model optimization. While reference [38] was included, we need …

au (code pays fourni par la source)

Multi‐task AI models in dermatology: Overcoming critical clinical translation challenges for enhanced skin lesion diagnosis

Deval Samirbhai Mehta, Clare Primiero, Brigid Betz‐Stablein, Toan Dinh Nguyen et autres

BACKGROUND: The surge in AI models for diagnosing skin lesions through image analysis is notable, yet their clinical implementation faces challenges. Common limitations include an over reliance on dermoscopy, lack of real-world applicability when only binary output (e.g. benign/malignant) is offered and …

au (code pays fourni par la source)

Hierarchical skin lesion image classification with prototypical decision tree

Zhen Tao Yu, Toan Dinh Nguyen, Lie Ju, Yaniv Gal et autres

Traditional disease classification models often disregard the clinical significance of misclassifications and lack interpretability. To overcome these challenges, we propose a hierarchical prototypical decision tree (HPDT) for skin lesion classification. HPDT combines prototypical networks and decision trees, leveraging a class hierarchy to …

au (code pays fourni par la source)

A Multimodal Vision Foundation Model for Clinical Dermatology

Siyuan Yan, Zhentao Yu, Clare Primiero, Cristina Vico‐Alonso et autres

Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks like skin cancer diagnosis from dermoscopic images, they struggle to meet the …

Revamping AI Models in Dermatology: Overcoming Critical Challenges for Enhanced Skin Lesion Diagnosis

Deval Mehta, Brigid Betz‐Stablein, Toan Dinh Nguyen, Yaniv Gal et autres

The surge in developing deep learning models for diagnosing skin lesions through image analysis is notable, yet their clinical black faces challenges. Current dermatology AI models have limitations: limited number of possible diagnostic outputs, lack of real-world testing on uncommon skin lesions, …

Hierarchical Knowledge Guided Learning for Real-World Retinal Disease Recognition

Lie Ju, Zhen Tao Yu, Lin Wang, Xin Bo Zhao et autres

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy the majority of the data, while most classes have only a limited number of samples), which results in a challenging long-tailed learning scenario. Some recently …

au (code pays fourni par la source)

Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings

Zhen Tao Yu, Toan Quang Nguyen, Yaniv Gal, Lie Ju et autres

In practice, many medical datasets have an underlying taxonomy defined over the disease label space. However, existing classification algorithms for medical diagnoses often assume semantically independent labels. In this study, we aim to leverage class hierarchy with deep learning algorithms for more …

Final Report: ARDC Environments to Accelerate Machine Learning Based Discovery

C. Paul Bonnington, Wojtek Goscinski, Komathy Padmanabhan, David Abramsom et autres

This project focused on the key objectives below, which address the most pressing medium-term priorities identified in our researcher survey (http://bit.ly/MLResearchSurvey): Bring together ML tools, libraries, and access to data, across large HPC/GPU deployments nationally. The environments developed will support core ML …

au (code pays fourni par la source)

Out-of-Distribution Detection for Long-tailed and Fine-grained Skin Lesion Images

Deval Mehta, Yaniv Gal, Adrian Bowling, C. Paul Bonnington et autres

Recent years have witnessed a rapid development of automated methods for skin lesion diagnosis and classification. Due to an increasing deployment of such systems in clinics, it has become important to develop a more robust system towards various Out-of-Distribution(OOD) samples (unknown skin …

Learning Network Architecture for Open-Set Recognition

Xuelin Zhang, Xuelian Cheng, Donghao Zhang, C. Paul Bonnington et autres

Given the incomplete knowledge of classes that exist in the world, Open-set Recognition (OSR) enables networks to identify and reject the unseen classes after training. This problem of breaking the common closed-set assumption is far from being solved. Recent studies focus on …

au (code pays fourni par la source)

Flexible Sampling for Long-tailed Skin Lesion Classification

Lie Ju, Yicheng Wu, Lin Wang, Zhen Tao Yu et autres

Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning methods usually treat each class equally to re-balance the long-tailed distribution. However, considering that some challenging classes …