Code-free deep learning for multi-modality medical image classification

Korot, Edward; Guan, Zeyu; Ferraz, Daniel; Wagner, Siegfried; Zhang, Gongyu; Liu, Xiaoxuan; Faes, Livia; Pontikos, Nikolas; Finlayson, Samuel G.; Khalid, Hagar; Moraes, Gabriella; Balaskas, Konstantinos; Denniston, Alastair K; Keane, Pearse A.

doi:10.1038/s42256-021-00305-2

Cited by 124 publications

(80 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ICDR is applied in the EYEPACS dataset [ 24 ], Asian Pacific Tele-Ophthalmology Society dataset [ 25 ], Indian Diabetic Retinopathy Image Dataset [ 26 ], Messidor 1 and 2 datasets [ 27 ] (Table 1 ).…”

Section: Main Textmentioning

confidence: 99%

Diabetic retinopathy classification for supervised machine learning algorithms

et al. 2022

View full text Add to dashboard Cite

Background Artificial intelligence and automated technology were first reported more than 70 years ago and nowadays provide unprecedented diagnostic accuracy, screening capacity, risk stratification, and workflow optimization. Diabetic retinopathy is an important cause of preventable blindness worldwide, and artificial intelligence technology provides precocious diagnosis, monitoring, and guide treatment. High-quality exams are fundamental in supervised artificial intelligence algorithms, but the lack of ground truth standards in retinal exams datasets is a problem. Main body In this article, ETDRS, NHS, ICDR, SDGS diabetic retinopathy grading, and manual annotation are described and compared in publicly available datasets. The various DR labeling systems generate a fundamental problem for AI datasets. Possible solutions are standardization of DR classification and direct retinal-finding identifications. Conclusion Reliable labeling methods also need to be considered in datasets with more trustworthy labeling.

show abstract

Section: Main Textmentioning

confidence: 99%

Diabetic retinopathy classification for supervised machine learning algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In contrast, automated machine learning (AutoML) techniques seek to accomplish these steps without user input. Recent studies assessing the feasibility of AutoML in healthcare have found promising results in comparison to bespoke models [11][12][13][14]. This represents an opportunity to enable clinicians with no computational background to leverage the power of ML.…”

Section: Introductionmentioning

confidence: 99%

Evaluating an automated machine learning model that predicts visual acuity outcomes in patients with neovascular age-related macular degeneration

Abbas

O’Byrne

et al. 2022

Graefes Arch Clin Exp Ophthalmol

Self Cite

View full text Add to dashboard Cite

Purpose Neovascular age-related macular degeneration (nAMD) is a major global cause of blindness. Whilst anti-vascular endothelial growth factor (anti-VEGF) treatment is effective, response varies considerably between individuals. Thus, patients face substantial uncertainty regarding their future ability to perform daily tasks. In this study, we evaluate the performance of an automated machine learning (AutoML) model which predicts visual acuity (VA) outcomes in patients receiving treatment for nAMD, in comparison to a manually coded model built using the same dataset. Furthermore, we evaluate model performance across ethnic groups and analyse how the models reach their predictions. Methods Binary classification models were trained to predict whether patients’ VA would be ‘Above’ or ‘Below’ a score of 70 one year after initiating treatment, measured using the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The AutoML model was built using the Google Cloud Platform, whilst the bespoke model was trained using an XGBoost framework. Models were compared and analysed using the What-if Tool (WIT), a novel model-agnostic interpretability tool. Results Our study included 1631 eyes from patients attending Moorfields Eye Hospital. The AutoML model (area under the curve [AUC], 0.849) achieved a highly similar performance to the XGBoost model (AUC, 0.847). Using the WIT, we found that the models over-predicted negative outcomes in Asian patients and performed worse in those with an ethnic category of Other. Baseline VA, age and ethnicity were the most important determinants of model predictions. Partial dependence plot analysis revealed a sigmoidal relationship between baseline VA and the probability of an outcome of ‘Above’. Conclusion We have described and validated an AutoML-WIT pipeline which enables clinicians with minimal coding skills to match the performance of a state-of-the-art algorithm and obtain explainable predictions.

show abstract

“…The recent emergence of automated machine learning (AutoML) has been a major step in the democratisation of AI. AutoML describes a set of tools and techniques for streamlining model development by automating the selection of optimal network architectures, pre-processing methods and hyperparameter optimization 9 . Using a simple graphical interface and without writing code, users can build highly-accurate machine learning (ML) models.…”

Section: Introductionmentioning

confidence: 99%

“…Such models have been shown to rival hand-designed (bespoke) models 7 . Multiple studies explored the use of AutoML for the classification of medical images such as fundus photography and optical coherence tomography 7 , 9 , 10 .…”

Section: Introductionmentioning

confidence: 99%

Development of a code-free machine learning model for the classification of cataract surgery phases

Touma

Antaki

Duval

2022

Sci Rep

View full text Add to dashboard Cite

This study assessed the performance of automated machine learning (AutoML) in classifying cataract surgery phases from surgical videos. Two ophthalmology trainees without coding experience designed a deep learning model in Google Cloud AutoML Video Classification for the classification of 10 different cataract surgery phases. We used two open-access publicly available datasets (total of 122 surgeries) for model training, validation and testing. External validation was performed on 10 surgeries issued from another dataset. The AutoML model demonstrated excellent discriminating performance, even outperforming bespoke deep learning models handcrafter by experts. The area under the precision-recall curve was 0.855. At the 0.5 confidence threshold cut-off, the overall performance metrics were as follows: sensitivity (81.0%), recall (77.1%), accuracy (96.0%) and F1 score (0.79). The per-segment metrics varied across the surgical phases: precision 66.7–100%, recall 46.2–100% and specificity 94.1–100%. Hydrodissection and phacoemulsification were the most accurately predicted phases (100 and 92.31% correct predictions, respectively). During external validation, the average precision was 54.2% (0.00–90.0%), the recall was 61.1% (0.00–100%) and specificity was 96.2% (91.0–99.0%). In conclusion, a code-free AutoML model can accurately classify cataract surgery phases from videos with an accuracy comparable or better than models developed by experts.

show abstract

Code-free deep learning for multi-modality medical image classification

Cited by 124 publications

References 47 publications

Diabetic retinopathy classification for supervised machine learning algorithms

Diabetic retinopathy classification for supervised machine learning algorithms

Evaluating an automated machine learning model that predicts visual acuity outcomes in patients with neovascular age-related macular degeneration

Development of a code-free machine learning model for the classification of cataract surgery phases

Contact Info

Product

Resources

About