ArticleScientific data2022
Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images.
Article in Scientific data, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 33 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
33 citing papers in PubMed.
- Comment on ensemble model assisted classification of gastrointestinal bleeding using wireless capsule endoscopy.Physical and engineering sciences in medicine · 2026Article
- A narrative review of artificial intelligence in dental imaging: from dataset design to clinical translation.Oral radiology · 2026Review
- Comparative Evaluation of EfficientNet-B3, Vision Transformers, and RETFound for Seven-Category Retinopathy Fundus Image Classification.Diagnostics (Basel, Switzerland) · 2026Article
- Article
- Symmetric Siamese Networks for Longitudinal Chest Radiograph Change Detection: A Leakage-Controlled Study on MIMIC-CXR.Tomography (Ann Arbor, Mich.) · 2026Article
- Coarse-to-Fine Curriculum Transfer Learning Using RF-Derived Ultrasound Representations for Small-Data Breast Tumor Detection.Bioengineering (Basel, Switzerland) · 2026Article
- Article
- Ultra-widefield color fundus photography in diabetic retinopathy: from panretinal assessment to multimodal integration.Frontiers in medicine · 2026Review
- Radiomics and deep learning in upper tract urothelial carcinoma: advancing preoperative risk stratification and clinical decision-making.Frontiers in oncology · 2026Review
- Artificial intelligence-assisted smart hydrogel bioinks in 3D bioprinting: design, optimization, and construct validation for functional tissue engineering.Frontiers in bioengineering and biotechnology · 2026Review
- Integration of nested cross-validation, automated hyperparameter optimization, high-performance computing to reduce and quantify the variance of test performance estimation of deep learning models.Computer methods and programs in biomedicine · 2025Article
- Artificial intelligence-driven anticancer peptide discovery.iMetaOmics · 2025Review
- A holistic air monitoring dataset with complaints and POIs for anomaly detection and interpretability tracing.Scientific data · 2025Article
- Machine and Deep Learning for the Diagnosis, Prognosis, and Treatment of Cervical Cancer: A Scoping Review.Diagnostics (Basel, Switzerland) · 2025Review
- Deep learning approach based on a patch residual for pediatric supracondylar subtle fracture detection.Biomolecules & biomedicine · 2025Article
- Integrating Retinal Segmentation Metrics with Machine Learning for Predictions from Mouse SD-OCT Scans.Current eye research · 2025Article
- Super-resolution mapping of anisotropic tissue structure with diffusion MRI and deep learning.Scientific reports · 2025Article
- Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets.Scientific data · 2025Article
- Taking a look at your speech: identifying diagnostic status and negative symptoms of psychosis using convolutional neural networks.NPP - digital psychiatry and neuroscience · 2025Article
- Unmasking biases and navigating pitfalls in the ophthalmic artificial intelligence lifecycle: A narrative review.PLOS digital health · 2024Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
In the application of deep learning on optical coherence tomography (OCT) data, it is common to train classification networks using 2D images originating from volumetric data. Given the micrometer resolution of OCT systems, consecutive images are often very similar in both visible structures and noise. Thus, an inappropriate data split can result in overlap between the training and testing sets, with a large portion of the literature overlooking this aspect. In this study, the effect of improper dataset splitting on model evaluation is demonstrated for three classification tasks using three OCT open-access datasets extensively used, Kermany's and Srinivasan's ophthalmology datasets, and AIIMS breast tissue dataset. Results show that the classification performance is inflated by 0.07 up to 0.43 in terms of Matthews Correlation Coefficient (accuracy: 5% to 30%) for models tested on datasets with improper splitting, highlighting the considerable effect of dataset handling on model evaluation. This study intends to raise awareness on the importance of dataset splitting given the increased research interest in implementing deep learning on OCT data.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.