Table 1.
Summary of reviewed literature with a focus on dataset split and reported test classification performance.
| Ref. | OCT dataset | Data split strategy | Model performance on testing set |
|---|---|---|---|
| 9 | Thyroid, parathyroid, fat and muscle samples | per-image | 97.12% accuracy |
| 35 | Pituitary adenoma | per-image | 0.96 AUC |
| 18 | Ophthalmology15* (version 2) | original split | 95.55% accuracy |
| 19 | Ophthalmology15* (version 2) | original split | 99.1% accuracy |
| 21 | Ophthalmology15* (version 3) | original split | 98.7% accuracy |
| 22 | Ophthalmology15* (version 3) | original split | 96.6% accuracy |
| 27 | Ophthalmology15* (train version 2, test version 3) | original split | 99.6% accuracy |
| 23 | (1) Ophthalmology15* (train version 2, test version 3) (2) Ophthalmology16* |
(1) original split (2) per-volume/subject |
(1) 99.80% accuracy (2) 100% accuracy |
| 36 | Coronary artery | per-volume/subject | 96.05% accuracy |
| 37 | Kidney† | per-volume/subject | 82.6% accuracy |
| 38 | High and low grade brain tumors | per-volume/subject | 97% accuracy |
| 39 | Colon**† | per-volume/subject | 88.95% accuracy on 2D images |
| 40 | Breast tissue | per-volume/subject | 91.7% specificity |
| 20 | Ophthalmology15* (version 2) | per-volume/subject | 98.46% accuracy |
| 10 |
(1) Ophthalmology15* (version 3) (2) Ophthalmology16* (3) Breast tissue14* |
(1) original split (2) per-volume/subject (3) per-image |
(1) ~96% accuracy (2) >98.8% accuracy (3) 98.8% accuracy |
| 24 |
(1) Ophthalmology16* (2) Ophthalmology41* (3) Ophthalmology42* (4) Ophthalmology15* (unclear version) |
(1) per-volume/subject (2) per-volume/subject (3) per-volume/subject (4) original split |
(1) 96.66% accuracy (2) 98.97% accuracy (3) 99.74% accuracy (4) 99.78% accuracy |
| 43 | Dentistry | No description given | 98% sensitivity 100% specificity |
| 44 | Ophthalmology | No description given | 99.19% accuracy |
Open-access datasets and the ones available upon request are marked by * and **, respectively. The dataset is not open-access if not specified. Datasets obtained from animal model samples are marked by †. The difference in performance between studies using the same datasets results from the different methods implemented.