DEEP LEARNING FOR ODONTOGENIC TUMORS' CLASSIFICATION
To evaluate Deep Learning performance for the classification of ameloblastoma and ameloblastic carcinoma. Materials and methods: digital slides were manually annotated to assign regions with the tumor to segment and further fragment into patches of 556x556 pixels, according to the models' kerne...
Saved in:
| Published in: | Oral surgery, oral medicine, oral pathology and oral radiology Vol. 137; no. 6; p. e277 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Inc
01-06-2024
|
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | To evaluate Deep Learning performance for the classification of ameloblastoma and ameloblastic carcinoma. Materials and methods: digital slides were manually annotated to assign regions with the tumor to segment and further fragment into patches of 556x556 pixels, according to the models' kernels. The total sample was divided into sets of training, validation, and test sets. In the training stage, different hyperparameters of the Resnet 50, VGG 16, and DenseNet networks were studied. Results and
Preliminary results revealed that the models have learning potential, but not generalization so far. The training and validation metrics did not show convergence, characterizing an overfit. In addition, the test assessment was unsatisfactory, with an average of 0.65, 0.67, 0.61, 0.68, and 0.63 for accuracy, precision, sensitivity, specificity, and F1 score, respectively. These results may be influenced by the overlapping of characteristics between the tumors. Further experiments will improve the models and test other techniques of sampling, data augmentation, use of different classes of tumors, and implementation of different convolutional neural networks. |
|---|---|
| ISSN: | 2212-4403 2212-4411 |
| DOI: | 10.1016/j.oooo.2023.12.617 |