Deep learning applied to the histopathological diagnosis of ameloblastomas and ameloblastic carcinomas

Abstract

BackgroundOdontogenic tumors (OT) are composed of heterogeneous lesions, which can be benign or malignant, with different behavior and histology. Within this classification, ameloblastoma and ameloblastic carcinoma (AC) represent a diagnostic challenge in daily histopathological practice due to their similar characteristics and the limitations that incisional biopsies represent. From these premises, we wanted to test the usefulness of models based on artificial intelligence (AI) in the field of oral and maxillofacial pathology for differential diagnosis. The main advantages of integrating Machine Learning (ML) with microscopic and radiographic imaging is the ability to significantly reduce intra‐and inter observer variability and improve diagnostic objectivity and reproducibility.MethodsThirty Digitized slides were collected from different diagnostic centers of oral pathology in Brazil. After performing manual annotation in the region of interest, the images were segmented and fragmented into small patches. In the supervised learning methodology for image classification, three models (ResNet50, DenseNet, and VGG16) were focus of investigation to provide the probability of an image being classified as class0 (i.e., ameloblastoma) or class1 (i.e., Ameloblastic carcinoma).ResultsThe training and validation metrics did not show convergence, characterizing overfitting. However, the test results were satisfactory, with an average for ResNet50 of 0.75, 0.71, 0.84, 0.65, and 0.77 for accuracy, precision, sensitivity, specificity, and F1‐score, respectively.ConclusionsThe models demonstrated a strong potential of learning, but lack of generalization ability. The models learn fast, reaching a training accuracy of 98%. The evaluation process showed instability in validation; however, acceptable performance in the testing process, which may be due to the small data set. This first investigation opens an opportunity for expanding collaboration to incorporate more complementary data; as well as, developing and evaluating new alternative models.

Benchmarking Deep Learning-Based Image Retrieval of Oral Tumor Histology

“…The diagnosis of oral pathology has long depended on histopathological image observation, which can be a burden for pathologists, especially when dealing with rare cases. In the last decade, various machine learning methods, such as supervised learning methods for classification, detection, and segmentation, have been proposed to aid in clinical and histopathological diagnosis and to improve speed and accuracy to avoid delays in diagnosis [3,4,[9][10][11][12]26]. However, the exploration for oral histopathology diagnosis has been hampered by the difficulty of obtaining an adequately extensive database that includes rare cases and constructing an effective model.…”

“…AI development for oral tumor diagnosis is limited and focused only on a few tumor types. Classification methods have been developed to predict the diagnosis, such as differentiating between ameloblastoma or odontogenic keratocysts, to which a histopathological image may belong [ 3 , 4 ]. These approaches are helpful in common cases.…”

Benchmarking Deep Learning-based Image Retrieval of Oral Tumor Histology

“…AI development for oral tumor diagnosis is limited and focused only on a few tumor types. Classification methods have been developed to predict the diagnosis, such as ameloblastoma or odontogenic keratocysts, to which a histopathological image may belong [3,4]. These approaches are helpful in common cases.…”