A pathology-based machine learning method to assist in epithelial dysplasia diagnosis
Year: 2022
Type: article
Abstract: Epithelial dysplasia (ED) is one of the most important factors in detecting the progression of an oral tissue alteration towards carcinoma. Its early detection is instrumental in avoiding the progression of the tumor. A major difficulty for detecting ED is the recognized variability of pathologist assessments. This study proposes a new method that leverages the pathologist expertise to design a simple and efficient classification system to support the detection of dysplastic epithelia. We employ a multilayer artificial neural network (MLP-ANN) and defining the regions of the epithelium to be assessed based on the knowledge of the pathologist. The performance of the proposed solution was statistically evaluated. The implemented MLP-ANN presented an average accuracy of $$87\%$$ , with a variability much inferior to that obtained from three trained evaluators. Moreover, the proposed solution led to results which are very close to those obtained using a convolutional neural network (CNN) implemented by transfer learning, with 100 times less computational complexity. In conclusion, our results show that a simple neural network structure combined with the pathologist expertise can lead to a performance equivalent to that of much more complex structures, which are routinely used in the literature.
Institution: Universidade Federal de Santa Catarina
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,780
Award: G1058501487
OpenAlex ID: W4291745537
