Litcius/Paper detail

An Approach to BI-RADS Uncertainty Levels Classification Via Deep Learning with Transfer Learning Technique

Aldísio G. Medeiros, Elene Firmeza Ohata, Francisco H. S. Silva, Paulo A. L. Rêgo, Pedro P. Rebouças Filho

202010 citationsDOI

Abstract

This work combines the transfer learning technique with Convolutional Neural Networks (CNN) to classify the pathology within BI-RADS levels 3 and 4 for malignancy of breast masses. These BI-RADS levels represent the zone of the uncertainty of the degree of malignancy of the found mass, making it difficult for the human experts in classifying as malignant or benign. Eleven CNN architectures were used as feature extractors and combined with four traditional classification models: Bayes, Multilayer Perceptron (MLP), Support Vector Machines, and Random Forest. The combination DenseNet201-MLP achieved an accuracy higher than 63%, surpassing the performance of a human expert by 9.0%.

Topics & Concepts

Computer scienceConvolutional neural networkTransfer of learningArtificial intelligenceRandom forestNaive Bayes classifierMachine learningPattern recognition (psychology)Feature (linguistics)Deep learningMultilayer perceptronArtificial neural networkMalignancyBayes' theoremFeature vectorPerceptronSupport vector machineBayesian probabilityBiologyGeneticsPhilosophyLinguisticsAI in cancer detectionGene expression and cancer classificationBrain Tumor Detection and Classification
An Approach to BI-RADS Uncertainty Levels Classification Via Deep Learning with Transfer Learning Technique | Litcius