Regression Constraint for an Explainable Cervical Cancer Classifier
This work addresses cervical cancer screening for medical diagnostics, but it is incremental as it applies existing methods to a specific dataset.
The paper tackled automatic classification of cervical cancer severity from cell images using deep learning, achieving 74.5% accuracy for severity classification and 94% for normal/abnormal classification.
This article adresses the problem of automatic squamous cells classification for cervical cancer screening using Deep Learning methods. We study different architectures on a public dataset called Herlev dataset, which consists in classifying cells, obtained by cervical pap smear, regarding the severity of the abnormalities they represent. Furthermore, we use an attribution method to understand which cytomorphological features are actually learned as discriminative to classify severity of the abnormalities. Through this paper, we show how we trained a performant classifier: 74.5\% accuracy on severity classification and 94\% accuracy on normal/abnormal classification.