Cervical cancer is the 4th most common cancer in women (and the 4th leading cause of cancer death in women) globally. The research work conducted contributes to a more efficient detection of pre-malignant intraepithelial lesions.
This publication describes the creation of a new AI/ML tool for pathological diagnosis that allows the detection and classification of low-grade and high-grade pre-malignant lesions (LSIL/HSIL) of the cervix.
The development of this algorithm was carried out on whole-slide images, unlike the usual cropped images, and based on 2000 slides, representing a unique dataset and an effective improvement in the clinical diagnostic process.
“A CAD system for automatic dysplasia grading on H&E cervical whole-slide images” is the title of the new article published in the “Scientific Reports”.
This is the latest scientific article published by the team that integrates IMP Diagnostics and INESC-TEC researchers.
Access the Scientific Article here.