Striano, Vincenzo Junior (A.A. 2022/2023) ODF semi-supervised learning, computer vision, andmachine learning for cervical cancer detection and other applications in healthcare. Tesi di Laurea in Machine learning, Luiss Guido Carli, relatore Giuseppe Francesco Italiano, pp. 67. [Master's Degree Thesis]

Full text for this thesis not available from the repository.

Abstract/Index

Medical overview. Cytology and traditional pap smear overview. Cervical cell abnormalities. AgNOR staining technique. Technical overview. Machine learning. Deep learning and artificial neural networks. Computer vision. Optimization and genetic algorithms. Dataset used and exploration. SIPakMeD dataset. CCAgT: images of cervical cells with AgNOR stain technique. Yolov8n image detection to avoid undersampling. AgNOR staining techniques. Visualizing the dataset using t-SNE. Assessing the predictive performance of silver-treated cell images using CNN. Assessing the predictive performance PAP-treated cell images using CNN. Naively assessing AgNORs number predictive performance using the correlation coefficient. Optimized derived features semi-supervised learning: the general approach. Optimized derived features semi-supervised learning: building the labeling machine using a clustering algorithm. Data science and computer vision for Covid-19 diagnosis based on chest X-ray.

References

Bibliografia: pp. 63-66.

Thesis Type:	Master's Degree Thesis
Institution:	Luiss Guido Carli
Degree Program:	Master's Degree Programs > Master's Degree Program in Data Science e Management (LM-91)
Chair:	Machine learning
Thesis Supervisor:	Italiano, Giuseppe Francesco
Thesis Co-Supervisor:	Sinaimeri, Blerina
Academic Year:	2022/2023
Session:	Summer
Deposited by:	Alessandro Perfetti
Date Deposited:	09 Jan 2024 14:07
Last Modified:	09 Jan 2024 14:07
URI:	https://tesi.luiss.it/id/eprint/37431

Downloads

Repository Staff Only

View Item