Supervised and weakly supervised counting-by-segmentation: the fluorescent microscopy use case

Morelli, Roberto (2023) Supervised and weakly supervised counting-by-segmentation: the fluorescent microscopy use case, [Dissertation thesis], Alma Mater Studiorum Università di Bologna. Dottorato di ricerca in Data science and computation, 34 Ciclo. DOI 10.48676/unibo/amsdottorato/10996.
Documenti full-text disponibili:
[img] Documento PDF (English) - Richiede un lettore di PDF come Xpdf o Adobe Acrobat Reader
Disponibile con Licenza: Creative Commons Attribution Non-commercial No Derivatives 4.0 (CC BY-NC-ND 4.0) .
Download (32MB)


This thesis focuses on automating the time-consuming task of manually counting activated neurons in fluorescent microscopy images, which is used to study the mechanisms underlying torpor. The traditional method of manual annotation can introduce bias and delay the outcome of experiments, so the author investigates a deep-learning-based procedure to automatize this task. The author explores two of the main convolutional-neural-network (CNNs) state-of-the-art architectures: UNet and ResUnet family model, and uses a counting-by-segmentation strategy to provide a justification of the objects considered during the counting process. The author also explores a weakly-supervised learning strategy that exploits only dot annotations. The author quantifies the advantages in terms of data reduction and counting performance boost obtainable with a transfer-learning approach and, specifically, a fine-tuning procedure. The author released the dataset used for the supervised use case and all the pre-training models, and designed a web application to share both the counting process pipeline developed in this work and the models pre-trained on the dataset analyzed in this work.

Tipologia del documento
Tesi di dottorato
Morelli, Roberto
Dottorato di ricerca
Settore disciplinare
Settore concorsuale
Parole chiave
deep learning, fluorescent microscopy, neuronal cells, ResUnet, counting objects, Image segmentation
Data di discussione
16 Giugno 2023

Altri metadati

Statistica sui download

Gestione del documento: Visualizza la tesi