TY - JOUR
T1 - Object detection for automatic cancer cell counting in zebrafish xenografts
AU - Albuquerque, Carina
AU - Vanneschi, Leonardo
AU - Henriques, Roberto
AU - Castelli, Mauro
AU - Póvoa, Vanda
AU - Fior, Rita
AU - Papanikolaou, Nickolas
N1 - info:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FCCI-INF%2F29168%2F2017/PT#
Albuquerque, C., Vanneschi, L., Henriques, R., Castelli, M., Póvoa, V., Fior, R., & Papanikolaou, N. (2021). Object detection for automatic cancer cell counting in zebrafish xenografts. PLoS ONE, 16(11), 1-28. [e0260609]. https://doi.org/10.1371/journal.pone.0260609 -----------------------------------------This work was supported by national funds through FCT (Fundaçâo para a Ciência e a Tecnologia), under project PTDC/CCI-INF/29168/2017 (BINDER). Mauro Castelli acknowledges the financial support from the Slovenian Research Agency (research core funding no. P5-0410).
PY - 2021/11/29
Y1 - 2021/11/29
N2 - Cell counting is a frequent task in medical research studies. However, it is often performed manually; thus, it is time-consuming and prone to human error. Even so, cell counting automation can be challenging to achieve, especially when dealing with crowded scenes and overlapping cells, assuming different shapes and sizes. In this paper, we introduce a deep learning-based cell detection and quantification methodology to automate the cell counting process in the zebrafish xenograft cancer model, an innovative technique for studying tumor biology and for personalizing medicine. First, we implemented a fine-tuned architecture based on the Faster R-CNN using the Inception ResNet V2 feature extractor. Second, we performed several adjustments to optimize the process, paying attention to constraints such as the presence of overlapped cells, the high number of objects to detect, the heterogeneity of the cells’ size and shape, and the small size of the data set. This method resulted in a median error of approximately 1% of the total number of cell units. These results demonstrate the potential of our novel approach for quantifying cells in poorly labeled images. Compared to traditional Faster R-CNN, our method improved the average precision from 71% to 85% on the studied data set.
AB - Cell counting is a frequent task in medical research studies. However, it is often performed manually; thus, it is time-consuming and prone to human error. Even so, cell counting automation can be challenging to achieve, especially when dealing with crowded scenes and overlapping cells, assuming different shapes and sizes. In this paper, we introduce a deep learning-based cell detection and quantification methodology to automate the cell counting process in the zebrafish xenograft cancer model, an innovative technique for studying tumor biology and for personalizing medicine. First, we implemented a fine-tuned architecture based on the Faster R-CNN using the Inception ResNet V2 feature extractor. Second, we performed several adjustments to optimize the process, paying attention to constraints such as the presence of overlapped cells, the high number of objects to detect, the heterogeneity of the cells’ size and shape, and the small size of the data set. This method resulted in a median error of approximately 1% of the total number of cell units. These results demonstrate the potential of our novel approach for quantifying cells in poorly labeled images. Compared to traditional Faster R-CNN, our method improved the average precision from 71% to 85% on the studied data set.
UR - https://github.com/calbuquerque-novaims/PLOS-ONE
UR - http://www.scopus.com/inward/record.url?scp=85120384966&partnerID=8YFLogxK
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000752076100109
U2 - 10.1371/journal.pone.0260609
DO - 10.1371/journal.pone.0260609
M3 - Article
SN - 1932-6203
VL - 16
SP - 1
EP - 28
JO - PLoS ONE
JF - PLoS ONE
IS - 11
M1 - e0260609
ER -