@article { , title = {Detection of morphological changes caused by chemical stress in the cyanobacterium Planktothrix agardhii using convolutional neural networks.}, abstract = {The presence of harmful algal bloom in many reservoirs around the world, alongside the lack of sanitation law/ordinance regarding cyanotoxin monitoring (particularly in developing countries), create a scenario in which the local population could potentially chronically consume cyanotoxin-contaminated waters. Therefore, it is crucial to develop low cost tools to detect possible systems failures and consequent toxin release inferred by morphological changes of cyanobacteria in the raw water. This paper aimed to look for the best combination of convolutional neural network (CNN), optimizer and image segmentation technique to differentiate P. agardhii trichomes before and after chemical stress caused by the addition of hydrogen peroxide. This method takes a step towards accurate monitoring of cyanobacteria in the field without the need for a mobile lab. After testing three different network architectures (AlexNet, 3ConvLayer and 2ConvLayer), four different optimizers (Adam, Adagrad, RMSProp and SDG) and five different image segmentations methods (Canny Edge Detection, Morphological Filter, HP filter, GrabCut and Watershed), the combination 2ConvLayer with Adam optimizer and GrabCut segmentation, provided the highest median accuracy (93.33\%) for identifying H2O2-induced morphological changes in P. agardhii. Our results emphasize the fact that the trichome classification problem can be adequately tackled with a limited number of learned features due to the lack of complexity in micrographs from before and after chemical stress. To the authors knowledge, this is the first time that CNNs were applied to detect morphological changes in cyanobacteria caused by chemical stress. Thus, it is a significant step forward in developing low cost tools based on image recognition, to shield water consumers, especially in the poorest regions, against cyanotoxin-contaminated water.}, doi = {10.1016/j.scitotenv.2021.146956}, eissn = {1879-1026}, issn = {0048-9697}, journal = {Science of the total environment}, note = {INFO COMPLETE (Now published, checked and updated 26/4/2021 LM; In Press, checked and updated 7/4/20201 LM; awaiting revisions before re-submitting 29/3/2021 LM; notified by email from contact, forwarding email re provisional acceptance pending edits resulting from peer-review 09.03.21 GB) PERMISSION GRANTED (block grant funds set aside to pay for Gold OA 09.03.21 GB) DOCUMENT READY (VOR now downloaded 13/5/2021 LM; uploaded AAM while awaiting Gold publication 26/4/2021 LM: AAM not yet ready to be sent, VOR not yet available; to be chased before the end of 19.03.2021 by GB; 09.03.21 GB) ADDITIONAL INFO: Linda Lawton; Carlos Pestana; Pam Johnston}, publicationstatus = {Published}, publisher = {Elsevier}, url = {https://rgu-repository.worktribe.com/output/1254826}, volume = {784}, keyword = {Environmental Engineering, Cyanobacteria, CNN, Water treatment, Hydrogen peroxide, Image recognition, Image segmentation}, year = {2021}, author = {Carloto, Ismael and Johnston, Pamela and Pestana, Carlos J. and Lawton, Linda A.} }