Hisham Abdeltawab1, Fahmi Khalifa1, Kamal Hammouda1, Jessica M Miller2, Moustafa M Meki2, Qinghui Ou2, Ayman El-Baz3, Tamer M A Mohamed4. 1. BioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY, USA. 2. Division of Cardiovascular Medicine, Department of Medicine, University of Louisville, Louisville, KY, USA. 3. BioImaging Laboratory, Department of Bioengineering, University of Louisville, Louisville, KY, USA. aselba01@louisville.edu. 4. Division of Cardiovascular Medicine, Department of Medicine, University of Louisville, Louisville, KY, USA. Tamer.mohamed@louisville.edu.
Abstract
PURPOSE: Drug induced cardiac toxicity is a disruption of the functionality of cardiomyocytes which is highly correlated to the organization of the subcellular structures. We can analyze cellular structures by utilizing microscopy imaging data. However, conventional image analysis methods might miss structural deteriorations that are difficult to perceive. Here, we propose an image-based deep learning pipeline for the automated quantification of drug induced structural deteriorations using a 3D heart slice culture model. METHODS: In our deep learning pipeline, we quantify the induced structural deterioration from three anticancer drugs (doxorubicin, sunitinib, and herceptin) with known adverse cardiac effects. The proposed deep learning framework is composed of three convolutional neural networks that process three different image sizes. The results of the three networks are combined to produce a classification map that shows the locations of the structural deteriorations in the input cardiac image. RESULTS: The result of our technique is the capability of producing classification maps that accurately detect drug induced structural deterioration on the pixel level. CONCLUSION: This technology could be widely applied to perform unbiased quantification of the structural effect of the cardiotoxins on heart slices.
PURPOSE: Drug induced cardiac toxicity is a disruption of the functionality of cardiomyocytes which is highly correlated to the organization of the subcellular structures. We can analyze cellular structures by utilizing microscopy imaging data. However, conventional image analysis methods might miss structural deteriorations that are difficult to perceive. Here, we propose an image-based deep learning pipeline for the automated quantification of drug induced structural deteriorations using a 3D heart slice culture model. METHODS: In our deep learning pipeline, we quantify the induced structural deterioration from three anticancer drugs (doxorubicin, sunitinib, and herceptin) with known adverse cardiac effects. The proposed deep learning framework is composed of three convolutional neural networks that process three different image sizes. The results of the three networks are combined to produce a classification map that shows the locations of the structural deteriorations in the input cardiac image. RESULTS: The result of our technique is the capability of producing classification maps that accurately detect drug induced structural deterioration on the pixel level. CONCLUSION: This technology could be widely applied to perform unbiased quantification of the structural effect of the cardiotoxins on heart slices.
Authors: Qinghui Ou; Zoë Jacobson; Riham R E Abouleisa; Xian-Liang Tang; Sajedah M Hindi; Ashok Kumar; Kathryn N Ivey; Guruprasad Giridharan; Ayman El-Baz; Kenneth Brittian; Benjamin Rood; Ying-Hsi Lin; Samuel A Watson; Filippo Perbellini; Timothy A McKinsey; Bradford G Hill; Steven P Jones; Cesare M Terracciano; Roberto Bolli; Tamer M A Mohamed Journal: Circ Res Date: 2019-07-16 Impact factor: 17.367
Authors: Kai Kretzschmar; Yorick Post; Marie Bannier-Hélaouët; Andrea Mattiotti; Jarno Drost; Onur Basak; Vivian S W Li; Maaike van den Born; Quinn D Gunst; Danielle Versteeg; Lieneke Kooijman; Stefan van der Elst; Johan H van Es; Eva van Rooij; Maurice J B van den Hoff; Hans Clevers Journal: Proc Natl Acad Sci U S A Date: 2018-12-07 Impact factor: 11.205
Authors: Jessica M Miller; Moustafa H Meki; Ahmed Elnakib; Qinghui Ou; Riham R E Abouleisa; Xian-Liang Tang; Abou Bakr M Salama; Ahmad Gebreil; Cindy Lin; Hisham Abdeltawab; Fahmi Khalifa; Bradford G Hill; Najah Abi-Gerges; Roberto Bolli; Ayman S El-Baz; Guruprasad A Giridharan; Tamer M A Mohamed Journal: Commun Biol Date: 2022-09-09