La Recherche de Deepecho sur l’Automatisation de la Biométrie Fœtale et du Volume du Liquide Amniotique Publiée dans Nature Communications
We are proud to announce that our groundbreaking work at Deepecho, titled “Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning,” has been published in Nature Communications. This publication marks a significant milestone in our mission to revolutionize prenatal care through cutting-edge AI technology.
Our research showcases the successful application of a Deep Learning algorithm, trained on a vast cohort of Moroccan and international patients, to automate fetal biometry and amniotic fluid volume assessments. The approach was rigorously tested on 172 patients, demonstrating narrower limits of agreement compared to expert physicians. This advancement is crucial for diagnosing life-threatening conditions, particularly in regions where access to quality prenatal care is limited, both in the Global South and the Global North. Efforts like these are essential to reducing fetal and maternal mortality rates, contributing to the achievement of #SDG3.
Acknowledgments
We are deeply grateful to all the physicians who contributed to this work: Pr. Dalal Laoudiyi, Pr. Amine Lamrissi, Pr. Hanane Saadi, Dr. Mustapha Akiki, Pr. Amal Bouziyane, Pr. Mohamed Jalal, and Pr. Said Bouhya. Our sincere thanks go out to their respective hospitals—CHU Ibn Rochd, Hôpital Universitaire International Cheikh Khalifa, Centre hospitalier universitaire Mohammed VI – Oujda, and Centre de Radiologie Abou Madi—for their unwavering support.
A special thank you to Bouabid Badaoui and Youssef Oulhote, whose expertise in statistics helped us make sense of our data. We also extend our gratitude to the exceptional team at Deepecho, including Youssef Bouyakhf, HOUNKA Salaheddine, Taha Rehah, El Houssine BOUYAKHF, and Abdelhak MAHMOUDI. Leïla Noureddine, our clinical team leader, played a vital role in managing the annotation workflow, and we are immensely thankful for her dedication.
We would also like to acknowledge our advisor and co-author, Musa Mhlanga, whose guidance has been invaluable since day one. Ilias Jennane’s trust and leadership have been instrumental in pushing our work forward.
This achievement would not have been possible without the early support from our friends and sponsors at UM6P Ventures and UM6P – Mohammed VI Polytechnic University, who continue to foster innovation in Morocco and Africa.
You can read the full publication in Nature Communications: https://www.nature.com/articles/s41467-023-42438-5.