Karissa C Hammer1, Victoria S Jiang2, Manoj Kumar Kanakasabapathy3, Prudhvi Thirumalaraju3, Hemanth Kandula3, Irene Dimitriadis4, Irene Souter4, Charles L Bormann5, Hadi Shafiee6. 1. Division of Reproductive Endocrinology and Infertility, Obstetrics and Gynecology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Suite 10A, Boston, MA, 02114, USA. karissa.c.hammer@gmail.com. 2. Division of Reproductive Endocrinology and Infertility, Obstetrics and Gynecology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Suite 10A, Boston, MA, 02114, USA. vjiang2@mgh.harvard.edu. 3. Division of Engineering in Medicine, Brigham and Women's Hospital, Harvard Medical School, 65 Landsdowne Street, Cambridge, MA, 02139, USA. 4. Division of Reproductive Endocrinology and Infertility, Obstetrics and Gynecology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Suite 10A, Boston, MA, 02114, USA. 5. Division of Reproductive Endocrinology and Infertility, Obstetrics and Gynecology, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, Suite 10A, Boston, MA, 02114, USA. cbormann@partners.org. 6. Division of Engineering in Medicine, Brigham and Women's Hospital, Harvard Medical School, 65 Landsdowne Street, Cambridge, MA, 02139, USA. hshafiee@bwh.harvard.edu.
Abstract
PURPOSE: To determine whether convolutional neural networks (CNN) can be used to accurately ascertain the patient identity (ID) of cleavage and blastocyst stage embryos based on image data alone. METHODS: A CNN model was trained and validated over three replicates on a retrospective cohort of 4889 time-lapse embryo images. The algorithm processed embryo images for each patient and produced a unique identification key that was associated with the patient ID at a timepoint on day 3 (~ 65 hours post-insemination (hpi)) and day 5 (~ 105 hpi) forming our data library. When the algorithm evaluated embryos at a later timepoint on day 3 (~ 70 hpi) and day 5 (~ 110 hpi), it generates another key that was matched with the patient's unique key available in the library. This approach was tested using 400 patient embryo cohorts on day 3 and day 5 and number of correct embryo identifications with the CNN algorithm was measured. RESULTS: CNN technology matched the patient identification within random pools of 8 patient embryo cohorts on day 3 with 100% accuracy (n = 400 patients; 3 replicates). For day 5 embryo cohorts, the accuracy within random pools of 8 patients was 100% (n = 400 patients; 3 replicates). CONCLUSIONS: This study describes an artificial intelligence-based approach for embryo identification. This technology offers a robust witnessing step based on unique morphological features of each embryo. This technology can be integrated with existing imaging systems and laboratory protocols to improve specimen tracking.
PURPOSE: To determine whether convolutional neural networks (CNN) can be used to accurately ascertain the patient identity (ID) of cleavage and blastocyst stage embryos based on image data alone. METHODS: A CNN model was trained and validated over three replicates on a retrospective cohort of 4889 time-lapse embryo images. The algorithm processed embryo images for each patient and produced a unique identification key that was associated with the patient ID at a timepoint on day 3 (~ 65 hours post-insemination (hpi)) and day 5 (~ 105 hpi) forming our data library. When the algorithm evaluated embryos at a later timepoint on day 3 (~ 70 hpi) and day 5 (~ 110 hpi), it generates another key that was matched with the patient's unique key available in the library. This approach was tested using 400 patient embryo cohorts on day 3 and day 5 and number of correct embryo identifications with the CNN algorithm was measured. RESULTS: CNN technology matched the patient identification within random pools of 8 patient embryo cohorts on day 3 with 100% accuracy (n = 400 patients; 3 replicates). For day 5 embryo cohorts, the accuracy within random pools of 8 patients was 100% (n = 400 patients; 3 replicates). CONCLUSIONS: This study describes an artificial intelligence-based approach for embryo identification. This technology offers a robust witnessing step based on unique morphological features of each embryo. This technology can be integrated with existing imaging systems and laboratory protocols to improve specimen tracking.