|
1
|
Miyagi Y, Habara T, Hirata R, Hayashi N. Predicting a live birth by artificial intelligence incorporating both the blastocyst image and conventional embryo evaluation parameters. Artif Intell Med Imaging 2020. [DOI: 10.35711/wjbc.v1.i3.87] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/06/2023] Open
|
|
2
|
Miyagi Y, Habara T, Hirata R, Hayashi N. Predicting a live birth by artificial intelligence incorporating both the blastocyst image and conventional embryo evaluation parameters. Artif Intell Med Imaging 2020; 1:94-107. [DOI: 10.35711/aimi.v1.i3.94] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/24/2020] [Revised: 09/15/2020] [Accepted: 09/19/2020] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND The achievement of live birth is the goal of assisted reproductive technology in reproductive medicine. When the selected blastocyst is transferred to the uterus, the degree of implantation of the blastocyst is evaluated by microscopic inspection, and the result is only about 30%-40%, and the method of predicting live birth from the blastocyst image is unknown. Live births correlate with several clinical conventional embryo evaluation parameters (CEE), such as maternal age. Therefore, it is necessary to develop artificial intelligence (AI) that combines blastocyst images and CEE to predict live births.
AIM To develop an AI classifier for blastocyst images and CEE to predict the probability of achieving a live birth.
METHODS A total of 5691 images of blastocysts on the fifth day after oocyte retrieval obtained from consecutive patients from January 2009 to April 2017 with fully deidentified data were retrospectively enrolled with explanations to patients and a website containing additional information with an opt-out option. We have developed a system in which the original architecture of the deep learning neural network is used to predict the probability of live birth from a blastocyst image and CEE.
RESULTS The live birth rate was 0.387 (= 1587/4104 cases). The number of independent clinical information for predicting live birth is 10, which significantly avoids multicollinearity. A single AI classifier is composed of ten layers of convolutional neural networks, and each elementwise layer of ten factors is developed and obtained with 42792 as the number of training data points and 0.001 as the L2 regularization value. The accuracy, sensitivity, specificity, negative predictive value, positive predictive value, Youden J index, and area under the curve values for predicting live birth are 0.743, 0.638, 0.789, 0.831, 0.573, 0.427, and 0.740, respectively. The optimal cut-off point of the receiver operator characteristic curve is 0.207.
CONCLUSION AI classifiers have the potential of predicting live births that humans cannot predict. Artificial intelligence may make progress in assisted reproductive technology.
Collapse
Affiliation(s)
- Yasunari Miyagi
- Department of Artificial Intelligence, Medical Data Labo, Okayama 703-8267, Japan
- Department of Gynecologic Oncology, Saitama Medical University International Medical Center, Hidaka 350-1298, Saitama, Japan
| | - Toshihiro Habara
- Department of Reproduction, Okayama Couples' Clinic, Okayama 701-1152, Japan
| | - Rei Hirata
- Department of Reproduction, Okayama Couples' Clinic, Okayama 701-1152, Japan
| | - Nobuyoshi Hayashi
- Department of Reproduction, Okayama Couples' Clinic, Okayama 701-1152, Japan
| |
Collapse
|
|
3
|
Badawy SZ, Singer S. Proximal Tubal Obstruction: Pathogenesis and Management. J Gynecol Surg 2019. [DOI: 10.1089/gyn.2019.0044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Affiliation(s)
- Shawky Z. Badawy
- Department of Obstetrics and Gynecology, SUNY Upstate Medical University, Syracuse, NY
| | - Stuart Singer
- Department of Interventional Radiology, Crouse Hospital, Syracuse, NY
| |
Collapse
|
|
4
|
Miyagi Y, Habara T, Hirata R, Hayashi N. Feasibility of predicting live birth by combining conventional embryo evaluation with artificial intelligence applied to a blastocyst image in patients classified by age. Reprod Med Biol 2019; 18:344-356. [PMID: 31607794 PMCID: PMC6780028 DOI: 10.1002/rmb2.12284] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2019] [Revised: 05/21/2019] [Accepted: 06/02/2019] [Indexed: 12/12/2022] Open
Abstract
PURPOSE To identify the multivariate logistic regression in a combination (combination method) involving artificial intelligence (AI) classifiers in images of blastocysts along with a conventional embryo evaluation (CEE) to predict the probability of accomplishing a live birth in patients classified by maternal age. METHODS Retrospectively, a total of 5691 blastocysts were enrolled. Images captured 115 hours or 139 hours if not yet sufficiently large after insemination were classified according to age as follows: <35, 35-37, 38-39, 40-41, and ≥42 years old. The classifiers for each category were created by using convolutional neural networks associated with deep learning. Next, the feasibility of a method combining AI with multivariate logistic model functions by CEE was investigated. RESULTS The values of the area under the curve (AUC) and the accuracies to predict live birth achieved by the CEE/AI/combination methods were 0.651/0.634/0.655, 0.697/0.688/0.723, 0.771/0.728/0.791, 0.788/0.743/0.806 and 0.820/0.837/0.888, and 0.631/0.647/0.616, 0.687/0.675/0.671, 0.725/0.697/0.732, 0.714/0.776/0.801, and 0.910/0.866/0.784 for age categories of <35, 35-37, 38-39, 40-41, and ≥42 years old, respectively. CONCLUSIONS Though there were mostly no significant differences regarding the AUC and the sensitivity plus specificity in all age categories, the combination method seemed to be the best.
Collapse
Affiliation(s)
- Yasunari Miyagi
- Medical Data LaboOkayama CityJapan
- Department of Gynecologic OncologySaitama Medical University International Medical CenterHidaka CityJapan
| | | | - Rei Hirata
- Okayama Couple’s ClinicOkayama CityJapan
| | | |
Collapse
|
|
5
|
Miyagi Y, Habara T, Hirata R, Hayashi N. Feasibility of artificial intelligence for predicting live birth without aneuploidy from a blastocyst image. Reprod Med Biol 2019; 18:204-211. [PMID: 30996684 PMCID: PMC6452008 DOI: 10.1002/rmb2.12267] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2018] [Revised: 01/01/2019] [Accepted: 01/28/2019] [Indexed: 01/22/2023] Open
Abstract
PURPOSE To make the artificial intelligence (AI) classifiers of the image of the blastocyst implanted later in order to predict the probability of achieving live birth. METHODS A system for using the machine learning approaches, which are logistic regression, naive Bayes, nearest neighbors, random forest, neural network, and support vector machine, of artificial intelligence to predict the probability of live birth from a blastocyst image was developed. Eighty images of blastocysts that led to live births and 80 images of blastocysts that led to aneuploid miscarriages were used to create an AI-based method with 5-fold cross-validation retrospectively for classifying embryos. RESULTS The logistic regression method showed the best results. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 0.65, 0.60, 0.70, 0.67, and 0.64, respectively. Area under the curve was 0.65 ± 0.04 (mean ± SE). Estimated probability of belonging to the live birth category was found significantly related to the probability of live birth (P < 0.005). CONCLUSIONS Classifiers using artificial intelligence applied toward a blastocyst image have a potential to show the probability of live birth being the outcome.
Collapse
Affiliation(s)
- Yasunari Miyagi
- Medical Data LaboOkayama CityJapan
- Department of Gynecologic OncologySaitama Medical University International Medical CenterHidaka CityJapan
| | | | - Rei Hirata
- Okayama Couple’s ClinicOkayama CityJapan
| | | |
Collapse
|
|
6
|
Miyagi Y, Habara T, Hirata R, Hayashi N. Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age. Reprod Med Biol 2019; 18:190-203. [PMID: 30996683 PMCID: PMC6452012 DOI: 10.1002/rmb2.12266] [Citation(s) in RCA: 31] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2018] [Revised: 01/02/2019] [Accepted: 01/28/2019] [Indexed: 02/01/2023] Open
Abstract
PURPOSE To identify artificial intelligence (AI) classifiers in images of blastocysts to predict the probability of achieving a live birth in patients classified by age. Results are compared to those obtained by conventional embryo (CE) evaluation. METHODS A total of 5691 blastocysts were retrospectively enrolled. Images captured 115 hours after insemination (or 139 hours if not yet large enough) were classified according to maternal age as follows: <35, 35-37, 38-39, 40-41, and ≥42 years. The classifiers for each category and a classifier for all ages were related to convolutional neural networks associated with deep learning. Then, the live birth functions predicted by the AI and the multivariate logistic model functions predicted by CE were tested. The feasibility of the AI was investigated. RESULTS The accuracies of AI/CE for predicting live birth were 0.64/0.61, 0.71/0.70, 0.78/0.77, 0.81/0.83, 0.88/0.94, and 0.72/0.74 for the age categories <35, 35-37, 38-39, 40-41, and ≥42 years and all ages, respectively. The sum value of the sensitivity and specificity revealed that AI performed better than CE (P = 0.01). CONCLUSIONS AI classifiers categorized by age can predict the probability of live birth from an image of the blastocyst and produced better results than were achieved using CE.
Collapse
Affiliation(s)
- Yasunari Miyagi
- Medical Data LaboOkayama CityJapan
- Department of Gynecologic OncologySaitama Medical University International Medical CenterHidaka CityJapan
| | | | - Rei Hirata
- Okayama Couple’s ClinicOkayama CityJapan
| | | |
Collapse
|
|
7
|
Evaluation of hysteroscopic tubal cannulation under laparoscopic control versus intracytoplasmic sperm injection in cases with proximal tubal obstruction. ACTA ACUST UNITED AC 2013. [DOI: 10.1097/01.ebx.0000431014.27511.a1] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
|
8
|
Allahbadia GN, Mangeshikar P, Dhungat PBP, Desai SK, Gudi AA, Arya A. Hysteroscopic fallopian tube recanalization using a flexible guide cannula and hydrophilic guide wire. ACTA ACUST UNITED AC 2001. [DOI: 10.1046/j.1365-2508.2000.00295.x] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
|
9
|
Transcervical Fallopian Tube Recanalization. J Vasc Interv Radiol 2000. [DOI: 10.1016/s1051-0443(00)70012-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022] Open
|
|
10
|
Abstract
OBJECTIVE To review the physiology, pathology, and treatment of proximal tubal disease. DATA IDENTIFICATION Relevant reports on the pathophysiology of proximal tubal disease were reviewed. All studies in English of microsurgery and macrosurgery, and of radiographic and hysteroscopic cannulation in women with proximal tubal blockage were identified through MEDLINE searches. STUDY SELECTION All studies of therapy for proximal blockage that included pregnancy rates were considered. Series of sterilization reversals, series of unilateral or combined procedures, and series in which the location of tubal blockage was not given were excluded from the data analyses. DATA ANALYSIS Raw data were assessed for homogeneity, then standardized and pooled. Total and ongoing pregnancy rates after microsurgery and macrosurgery, as well as radiographic and hysteroscopic transcervical cannulation, were compared by the chi2 test. Relative risks for total and ongoing pregnancies were calculated for all treatment methods. RESULT(S) This meta-analysis suggests that, overall, microsurgical anastomosis results in higher total and ongoing pregnancy rates than macrosurgery or radiographic tubal cannulation. However, pregnancy rates in selected series of transcervical tubal cannulation are similar to those reported for microsurgery. CONCLUSION(S) Ongoing intrauterine pregnancy rates near 50% can be achieved in patients with proximal blockage of the fallopian tube. Selective salpingography and transcervical cannulation under fluoroscopic guidance are effective at establishing patency in appropriately selected patients and are less invasive and costly than the surgical alternatives.
Collapse
Affiliation(s)
- G M Honoré
- Department of Obstetrics and Gynecology, University of Texas Health Science Center at San Antonio, 78284-7836, USA.
| | | | | |
Collapse
|
|
11
|
|
|
12
|
Surrey ES, Adamson GD, Nagel TC, Malo JW, Surrey MW, Jansen R, Molloy D. Multicenter feasibility study of a new coaxial falloposcopy system. THE JOURNAL OF THE AMERICAN ASSOCIATION OF GYNECOLOGIC LAPAROSCOPISTS 1997; 4:473-8. [PMID: 9224583 DOI: 10.1016/s1074-3804(05)80042-8] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
We compared falloposcopy employing a new coaxial system with traditional laparoscopic chromotubation and hysterosalpingography in a prospective, multicenter clinical trial at five tertiary infertility centers. Based on findings at hysterosalpingography or laparoscopic chromotubation, the 16 women (22 tubes) in group 1 had a presumed diagnosis of proximal tubal obstruction, and the 4 (7 tubes) in group 2 had unexplained infertility. Cannulation was successfully achieved in 83.3% of tubes. In group 1, 85% (17/20) of visualized tubes were patent and 35% (7/20) were normal. In group 2, 40% (2/5) of visualized tubes were abnormal. Management was changed in 52.4% of women as a result of falloposcopic findings. Falloposcopy with this new coaxial system allows improved visualization with less bulky and less traumatic instruments. The system provides valuable information regarding the fallopian tube lumen that correlates poorly with that obtained with more traditional techniques.
Collapse
Affiliation(s)
- E S Surrey
- Department of Obstetrics and Gynecology, UCLA, Los Angeles, California, USA
| | | | | | | | | | | | | |
Collapse
|
|
13
|
|
|
14
|
Thompson KA, Kiltz RJ, Koci T, Cabus ET, Kletzky OA. Transcervical fallopian tube catheterization and recanalization for proximal tubal obstruction**Presented in part at the Pacific Coast Fertility Society, Indian Wells, California, April 16, 1993. Fertil Steril 1994. [DOI: 10.1016/s0015-0282(16)56510-8] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
|
15
|
Kerin JF, Williams DB, San Roman GA, Pearlstone AC, Grundfest WS, Surrey ES. Falloposcopic classification and treatment of fallopian tube lumen disease. Fertil Steril 1992; 57:731-41. [PMID: 1555683 DOI: 10.1016/s0015-0282(16)54951-6] [Citation(s) in RCA: 52] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
OBJECTIVE To devise a diagnostic classification and scoring system for tubal lumen disease based on falloposcopy and to evaluate it against tuboplasty procedures and pregnancy outcomes. DESIGN Prospective study approved by the hospital Institutional Review Board. SETTING Academic tertiary infertility center. PATIENTS Seventy-five women with hysterosalpingographic and laparoscopic evidence of endotubal disease had 112 tubes available for falloposcopic evaluation. INTERVENTION Diagnostic and operative falloposcopy was performed, when indicated, using aquadissection, flexible wire cannulation, or direct balloon tuboplasty. RESULTS The endotubal lumens were considered to be falloposcopically normal in 52 tubes (46%), to contain mild to moderate disease in 33 (29%), and severe to obstructive disease in 27 (25%) cases. Within a year of the procedure, 6 of the 28 women (21%) in whom at least 1 tube was normal conceived, in 2 of 22 (9%) with mild to moderate disease, and in 0 of 16 (0%) with severe endotubal disease. CONCLUSIONS Falloposcopy provides a visual means of scoring endotubal disease and may be intrinsically therapeutic for dislodging intraluminal debris and breaking down filmy adhesions in normal or minimally diseased tubes. The presence of severe disease remains resistant to the use of current endotuboplasty treatments as reflected by poor pregnancy outcome, and such women should be provided the option of microsurgical tubal repair or in vitro fertilization and embryo transfer procedures.
Collapse
Affiliation(s)
- J F Kerin
- Cedars-Sinai Medical Center, Los Angeles, California
| | | | | | | | | | | |
Collapse
|
|
16
|
Forman RG, Chapman MG. Therapeutic uses of transcervical catheterization of the fallopian tubes. BRITISH JOURNAL OF OBSTETRICS AND GYNAECOLOGY 1992; 99:178-80. [PMID: 1606111 DOI: 10.1111/j.1471-0528.1992.tb14493.x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Affiliation(s)
- R G Forman
- Department of Obstetrics and Gynaecology, Guy's Hospital, London
| | | |
Collapse
|
|
17
|
Lisse K, Sydow P. Fallopian tube catheterization and recanalization under ultrasonic observation: a simplified technique to evaluate tubal patency and open proximally obstructed tubes. Fertil Steril 1991; 56:198-201. [PMID: 1830006 DOI: 10.1016/s0015-0282(16)54471-9] [Citation(s) in RCA: 21] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
OBJECTIVE To test a sonoscopic technique developed for transvaginal catheterization and recanalization of the fallopian tube. DESIGN In a feasibility study, catheterization was performed with the use of laparoscopic control. Patients with bilateral proximal tubal obstruction underwent fallopian tube recanalization under ultrasonic observation. SETTING This study represents patients evaluated for primary or secondary infertility at Humboldt University Hospital. PATIENTS, PARTICIPANTS Proximal tubal obstruction had been diagnosed on previous hysterosalpingogram and with laparoscopy. INTERVENTIONS None. MAIN OUTCOME MEASURE Tubal patency was assessed by hydrotubation under ultrasonic observation. RESULTS Transvaginal catheterization was successful in 31 (91.2%) of the 34 tubes. In 19 patients with proximal tubal obstruction, patency of both or at least one tube was achieved in 16 (84.2%) women. Five (31.6%) of 16 patients successfully recanalized were found to have an intrauterine pregnancy at a 6-month follow-up interval. CONCLUSION This catheterization technique should be investigated for possible use in diagnostic schedule early in the evaluation of the infertile patient. Also, the transvaginal recanalization of proximally obstructed tubes calls into question the application of microsurgical treatment of a selected group of patients.
Collapse
Affiliation(s)
- K Lisse
- Department of Obstetrics and Gynecology, Humboldt University Medical Center Charité, Berlin, Germany
| | | |
Collapse
|