Artificial intelligence in reproductive medicine

Wang, Renjie; Pan, Wei; Jin, Lei; Li, Yuehan; Geng, Yichao; Gao, Chun; Chen, Gang; Wang, Hui; Ma, Ding; Liao, Shujie

doi:10.1530/rep-18-0523

Cited by 140 publications

(107 citation statements)

References 128 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Convolutional neural network (CNN), a kind of an artificial neural network, has shown excellent promise in reading fundus and skin photographs 16 , 17 . Machine learning has therefore been rapidly incorportaed in radiology, cardiology, gastroenterology, and even reproductive medicine 18 – 21 . Machine learning has already been introduced in colposcopic imaging; however, available evidence on its specificity and sensitivity is limited, preventing its full use in this field 22 , 23 .…”

Section: Introductionmentioning

confidence: 99%

Classification of cervical neoplasms on colposcopic photography using deep learning

Cho

Choi

Lee

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Colposcopy is widely used to detect cervical cancers, but experienced physicians who are needed for an accurate diagnosis are lacking in developing countries. Artificial intelligence (AI) has been recently used in computer-aided diagnosis showing remarkable promise. In this study, we developed and validated deep learning models to automatically classify cervical neoplasms on colposcopic photographs. Pre-trained convolutional neural networks were fine-tuned for two grading systems: the cervical intraepithelial neoplasia (CIN) system and the lower anogenital squamous terminology (LAST) system. The multi-class classification accuracies of the networks for the CIN system in the test dataset were 48.6 ± 1.3% by Inception-Resnet-v2 and 51.7 ± 5.2% by Resnet-152. The accuracies for the LAST system were 71.8 ± 1.8% and 74.7 ± 1.8%, respectively. The area under the curve (AUC) for discriminating high-risk lesions from low-risk lesions by Resnet-152 was 0.781 ± 0.020 for the CIN system and 0.708 ± 0.024 for the LAST system. The lesions requiring biopsy were also detected efficiently (AUC, 0.947 ± 0.030 by Resnet-152), and presented meaningfully on attention maps. These results may indicate the potential of the application of AI for automated reading of colposcopic photographs. Cervical cancer is the fourth most common cancer in women worldwide, and the second most common cancer among females in developing countries 1. Screening is the principal prevention method aimed at reducing mortality rates. Screening includes certain steps, including population-based Papanicolaou (Pap) testing, colposcopydirected biopsy of suspicious lesions, and the treatment of confirmed pre-cancer lesions 2,3. In women with low-grade intraepithelial lesions (LSIL) or high-grade intraepithelial lesions (HSIL), the risk of pre-cancer is medium to high, and immediate referral for colposcopy is necessary. However, referring all women with atypical squamous cells of undetermined significance (ASC-US) is considered inefficient, as the risk of such cases being pre-cancerous is lower 4. Screening programs have been successful in the developed countries, leading to an approximately 80% decrease in the cervical cancer incidence over the past 4 decades. In contrast, the increase in cervical cancer incidence reported in developing countries 5 has been attributed to the unsuccessful implementation of screening programs. This, has been attributed to logistics in health systems, infrastructural inadequacies, and the lack of expert physicians capable of introducing screening programs and follow-up 6 .

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of cervical neoplasms on colposcopic photography using deep learning

Cho

Choi

Lee

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Embryologists may choose to exclusively perform ICSI in these cycles in order to keep high fertilization rates [ 141 ]. Moreover, in this new era of artificial intelligence in IVF laboratories, time-lapse technology, when possible, may provide important information on the development of these embryos [ 142 , 143 ]. Further to that, as poor responders mainly refer to women of advanced maternal age and previous failed attempts, we may consider employing preimplantation genetic testing for aneuploidy to ensure the chromosomal integrity of the embryos prior to embryo transfer [ 144 ].…”

Section: Discussionmentioning

confidence: 99%

The Conundrum of Poor Ovarian Response: From Diagnosis to Treatment

et al. 2020

View full text Add to dashboard Cite

Despite recent striking advances in assisted reproductive technology (ART), poor ovarian response (POR) diagnosis and treatment is still considered challenging. Poor responders constitute a heterogeneous cohort with the common denominator of under-responding to controlled ovarian stimulation. Inevitably, respective success rates are significantly compromised. As POR pathophysiology entails the elusive factor of compromised ovarian function, both diagnosis and management fuel an ongoing heated debate depicted in the literature. From the criteria employed for diagnosis to the plethora of strategies and adjuvant therapies proposed, the conundrum of POR still puzzles the practitioner. What is more, novel treatment approaches from stem cell therapy and platelet-rich plasma intra-ovarian infusion to mitochondrial replacement therapy have emerged, albeit not claiming clinical routine status yet. The complex and time sensitive nature of this subgroup of infertile patients indicates the demand for a consensus on a horizontally accepted definition, diagnosis and subsequent effective treating strategy. This critical review analyzes the standing criteria employed in order to diagnose and aptly categorize POR patients, while it proceeds to critically evaluate current and novel strategies regarding their management. Discrepancies in diagnosis and respective implications are discussed, while the existing diversity in management options highlights the need for individualized management.

show abstract

“…Another study utilized a DL model for automated embryo quality evaluation by analyzing timelapse images [85]. The impact of AI in IVF and embryo selection are viewed in different papers [3,86,14,25].…”

Section: Opportunity Analysis For Ml-based Embryo Selectionmentioning

confidence: 99%

“…It is confirmed that ML algorithms have an advantage over logistic regression for the prediction of the IVF outcome in assisting fertility specialists to counsel their patients and adjusting the appropriate treatment strategy [13]. The fundamental aspects of AI and ML in reproductive medicine were addressed in terms of applications, limitations, and challenges in the review [14].…”

Section: Introductionmentioning

confidence: 99%