1 January 2022 in Reproductive Medicine and Biology
Purpose: To create and evaluate a machine‐learning model for YOLOv3 that can simultaneously perform morphological evaluation and tracking in a short time, which can be adapted to video data under an inverted microscope.Methods: Japanese patients who underwent intracytoplasmic sperm injection at the Jikei University School of Medicine and Keiai Reproductive and Endosurgical Clinic from January 2019 to March 2020 were included. An AI model that simultaneously performs morphological assessment and tracking was created and its performance was evaluated.Results: For morphological assessment, the sensitivity and positive predictive value (PPV) of this model for abnormal sperm were 0.881 and 0.853, respectively. The sensitivity and PPV for normal sperm were 0.794 and 0.689, respectively. For tracking performance, among the 51 objects, 40 (78.4%) were mostly tracked, 11 (21.6%) were partially tracked, and 0 (0%) were mostly lost.Conclusions: This study showed that evaluating sperm morphology while tracking in a single model is possible by training YOLO v3. This model could acquire time‐series data of one sperm, which will assist in acquiring and annotating sperm image data.
14 December 2015 in Physical Review B
We studied the physical properties of hollandite titanates, , which have double chains of edge-sharing octahedra with electrons in the states. We found that there is an electronic phase transition at K, at which various properties exhibit anomalies. This phase transition is characterized by a modulation in the chains and a spectral weight transfer of over 2 eV in the optical conductivity spectrum, which are presumably caused by charge and orbital ordering of the Ti electrons.
19 March 2021 in Reproductive Medicine and Biology
Purpose: To provide information about the relationship between follow‐up period and follicular development in patients with infertility due to premature ovarian insufficiency (POI) who are undergoing hormone replacement therapy (HRT). It is necessary to detect follicle development for artificial insemination or in vitro fertilization.Methods: This retrospective cohort study was conducted at a university hospital in Tokyo, Japan, from April 2014 to February 2019 in 20 patients [follicular development group, 11 women (55%); non‐follicular development group, 9 women (45%)] with POI; their follicular development was followed up weekly. Background characteristics, including age, follicle‐stimulating hormone (FSH) and anti‐Mullerian hormone levels (AMH), the period from the last spontaneous menstruation to hormone replacement therapy initiation, and follow‐up period during HRT were investigated. The period without follicular development was tabulated, and the subsequent cumulative follicular development detection rate was calculated.Results: At least 1‐year follow‐up, the cumulative follicular development rate was 70%; follicular development was observed with a probability of 49.1% at 3 months, 33.4% at 6 months, and 8.3% at 12 months in the follow‐up period.Conclusions: The results show that the longer the non‐follicle development period, the lower the probability of subsequent follicular development in patients with POI during HRT.