Faster region convolutional neural network and semen tracking algorithm for sperm analysis

Devaraj, Somasundaram; Nirmala, M.

doi:10.1016/j.cmpb.2020.105918

Cited by 16 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several reports on tracking motile sperm using deep learning, 20 , 21 , 22 , 23 of which the latest and highest performing ones were reported by Somasundaram et al 12 The sperm with the fastest movement speed was detected in 1.12 se, and the error rate was 2.31 with high accuracy. Those authors dealt with vertical defocus by using a cover glass to drop unstained sperm.…”

Section: Discussionmentioning

confidence: 99%

“… 10 , 11 Studies evaluating sperm motility reported the use of images with a cover glass taken with an upright microscope. 12 When performing ICSI, the embryologist uses an inverted microscope to observe the head and neck of unstained sperm at a low magnification of 400× while at the same time evaluating motility and morphology. To date, there have been no reports of a machine‐learning model that can support such a series of work procedures at the same time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new deep‐learning model using YOLOv3 to support sperm selection during intracytoplasmic sperm injection procedure

Sato

Kishi

Murakata

et al. 2022

Reprod Medicine & Biology

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A new deep‐learning model using YOLOv3 to support sperm selection during intracytoplasmic sperm injection procedure

Sato

Kishi

Murakata

et al. 2022

Reprod Medicine & Biology

View full text Add to dashboard Cite

show abstract

“…Refer to the analysis results of human experts, the proposed sperm detection and tracking algorithm is compared with the following four widely adopted state‐of‐the‐art method for the above ten samples. FRCNN‐THMA [26]: Fast Regional Convolutional Neural Network combined with elliptical scanning method is used to detect human sperm. Tail to Head movement algorithm is employed for the motility analysis and tracking. AWAS [5]: Nafisi et al.…”

Section: Discussionmentioning

confidence: 99%

“…Alabdulla et al [25] proposes a new method to optimize uneven lighting images to improve sperm cells detection, and Kalman filter tracking is used to track sperm cells. Somasundaram et al [26] proposes a faster region CNN (FRCNN) based on elliptic scanning algorithm and a tail head movement algorithm (THMA) for tracking, which improves the accuracy of CASA.…”

Section: Related Workmentioning

confidence: 99%

Efficient detection and robust tracking of spermatozoa in microscopic video

Zhu

Cui

Hou³

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Sperm concentration and motility are generally analysed only in the discrete state in microscopic videos. As for sperm nonspecific aggregation areas, it brings difficulties to accurate sperm detection. In this paper, an algorithm for nonspecific aggregates automatic segmentation, detection and tracking of sperm is proposed. A grid model commensurate with the size of a sperm head is created to segment nonspecific aggregation areas. Multi-scale edge function and new energy functional are designed based on the level set method to realize sperm head segmentation. In the sperm tracking stage, we improve the weight condition and the standard of trust flow quantization based on graph theory method, and simplify the sperm tracking to the vertex matching between two frames to solve the matching failure problem of adjacent frames with small space distance. The proposed method achieves accurate segmentation of sperm non-specific aggregation regions, which outperforms the level set methods of LBF and SBGFR. At the same time, our method can real-time calculation of sperm concentration and motility during sperm tracking. It is compared with four state-of-the-art algorithms, and it gives lower tracking error rates, which has potential applications in male fertility field.

show abstract

“…One study applied artificial intelligence to microscopic images of sperm analysis results to simplify and speed up the process of classifying sperm cells using the faster region convolutional neural network (FRCNN) with elliptic scanning algorithm (ESA). This new method can detect sperm and identify sperm motility within 1.12 seconds with an accuracy of 97.37% [2].…”

Section: Introductionmentioning

confidence: 99%

Predicting the value of sperm analysis using an electronic nose

Wijaya

Kusumaatmaja

Rizal

2022

IJEECS

View full text Add to dashboard Cite

Total motile sperm count and DNA fragmentation Index are two parameters in sperm analysis that have recently been used to determine the outcome of the management of cases of male infertility. Total Motile Sperm Count is one of the values considered better than the 2010 World Health Organization standard sperm analysis in terms of predictive value for the success of the spontaneous ongoing pregnancy rate. High DNA Fragmentation Index values were associated with lower pregnancy success and an increased risk of low fertilization rate or total fertilization failure. In this study, we developed a method to classify sperm analysis based on total motility sperm count and DNA Fragmentation Index values by using an electronic nose. In the total motility sperm count (TMSC) study, we use four algorithms with the result of accuracy values 95% and in the DNA fragmentation Index study, we get a fairly good accuracy value for two algorithms with the accuracy values 70%.

show abstract

Faster region convolutional neural network and semen tracking algorithm for sperm analysis

Cited by 16 publications

References 14 publications

A new deep‐learning model using YOLOv3 to support sperm selection during intracytoplasmic sperm injection procedure

A new deep‐learning model using YOLOv3 to support sperm selection during intracytoplasmic sperm injection procedure

Efficient detection and robust tracking of spermatozoa in microscopic video

Predicting the value of sperm analysis using an electronic nose

Contact Info

Product

Resources

About