An improvised follicle polycystic ovarian detection using AKF from a sequence of given ultrasound images
Article type: Research Article
Authors: Srinivas, Kachibhotlaa; * | Phani Kumar, Ch. Raghavendrab
Affiliations: [a] GITAM Deemed to be University, India | [b] Department of EECE, GITAM Deemed to be University, India
Correspondence: [*] Corresponding author. Kachibhotla Srinivas, GITAM Deemed to be University, India. E-mail: kachibhotlasrinivasphd@gmail.com.
Abstract: The segmentation of images is a technique used to extract information from a digital picture. One of the main applications in image segmentation is especially in medical image processing detection of an abnormal aspect to diagnose diseases. Ovarian cysts are formed in women who are unbalanced in estrogen and progesterone hormones. The polycystic ovarian syndrome is known as this condition. Women have a fluid collection in their ovaries called follicles. The image captures the follicles by ultrasound scanning. The detection of follicles from the echo sound image requires an optimized segmentation algorithm. Quantification of the ovary and follicle volumes and follicle counts for diagnosis and management in assisted replication is performed in clinical practice. Now for a few days, most women face infertility problems in the age group between 22 and 35. To analyze and classify the problems, the decision can start with the use of advanced technology to structurally compare the normal ovary to the affected ovary. Ovarian imagery is an effective instrument for the treatment of infertility. In human reproduction, follicle monitoring is particularly important. The primary method of doctors’ assessment is a periodic measurement of the size and form of follicles over several days. The field of medical imaging is one of the most popular applications of image processing techniques. The widespread popularity of image analysis technology in the field of diagnostic devices is due to the advancement of advanced imaging instruments combined with developments in algorithms unique to medical image processing, both for diagnostic tests and therapeutic preparation. Ultrasound imaging is a technique that uses high-frequency sound waves to capture images from within the human body. The echoes of reflected sound waves are captured and shown in real-time. It’s a good way to look at the nucleus, liver, kidneys, gall bladder, and ovaries, among other internal organs. The main contribution lies in identifying dominant follicles, that is growing and capable of producing an egg after the follicular phase, which is our primary goal, and this is where our suggested study comes in. Follicular ovulation doesn’t occur in all women, and not all of the dominant follicular levels are strong enough just to result in a pregnancy. Today, the follicles monitor human interaction using non-automatic means. Our proposed approach for the detection of follicle polycystic ovarian using AKF is not only helpful for generating highly efficient results but also proves to be best when compared with the state of art results from the existing methods.
Keywords: Advanced Kalman Filter (AKF), Adaptive Particle Swarm Optimization (APSO), Dice similarity coefficient (DSC), Kalman Filter (KF), Pigeon Inspired Optimization (PIO), Machine Learning (ML), True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN)
DOI: 10.3233/JIFS-212857
Journal: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 6, pp. 7717-7732, 2022