Despite improvements in medical knowledge, diagnostic equipment, electronic databases, and other easily accessible supporting material, fetal syndrome diagnosis remains difficult for medical professionals throughout both the prenatal and postpartum periods. Prenatal diagnosis of illness is a challenging jigsaw puzzle that needs meticulous analysis of several elements. When one anomaly is found, it is logical to assume that there are more. Additionally, the discovery of one anomaly may spur further research that results in the discovery of other anomalies. For biometric evaluation and diagnosis, the collection of a reference frame during an ultrasonography (US) test is crucial. A new collection of algorithms known as Neuro-Fuzzy evolutionary algorithms was developed as a result of study into pre-existing algorithms that allow autonomous fetal development monitoring. The Normal Shrink Elliptic curve approach was used to a benchmark picture of a prenatal ultrasound in a first for automated pre-processing. the intensity histogram (IH), rotation invariant moments (RIM), and gray level co-occurrence matrix are used to create features for analysis (GLCM). Last but not least, a genetics-based application of the Neuro-Fuzzy approach is utilized to differentiate between aberrant and typical embryonic development. The suggested technique surpasses state-of-the-art algorithms in experiments utilizing a benchmark and real-world dataset by a factor of 97 in terms of sensitivity, selectivity, recall, F -measure, and precision race. The ROC curve containing 0.97 percent is superior to other classification techniques including KNN, ensemble methods, linear discriminant analysis (LDA), and decision trees. The highest accuracy percentage, 95.7%, was achieved with SVM. The confusion matrix and the area under the receiver operating characteristic curve (AUC) are cross-validated using a variety of different classification approaches.
A Survey on Genetic Disorder Prediction of Fetus from Ultrasound-Based Computer-Aided Diagnosis
2022-12-01
1400709 byte
Conference paper
Electronic Resource
English
Computer-aided fault diagnosis
Automotive engineering | 1985
Automated Computer Aided Diagnosis and Simulation
British Library Conference Proceedings | 1997
|Perceptual challenges to computer-aided diagnosis
SPIE | 2012
|Survey of Intelligent Computer-Aided Training
AIAA | 1992
|Computer-Aided System for the Diagnosis of Alzheimer's Disease
Online Contents | 1997
|