A Genetic Algorithm-Based Optimized Transfer Learning Approach for Breast Cancer Diagnosis

Breast cancer diagnosis through mammography is a pivotal application within medical image-based diagnostics,integral for early detection and effective treatment.While deep learning has significantly advanced the analysis of mammographic images,challenges such as low contrast,image noise,and the high dimensionality of features often degrade model performance.Addressing these challenges,our study introduces a novel method integrating Genetic Algorithms(GA)with pre-trained Convolutional Neural Network(CNN)models to enhance feature selection and classification accuracy.Our approach involves a systematic process:first,we employ widely-used CNN architectures(VGG16,VGG19,MobileNet,and DenseNet)to extract a broad range of features from the Medical Image Analysis Society(MIAS)mammography dataset.Subsequently,a GA optimizes these features by selecting the most relevant and least redundant,aiming to overcome the typical pitfalls of high dimensionality.The selected features are then utilized to train several classifiers,including Linear and Polynomial Support Vector Machines(SVMs),K-Nearest Neighbors,Decision Trees,and Random Forests,enabling a robust evaluation of the method’s effectiveness across varied learning algorithms.Our extensive experimental evaluation demonstrates that the integration of MobileNet and GA significantly improves classification accuracy,from 83.33%to 89.58%,underscoring the method’s efficacy.By detailing these steps,we highlight the innovation of our approach which not only addresses key issues in breast cancer imaging analysis but also offers a scalable solution potentially applicable to other domains within medical imaging.

Usher syndrome:Genetic diagnosis and current therapeutic approaches

Usher Syndrome(USH)is the most common deaf-blind syndrome,affecting approximately 1 in 6000 people in the deaf population.This genetic condition is characterized by a combination of hearing loss(HL),retinitis pigmentosa,and,in some cases,vestibular areflexia.Among the subtypes of USH,USH type 1 is considered the most severe form,presenting profound bilateral congenital deafness,vestibular areflexia,and early onset RP.USH type 2 is the most common form,exhibiting congenital moderate to severe HL for low frequencies and severe to profound HL for high frequencies.Conversely,type 3 is the rarest,initially manifesting mild symptoms during childhood that become more prominent in the first decades of life.The dual impact of USH on both visual and auditory senses significantly impairs patients'quality of life,restricting their daily activities and interactions with society.To date,9 genes have been confirmed so far for USH:MYO7A,USH1C,CDH23,PCDH15,USH1G,USH2A,ADGRV1,WHRN and CLRN1.These genes are inherited in an autosomal recessive manner and encode proteins expressed in the inner ear and retina,leading to functional loss.Although non-genetic methods can assist in patient triage and disease extension evaluation,genetic and molecular tests play a pivotal role in providing genetic counseling,enabling appropriate gene therapy,and facilitating timely cochlear implantation(CI).The CRISPR/Cas9 system and viral-based gene replacement therapy have recently emerged as highly promising techniques for treating USH.Regarding drug therapy,PTC-124 and Nb54 have been identified as promising drug interventions for genetic HL in USH.Simultaneously,CI has proven to be critical in the restoration of hearing.This review aims to summarize the genetic and molecular diagnosis of USH and highlight the importance of early diagnosis in Cuzzuol BR et al.Diagnosis and current treatments of USH WJO https://www.wjgnet.com 2 January 19,2024 Volume 11 Issue 1 guiding appropriate treatment strategies and improving patient prognosis.

Prenatal ultrasonography and genetic analysis of fetal cleidocranial dysplasia:A case report

BACKGROUND Cleidocranial dysplasia(CCD)is an infrequent clinical condition with an autosomal dominant inheritance pattern.It is characterized by abnormal clavicles,patent sutures and fontanelles,supernumerary teeth,and short stature.Approximately 60%-70%of patients with CCD have mutations in the RUNX family transcription factor 2 gene.However,prenatal diagnosis of CCD is difficult when the family history is unknown.CASE SUMMARY We report a rare case of fetal CCD with an unknown family history,confirmed by prenatal ultrasonography and genetic testing at a gestational age of 16 weeks.The genetic reports indicated that the fetus carried pathogenic mutations in the RUNX family transcription factor 2 gene(c.674G>A).After careful consideration,the pregnant woman and her family decided to continue the pregnancy.CONCLUSION Definitive prenatal diagnosis of CCD should include family history,ultrasound diagnosis,and genetic analysis,especially if family history is unknown.

Role of genetics in the diagnosis and prognosis of Crohn's disease

Considering the epidemiological, genetic and immunological data, we can conclude that the inflammatory bowel diseases are heterogeneous disorders of multifactorial etiology in which hereditability and environment interact to produce the disease. It is probable that patients have a genetic predisposition for the development of the disease coupled with disturbances in immunoregulation. Several genes have so far been related to the diagnosis of Crohn's disease. These genes are related to innate pattern recognition receptors, to epithelial barrier homeostasis and maintenance of epithelial barrier integrity, to autophagy and to lymphocyte differentiation. So far, the strongest and most replicated associations with Crohn's disease have been demonstrated with NOD2 , IL23R and ATG16L1 genes. Many genes have so far been implicated in the prognosis of Crohn's disease and many attempts have been made for classification of genetic profiles in Crohn's disease.CARD15 seems to be not only a susceptibility gene, but also a disease-modifier gene for Crohn's disease. Enriching our understanding of Crohn's disease genetics is of value, but when combining genetic data with functional data the outcome could be of major importance to clinicians.

Application of Improved Genetic Algorithm in Network Fault Diagnosis Expert System

Knowledge acquisition is the “bottleneck” of building an expert system. Based on the optimization model, an improved genetic algorithm applied to knowledge acquisition of a network fault diagnostic expert system is proposed. The algorithm applies operators such as selection, crossover and mutation to evolve an initial population of diagnostic rules. Especially, a self adaptive method is put forward to regulate the crossover rate and mutation rate. In the end, a knowledge acquisition problem of a simple network fault diagnostic system is simulated, the results of simulation show that the improved approach can solve the problem of convergence better.

Role of genetics in the diagnosis and prognosis of Crohn's disease

Considering epidemiological,genetic and immunological data,we can conclude that the inflammatory bowel diseases are heterogeneous disorders of multifactorial etiology in which hereditability and environment interact to produce the disease.It is probable that patients have a genetic predisposition for the development of the disease coupled with disturbances in immunoregulation.Several genes have been so far related to the diagnosis of Crohn's disease.Those genes are related to innate pattern recognition receptors,to epithelial barrier homeostasis and maintenance of epithelial barrier integrity,to autophagy and to lymphocyte differentiation.So far,the most strong and replicated associations with Crohn's disease have been done with NOD2,IL23R and ATG16L1 genes.Many genes have so far been implicated in prognosis of Crohn's disease and many attempts have been made to classify genetic profiles in Crohn's disease.CARD15 seems not only a susceptibility gene,but also a disease-modifier gene for Crohn's disease.Enriching our understanding on Crohn's disease genetics is important but when combining genetic data with functional data the outcome could be of major importance to clinicians.

Forward and backward models for fault diagnosis based on parallel genetic algorithms

In this paper, a mathematical model consisting of forward and backward models is built on parallel genetic algorithms (PGAs) for fault diagnosis in a transmission power system. A new method to reduce the scale of fault sections is developed in the forward model and the message passing interface (MPI) approach is chosen to parallel the genetic algorithms by global sin-gle-population master-slave method (GPGAs). The proposed approach is applied to a sample system consisting of 28 sections, 84 protective relays and 40 circuit breakers. Simulation results show that the new model based on GPGAs can achieve very fast computation in online applications of large-scale power systems.

Study on Genetic Diagnosis of Spinal Muscular Atrophy

An improved method of mismatching polymerase chain reactionrestrictive fragment length polymorphisms(PCR-RFLP) was performed in our lab for genetic diagnosis of spinal muscular atrophy(SMA). PCR amplification and restriction endonuclease digestion of exons 7 and 8 permit distinction of the telomeric survival motor neuron (SMN) gene and its centromeric copy. Lack of a PCR product from either exon and from either gene is indicative of homozygous deletion of that sequence, and a high correlation with clinical SMA. Our data showed: 9 cases in 10 presumed SMA children were positive, i.e. deletion of telomeric SMN gene. One case was negative. 20 cases of normal familial members and 20 cases of normal health persons were all negative. Our results matched the criteria and reports of foreign countries. The method we used is highly specific, sensitive and reliable and is suitable for genetic diagnosis of SMA and its prenatal diagnosis.

Insights for hepatitis C virus related hepatocellular carcinoma genetic biomarkers: Early diagnosis and therapeutic intervention

The current review explores the role of emerging molecular contributing factors in liver carcinogenesis on top of hepatitis C virus(HCV). Here we will try to discuss the role genetic and epigenetic factors in pathogenesis of hepatocellular carcinoma. Understanding the role of these factors will help in discovering the mystery of liver carcinogenesis on top of chronic HCV infection. Moreover, use of the studied molecular factors will provide the hepatologists with tailored diagnostic promising biomarkers and flatten the way for establishment of emerging molecular treatment based on exploring the molecular subscription of this aggressive liver cancer.

Establishment of a Simple and Useful Way for Preimplantation Genetic Diagnosis of Chromosomal Diseases

In order to establish a simple and useful way for preimplantation genetic diagnosis (PGD) of chromosomal diseases in general IVF laboratory, the methods that are most commonly used in the embryo biopsy, fixation of blastomere and fluorescence in situ hybridization were compared. The three aspects of PGD were analyzed respectively. There was no significant difference in further de- velopment capacity of embryos between mechanical (79.7%) and chemical biopsy group (78.6%) (P>0.05). In this study, more cells were successfully fixed with the Tween/HCL method (93.8%) than with the methanol/acetic acid method (80.5%, P<0.05). There was no significant difference in cyto- plasm remains between methanol/acetic acid method and Tween/HCL method (P>0.05). The hy- bridization efficiency of fluorescence in situ hybridization was 89.5% in successive denaturation method and 90.9% in codenaturation method with the difference being not significant (P>0.05). In conclusion, the mechanical or chemical method, Tween/HCL fixation method and codenaturation fluorescence in situ hybridization method can constitute a simple and useful way for PGD of chro- mosomal diseases.

Early genetic diagnosis of clarithromycin resistance in Helicobacter pylori

BACKGROUND The drug resistance rate of clinical Helicobacter pylori(H.pylori)isolates has increased.However,the mechanism of drug resistance remains unclear.In this study,drug-resistant H.pylori strains were isolated from different areas and different populations of Chinese for genomic analysis.AIM To investigate drug-resistant genes in H.pylori and find the genes for the early diagnosis of clarithromycin resistance.METHODS Three drug-resistant H.pylori strains were isolated from patients with gastritis in Bama County,China.Minimal inhibitory concentrations of clarithromycin,metronidazole,and levofloxacin were determined and complete genome sequencing was performed with annotation.Hp1181 and hp1184 genes were found in these strains and then detected by reverse transcription polymerase chain reaction.The relationships between hp1181 or hp1184 and clarithromycin resistance were ascertained with gene mutant and drug-resistant strains.The homology of the strains with hp26695 was assessed through complete genome detection and identification.Differences in genome sequences,gene quantity,and gene characteristics were detected amongst the three strains.Prediction and analysis of the function of drug-resistant genes indicated that the RNA expression of hp1181 and hp1184 increased in the three strains,which was the same in the artificially induced clarithromycin-resistant bacteria.After gene knockout,the drug sensitivity of the strains was assessed.RESULTS The strains showing a high degree of homology with hp26695,hp1181,and hp1184 genes were found in these strains;the expression of the genes hp1184 and hp1181 was associated with clarithromycin resistance.CONCLUSION Hp1181 and hp1184 mutations may be the earliest and most persistent response to clarithromycin resistance,and they may be the potential target genes for the diagnosis,prevention,and treatment of clarithromycin resistance.CONCLUSION Hp1181 and hp1184 mutations may be the earliest and most persistent response to clarithromycin resistance,and they may be the potential target genes for the diagnosis,prevention,and treatment of clarithromycin resistance.

A Comparative Study of Genetic Algorithm Parameters for the Inverse Problem-based Fault Diagnosis of Liquid Rocket Propulsion Systems

Fault diagnosis of liquid rocket propulsion systems （LRPSs） is a very important issue in space launch activities particularly when manned space missions are accompanied, since the safety and reliability can be significantly enhanced by exploiting an efficient fault diagnosis system. Currently, inverse problem-based diagnosis has attracted a great deal of research attention in fault diagnosis domain. This methodology provides a new strategy to model-based fault diagnosis for monitoring the health of propulsion systems. To solve the inverse problems arising from the fault diagnosis of LRPSs, GAs have been adopted in recent years as the first and effective choice of available numerical optimization tools. However, the GA has many control parameters to be chosen in advance and there still lack sound theoretical tools to analyze the effects of these parameters on diagnostic performance analytically. In this paper a comparative study of the influence of GA parameters on diagnostic results is conducted by performing a series of numerical experiments. The objective of this study is to investigate the contribution of individual algorithm parameter to final diagnostic result and provide reasonable estimates for choosing GA parameters in the inverse problem-based fault diagnosis of LRPSs. Some constructive remarks are made in conclusion and will be helpful for the implementation of GA to the fault diagnosis practice of LRPSs in the future.

Preimplantation genetic diagnosis for Down syndrome pregnancy

Objective: To evaluate the effect of preimplantation genetic diagnosis (PGD) conducted for women who had Down syndrome pregnancy previously. Methods: Trisomy 21 was diagnosed by using fluorescence in site hybridization (FISH) before embryo transfer in two women who had Down syndrome pregnancies. Each received one or two PGD cycles respectively. Results: Case 1: one PGD cycle was conducted, two oocytes were fertilized and biopsied. One embryo is of trisomy 21 and the other of monosomy 21. No embryo was transferred. Case 2: two PGD cycles were conducted, in total, sixteen oocytes were fertilized and biopsied. Four embryos were tested to be normal, six of trisomy 21, and one of monosomy 21. Five had no signal. Four normal embryos were transferred but no pregnancy resulted. Conclusion: For couples who had pregnancies with Down syndrome pre-viously, PGD can be considered, and has been shown to be an effective strategy.

Identification of embryonic chromosomal abnormality using FISH-based preimplantaion genetic diagnosis

Objective: Embryonic chromosomal abnormality is one of the main reasons for in vitro fertilization (IVF) failure. This study aimed at evaluating the value of Fluorescence in-situ Hybridization (FISH)-based Preimplantation Genetic Diagnosis (PGD) in screening for embryonic chromosomal abnormality to increase the successful rate of IVF. Method: Ten couples, four with high risk of chromosomal abnormality and six infertile couples, underwent FISH-based PGD during IVF procedure. At day 3, one or two blastomeres were aspirated from each embryo. Biopsied blastomeres were examined using FISH analysis to screen out embryos with chromosomal abnormalities. At day 4, embryos without detectable chromosomal abnormality were transferred to the mother bodies as in regular IVF. Results: Among 54 embryos screened using FISH-based PGD, 30 embryos were detected to have chromosomal abnormalities. The 24 healthy embryos were implanted, resulting in four clinical pregnancies, two of which led to successful normal birth of two healthy babies; one to ongoing pregnancy during the writing of this article; and one to ectopic pregnancy. Conclusion: FISH-based PGD is an effective method for detecting embryonic chromosomal abnormality, which is one of the common causes of spontaneous miscarriages and chromosomally unbalanced offsprings.

Research on Genetic Algorithm Based Knowledge Auto Acquisition for Fault Diagnosis

In this paper, a genetic algorithm based knowledge auto acquisition approach for fault diagnosis is proposed. Under the circumstances that diagnostic examples are available but no empirical knowledge can be obtained, knowledge for fault diagnosis can be

Learning Fault Diagnosis Knowledge for a FCC Expert System by Genetic Algorithms

This paper introduces a GA-based Fault Matrix Learning System(GAFMLS) which applies Genetic Algorithms to a FCC expert system (FCCES) to learn a near-optimal fault matrix used in the fault diagnosis of an oil catalytic and cracking unit. The practical running results show that more effective fault matrixes can be generated by GAFMLS, and the reliability and precision of FCC expert system are improved.

Classification of osteogenesis imperfecta:Importance for prophylaxis and genetic counseling

Osteogenesis imperfecta(OI)is a genetically heterogeneous monogenic disease characterized by decreased bone mass,bone fragility,and recurrent fractures.The phenotypic spectrum varies considerably ranging from prenatal fractures with lethal outcomes to mild forms with few fractures and normal stature.The basic mechanism is a collagen-related defect,not only in synthesis but also in folding,processing,bone mineralization,or osteoblast function.In recent years,great progress has been made in identifying new genes and molecular mechanisms underlying OI.In this context,the classification of OI has been revised several times and different types are used.The Sillence classification,based on clinical and radiological characteristics,is currently used as a grading of clinical severity.Based on the metabolic pathway,the functional classification allows identifying regulatory elements and targeting specific therapeutic approaches.Genetic classification has the advantage of identifying the inheritance pattern,an essential element for genetic counseling and prophylaxis.Although genotype-phenotype correlations may sometimes be challenging,genetic diagnosis allows a personalized management strategy,accurate family planning,and pregnancy management decisions including options for mode of delivery,or early antenatal OI treatment.Future research on molecular pathways and pathogenic variants involved could lead to the development of genotype-based therapeutic approaches.This narrative review summarizes our current understanding of genes,molecular mechanisms involved in OI,classifications,and their utility in prophylaxis.

2+0 CYP21A2 deletion carrier—a limitation of the genetic testing and counseling:A case report

BACKGROUND CYP21A2 gene mutations may all cause reduction or loss of 21-hydroxylase activity,leading to development of congenital adrenal hyperplasia(CAH)with different clinical phenotypes.For families with CAH children,genetic testing of the parents and genetic counseling are recommended to assess the risk of recurrence.CASE SUMMARY We report a case of CAH with a high suspicion before delivery.The risk of the child suffering from CAH during the pregnancy had been underestimated due to the deviation of genetic counseling and genetic testing results.Our report confirmed a CYP21A2 homozygous deletion in this case,CYP21A2 heterozygous deletion in the mother,and a rare 2+0 CYP21A2 deletion in the father.CONCLUSION It is important to analyze the distribution of CYP21A2 gene in the two alleles of parents of children with CAH.

Preimplantation testing:Transition from genetic to genomic diagnosis

Preimplantation genetic testing refers to the procedure to determine the genetic status of embryos formed by in vitro fertilization(IVF) prior to initiating a pregnancy.Traditional genetic methods for preimplantation genetic diagnosis(PGD) examine distinct parts of an individua genome, require the development of a custom assay for every patient family, and are time consuming and inefficient. In the last decade technologies for wholegenome amplification(WGA) from single cells have led to innovative strategies for preimplantation testing.Applications of WGA technology can lead to a universa approach that uses single-nucleotide polymorphisms(SNPs) and mutations across the entire genome for the analysis. Single-cell WGA by multiple displacement amplification has enabled a linkage approach to PGD known as "preimplantation genetic haplotyping", as well as microarray-based techniques for preimplantation diagnosis. The use of microarrays in preimplantation diagnosis has provided genome-wide testing for gains or losses of single chromosomes(aneuploidies)or chromosomal segments. Properly designed randomized controlled trials are, however, needed to determine whether these new technologies improve IVF outcomes by increasing implantation rates and decreasing mis-carriage rates. In genotype analysis of single cells, allele dropout occurs frequently at heterozygous loci. Preimplantation testing of multiple cells biopsied from blastocysts, however, can reduce allele dropout rates and increase the accuracy of genotyping, but it allows less time for PGD. Future development of fast SNP microarrays will enable a universal preimplantation testing for aneuploidies, single-gene disorders and unbalanced translocations within the time frame of an IVF cycle.

Preimplantation genetic diagnosis and the biopsy technique: Important considerations

Preimplantation genetic diagnosis allows to test the genetic status of embryos prior to implantation. In order to obtain genetic material, on which carry out a genetic diagnosis, a procedure named embryo biopsy is required. In the last two decades, embryo biopsy at the cleavage stage has been the mostly performed procedure. However, recently, alternative methods allowing the retrieval of a larger number of cells (blastocyst stage biopsy), or representing a valid alternative to overcome ethical issues (polar body biopsy) have obtained increasing consensus. This article reviews different methods of embryo biopsy and points out their positive and negative aspects.