Chromosome Karyotype Analysis Research Articles

Classification of Giemsa staining chromosome using input-aware deep convolutional neural network with integrated uncertainty estimates

A fully automated chromosome analysis system can substitute cytogenetic experts for the task of chromosome karyotype analysis, which in turn can substantially increase the efficiency of disease diagnosis. However, the construction of such a system is most crucially restricted by the accuracy of chromosome classification, during karyotype analysis. To facilitate the construction of an automatic chromosome analysis system, an input-aware and probabilistic prediction convolutional neural network (IAPP-CNN) is presented in this paper for high accuracy of chromosome classification. The approach follows three stages and consists of one input-aware module, one feature extractor module and one probabilistic prediction module. In the first stage, the input-aware module develops raw images automatically into the global-scale image, the object-scale image and the part-scale image, by introducing an attention mechanism. In the second stage, the three scale images are input into the feature extraction module through three branches, then the respective feature operators are obtained via their independent CNN feature extractors. In the third stage, the probabilistic prediction module uses three dynamic probabilistic parameters to estimate the prediction of each CNN branch separately, and then combined the three CNN votes for the final decision. The feature expression ability of the key feature was improved and the network was enabled to focus on the recognizable regions in the image. Evaluation results from a large dataset of healthy patients showed that the proposed IAPP-CNN achieved the highest accuracy of 99.2% for the chromosome classification task, surpassing the performance of a competitive baseline created by state-of-the-art methods.

Chromosomal microarray analysis vs. karyotyping for fetal ventriculomegaly: a meta-analysis.

Background:Chromosomal abnormalities are important causes of ventriculomegaly (VM). In mild and isolated cases of fetal VM, obstetricians rarely give clear indications for pregnancy termination. We aimed to calculate the incidence of chromosomal abnormalities and incremental yield of chromosomal microarray analysis (CMA) in VM, providing more information on genetic counseling and prognostic evaluation for fetuses with VM.Methods:The Chinese language databases Wanfang Data, China National Knowledge Infrastructure, and China Biomedical Literature Database (from January 1, 1991 to April 29, 2020) and English language databases PubMed, Embase, and Cochrane Library (from January 1, 1945 to April 29, 2020) were systematically searched for articles on fetal VM. Diagnostic criteria were based on ultrasonographic or magnetic resonance imaging (MRI) assessment of lateral ventricular atrium width: ≥10 to <15 mm for mild VM, and ≥15 mm for severe VM. Isolated VM was defined by the absence of structural abnormalities other than VM detected by ultrasonography or MRI. R software was used for the meta-analysis to determine the incidence of chromosomal abnormalities and incremental yield of CMA in VM, and the combined rate and 95% confidence interval (CI) were calculated.Results:Twenty-three articles involving 1635 patients were included. The incidence of chromosomal abnormalities in VM was 9% (95% CI: 5%–12%) and incremental yield of CMA in VM was 11% (95% CI: 7%–16%). The incidences of chromosomal abnormalities in mild, severe, isolated, and non-isolated VM were 9% (95% CI: 4%–16%), 5% (95% CI: 1%–11%), 3% (95% CI: 1%–6%), and 13% (95% CI: 4%–25%), respectively.Conclusions:Applying CMA in VM improved the detection rate of abnormalities. When VM is confirmed by ultrasound or MRI, obstetricians should recommend fetal karyotype analysis to exclude chromosomal abnormalities. Moreover, CMA should be recommended preferentially in pregnant women with fetal VM who are undergoing invasive prenatal diagnosis. CMA cannot completely replace chromosome karyotype analysis.

Analysis of genetic abnormalities and clinical outcome of fetus with ultrasonic nonstructural abnormality

Objective: To analysis the incidence of abnormal genetics and the clinical outcome of fetuses with ultrasonic nonstructural abnormality. Methods: This study was conducted retrospectively. 631 pregnant women were enrolled in the Prenatal Diagnostic Center of Fujian Maternal and Child Health Hospital due to ultrasonic nonstructural abnormality from January 2016 to January 2019. According to different gestational weeks, amniotic fluid or umbilical cord blood samples were collected for chromosome karyotype analysis and SNP-array. According to the number of nostructural abnormalities, they were divided into 1 nostructural abnormality group, 2 nostructural abnormalities group, and ≥3 nostructural abnormalities group. Chi-square test was used for comparison between groups. Results: Of the 631 cases, 34 cases (5.4%, 34/631) had abnormal karyotypes, including 20 cases with abnormal chromosome number and 14 cases with abnormal chromosome structure. In results of SNP-array, there were 53 abnormal results (8.4%, 53/631), including 32 cases of pathogenic copy number variations (CNV) and 21 cases of variations of uncertain clinical significance (VOUS). The rates of pathogenic CNV were 4.57% (21/260), 4.76% (7/147) and 16.67% (4/24) in the group of 1, 2 and ≥3 nostructural abnormalities, respectively. The rate of the three groups showed a linear trend, and the difference was statistically significant (χ²=7.419,P<0.05). In the single nostructural abnormality group, the rate of pathogenic CNV of nasal bone dysplasia, fetal growth restriction (FGR) and thickened nuchal translucency (NT) were 8.11% (3/37), 7.04% (5/71) and 5.60% (7/125), respectively. Conclusions: Compared with the karyotype analysis, SNP-array can significantly improve the detection rate of genetic abnormalities in ultrasonic nonstructural abnormality. When multiple ultrasonic nonstructural abnormality were combined, the risk of genetic abnormalities showed an upward trend.

Karyotype Analysis of Two Varieties of Paronychia amani (Caryophyllaceae, Paronychioideae)

The chromosome number and karyotype analysis of Paroncyhia amani var. amani and P. amani var. minutiflora are described for the first time. The diploid chromosome numbers and karyotype formulae are 2n = 4x = 36 = 32m + 4sm in taxa. The karyotypes are symmetrical type including metacentric and submetacentric chromosomes. The small chromosomes varied from 0.96 μm (var. amani) to 2.74 μm (var. minutiflora). P. amani var. amani and P. amani var. minutiflora are very little different varieties morphologically. There are some similarities between varieties in the karyological data. (i) equal number of chromosomes, (ii) same karyotype formula, (iii) very close karyotype asymmetry values, (iv) polyploidy by ploidy level of 4x. These seem to support morphological closeness.

Study on clinical features and diagnostic methods of prenatal Wolf-Hirschhorn syndrome

To investigate the clinical features of fetuses with Wolf-Hirschhorn syndrome(WHS) and explore the diagnostic methods and prenatal ultrasound characteristics and provide evidence for prenatal genetic counseling. We retrospectively analyzed 5 cases of WHS fetuses diagnosed from March 2016 to February 2020, and analyzed the results of chromosomal karyotype analysis and chromosomal microarray analysis (CMA) of the fetuses. Five cases of WHS were detected by CMA, four cases were detected by karyotype analysis. Prenatal ultrasound revealed 4 abnormalities, of which 3 had intrauterine growth restriction, and only 1 had abnormalities of the maxillofacial region. The sequence of the fragments was 4p16.3p16.1 with a loss of 6.5 Mb, 4p16.3p15.32 with a loss of 15.6 Mb combined with 2p25.3 increased by 906kb, 4p16.3p15.31 with a loss of 20.4 Mb, 4p16.p15.1 with a loss of 35 Mb and 4p16.3p14 with a loss of 37 Mb. Fetal growth restriction may be one of the early manifestations of WHS. Absence of fetal facial abnormality by prenatal ultrasound screening cannot exclude WHS. Karyotype analysis may miss the diagnosis of WHS, while combined CMA techniques can improve the diagnostic accuracy.

Application of Single Nucleotide Polymorphism Microarray in Prenatal Diagnosis of Fetuses with Central Nervous System Abnormalities.

BackgroundThe current gold standard of karyotype analysis for prenatal diagnosis of fetuses with central nervous system (CNS) abnormalities has some limitations. Here, we assessed the value of single nucleotide polymorphism (SNP) arrays as a diagnostic tool.MethodsThe results of prenatal diagnosis of 344 fetuses with CNS abnormalities as determined by ultrasonographic screening were retrospectively analyzed. All fetuses underwent chromosomal karyotype analysis and genome-wide SNP array analysis simultaneously. The resultant rates and frequencies of genomic abnormalities were compared.ResultsKaryotype analysis found 45 (13.2%) abnormal CNS cases, while SNP array found 60 (17.4%) cases. SNP array detected 23 (6.7%) cases of submicroscopic abnormalities that karyotype analysis did not find. The detection rate of karyotype analysis was 8.1% in the group with isolated CNS anomalies, but 16.5% in the group with CNS abnormalities plus extra ultrasound anomalies. Detection rates of SNP array were 12.4% and 20.8% in these two groups, respectively. Statistical analysis showed that the detection rates of both methods were significantly higher in the group with CNS malformations and other ultrasound anomalies than in the group with isolated CNS anomalies. Abnormal chromosomes were detected most frequently in fetuses with holoprosencephaly.ConclusionGenome-wide SNP array technology can significantly improve the positive detection rate of fetuses with CNS abnormalities. Combining karyotype analysis and SNP array technology is recommended for detecting the development of fetuses with abnormal CNS.

Amniotic fluid and urine metabolomic alterations associated with pregnant women with Down syndrome fetuses

Background Down syndrome (DS) is a chromosomal disorder caused by a third copy of all or part of chromosome 21. Clinical observations and preclinical studies both suggest that DS may be associated with significant metabolic and bioenergetic alterations. But the metabolic alterations in pregnant women carrying DS fetuses still remains unclear. In this study, we investigated the characteristic metabolomics and lipidomics changes during fetal development of DS. Methods The AF and random urine specimens were selected from 20 pregnant women carrying DS fetuses and 20 pregnant women carrying healthy fetuses. The diagnosis of DS was screened according to chromosome karyotype analysis, and untargeted metabolomic and lipidomic analyses were performed. Results Through the analyses of AF, 308 differential metabolites were selected between DS and controls. The metabolites with significant changes mainly involved lipid molecules, organic acids, nucleotides and carbon. Further analysis of lipidomics showed 64 differential metabolites, mainly involving glycerides, sphingolipids and glycerolipids. As for urine metabolomic and lipidomic analyses, there existed consistent metabolites with AF, but the number was much less. Conclusions Compared with the controls, carbon metabolism, amino acid metabolism, glyceride metabolism, sphingolipid metabolism and glycerophospholipid metabolism were significantly changed in DS cases. In addition, characterized biomarkers in AF and urine were screened for DS diagnosis, and these metabolites were mainly involved in energy metabolism and liver dysfunction. This finding may help improve the efficiency of prenatal screening for DS.

Prenatal diagnosis of a fetus with chromosome 18p deletion and duplication

To assess the value of chromosomal microarray analysis (CMA) to verify a fetus with partial 18p deletion signaled by non-invasive prenatal testing. G-banding chromosomal karyotyping analysis was carried out on amniotic fluid sample of the fetus and peripheral blood samples from the parents. Amniotic DNA was also subjected to CMA analysis. The fetus was also subjected to systematic ultrasound scan. The fetus was found to have a karyotype of 46,XX,18p+. CMA has revealed a 5 Mb deletion at 18p11.32-p11.31, a 2.9 Mb duplication at 18p11.31-p11.23, and a 2.5 Mb duplication at 18p11.23-p11.22. No chromosomal aberration or microdeletion/microduplication was detected in either parent. Non-invasive prenatal testing and CMA are both sensitive for the detection of chromosomal microdeletions and microduplications. CMA can help with clarification of genotype-phenotype correlation and facilitate prenatal diagnosis and genetic counseling for the family.

Value of chromosomal microarray analysis for the prenatal diagnosis of pregnancy with high risk signaled by non-invasive prenatal testing

To explore the value of chromosomal microarray analysis (CMA) for the diagnosis of fetuses with high risk signaled by non-invasive prenatal testing (NIPT). From June 2017 to August 2019, 628 pregnant women with high risk signaled by NIPT underwent invasive prenatal diagnosis. Amniotic fluid or cord blood samples were subjected to chromosomal karyotyping analysis or CMA. Pregnancy outcome and postnatal conditions of the fetuses were followed up. The positive predictive value for trisomy 21, trisomy 18, trisomy 13, sex chromosome aneuploidy, other rare trisomies and copy number variants (CNVs) among the 628 women were 86.4% (127/147), 41.7% (30/72), 12.9% (4/31), 43.7% (101/231), 16.5% (14/85) and 52.2% (35/67), respectively. In 218 samples with normal karyotype, 5.5% (12/218) of additional pathogenic CNVs and 2.3% (5/218) of loss of heterozygosity were detected by CMA. CMA combined with karyotyping analysis can be used as first-tier test for prenatal diagnosis for women with high-risk signaled by NIPT.

Guidelines for the interpretation of fetal chromosomal karyotyping analysis

Karyotyping analysis is a classical cytogenetic method for the prenatal diagnosis of fetal chromosomal aberrations. In order to standardize fetal chromosomal karyotyping analysis and adapt to the development of medical genetics technology, the Committee for the Prevention and Control of Birth Defect, Chinese Association of Preventive Medicine has organized the formulation of this guideline. The content has covered general requirements and standards for the analysis of fetal chromosomal karyotypes, analysis of chromosomal mosaicisms, and methods for determining the resolution of G-banding, etc., with the purpose to serve the clinical practice.

Detection and analysis of null alleles of amelogenin in gender identification.

In this study, we located eight samples with null alleles of amelogenin out of 10,750 cases, and discussed the influence in gender identification and forensic personal identification. Amelogenin was detected and retested by several autosomal STR kits and sex chromosomal STR kits, and the causes were analyzed by chromosome karyotype analysis and Y chromosome microdeletion detection if necessary. Suspected AMEL-X loss was observed in five samples, but no abnormality was detected in the X-STR loci. AMEL-X was recovered when samples were retested by other detection systems designed with different primers. One sample had AMEL-X and X-STR loci loss, and the karyotype was chimeric 45,X0[70]/46,X,+mar[13].Two male samples lost AMEL-Y fragment, and both of them lost DYS522-DYS570-DYS576 loci, but no abnormalities were found in the STS loci of SRY and AZF regions. Therefore, when carrying out gender identification by using amelogenin, it is essential to focus on null alleles of amelogenin. In especially, deal with the samples collected from the individuals who had chromosomal hereditary disorders(e.g. Turner Syndrome and Oligospermia / Azoospermia). In order to achieve this, laboratories should have various techniques to verify the null alleles of amelogenin and ensure accurate genotyping. Accurate genotyping of amelogenin and DNA database establishment are vital for personal identification.

Value of non-invasive prenatal testing for the detection of fetal chromosomal copy number variations

To explore the value of non-invasive prenatal testing (NIPT) for the detection of fetal chromosome copy number variations (CNVs). Clinical data of 18 661 pregnant women who underwent NIPT were collected. For fetuses suspected for carrying CNVs, amniotic fluid samples were collected for chromosomal karyotyping and/or chromosomal microarray analysis (CMA). Among all samples, NIPT suggested that 58 fetuses carried trisomy 21, 18 carried trisomy 18, 19 carried trisomy 13, 1 carried trisomies 18 and 21. Eighty eight women accepted invasive prenatal diagnosis. The results of CMA in 59 cases were consistent with those of NIPT, which yielded a consistency rate of 67.05%. In addition, 37 cases of fetal CNVs were detected by NIPT, of which 19 (15 microdeletions and 4 microduplications) have accepted invasive prenatal diagnosis. In 14 cases, the results were consistency with those of NIPT, with a consistent rate of 73.68%. NIPT features high sensitivity and accuracy. Invasive prenatal diagnosis should be considered for CNVs detected by NIPT, and by tracing its parental origin, it can provide guidance for clinical practice.

Results of non-invasive prenatal testing for 2473 women with twin pregnancy

To assess the value of non-invasive prenatal testing (NIPT) for the detection of fetal chromosomal aneuploidies in women with twin pregnancy. A total of 2473 women with twin pregnancy underwent the NIPT test to assess the risk for fetal chromosomal aneuploidies from January 2016 to September 2019. Those with a high risk by NIPT were confirmed by amniocentesis or chorionic villus sampling. All cases were followed up to evaluate the positive prediction value of NIPT for twin pregnancies. Among the 2473 women, the NIPT test has identified 31 cases (1.25%) with a high risk for fetal chromosomal aneuploidies, which included 5 cases of trisomy 21, 1 case of chromosome 21 deletion, 4 cases of trisomy 18, 7 cases of sex chromosome abnormality and 14 cases of microdeletion and microduplication. By invasive prenatal diagnosis or chromosomal karyotyping analysis of neonates, 5 cases of trisomy 21, 3 cases of trisomy 18, 1 case of sex chromosome abnormality, and 2 cases of microdeletion and microduplication were confirmed, which yielded a positive predictive value of 100%, 75%, 25% and 25%, respectively. NIPT can be used for the screening of fetal chromosomal aneuploidies in women with twin pregnancy with high accuracy. The method is non-invasive, safe and effective for the screening of fetal chromosomal aneuploidies, in particular trisomy 21.

Value of copy number variation analysis and chromosomal karyotyping for the diagnosis of children with intellectual disability/developmental delay

To assess the value of copy number variations (CNVs) and chromosomal karyotyping analysis for patients with intellectual disability/developmental delay (ID/DD). Chromosomal karyotype analysis was applied to 530 children diagnosed with ID/DD. Single nucleotide polymorphism array (SNP-array) was further applied for 120 children with unknown etiology. Among the 530 children with ID/DD, 104 (19.62%) were detected with chromosomal abnormalities. For the 120 children analyzed by SNP-array, 44 (36.67%) were detected with CNVs, among which 20 were predicted as pathogenic, 6 as likely pathogenic, 10 as variants of unknown significance, 7 as likely benign,and 1 as loss of heterozygosity. SNP-array can facilitate delineation of the etiology of patients with ID/DD, which may provide a basis for their prognosis, consultation and clinical intervention.

Identification of a fetus with complex chromosomal structural aberration by next-generation sequencing and karyotype analysis

To perform prenatal diagnosis for a woman carrying a balanced translocation. Clinical phenotype of the woman and her first child was analyzed. Peripheral blood sample of the woman and amniotic fluid sample from two subsequent pregnancies were subjected to chromosomal karyotyping and copy number variation analysis through next-generation sequencing (NGS). The karyotypes of the woman and her first child were determined as 46,XX,t(5;6)(p15:p23) and 46,XX,?der(5),t(5;6)(p15.32;p22.3), respectively. The karyotype of the amniocyte from her second pregnancy was 46,XN,t(5;6)(p15:p23). No pathogenic copy number variation was detected. The karyotype of her third pregnancy was 46,XN,?der(5),t(5;6)(p15.32;p22. 3), in addition with a 6.04 Mb deletion at 5p15.33p15.32 (20 000 - 6 060 000) and a 18.50 Mb duplication at 6p25.3p22.3 (160 000 - 18 660 000). Combined karyotyping analysis and NGS has enabled detection of fetal copy number variations for a woman carrying a balanced chromosomal translocation.

Clinical characterization and genetic analysis of a newborn with chromosome 8q21.11 deletion syndrome

To explore the genetic etiology for a newborn with corneal opacity. The neonate and her parents were subjected to routine G-banding chromosomal karyotyping analysis. Copy number variation (CNV) was analyzed with low-coverage whole-genome sequencing (WGS) and single nucleotide polymorphism microarray (SNP array). No karyotypic abnormality was found in the newborn and her parents. Low-coverage WGS has identified a de novo 5.5 Mb microdeletion at chromosome 8q21.11-q21.13 in the neonate, which encompassed the ZFHX4 and PEX2 genes. The result was confirmed by SNP array-based CNV analysis. The newborn was diagnosed with chromosome 8q21.11 deletion syndrome. ZFHX4 may be one of the key genes underlying this syndrome.

A real-world study of 176 cases with aplastic anemia treated in outpatient

目的探索真实世界门诊治疗再生障碍性贫血（AA）患者的诊断流程、治疗及疗效。方法评估2018年1月至2019年12月门诊治疗176例AA患者的诊断流程、治疗方案及疗效。结果患者出现症状至首次就诊中位时间7（5～120）个月，就诊原因包括出血（52.3%）、贫血（51.7%）、感染（6.8%）。诊断流程中168例（95.5%）患者完成髂骨骨髓穿刺（骨穿），仅22例（17.1%）完善了多部位骨穿（胸骨分类）；骨髓活检完成率85.1%（143/168）；只有59.5%（100/168）和58.9%（99/168）完成了骨髓流式免疫分型及染色体核型分析；86例（48.5%）完成阵发性睡眠性血红蛋白尿（PNH）克隆筛查；造血祖细胞培养检查完成率最低，仅45例（26.8%）。环孢素A（CsA）联合雄激素及左旋咪唑为最常见治疗方案，总计77例（43.8%），其次为CsA联合雄激素45例（25.6%），单用CsA者24例（13.6%），单用雄激素者16例（9.1%），14例（7.9%）患者确诊后选择中药或未治疗。根据门诊复诊频率将176例患者分为复诊规律组（每年≥4次）130例（73.9%）和复诊欠规律组（每年<4次）46例（26.1%）。复诊规律组6个月有效率较高（52.5%对28.0%，P＝0.005），12个月高质量缓解率更好（40.7%对16.7%，P＝0.027），24个月复发率更低（4.4%对36.4%，P＝0.001）。结论真实世界治疗的AA患者诊断流程需重视多部位骨穿检查并完成PNH克隆筛查、流式免疫分型、染色体核型分析及造血祖细胞培养检查；门诊规律复诊患者可获得高质量缓解，复发率低，推荐每年至少复诊4次。

Cytogenetics of Two Kaempferia L. Species in Thailand

The chromosome numbers and karyotype analyses of Kaempferia laotica Gapnep and K. rotunda L. belonging to family Zingiberaceae in Thailand were studied from root tips. The results show that the chromosome number of Kaempferia laotica and K. rotunda was found the same numbers to be 2n = 22 and the different karyotype formula with different in position of satellite chromosome has been found in 14m + 4sm + 4st (and one visible satellite chromosome) and 12m + 10sm (and one visible satellite chromosome), respectively. Therefore, chromosome structure, karyotype formula and satellite chromosomes can be used for classification in each species. The satellite chromosomes of both species are the first time reported. The karyotype of K. laotica was studied for the first time.

Application of Multiple Short Tandem Repeat Loci for Rapid Diagnosis of Down Syndrome and Edward Syndrome.

Chromosomal diseases with chromosomal abnormalities are one of the most common genetic diseases in humans, including abnormal numbers and structural abnormalities. Patau syndrome (also known as trisomy 13), Edward syndrome (also called trisomy 18), and Down syndrome (also known as trisomy 21) are all clinically fatal diseases caused by abnormal numbers of autosomes. However, there is no reliable and effective cure for chromosomal diseases, mainly relying on fast and accurate prenatal diagnosis technology to reduce the rate of birth defects. Fluorescent-labeled primers were designed and then used in fluorescence quantitative polymerase chain reaction (FQ-PCR) composite amplification, capillary electrophoresis typing, and gene fragment analysis technology to detect 64 amniotic fluid samples, which were indicated high risks of trisomy 18 and 21 by non-invasive prenatal diagnostic technology (NIPT). The results are compared with the results of karyotype analysis and chromo-some copy variations (CNVs). Sixty-four samples were determined by FQ-PCR technology with the help of short tandem repeat (STR) regarded as molecular marker (STR-FQ-PCR), the result showed 61 cases of chromosomal aneuploidy were positive, including 14 cases of Edward syndrome and 47 cases of Down syndrome. A total of 460 STR locus genotypes were detected, containing 84 STR locus genotypes of Edward syndrome and 376 STR locus genotypes of Down syndrome. Chromosome karyotype analysis showed that the detected samples were all chromosomal aneuploidy. Among them were 15 cases of trisomy 18, including 14 cases of homozygous type and 1 case of chimeric type, 49 cases of trisomy 21, consisting of 47 cases homozygous type and 2 cases chimeric type. Sixty-two cases of chromosomal aneuploidy were detected by CNVs with 14 cases of trisomy 18 and 48 cases of trisomy 21. The detectable rate of STR-FQ-PCR technology is 95.31% while the karyotype analysis is the highest with 100%. For non-chimera and non-structural abnormal samples, the coincidence rate of results between STR-FQ-PCR technology and karyotype analysis was 100%. All above manifested the application of multiple STR loci for rapid diagnosis of Down syndrome and Edward syndrome has high clinical value.

A novel chromosome cluster types identification method using ResNeXt WSL model.

Chromosome karyotyping analysis plays a crucial role in prenatal diagnosis for diagnosing whether a fetus has severe defects or genetic diseases. However, due to the complicated morphological characteristics of various types of chromosome clusters, chromosome instance segmentation is the most challenging stage of chromosome karyotyping analysis, leading chromosome karyotyping analysis to highly dependent on skilled clinical analysts. Since most of the chromosome instance segmentation efforts are currently devoted to segmenting chromosome instances from different types of chromosome clusters, type identification of chromosome clusters is a vital anterior task for chromosome instance segmentation. Firstly, this paper proposes an automatic approach for chromosome cluster identification using recent transfer learning techniques. The proposed framework is based on ResNeXt weakly-supervised learning (WSL) pre-trained backbone and a task-specific network header. Secondly, this paper proposes a fast training methodology that tunes our framework from coarse-to-fine gradually. Extensive evaluations on a clinical dataset consisting of 6592 clinical chromosome samples show that the proposed framework achieves 94.09%accuracy, 92.79%sensitivity, and 98.03%specificity. Such performance is superior to the best baseline model that we obtain 92.17%accuracy, 89.1%sensitivity, and 97.42%specificity. To foster research and application in the chromosome cluster type identification, we make our clinical dataset and code available via GitHub.