BACKGROUND Studies correlating specific genetic mutations and treatment response are ongoing to establish an effective treatment strategy for gastric cancer(GC).To facilitate this research,a cost-and time-effective me...BACKGROUND Studies correlating specific genetic mutations and treatment response are ongoing to establish an effective treatment strategy for gastric cancer(GC).To facilitate this research,a cost-and time-effective method to analyze the mutational status is necessary.Deep learning(DL)has been successfully applied to analyze hematoxylin and eosin(H and E)-stained tissue slide images.AIM To test the feasibility of DL-based classifiers for the frequently occurring mutations from the H and E-stained GC tissue whole slide images(WSIs).METHODS From the GC dataset of The Cancer Genome Atlas(TCGA-STAD),wildtype/mutation classifiers for CDH1,ERBB2,KRAS,PIK3CA,and TP53 genes were trained on 360×360-pixel patches of tissue images.RESULTS The area under the curve(AUC)for the receiver operating characteristic(ROC)curves ranged from 0.727 to 0.862 for the TCGA frozen WSIs and 0.661 to 0.858 for the TCGA formalin-fixed paraffin-embedded(FFPE)WSIs.The performance of the classifier can be improved by adding new FFPE WSI training dataset from our institute.The classifiers trained for mutation prediction in colorectal cancer completely failed to predict the mutational status in GC,indicating that DL-based mutation classifiers are incompatible between different cancers.CONCLUSION This study concluded that DL could predict genetic mutations in H and E-stained tissue slides when they are trained with appropriate tissue data.展开更多
BACKGROUND Mycobacterium mucogenicum(M.mucogenicum)belongs to the group of rapidly growing Nontuberculous mycobacteria.This microorganism is associated with a wide spectrum of infectious diseases.Due to a low detectio...BACKGROUND Mycobacterium mucogenicum(M.mucogenicum)belongs to the group of rapidly growing Nontuberculous mycobacteria.This microorganism is associated with a wide spectrum of infectious diseases.Due to a low detection rate or the time required for conventional culture methodology,a rapid and broad-spectrum method is necessary to identify rare pathogens.CASE SUMMARY A 12-year-old immunocompetent girl presented with painful masses for five months.The first mass was found in the right upper quadrant of the abdomen,and was about 1 cm×1.5 cm in size,tough but pliable in texture,with an irregular margin and tenderness.An abscess gradually formed and ulcerated with suppuration of the mass.Three new masses appeared on the back one by one.Chest computed tomography showed patchy and streaky cloudy opacities in both lungs.Needle aspiration of the abscess was performed,but the smear and conventional culture were negative,and the pathological examination showed no pathogens.We then performed next-generation sequencing using a formalinfixed,paraffin-embedded specimen to identify the pathogen.A significantly high abundance of M.mucogenicum was detected.The patient’s abscesses gradually decreased in size,while inflammation in both lungs improved following 12-wk of treatment.No recurrence was observed four months after the end of the one-year treatment period.CONCLUSION Next-generation sequencing is a promising tool for the rapid and accurate diagnosis of rare pathogens,even when using a formalin-fixed,paraffin-embedded specimen.展开更多
目的分析术中快速病理诊断技术的优化对提高编号效率与正确率、制片效率、制片质量与术中快速病理诊断及时率的影响。方法以2017~2021年优化前后的冷冻切片为研究对象,各选取2017年(优化前)与2021年(优化后)的100个冷冻标本,2017年为传...目的分析术中快速病理诊断技术的优化对提高编号效率与正确率、制片效率、制片质量与术中快速病理诊断及时率的影响。方法以2017~2021年优化前后的冷冻切片为研究对象,各选取2017年(优化前)与2021年(优化后)的100个冷冻标本,2017年为传统包埋盒生成方式,2021年为包埋盒打号机关联病理信息系统实现精准匹配打印。比较优化前后单个包埋盒病理号的平均生成时间及100个包埋盒的生成错误率。2017年为传统组织块速冻方法,2021年为将专利冰锤组件应用于病理冷冻切片制备的组织速冻环节,比较优化前后的速冻时间、冷冻切片组织完整性与细胞质挤压变形得分。随机取150个冷冻组织冻块,每块连续切取2片,1片手工染色,1片运用全自动染色机染色,比较优化前后的染色优良率及染色时间。比较优化前后两个年度的诊断报告及时率。结果优化后包埋盒病理号的平均生成时间(5.51±0.14)s/个显著短于优化前的(8.39±0.19)s/个,差异有统计学意义(P<0.05);优化后生成冷冻标本包埋盒病理号错误率为0,显著低于优化前的4.00%,差异有统计学意义(P<0.05)。优化后对组织的速冻时间(61.27±0.58)s明显短于优化前的(62.03±0.58)s,组织完整性得分(8.76±0.08)分及细胞质无挤压变形得分(9.16±0.06)分均显著高于优化前的(7.36±0.07)、(6.85±0.08)分,差异有统计学意义(P<0.05)。优化后的染色优良率97.33%高于优化前的89.33%,差异有统计学意义(P<0.05)。若两份冷冻标本同时送检或两份冷冻标本送检时间相距<3 min 150次,制成的冷冻切片需在同一时段染色,优化后染色完成时间(485.10±0.99)s短于优化前的(554.20±1.26)s,差异有统计学意义(P<0.05)。优化后术中病理诊断报告及时率显著高于优化前,差异有统计学意义(P<0.05)。结论优化术中快速病理诊断技术重要环节后缩短了术中冷冻切片的制备时间,提高了冷冻切片的制片与染色质量,可在规定时间内为病理医师提供优质的染色片,缩短术中冷冻标本的报告等待时间,提高手术进程。展开更多
文摘BACKGROUND Studies correlating specific genetic mutations and treatment response are ongoing to establish an effective treatment strategy for gastric cancer(GC).To facilitate this research,a cost-and time-effective method to analyze the mutational status is necessary.Deep learning(DL)has been successfully applied to analyze hematoxylin and eosin(H and E)-stained tissue slide images.AIM To test the feasibility of DL-based classifiers for the frequently occurring mutations from the H and E-stained GC tissue whole slide images(WSIs).METHODS From the GC dataset of The Cancer Genome Atlas(TCGA-STAD),wildtype/mutation classifiers for CDH1,ERBB2,KRAS,PIK3CA,and TP53 genes were trained on 360×360-pixel patches of tissue images.RESULTS The area under the curve(AUC)for the receiver operating characteristic(ROC)curves ranged from 0.727 to 0.862 for the TCGA frozen WSIs and 0.661 to 0.858 for the TCGA formalin-fixed paraffin-embedded(FFPE)WSIs.The performance of the classifier can be improved by adding new FFPE WSI training dataset from our institute.The classifiers trained for mutation prediction in colorectal cancer completely failed to predict the mutational status in GC,indicating that DL-based mutation classifiers are incompatible between different cancers.CONCLUSION This study concluded that DL could predict genetic mutations in H and E-stained tissue slides when they are trained with appropriate tissue data.
基金Supported by the Clinical Research Foundation of the Third Affiliated Hospital of Sun Yat-Sen University,No.YHJH201904National Science and Technology Major Project,No.2018ZX10302204.
文摘BACKGROUND Mycobacterium mucogenicum(M.mucogenicum)belongs to the group of rapidly growing Nontuberculous mycobacteria.This microorganism is associated with a wide spectrum of infectious diseases.Due to a low detection rate or the time required for conventional culture methodology,a rapid and broad-spectrum method is necessary to identify rare pathogens.CASE SUMMARY A 12-year-old immunocompetent girl presented with painful masses for five months.The first mass was found in the right upper quadrant of the abdomen,and was about 1 cm×1.5 cm in size,tough but pliable in texture,with an irregular margin and tenderness.An abscess gradually formed and ulcerated with suppuration of the mass.Three new masses appeared on the back one by one.Chest computed tomography showed patchy and streaky cloudy opacities in both lungs.Needle aspiration of the abscess was performed,but the smear and conventional culture were negative,and the pathological examination showed no pathogens.We then performed next-generation sequencing using a formalinfixed,paraffin-embedded specimen to identify the pathogen.A significantly high abundance of M.mucogenicum was detected.The patient’s abscesses gradually decreased in size,while inflammation in both lungs improved following 12-wk of treatment.No recurrence was observed four months after the end of the one-year treatment period.CONCLUSION Next-generation sequencing is a promising tool for the rapid and accurate diagnosis of rare pathogens,even when using a formalin-fixed,paraffin-embedded specimen.
文摘目的分析术中快速病理诊断技术的优化对提高编号效率与正确率、制片效率、制片质量与术中快速病理诊断及时率的影响。方法以2017~2021年优化前后的冷冻切片为研究对象,各选取2017年(优化前)与2021年(优化后)的100个冷冻标本,2017年为传统包埋盒生成方式,2021年为包埋盒打号机关联病理信息系统实现精准匹配打印。比较优化前后单个包埋盒病理号的平均生成时间及100个包埋盒的生成错误率。2017年为传统组织块速冻方法,2021年为将专利冰锤组件应用于病理冷冻切片制备的组织速冻环节,比较优化前后的速冻时间、冷冻切片组织完整性与细胞质挤压变形得分。随机取150个冷冻组织冻块,每块连续切取2片,1片手工染色,1片运用全自动染色机染色,比较优化前后的染色优良率及染色时间。比较优化前后两个年度的诊断报告及时率。结果优化后包埋盒病理号的平均生成时间(5.51±0.14)s/个显著短于优化前的(8.39±0.19)s/个,差异有统计学意义(P<0.05);优化后生成冷冻标本包埋盒病理号错误率为0,显著低于优化前的4.00%,差异有统计学意义(P<0.05)。优化后对组织的速冻时间(61.27±0.58)s明显短于优化前的(62.03±0.58)s,组织完整性得分(8.76±0.08)分及细胞质无挤压变形得分(9.16±0.06)分均显著高于优化前的(7.36±0.07)、(6.85±0.08)分,差异有统计学意义(P<0.05)。优化后的染色优良率97.33%高于优化前的89.33%,差异有统计学意义(P<0.05)。若两份冷冻标本同时送检或两份冷冻标本送检时间相距<3 min 150次,制成的冷冻切片需在同一时段染色,优化后染色完成时间(485.10±0.99)s短于优化前的(554.20±1.26)s,差异有统计学意义(P<0.05)。优化后术中病理诊断报告及时率显著高于优化前,差异有统计学意义(P<0.05)。结论优化术中快速病理诊断技术重要环节后缩短了术中冷冻切片的制备时间,提高了冷冻切片的制片与染色质量,可在规定时间内为病理医师提供优质的染色片,缩短术中冷冻标本的报告等待时间,提高手术进程。
