Julia Kar, Michael V Cohen, Samuel A McQuiston, Teja Poorsala, Christopher M Malozzi
{"title":"利用全卷积网络从磁共振成像中自动分割左心室,研究乳腺癌患者的 CTRCD。","authors":"Julia Kar, Michael V Cohen, Samuel A McQuiston, Teja Poorsala, Christopher M Malozzi","doi":"10.1117/1.JMI.11.2.024003","DOIUrl":null,"url":null,"abstract":"<p><p><b>Purpose:</b> The goal of this study was to develop a fully convolutional network (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in displacement encoding with stimulated echoes MRI. The segmentation results are used for LV chamber quantification and strain analyses in breast cancer patients susceptible to cancer therapy-related cardiac dysfunction (CTRCD). <b>Approach:</b> A DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber quantification on 45 female breast cancer datasets (23 training, 11 validation, and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were measured, and myocardial strains estimated with the radial point interpolation method. Myocardial classification validation was against quantization-based ground-truth with computations of accuracy, Dice score, average perpendicular distance (APD), Hausdorff-distance, and others. Additional validations were conducted with equivalence tests and Cronbach's alpha (<math><mrow><mi>C</mi><mtext>-</mtext><mi>α</mi></mrow></math>) intraclass correlation coefficients between the FCN and a vendor tool on chamber quantification and myocardial strain computations. <b>Results:</b> Myocardial classification results against ground-truth were <math><mrow><mtext>Dice</mtext><mo>=</mo><mn>0.89</mn></mrow></math>, <math><mrow><mi>APD</mi><mo>=</mo><mn>2.4</mn><mtext> </mtext><mi>mm</mi></mrow></math>, and <math><mrow><mtext>accuracy</mtext><mo>=</mo><mn>97</mn><mo>%</mo></mrow></math> for the validation set and <math><mrow><mtext>Dice</mtext><mo>=</mo><mn>0.90</mn></mrow></math>, <math><mrow><mi>APD</mi><mo>=</mo><mn>2.5</mn><mtext> </mtext><mi>mm</mi></mrow></math>, and <math><mrow><mtext>accuracy</mtext><mo>=</mo><mn>97</mn><mo>%</mo></mrow></math> for the test set. The confidence intervals (CI) and two one-sided t-test results of equivalence tests between the FCN and vendor-tool were <math><mrow><mi>CI</mi><mo>=</mo><mo>-</mo><mn>1.36</mn><mo>%</mo></mrow></math> to 2.42%, p-value < 0.001 for LVEF (<math><mrow><mn>58</mn><mo>±</mo><mn>5</mn><mo>%</mo></mrow></math> versus <math><mrow><mn>57</mn><mo>±</mo><mn>6</mn><mo>%</mo></mrow></math>), and <math><mrow><mi>CI</mi><mo>=</mo><mo>-</mo><mn>0.71</mn><mo>%</mo></mrow></math> to 0.63%, p-value < 0.001 for longitudinal strain (<math><mrow><mo>-</mo><mn>15</mn><mo>±</mo><mn>2</mn><mo>%</mo></mrow></math> versus <math><mrow><mo>-</mo><mn>15</mn><mo>±</mo><mn>3</mn><mo>%</mo></mrow></math>). <b>Conclusions:</b> The validation results were found equivalent to the vendor tool-based parameter estimates, which show that accurate LV chamber quantification followed by strain analysis for CTRCD investigation can be achieved with our proposed FCN methodology.</p>","PeriodicalId":1,"journal":{"name":"Accounts of Chemical Research","volume":null,"pages":null},"PeriodicalIF":16.4000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10950093/pdf/","citationCount":"0","resultStr":"{\"title\":\"Automated segmentation of the left-ventricle from MRI with a fully convolutional network to investigate CTRCD in breast cancer patients.\",\"authors\":\"Julia Kar, Michael V Cohen, Samuel A McQuiston, Teja Poorsala, Christopher M Malozzi\",\"doi\":\"10.1117/1.JMI.11.2.024003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b>Purpose:</b> The goal of this study was to develop a fully convolutional network (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in displacement encoding with stimulated echoes MRI. The segmentation results are used for LV chamber quantification and strain analyses in breast cancer patients susceptible to cancer therapy-related cardiac dysfunction (CTRCD). <b>Approach:</b> A DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber quantification on 45 female breast cancer datasets (23 training, 11 validation, and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were measured, and myocardial strains estimated with the radial point interpolation method. Myocardial classification validation was against quantization-based ground-truth with computations of accuracy, Dice score, average perpendicular distance (APD), Hausdorff-distance, and others. Additional validations were conducted with equivalence tests and Cronbach's alpha (<math><mrow><mi>C</mi><mtext>-</mtext><mi>α</mi></mrow></math>) intraclass correlation coefficients between the FCN and a vendor tool on chamber quantification and myocardial strain computations. <b>Results:</b> Myocardial classification results against ground-truth were <math><mrow><mtext>Dice</mtext><mo>=</mo><mn>0.89</mn></mrow></math>, <math><mrow><mi>APD</mi><mo>=</mo><mn>2.4</mn><mtext> </mtext><mi>mm</mi></mrow></math>, and <math><mrow><mtext>accuracy</mtext><mo>=</mo><mn>97</mn><mo>%</mo></mrow></math> for the validation set and <math><mrow><mtext>Dice</mtext><mo>=</mo><mn>0.90</mn></mrow></math>, <math><mrow><mi>APD</mi><mo>=</mo><mn>2.5</mn><mtext> </mtext><mi>mm</mi></mrow></math>, and <math><mrow><mtext>accuracy</mtext><mo>=</mo><mn>97</mn><mo>%</mo></mrow></math> for the test set. The confidence intervals (CI) and two one-sided t-test results of equivalence tests between the FCN and vendor-tool were <math><mrow><mi>CI</mi><mo>=</mo><mo>-</mo><mn>1.36</mn><mo>%</mo></mrow></math> to 2.42%, p-value < 0.001 for LVEF (<math><mrow><mn>58</mn><mo>±</mo><mn>5</mn><mo>%</mo></mrow></math> versus <math><mrow><mn>57</mn><mo>±</mo><mn>6</mn><mo>%</mo></mrow></math>), and <math><mrow><mi>CI</mi><mo>=</mo><mo>-</mo><mn>0.71</mn><mo>%</mo></mrow></math> to 0.63%, p-value < 0.001 for longitudinal strain (<math><mrow><mo>-</mo><mn>15</mn><mo>±</mo><mn>2</mn><mo>%</mo></mrow></math> versus <math><mrow><mo>-</mo><mn>15</mn><mo>±</mo><mn>3</mn><mo>%</mo></mrow></math>). <b>Conclusions:</b> The validation results were found equivalent to the vendor tool-based parameter estimates, which show that accurate LV chamber quantification followed by strain analysis for CTRCD investigation can be achieved with our proposed FCN methodology.</p>\",\"PeriodicalId\":1,\"journal\":{\"name\":\"Accounts of Chemical Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":16.4000,\"publicationDate\":\"2024-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10950093/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Accounts of Chemical Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1117/1.JMI.11.2.024003\",\"RegionNum\":1,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/3/19 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Accounts of Chemical Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1117/1.JMI.11.2.024003","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/3/19 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
Automated segmentation of the left-ventricle from MRI with a fully convolutional network to investigate CTRCD in breast cancer patients.
Purpose: The goal of this study was to develop a fully convolutional network (FCN) tool to automatedly segment the left-ventricular (LV) myocardium in displacement encoding with stimulated echoes MRI. The segmentation results are used for LV chamber quantification and strain analyses in breast cancer patients susceptible to cancer therapy-related cardiac dysfunction (CTRCD). Approach: A DeepLabV3+ FCN with a ResNet-101 backbone was custom-designed to conduct chamber quantification on 45 female breast cancer datasets (23 training, 11 validation, and 11 test sets). LV structural parameters and LV ejection fraction (LVEF) were measured, and myocardial strains estimated with the radial point interpolation method. Myocardial classification validation was against quantization-based ground-truth with computations of accuracy, Dice score, average perpendicular distance (APD), Hausdorff-distance, and others. Additional validations were conducted with equivalence tests and Cronbach's alpha () intraclass correlation coefficients between the FCN and a vendor tool on chamber quantification and myocardial strain computations. Results: Myocardial classification results against ground-truth were , , and for the validation set and , , and for the test set. The confidence intervals (CI) and two one-sided t-test results of equivalence tests between the FCN and vendor-tool were to 2.42%, p-value < 0.001 for LVEF ( versus ), and to 0.63%, p-value < 0.001 for longitudinal strain ( versus ). Conclusions: The validation results were found equivalent to the vendor tool-based parameter estimates, which show that accurate LV chamber quantification followed by strain analysis for CTRCD investigation can be achieved with our proposed FCN methodology.
期刊介绍:
Accounts of Chemical Research presents short, concise and critical articles offering easy-to-read overviews of basic research and applications in all areas of chemistry and biochemistry. These short reviews focus on research from the author’s own laboratory and are designed to teach the reader about a research project. In addition, Accounts of Chemical Research publishes commentaries that give an informed opinion on a current research problem. Special Issues online are devoted to a single topic of unusual activity and significance.
Accounts of Chemical Research replaces the traditional article abstract with an article "Conspectus." These entries synopsize the research affording the reader a closer look at the content and significance of an article. Through this provision of a more detailed description of the article contents, the Conspectus enhances the article's discoverability by search engines and the exposure for the research.