Ali, Muhaddisa Barat, Gu, Irene Yu-Hua, Lidemar, Alice, Berger, Mitchel S., Widhalm, Georg, Jakola, Asgeir Store
{"title":"胶质瘤亚型预测:使用边界框区域与注释肿瘤在DL分类器上的性能比较","authors":"Ali, Muhaddisa Barat, Gu, Irene Yu-Hua, Lidemar, Alice, Berger, Mitchel S., Widhalm, Georg, Jakola, Asgeir Store","doi":"10.1186/s42490-022-00061-3","DOIUrl":null,"url":null,"abstract":"For brain tumors, identifying the molecular subtypes from magnetic resonance imaging (MRI) is desirable, but remains a challenging task. Recent machine learning and deep learning (DL) approaches may help the classification/prediction of tumor subtypes through MRIs. However, most of these methods require annotated data with ground truth (GT) tumor areas manually drawn by medical experts. The manual annotation is a time consuming process with high demand on medical personnel. As an alternative automatic segmentation is often used. However, it does not guarantee the quality and could lead to improper or failed segmented boundaries due to differences in MRI acquisition parameters across imaging centers, as segmentation is an ill-defined problem. Analogous to visual object tracking and classification, this paper shifts the paradigm by training a classifier using tumor bounding box areas in MR images. The aim of our study is to see whether it is possible to replace GT tumor areas by tumor bounding box areas (e.g. ellipse shaped boxes) for classification without a significant drop in performance. In patients with diffuse gliomas, training a deep learning classifier for subtype prediction by employing tumor regions of interest (ROIs) using ellipse bounding box versus manual annotated data. Experiments were conducted on two datasets (US and TCGA) consisting of multi-modality MRI scans where the US dataset contained patients with diffuse low-grade gliomas (dLGG) exclusively. Prediction rates were obtained on 2 test datasets: 69.86% for 1p/19q codeletion status on US dataset and 79.50% for IDH mutation/wild-type on TCGA dataset. Comparisons with that of using annotated GT tumor data for training showed an average of 3.0% degradation (2.92% for 1p/19q codeletion status and 3.23% for IDH genotype). Using tumor ROIs, i.e., ellipse bounding box tumor areas to replace annotated GT tumor areas for training a deep learning scheme, cause only a modest decline in performance in terms of subtype prediction. With more data that can be made available, this may be a reasonable trade-off where decline in performance may be counteracted with more data.","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"6 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Prediction of glioma-subtypes: comparison of performance on a DL classifier using bounding box areas versus annotated tumors\",\"authors\":\"Ali, Muhaddisa Barat, Gu, Irene Yu-Hua, Lidemar, Alice, Berger, Mitchel S., Widhalm, Georg, Jakola, Asgeir Store\",\"doi\":\"10.1186/s42490-022-00061-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"For brain tumors, identifying the molecular subtypes from magnetic resonance imaging (MRI) is desirable, but remains a challenging task. Recent machine learning and deep learning (DL) approaches may help the classification/prediction of tumor subtypes through MRIs. However, most of these methods require annotated data with ground truth (GT) tumor areas manually drawn by medical experts. The manual annotation is a time consuming process with high demand on medical personnel. As an alternative automatic segmentation is often used. However, it does not guarantee the quality and could lead to improper or failed segmented boundaries due to differences in MRI acquisition parameters across imaging centers, as segmentation is an ill-defined problem. Analogous to visual object tracking and classification, this paper shifts the paradigm by training a classifier using tumor bounding box areas in MR images. The aim of our study is to see whether it is possible to replace GT tumor areas by tumor bounding box areas (e.g. ellipse shaped boxes) for classification without a significant drop in performance. In patients with diffuse gliomas, training a deep learning classifier for subtype prediction by employing tumor regions of interest (ROIs) using ellipse bounding box versus manual annotated data. Experiments were conducted on two datasets (US and TCGA) consisting of multi-modality MRI scans where the US dataset contained patients with diffuse low-grade gliomas (dLGG) exclusively. Prediction rates were obtained on 2 test datasets: 69.86% for 1p/19q codeletion status on US dataset and 79.50% for IDH mutation/wild-type on TCGA dataset. Comparisons with that of using annotated GT tumor data for training showed an average of 3.0% degradation (2.92% for 1p/19q codeletion status and 3.23% for IDH genotype). Using tumor ROIs, i.e., ellipse bounding box tumor areas to replace annotated GT tumor areas for training a deep learning scheme, cause only a modest decline in performance in terms of subtype prediction. With more data that can be made available, this may be a reasonable trade-off where decline in performance may be counteracted with more data.\",\"PeriodicalId\":72425,\"journal\":{\"name\":\"BMC biomedical engineering\",\"volume\":\"6 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-05-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC biomedical engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1186/s42490-022-00061-3\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC biomedical engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s42490-022-00061-3","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
摘要
对于脑肿瘤,通过磁共振成像(MRI)识别分子亚型是可取的,但仍然是一项具有挑战性的任务。最近的机器学习和深度学习(DL)方法可能有助于通过mri对肿瘤亚型进行分类/预测。然而,这些方法中的大多数都需要医学专家手动绘制的带有ground truth (GT)肿瘤区域的注释数据。手工标注耗时长,对医护人员要求高。作为一种替代方法,经常使用自动分割。然而,由于分割是一个定义不明确的问题,它并不能保证质量,并且由于不同成像中心的MRI采集参数不同,可能导致分割边界不正确或失败。与视觉目标跟踪和分类类似,本文通过使用MR图像中的肿瘤边界框区域训练分类器来改变范式。我们研究的目的是看看是否有可能用肿瘤边界框区域(如椭圆形框)代替GT肿瘤区域进行分类,而不会显著降低性能。在弥漫性胶质瘤患者中,通过使用椭圆边界框与手动注释数据对比,使用感兴趣的肿瘤区域(roi)来训练深度学习分类器进行亚型预测。实验在由多模态MRI扫描组成的两个数据集(US和TCGA)上进行,其中US数据集仅包含弥漫性低级别胶质瘤(dLGG)患者。在2个测试数据集上获得了预测率:美国数据集对1p/19q编码状态的预测率为69.86%,TCGA数据集对IDH突变/野生型的预测率为79.50%。与使用带注释的GT肿瘤数据进行训练的结果相比,平均降解率为3.0% (1p/19q编码状态为2.92%,IDH基因型为3.23%)。使用肿瘤roi(即椭圆边界框肿瘤区域)代替带注释的GT肿瘤区域来训练深度学习方案,在亚型预测方面只会导致性能的适度下降。由于可以提供更多的数据,这可能是一种合理的权衡,性能下降可以用更多的数据来抵消。
Prediction of glioma-subtypes: comparison of performance on a DL classifier using bounding box areas versus annotated tumors
For brain tumors, identifying the molecular subtypes from magnetic resonance imaging (MRI) is desirable, but remains a challenging task. Recent machine learning and deep learning (DL) approaches may help the classification/prediction of tumor subtypes through MRIs. However, most of these methods require annotated data with ground truth (GT) tumor areas manually drawn by medical experts. The manual annotation is a time consuming process with high demand on medical personnel. As an alternative automatic segmentation is often used. However, it does not guarantee the quality and could lead to improper or failed segmented boundaries due to differences in MRI acquisition parameters across imaging centers, as segmentation is an ill-defined problem. Analogous to visual object tracking and classification, this paper shifts the paradigm by training a classifier using tumor bounding box areas in MR images. The aim of our study is to see whether it is possible to replace GT tumor areas by tumor bounding box areas (e.g. ellipse shaped boxes) for classification without a significant drop in performance. In patients with diffuse gliomas, training a deep learning classifier for subtype prediction by employing tumor regions of interest (ROIs) using ellipse bounding box versus manual annotated data. Experiments were conducted on two datasets (US and TCGA) consisting of multi-modality MRI scans where the US dataset contained patients with diffuse low-grade gliomas (dLGG) exclusively. Prediction rates were obtained on 2 test datasets: 69.86% for 1p/19q codeletion status on US dataset and 79.50% for IDH mutation/wild-type on TCGA dataset. Comparisons with that of using annotated GT tumor data for training showed an average of 3.0% degradation (2.92% for 1p/19q codeletion status and 3.23% for IDH genotype). Using tumor ROIs, i.e., ellipse bounding box tumor areas to replace annotated GT tumor areas for training a deep learning scheme, cause only a modest decline in performance in terms of subtype prediction. With more data that can be made available, this may be a reasonable trade-off where decline in performance may be counteracted with more data.