arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.08896cs.CVcs.AIcs.LG
收藏

用EfficientNet对胶质母细胞瘤进行组织学亚区分类

Classifying Histopathologic Glioblastoma Sub-regions with EfficientNet

Division of Computational Pathology, Department of Pathology \& Laboratory Medicine, Indiana University School of Medicine, Indianapolis, IN, USA Indiana University Melvin;Bren Simon Comprehensive Cancer Center, Indianapolis, IN, USA Department of Radiology \& Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN, USA Department of Biostatistics \& Health Data Science, Indiana University School of Medicine, Indianapolis, IN, USA Department of Neurological Surgery, Indiana University School of Medicine, Indianapolis, IN, USA Department of Computer Science, Luddy School of Informatics, Computing;Engineering, Indiana University, Indianapolis, IN, USA Corresponding authors: , , Equal senior authors

Sanyukta Adap, Ujjwal Baid, Spyridon Bakas

摘要:

胶质母细胞瘤(GBM)是最常见的侵袭性、快速生长的脑肿瘤,预后很差。尽管临床诊断取得了进展,但患者预后没有任何实质性改善。切除肿瘤的组织学评估是临床诊断常规的第一线。我们假设,GBM内不同组织学亚区域的自动化、鲁棒性和准确识别可能有助于从形态学上大规模了解这种疾病。在这项研究中,我们设计了一种四步深度学习方法来对六(6)个组织病理学区域进行分类,并在BrTS-Path 2024挑战数据集上对其进行定量评估,该数据集包括数字化的苏木精-伊红(H\&E)染色的GBM组织切片,注释了六个不同的区域。我们使用挑战赛的公开训练数据集来开发和评估EfficientNet架构的几种变体的有效性(即,B0、B1、B2、B3、B4)。EfficientNet-B1和EfficientNet-B4实现了最佳性能,在使用BraTS-Path训练集的5倍交叉验证配置中实现了0.98的F1得分。定量性能评估,我们提出的方法与EfficientNet-B1的BraTS路径保持了验证数据和最终的隐藏测试数据产生的F1分数分别为0.546和0.517,为相关的6类分类任务。训练、验证和测试数据的性能差异凸显了开发能够很好地推广新数据的模型的挑战,这对临床应用至关重要。所提出的方法的源代码可以在印第安纳大学计算病理学分部的GitHub存储库中找到:https://github.com/IUCompPath/brats-path-2024-enet。

英文摘要:

Glioblastoma (GBM) is the most common aggressive, fast-growing brain tumor, with a grim prognosis. Despite clinical diagnostic advancements, there have not been any substantial improvements to patient prognosis. Histopathological assessment of excised tumors is the first line of clinical diagnostic routine. We hypothesize that automated, robust, and accurate identification of distinct histological sub-regions within GBM could contribute to morphologically understanding this disease at scale. In this study, we designed a four-step deep learning approach to classify six (6) histopathological regions and quantitatively evaluated it on the BraTS-Path 2024 challenge dataset, which includes digitized Hematoxylin \& Eosin (H\&E) stained GBM tissue sections annotated for six distinct regions. We used the challenge's publicly available training dataset to develop and evaluate the effectiveness of several variants of EfficientNet architectures (i.e., B0, B1, B2, B3, B4). EfficientNet-B1 and EfficientNet-B4 achieved the best performance, achieving an F1 score of 0.98 in a 5-fold cross-validation configuration using the BraTS-Path training set. The quantitative performance evaluation of our proposed approach with EfficientNet-B1 on the BraTS-Path hold-out validation data and the final hidden testing data yielded F1 scores of 0.546 and 0.517, respectively, for the associated 6-class classification task. The difference in the performance on training, validation, and testing data highlights the challenge of developing models that generalize well to new data, which is crucial for clinical applications. The source code of the proposed approach can be found at the GitHub repository of Indiana University Division of Computational Pathology: https://github.com/IUCompPath/brats-path-2024-enet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑