Wang Liping, Chen Lin, Wei Kaixi, Zhou Huiyu, Zwiggelaar Reyer, Fu Weiwei, Liu Yingchao
Shandong Normal University, School of Information Science and Engineering, Jinan, China.
The Affiliated Hospital of Southwest Medical University, Department of Neurosurgery, Luzhou, China.
J Med Imaging (Bellingham). 2025 Jan;12(1):017502. doi: 10.1117/1.JMI.12.1.017502. Epub 2025 Jan 11.
Differentiating primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM) is crucial because their prognosis and treatment differ substantially. Manual examination of their histological characteristics is considered the golden standard in clinical diagnosis. However, this process is tedious and time-consuming and might lead to misdiagnosis caused by morphological similarity between their histology and tumor heterogeneity. Existing research focuses on radiological differentiation, which mostly uses multi-parametric magnetic resonance imaging. By contrast, we investigate the pathological differentiation between the two types of tumors using whole slide images (WSIs) of postoperative formalin-fixed paraffin-embedded samples.
To learn the specific and intrinsic histological feature representations from the WSI patches, a self-supervised feature extractor is trained. Then, the patch representations are fused by feeding into a weakly supervised multiple-instance learning model for the WSI classification. We validate our approach on 134 PCNSL and 526 GBM cases collected from three hospitals. We also investigate the effect of feature extraction on the final prediction by comparing the performance of applying the feature extractors trained on the PCNSL/GBM slides from specific institutions, multi-site PCNSL/GBM slides, and large-scale histopathological images.
Different feature extractors perform comparably with the overall area under the receiver operating characteristic curve value exceeding 85% for each dataset and close to 95% for the combined multi-site dataset. Using the institution-specific feature extractors generally obtains the best overall prediction with both of the PCNSL and GBM classification accuracies reaching 80% for each dataset.
The excellent classification performance suggests that our approach can be used as an assistant tool to reduce the pathologists' workload by providing an accurate and objective second diagnosis. Moreover, the discriminant regions indicated by the generated attention heatmap improve the model interpretability and provide additional diagnostic information.
鉴别原发性中枢神经系统淋巴瘤（PCNSL）和胶质母细胞瘤（GBM）至关重要，因为它们的预后和治疗方法有很大差异。对其组织学特征进行人工检查被认为是临床诊断的金标准。然而，这个过程繁琐且耗时，并且可能由于它们的组织学形态相似性和肿瘤异质性而导致误诊。现有研究集中在放射学鉴别上，主要使用多参数磁共振成像。相比之下，我们使用术后福尔马林固定石蜡包埋样本的全切片图像（WSIs）来研究这两种肿瘤之间的病理鉴别。
为了从WSI切片中学习特定的内在组织学特征表示，训练了一个自监督特征提取器。然后，通过将切片表示输入到一个弱监督多实例学习模型中进行WSI分类，从而实现融合。我们在从三家医院收集的134例PCNSL和526例GBM病例上验证了我们的方法。我们还通过比较应用在特定机构的PCNSL/GBM切片、多中心PCNSL/GBM切片和大规模组织病理学图像上训练的特征提取器的性能，来研究特征提取对最终预测的影响。
不同的特征提取器表现相当，每个数据集的受试者操作特征曲线下面积总值超过85%，对于组合的多中心数据集接近95%。使用特定机构的特征提取器通常能获得最佳的总体预测，每个数据集的PCNSL和GBM分类准确率均达到80%。
出色的分类性能表明，我们的方法可以作为一种辅助工具，通过提供准确、客观的二次诊断来减轻病理学家的工作量。此外，生成的注意力热图所指示的判别区域提高了模型的可解释性，并提供了额外的诊断信息。
