Ren Jinjing, Chen Ling, Xu Huilin, Zheng Xinlei, Ren He
Research Center for Electromagnetic Environment Effects, Southeast University, Nanjing, China.
Faculty of Medical Instrumentation, Shanghai University of Medicine & Health Sciences, Shanghai, China.
Quant Imaging Med Surg. 2023 Jul 1;13(7):4245-4256. doi: 10.21037/qims-22-848. Epub 2023 May 10.
The radiological features of computed tomography (CT) images and the sequence of radiomics signatures in continuous slices of lung CT lesions are helpful in identifying subtypes of lung adenocarcinoma. A model based on bidirectional long short-term memory (Bi-LSTM) and multihead attention can learn the rules of this sequence well.
In this study, 421 patients with 427 lesions confirmed as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) or invasive adenocarcinoma (IAC) were recruited from three hospitals. The radiomics signatures of the identified lesion regions in each CT image were extracted using 'PyRadiomics' software, and the corresponding radiological features were subsequently documented and collected. Then, the top 100 features were extracted by the minimum redundancy maximum relevance (mRMR) feature ranking method. A model based on the radiological and imaging features was established to classify the lesions using Bi-LSTM and multihead attention. The diagnostic performance of the model was measured by the area under the curve (AUC) of the receiver operating characteristic (ROC).
The model combined radiological features and radiomics signatures. The AUCs of the model in the training, testing, and validation groups were 0.985, 0.94 and 0.981, respectively, and the accuracy was 0.92, 0.976 and 0.91, respectively. In addition, we trained two other models [convolutional neural network (CNN) + multihead attention, long short-term memory (LSTM) + multihead attention] and compared them using the testing dataset. The precision of the two models was 0.89 and 0.88, respectively, and the accuracy was 0.88 and 0.87, respectively.
Bi-LSTM and multihead attention based on radiomics signatures and radiological features provide a way to distinguish AIS, MIA, and IAC.
计算机断层扫描（CT）图像的放射学特征以及肺CT病变连续切片中放射组学特征序列有助于识别肺腺癌的亚型。基于双向长短期记忆（Bi-LSTM）和多头注意力的模型可以很好地学习该序列的规则。
本研究从三家医院招募了421例有427个病变的患者，这些病变经确诊为原位腺癌（AIS）、微浸润腺癌（MIA）或浸润性腺癌（IAC）。使用“PyRadiomics”软件提取每个CT图像中识别出的病变区域的放射组学特征，随后记录并收集相应的放射学特征。然后，通过最小冗余最大相关性（mRMR）特征排序方法提取前100个特征。建立基于放射学和影像学特征的模型，使用Bi-LSTM和多头注意力对病变进行分类。通过接收器操作特征（ROC）曲线下面积（AUC）来衡量模型的诊断性能。
该模型结合了放射学特征和放射组学特征。该模型在训练组、测试组和验证组中的AUC分别为0.985、0.94和0.981，准确率分别为0.92、0.976和0.91。此外，我们还训练了另外两个模型[卷积神经网络（CNN）+多头注意力、长短期记忆（LSTM）+多头注意力]，并使用测试数据集对它们进行比较。这两个模型的精确率分别为0.89和0.88，准确率分别为0.88和0.87。
基于放射组学特征和放射学特征的Bi-LSTM和多头注意力为区分AIS、MIA和IAC提供了一种方法。
