Chen Wen, Liu Fei, Wang Rui, Qi Ming, Zhang Jianping, Liu Xiaosheng, Song Shaoli
Department of Nuclear Medicine, Fudan University Shanghai Cancer Center, Shanghai, China.
Academy for Engineering and Technology, Fudan University, Shanghai, China.
Quant Imaging Med Surg. 2023 Oct 1;13(10):6598-6614. doi: 10.21037/qims-22-1333. Epub 2023 Aug 15.
Apart from invasive pathological examination, there is no effective method to differentiate breast diffuse large B-cell lymphoma (DLBCL) from breast invasive ductal carcinoma (IDC). In this study, we aimed to develop and validate an effective deep learning radiomics model to discriminate between DLBCL and IDC.
A total of 324 breast nodules from 236 patients with baseline F-fluorodeoxyglucose (F-FDG) positron emission tomography/computed tomography (PET/CT) were retrospectively analyzed. After grouping breast DLBCL and breast IDC patients, external and internal datasets were divided according to the data collected by different centers. Preprocessing was then used to process the original PET/CT images and an attention-based aggregate convolutional neural network (AACNN) model was designed. The AACNN model was trained using patches of CT or PET tumor images and optimized with an improved loss function. The final ensemble predictive model was built using distance weight voting. Finally, the model performance was evaluated and statistically verified.
A total of 249 breast nodules from Fudan University Shanghai Cancer Center (FUSCC) and 75 breast nodules from Shanghai Proton and Heavy Ion Center (SPHIC) were selected as internal and external datasets, respectively. On the internal testing, our method yielded an area under the curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and harmonic mean of precision and sensitivity (F1) of 0.886, 83.0%, 80.9%, 85.0%, 84.8%, 81.2%, and 0.828, respectively. Meanwhile on the external testing, the results were 0.788, 71.6%, 61.4%, 84.7%, 84.0%, 62.6%, and 0.709, respectively.
Our study outlines a deep learning radiomics method which can automatically, noninvasively, and accurately differentiate breast DLBCL from breast IDC, which will be more in line with the needs and strategies of precision medicine, individualized diagnosis, and treatment.
除侵入性病理检查外，尚无有效方法区分乳腺弥漫性大B细胞淋巴瘤（DLBCL）与乳腺浸润性导管癌（IDC）。在本研究中，我们旨在开发并验证一种有效的深度学习放射组学模型，以鉴别DLBCL和IDC。
回顾性分析了236例基线氟代脱氧葡萄糖（F-FDG）正电子发射断层扫描/计算机断层扫描（PET/CT）患者的324个乳腺结节。将乳腺DLBCL和乳腺IDC患者分组后，根据不同中心收集的数据划分外部和内部数据集。然后对原始PET/CT图像进行预处理，并设计了基于注意力的聚合卷积神经网络（AACNN）模型。使用CT或PET肿瘤图像块对AACNN模型进行训练，并用改进的损失函数进行优化。最终的集成预测模型采用距离权重投票构建。最后，对模型性能进行评估并进行统计学验证。
分别选取复旦大学附属肿瘤医院（FUSCC）的249个乳腺结节和上海质子重离子中心（SPHIC）的75个乳腺结节作为内部和外部数据集。在内部测试中，我们的方法得到的曲线下面积（AUC）、准确率（ACC）、灵敏度（SEN）、特异度（SPE）、阳性预测值（PPV）、阴性预测值（NPV）以及精度和灵敏度的调和均值（F1）分别为0.886、83.0%、80.9%、85.0%、84.8%、81.2%和0.828。同时在外部测试中，结果分别为0.788、71.6%、61.4%、84.7%、84.0%、62.6%和0.709。
我们的研究概述了一种深度学习放射组学方法，该方法可以自动、无创且准确地区分乳腺DLBCL和乳腺IDC，这将更符合精准医学、个体化诊断和治疗的需求与策略。
