将具有多个 b 值的 MRI 数据转换为类似特征图的图片，以预测直肠癌的治疗反应。
The Conversion of MRI Data With Multiple b-Values into Signature-Like Pictures to Predict Treatment Response for Rectal Cancer.
机构信息
Department of Radiology, Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Peking University Cancer Hospital & Institute, Hai Dian District, Beijing, China.
出版信息
J Magn Reson Imaging. 2022 Aug;56(2):562-569. doi: 10.1002/jmri.28033. Epub 2021 Dec 16.
BACKGROUND
Diffusion weighted imaging (DWI) at multiple b-values has been used to predict the pathological complete response (pCR) to neoadjuvant chemoradiotherapy for locally advanced rectal cancer. Non-Gaussian models fit the signal decay of diffusion by several physical values from different approaches of approximation.
PURPOSE
To develop a deep learning method to analyze DWI data scanned at multiple b-values independent on Gaussian or non-Gaussian models and to apply to a rectal cancer neoadjuvant chemoradiotherapy model.
STUDY TYPE
Retrospective.
POPULATION
A total of 472 participants (age: 56.6 ± 10.5 years; 298 males and 174 females) with locally advanced adenocarcinoma were enrolled and chronologically divided into a training group (n = 200; 42 pCR/158 non-pCR), a validation group (n = 72; 11 pCR/61 non-pCR) and a test group (n = 200; 44 pCR/156 non-pCR).
FIELD STRENGTH/SEQUENCE: A 3.0 T MRI scanner. DWI with a single-shot spin echo-planar imaging pulse sequence at 12 b-values (0, 20, 50, 100, 200, 400, 600, 800, 1000, 1200, 1400, and 1600 sec/mm ).
ASSESSMENT
DWI signals from manually delineated tumor region were converted into a signature-like picture by concatenating all histograms from different b-values. Pathological results (pCR/non-pCR) were used as the ground truth for deep learning. Gaussian and non-Gaussian methods were used for comparison.
STATISTICAL TESTS
Analysis of variance for age; Chi-square for gender and pCR/non-pCR; area under the receiver operating characteristic (ROC) curve (AUC); DeLong test for AUC. P < 0.05 for significant difference.
RESULTS
The AUC in the test group is 0.924 (95% CI: 0.866-0.983) for the signature-like pictures converted from 35 bins, and it is 0.931 (95% CI: 0.884-0.979) for the signature-like pictures converted from 70 bins, which is significantly (Z = 3.258, P < 0.05) larger than D , the best predictor in non-Gaussian methods with AUC = 0.773 (95% CI: 0.682-0.865).
DATA CONCLUSION
The proposed signature-like pictures provide more accurate pretreatment prediction of the response to neoadjuvant chemoradiotherapy than the fitted methods for locally advanced rectal cancer.
EVIDENCE LEVEL
3 TECHNICAL EFFICACY: Stage 2.
背景
扩散加权成像（DWI）在多个 b 值下已被用于预测局部晚期直肠癌新辅助放化疗的病理完全缓解（pCR）。非高斯模型通过几种不同方法的近似来拟合信号衰减。
目的
开发一种深度学习方法，以分析独立于高斯或非高斯模型的多 b 值 DWI 数据，并将其应用于直肠癌新辅助放化疗模型。
研究类型
回顾性。
人群
共纳入 472 名患有局部晚期腺癌的参与者（年龄：56.6±10.5 岁；男性 298 名，女性 174 名），并按时间顺序分为训练组（n=200；42 例 pCR/158 例非 pCR）、验证组（n=72；11 例 pCR/61 例非 pCR）和测试组（n=200；44 例 pCR/156 例非 pCR）。
磁场强度/序列：3.0T MRI 扫描仪。使用单次激发自旋回波平面成像脉冲序列进行 DWI，共 12 个 b 值（0、20、50、100、200、400、600、800、1000、1200、1400 和 1600 sec/mm）。
评估
手动勾画肿瘤区域的 DWI 信号通过连接不同 b 值的所有直方图转化为类似特征的图片。病理结果（pCR/非 pCR）被用作深度学习的真实数据。比较了高斯和非高斯方法。
统计学检验
方差分析用于年龄；卡方检验用于性别和 pCR/非 pCR；受试者工作特征（ROC）曲线下面积（AUC）；DeLong 检验用于 AUC。P<0.05 为差异有统计学意义。
结果
在测试组中，35 个 bin 转换的特征图的 AUC 为 0.924（95%CI：0.866-0.983），70 个 bin 转换的特征图的 AUC 为 0.931（95%CI：0.884-0.979），明显（Z=3.258，P<0.05）大于非高斯方法中 AUC 为 0.773（95%CI：0.682-0.865）的最佳预测因子 D。
数据结论
与局部晚期直肠癌的拟合方法相比，所提出的特征图为新辅助放化疗的反应提供了更准确的预处理预测。
证据水平
3 级 技术功效：2 级。
Zotero 插件