Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods.
Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods.
复制标题
评估用于早期检测胰腺腺癌 (PDA) 的机器学习模型的稳健性：使用图像扰动方法评估对图像采集和放射组学工作流程变化的恢复能力。
DOI：
10.1007/s00261-023-04127-1
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Goenka,AjitH
中科院分区：
文献类型：
--
作者：
Mukherjee,Sovanlal;Korfiatis,Panagiotis;Patnam,NandakumarG;Trivedi,KamaxiH;Karbhari,Aashna;Suman,Garima;Fletcher,JoelG;Goenka,AjitH
PurposeTo评估基于放射学的支持向量机（SVM）模型的鲁棒性，通过模拟图像采集和放射学工作流程中的常见变化，使用图像扰动方法，在诊断前CT上检测视觉隐匿性PDA。（σ，2σ，3σ，5σ），图像旋转[CT图像和相应的胰腺分割掩模在轴向平面上旋转45°和90°]，体素重建（各向同性和各向异性）、灰度离散化[箱宽（BW）32和64）]和胰腺分割（从边界依次腐蚀3、4、6和8个像素，膨胀3、4和6个像素），被引入到原始图像中。（未扰动）测试子集（n= 128; 45例诊断前CT，83例正常胰腺对照CT）。放射组学特征提取胰腺面具的这些额外的测试子集，和模型的性能进行了比较相对于一个-相对于未扰动的测试subset.ResultsThe模型正确分类43的45个诊断前CT和75的83个控制CT在未扰动的测试子集，达到92.2%的准确性和0.98 AUC。模型的性能不受噪声水平增加三倍的影响，除了灵敏度在3σ时下降至80%（p= 0.02）。尽管图像旋转有变化，但性能与未受干扰的测试子集相当（p= 0.99），体素恢复（p= 0.25-0.31），灰度级BW变化为32（p= 0.31-0.99），以及距胰腺边界高达4个像素的糜烂/扩张（p= 0.12-0.34）.结论该模型在图像采集和放射组学工作流程中的广泛临床相关变化范围内检测视觉隐匿性PDA的高性能是稳健的。
PurposeTo evaluate robustness of a radiomics-based support vector machine (SVM) model for detection of visually occult PDA on pre-diagnostic CTs by simulating common variations in image acquisition and radiomics workflow using image perturbation methods.MethodsEighteen algorithmically generated-perturbations, which simulated variations in image noise levels (σ, 2σ, 3σ, 5σ), image rotation [both CT image and the corresponding pancreas segmentation mask by 45° and 90° in axial plane], voxel resampling (isotropic and anisotropic), gray-level discretization [bin width (BW) 32 and 64)], and pancreas segmentation (sequential erosions by 3, 4, 6, and 8 pixels and dilations by 3, 4, and 6 pixels from the boundary), were introduced to the original (unperturbed) test subset (n= 128; 45 pre-diagnostic CTs, 83 control CTs with normal pancreas). Radiomic features were extracted from pancreas masks of these additional test subsets, and the model's performance was compared vis-a-vis the unperturbed test subset.ResultsThe model correctly classified 43 out of 45 pre-diagnostic CTs and 75 out of 83 control CTs in the unperturbed test subset, achieving 92.2% accuracy and 0.98 AUC. Model's performance was unaffected by a three-fold increase in noise level except for sensitivity declining to 80% at 3σ(p= 0.02). Performance remained comparable vis-a-vis the unperturbed test subset despite variations in image rotation (p= 0.99), voxel resampling (p= 0.25–0.31), change in gray-level BW to 32 (p= 0.31–0.99), and erosions/dilations up to 4 pixels from the pancreas boundary (p= 0.12–0.34).ConclusionThe model’s high performance for detection of visually occult PDA was robust within a broad range of clinically relevant variations in image acquisition and radiomics workflow.