Diagnosis of melanoma by imaging mass spectrometry: Development and validation of a melanoma prediction model.
Diagnosis of melanoma by imaging mass spectrometry: Development and validation of a melanoma prediction model.
复制标题
DOI：
10.1111/cup.14083
复制
发表时间：
2021-12
影响因子：
1.7
通讯作者：
Alomari AK
中科院分区：
文献类型：
--
作者：
Al-Rohil RN;Moore JL;Patterson NH;Nicholson S;Verbeeck N;Claesen M;Muhammad JZ;Caprioli RM;Norris JL;Kantrow S;Compton M;Robbins J;Alomari AK
仅通过组织病理学评价来明确诊断黑素细胞瘤是具有挑战性的。需要客观地确认诊断的新技术。本研究详细介绍了从空间分辨的多变量蛋白质表达谱成像质谱（IMS）生成的黑色素瘤预测模型的开发和验证。三位委员会认证的皮肤病理学家对333个样本进行了盲法评价。本研究纳入了具有三重一致诊断的样本，分为训练集（n=241）和测试集（n=92）。训练集和测试集都包括明确的痣和黑色素瘤的各种代表性子类。使用线性支持向量机（SVM）分类模型从训练集开发预测模型。我们在92个样本的独立测试集上验证了预测模型（75个正确分类，2个错误分类，15个不确定）。IMS检测黑色素瘤的敏感性为97.6%，特异性为96.4%，当评估每个独特的斑点。IMS在样本水平预测黑色素瘤的敏感性为97.3%，特异性为97.5%。从灵敏度和特异性计算中排除不确定结果。这项研究提供的证据表明，IMS为基础的蛋白质组学的结果是高度一致的诊断结果，通过仔细的组织病理学评估专家皮肤病理学家小组。
The definitive diagnosis of melanocytic neoplasia using solely histopathologic evaluation can be challenging. Novel techniques that objectively confirm diagnoses are needed. This study details the development and validation of a melanoma prediction model from spatially resolved multivariate protein expression profiles generated by Imaging Mass Spectrometry (IMS). Three board-certified dermatopathologists blindly evaluated 333 samples. Samples with triply concordant diagnoses were included in this study, divided into a training set (n=241) and a test set (n=92). Both the training and test sets included various representative subclasses of unambiguous nevi and melanomas. A prediction model was developed from the training set using a linear support vector machine (SVM) classification model. We validated the prediction model on the independent test set of 92 specimens (75 classified correctly, two misclassified, and 15 indeterminate). IMS detects melanoma with a sensitivity of 97.6% and a specificity of 96.4% when evaluating each unique spot. IMS predicts melanoma at the sample level with a sensitivity of 97.3% and a specificity of 97.5%. Indeterminate results were excluded from sensitivity and specificity calculations. This study provides evidence that IMS-based proteomics results are highly concordant to diagnostic results obtained by careful histopathologic evaluation from a panel of expert dermatopathologists.
登录
查看更多内容
DOI：
10.1159/000377698
发表时间：
2015-01
期刊：
Dermatopathology (Basel, Switzerland)
影响因子：
--
作者：
Compton LA;Murphy GF;Lian CG
通讯作者：
Lian CG
影响因子：
7.5
作者：
Alomari, Ahmed K.;Miedema, Jayson R.;Andea, Aleodor A.
通讯作者：
Andea, Aleodor A.
影响因子：
1.7
作者：
Dinehart, Matthew S.;Dinehart, Scott M.;High, Whitney A.
通讯作者：
High, Whitney A.
影响因子：
7.5
作者：
Gaiser, Timo;Kutzner, Heinz;Becker, Maria R.
通讯作者：
Becker, Maria R.
影响因子：
13.8
作者：
Gaudi, Sudeep;Zarandona, J. Manuel;Jukic, Drazen M.
通讯作者：
Jukic, Drazen M.