Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images
Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images
复制标题
DOI：
10.1073/pnas.1505935112
复制
发表时间：
2015-11-17
影响因子：
11.1
通讯作者：
Deasy, Joseph O.
中科院分区：
文献类型：
--
作者：
Fehr, Duc;Veeraraghavan, Harini;Deasy, Joseph O.
基于放射图像的无创格里森模式检测和分层可以影响临床结果、治疗选择以及诊断时疾病状态的确定，而无需对患者进行手术活检。我们通过结合表观扩散系数 (ADC) 和基于 T2 加权 (T2-w) MRI 的纹理特征，提出基于机器学习的前列腺癌侵袭性自动分类。尽管存在高度不平衡的样本，但我们的方法通过使用两种不同的样本增强技术和基于特征选择的分类，实现了格里森分数 (GS) 6(3 + 3) 与 >= 7 和 7(3 + 4) 与 7(4 + 3) 的相当准确的分类。我们的方法区分了 GS 6(3 + 3) 和 >= 7 种癌症，对于发生在外周 (PZ) 和过渡区 (TZ) 的癌症，准确率为 93%，对于仅发生在 PZ 的癌症，准确率为 92%。我们的方法将 GS 7(3 + 4) 与 GS 7(4 + 3) 区分开来，对于同时发生在 PZ 和 TZ 的癌症，准确率为 92%；对于仅发生在 PZ 的癌症，准确率为 93%。相比之下，仅使用 ADC 平均值的分类器在区分 GS 6(3 + 3) 与 GS >= 7 发生在 PZ 和 TZ 的癌症方面达到了 58% 的最高准确度，而区分仅发生在 PZ 中的癌症的最高准确度为 63%。相同的分类器在区分 PZ 和 TZ 中发生的 GS 7(3 + 4) 与 GS 7(4 + 3) 方面达到了 59% 的准确度，而对于仅发生在 PZ 中的癌症则达到了 60% 的准确度。由于样本数量有限，没有对仅在 TZ 中发生的癌症进行单独分析。我们的结果表明，从 ADC 和 T2-w MRI 导出的纹理特征以及样本增强可以帮助获得相当准确的格里森模式分类。
Noninvasive, radiological image-based detection and stratification of Gleason patterns can impact clinical outcomes, treatment selection, and the determination of disease status at diagnosis without subjecting patients to surgical biopsies. We present machine learning-based automatic classification of prostate cancer aggressiveness by combining apparent diffusion coefficient (ADC) and T2-weighted (T2-w) MRI-based texture features. Our approach achieved reasonably accurate classification of Gleason scores (GS) 6(3 + 3) vs. >= 7 and 7(3 + 4) vs. 7(4 + 3) despite the presence of highly unbalanced samples by using two different sample augmentation techniques followed by feature selection-based classification. Our method distinguished between GS 6(3 + 3) and >= 7 cancers with 93% accuracy for cancers occurring in both peripheral (PZ) and transition (TZ) zones and 92% for cancers occurring in the PZ alone. Our approach distinguished the GS 7(3 + 4) from GS 7(4 + 3) with 92% accuracy for cancers occurring in both the PZ and TZ and with 93% for cancers occurring in the PZ alone. In comparison, a classifier using only the ADC mean achieved a top accuracy of 58% for distinguishing GS 6(3 + 3) vs. GS >= 7 for cancers occurring in PZ and TZ and 63% for cancers occurring in PZ alone. The same classifier achieved an accuracy of 59% for distinguishing GS 7(3 + 4) from GS 7(4 + 3) occurring in the PZ and TZ and 60% for cancers occurring in PZ alone. Separate analysis of the cancers occurring in TZ alone was not performed owing to the limited number of samples. Our results suggest that texture features derived from ADC and T2-w MRI together with sample augmentation can help to obtain reasonably accurate classification of Gleason patterns.