Purpose: To implement and evaluate the performance of a computerized statistical tool designed for robust and quantitative analysis of hemodynamic response imaging (HRI) -derived maps for the early identification of colorectal liver metastases (CRLM).
Materials and methods: CRLM-bearing mice were scanned during the early stage of tumor growth and subsequently during the advanced-stage. Three experienced radiologists marked various suspected-foci on the early stage anatomical images and classified each as either highly certain or as suspected tumors. The statistical model construction was based on HRI maps (functional-MRI combined with hypercapnia and hyperoxia) using a supervised learning paradigm which was further trained either with the advanced-stage sets (late training; LT) or with the early stage sets (early training; ET). For each group of foci, the classifier results were compared with the ground-truth.
Results: The ET-based classification significantly improved the manual classification of the highly certain foci (P < 0.05) and was superior compared with the LT-based classification (P < 0.05). Additionally, the ET-based classification, offered high sensitivity (57-63%), accompanied with high positive predictive value (>94%) and high specificity (>98%) for suspected-foci.
Conclusion: The ET-based classifier can strengthen the radiologist's classification of highly certain foci. Additionally, it can aid in classifying suspected-foci, thus enabling earlier intervention which can often be lifesaving.
Keywords: SVM; cancer; hemodynamic response imaging; machine learning.
Copyright © 2013 Wiley Periodicals, Inc.