A multivariate curve resolution analysis of multicenter proton spectroscopic imaging of the prostate for cancer localization and assessment of aggressiveness

• Published in: NMR in biomedicine Vol. 37; no. 3; pp. e5062 - n/a
• Main Authors: Stamatelatou, Angeliki, Bertinetto, Carlo Giuseppe, Jansen, Jeroen J., Postma, Geert, Selnæs, Kirsten Margrete, Bathen, Tone F., Heerschap, Arend, Scheenen, Tom W. J., Attenberger, Ulrike I., Baltzer, Pascal A. T., Fütterer, Jurgen J., Haider, Masoom A., Helbich, Thomas H., Kiefer, Berthold, Maas, Marnix C., Macura, Katarzyna J., Margolis, Daniel J. A., Padhani, Anwar R., Polanec, Stephen H., Praet, Marleen, Scheenen, Tom W., Schoenberg, Stefan O., Selnaes, Kirsten M., Kwast, Theodorus H., Villeirs, Geert M., Viset, Trond, Busch, Heninrich
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.03.2024
• Subjects: Algorithms; Dimensional analysis; Histopathology; Lesions; Localization; Magnetic resonance; Multivariate analysis; multivariate curve resolution; Prostate; Prostate cancer; prostate cancer aggressiveness; proton MR spectroscopy and spectroscopic imaging methods; Quality control; Quantitative analysis; Singular value decomposition; Spectra; Test sets; Training; Tumors; proton MR spectroscopy and spectroscopic imaging methods; prostate cancer; prostate cancer aggressiveness; multivariate curve resolution
• ISSN: 0952-3480; 1099-1492; 1099-1492
• DOI: 10.1002/nbm.5062

In this study, we investigated the potential of the multivariate curve resolution alternating least squares (MCR‐ALS) algorithm for analyzing three‐dimensional (3D) 1H‐MRSI data of the prostate in prostate cancer (PCa) patients. MCR‐ALS generates relative intensities of components representing spectral profiles derived from a large training set of patients, providing an interpretable model. Our objectives were to classify magnetic resonance (MR) spectra, differentiating tumor lesions from benign tissue, and to assess PCa aggressiveness. We included multicenter 3D 1H‐MRSI data from 106 PCa patients across eight centers. The patient cohort was divided into a training set (N = 63) and an independent test set (N = 43). Singular value decomposition determined that MR spectra were optimally represented by five components. The profiles of these components were extracted from the training set by MCR‐ALS and assigned to specific tissue types. Using these components, MCR‐ALS was applied to the test set for a quantitative analysis to discriminate tumor lesions from benign tissue and to assess tumor aggressiveness. Relative intensity maps of the components were reconstructed and compared with histopathology reports. The quantitative analysis demonstrated a significant separation between tumor and benign voxels (t‐test, p < 0.001). This result was achieved including voxels with low‐quality MR spectra. A receiver operating characteristic analysis of the relative intensity of the tumor component revealed that low‐ and high‐risk tumor lesions could be distinguished with an area under the curve of 0.88. Maps of this component properly identified the extent of tumor lesions. Our study demonstrated that MCR‐ALS analysis of 1H‐MRSI of the prostate can reliably identify tumor lesions and assess their aggressiveness. It handled multicenter data with minimal preprocessing and without using prior knowledge or quality control. These findings indicate that MCR‐ALS can serve as an automated tool to assess the presence, extent, and aggressiveness of tumor lesions in the prostate, enhancing diagnostic capabilities and treatment planning of PCa patients. In this study, we applied multivariate curve resolution alternating least squares (MCR‐ALS) to analyze 3D 1H‐MRSI data of the prostate in prostate cancer patients. The study included multicenter data from 106 subjects, divided into training and test sets. Aiming to classify MR spectra, MCR‐ALS successfully differentiated between benign and tumor tissue and assessed spectra of tumors according to aggressiveness. These findings demonstrate the potential of MCR‐ALS as an automated tool for prostate cancer diagnosis and treatment planning.