Dynamic contrast-enhanced (DCE) MRI has been used to quantitatively evaluate pulmonary perfusion based on the assumption of a gamma-variate function and an arterial input function (AIF) for deconvolution. However, these assumptions may be too simplistic and may not be valid in pathological conditions, especially in patients with complex inflow patterns (such as in congenital heart disease). Exploratory data analysis methods make minimal assumptions on the data and could overcome these pitfalls. In this work, two temporal clustering methodsKohonen clustering network (KCN) and Fuzzy C-Means (FCM)-were concatenated to identify pixel time-course patterns. The results from seven normal volunteers show that this technique is superior for discriminating vessels and compartments in the pulmonary circulation. Patient studies with five cases of acquired or congenital pulmonary perfusion disorders demonstrate that pathologies can be highlighted in a concise map that combines information of the mean transit time (MTT) and pulmonary blood volume (PBV). The method was found to provide greater insight into the perfusion dynamics that might be over- Proper regulation of pulmonary perfusion and ventilation is required for efficient gas exchange. Therefore, it is essential to accurately estimate pulmonary perfusion to assess the pathophysiology of the lung. In current clinical practice, pulmonary perfusion is evaluated with the use of nucleotide scintigraphic methods. However, these techniques are limited by poor spatial resolution and artifacts introduced by long imaging times (1). Magnetic resonance imaging (MRI) has been demonstrated to be a promising tool for evaluating brain perfusion with a spatial resolution of less than 1.5 mm and temporal resolution of about 1 s using Gd-DTPA as a contrast agent (2). When the same strategy is extended to image pulmonary perfusion, the poor magnetic field homogeneity caused by the complex air-tissue interfaces in the lung reduces the T* 2 of the lung tissue to only a few milliseconds. The resulting low signalto-noise ratio (SNR) limits the application of MRI in the lungs. Recent developments in short-TE imaging sequences have overcome the T* 2 decay and made it feasible to assess pulmonary perfusion by dynamic contrast-enhanced (DCE) MRI, as used in brain perfusion studies (1,3-7).Assuming that the contrast agent is a nondiffusible, intravascular tracer, quantitative indices, such as the relative pulmonary blood volume (PBV), relative mean transit time (MTT), and relative pulmonary blood flow (PBF), can be derived from the time courses of signal intensity (SI) in DCE-MRI (1,8,9). To eliminate the SI change from recirculation of the tracer, the time course is fitted to an assumed bolus-shaped function (typically a gamma-variate function) before the calculation is performed. Summary parameters, such as time-to-peak and gamma-fitting parameters, can be obtained as well (10). Furthermore, to achieve the absolute quantification of PBV, PBF, and MTT, a suitable arterial input function (AIF) is ...