Ganoderma fungal disease is a plague suffered by most of the oil-palm plantations in South-East Asia. Its detection is a major issue in estate management and production. However, diagnostic is today far from reliable when done only by visual symptom observation, and very expansive and damaging when obtained by root or stem tissue chemical analysis. As an alternative, we propose in this study to evaluate the potential of hyperspectral reflectance data to help detecting efficiently the disease without destruction of tissues. This study focuses on the calibration of a statistical model of discrimination between several stages of Ganoderma attack on oil palm, based on field hyperspectral measurements at the canopy scale. Field protocol and measurements are first described. Then, combinations of pre-processing, partial least square regression and factorial discriminant analysis are tested on a hundred of samples to prove the efficiency of canopy reflectance to provide information about the plant sanitary status. A robust algorithm is thus derived, allowing classifying oil palm in a 4-level typology, based on disease severity levels from the sane to the critically sick tree with a global performance of more than 92%. Basic discrimination of trees in two classes: "sane" and "sick", is efficient at 100%. Applications and further improvements of this experiment are finally discussed.