Computer vision analysis of somatic embryos of sweet potato [Ipomoea batatas (L.) Lam.] for assessing their ability to convert to plants.

Apical and axial shoot tips of sweet potato were cultured to produce somatic embryos that mature and develop into plants in basal nutrient medium. However, the lack of high regeneration efficiency is an impediment to the use of somatic embryos to produce synthetic seeds. Conversion experiments with mature embryos over a 20-day period revealed that 80-90% of the embryos formed roots but only 40-50% formed shoots. Using computer vision and canonical or Fisher discriminant function (CDA) analysis along with conversion results, it was possible to correctly classify competent embryos 40-50% of the time based on size features, 50-60% of the time based on shape features, and 55-60% of the time based on color features. Non-competent embryos were correctly classified 65-75%, 55-60%, and 70-75% of the time based on size, shape, and color, respectively. These results can be used effectively to identify and select competent embryos for improved regeneration efficiency.

A comparison of shoot-forming and non-shoot-forming somatic embryos of sweet potato [Ipomoea batatas (L.) Lam.] using computer vision and histological analyses.

Diagnostic structural features for competence to form shoots were tested among sweet potato embryos by combining morphological image capture (using a computer vision system) with anatomical analyses (using light microscopy). Five major morphological variants (`perfect', `near perfect', `limited/no meristematic activity', `disrupted internal anatomy', and `proliferating') were identified among torpedo- and cotyledonary-stage embryos. Among these, only the first two were found to be competent for conversion into plantlets. Lack of organized shoot development in somatic embryos of sweet potato was associated with the following abnormalities: lack of an organized apical meristem, sparcity of dividing cells in the apical region, flattened apical meristem, and multiple meristemoids and/or diffuse meristematic activity throughout the embryo. Diagnostic separation of most shoot-forming and non-shoot-forming torpedo and cotyledonary embryo variants was achieved.

Noninvasive evaluation of somatic embryogenesis.

Callus Suspension Cultures of Ipomea batates Poir. cv. White Star were grown in an airlift bioreactor. A machine vision system was used to monitor nondestructively callus growth during a 10 day culture period. Growth data obtained with this system included the overall reactor population and population estimates for the 200-1200-microm fractions at 200-microm intervals. A model of callus growth was developed to explain the mechanics of callus enlargement. The model was based on the assumptions that (1) the calli could not subdivide or shrink, (2) there was a fixed percentage of the initial population for each fraction that was nonviable, and (3) growth rates did not vary with time during the culture period. It was determined that the growth rates and nonviable ratios decreased as fraction size increased.