Abstract: Apparatus and methods are described including analyzing one or more microscopic images of the blood sample using a machine-learning classifier. An entity within the one or more microscopic images is identified using a first classification model, and a first estimated concentration of the entity within the sample is determined, based upon the entity as identified using the first classification model. The entity is identified within the one or more microscopic images using a second classification model, and a second estimated concentration of the entity within the sample is determined, based upon the entity as identified using the second classification model. The first and second estimated concentrations are compared to each other, and, in response to the comparison, a hybrid classification model that is a hybrid of the first and second classification models is used. Other applications are also described.

Abstract: Apparatus and methods are described including analyzing one or more microscopic images of the blood sample using a machine-learning classifier. An entity within the one or more microscopic images is identified using a first classification model, and a first estimated concentration of the entity within the sample is determined, based upon the entity as identified using the first classification model. The entity is identified within the one or more microscopic images using a second classification model, and a second estimated concentration of the entity within the sample is determined, based upon the entity as identified using the second classification model. The first and second estimated concentrations are compared to each other, and, in response to the comparison, a hybrid classification model that is a hybrid of the first and second classification models is used. Other applications are also described.

Abstract: Apparatus and methods are described use with a bodily sample that contains cells. A microscope (24) is focused, such that a focal plane of the microscope (24) at least approximately coincides with a level at which at least some cells belonging to the sample are at least partially disposed. At least one on-focus microscopic image of the sample, while the focal plane of the microscope (24) approximately coincides with the level. The microscope (24) is focused such that the focal plane of the microscope is offset with respect to the level, at least one off-focus microscopic image of the sample is acquired, while the focal plane of the microscope (24) is offset with respect to the level. A property of at least a portion of the sample is determined, at least partially based upon the on-focus and off-focus images. Other applications are also described.