Fractal Dimension, Form and Shape Factors for the Quantification of Nuclear Signature Profiles

Patient-oriented diagnosis based on an accurate quantification of the lesion may improve the patient's diagnosis/prognosis as compared to diagnosis/prognosis based on population statistics. A nuclear signature is a technique developed to quantify lesions with great specificity and accuracy and is an important tool for patient-oriented diagnosis. However, nuclear signatures are thus far mainly applied in visual evaluations. This paper describes a method to quantify nuclear signatures based on a fractal and geometrical analysis. The result - a new set of fractal-geometrical features - is evaluated by comparing its diagnostic performance with classical karyometric features on 3 tumour types. Results show that the diagnostic performance of the feature sets is similar but that classification scores are increased by combining the two sets. Moreover, classification rates of malignancy associated changes of colon lesions are higher by using the fractal-geometrical feature set, proving its ability to detect sub visual changes of early premalignant transformation.