Genetic algorithm optimization of adaptive multi-scale GLCM features

We introduce a new second-order method of texture analysis called Adaptive Multi-Scale Grey Level Co-occurrence Matrix (AMSGLCM), based on the well-known Grey Level Co-occurrence Matrix (GLCM) method. The method deviates significantly from GLCM in that features are extracted, not via a fixed 2D weighting function of co-occurrence matrix elements, but by a variable summation of matrix elements in 3D localized neighborhoods. We subsequently present a new methodology for extracting optimized, highly discriminant features from these localized areas using adaptive Gaussian weighting functions. Genetic Algorithm (GA) optimization is used to produce a set of features whose classification worth is evaluated by discriminatory power and feature correlation considerations. We critically appraised the performance of our method and GLCM in pairwise classification of images from visually similar texture classes, captured from Markov Random Field (MRF) synthesized, natural, and biological origins. In these cross-validated classification trials, our method demonstrated significant benefits over GLCM, including increased feature discriminatory power, automatic feature adaptability, and significantly improved classification performance.

Multi-centre Phase II trial of the polyamine synthesis inhibitor SAM486A (CGP48664) in patients with metastatic melanoma

Purpose: To determine the activity and tolerability of SAM496A, an inhibitor of S-adenosylmethionine decarboxylase (SAMDC), in patients with metastatic melanoma who had not received prior chemotherapy. Selected patients were offered participation in two sub-studies examining early changes in tumor metabolism with FDG-PET and changes in tumor polyamine content. Patients and methods: Fifteen patients with measurable metastatic melanoma, normal cardiac function, and no known CNS metastases were eligible and received SAM486A by 1-hour IV infusion daily for 5 days every 3 weeks. Response was assessed by SWOG criteria. Results: No patient had a confirmed partial response. Fatigue/lethargy, myalgia and neutropenia were the main toxicities but no febrile neutropenia or grade 4 non-hematological toxicity occurred. Five patients had PET scans pre-treatment and on days 8-12 of cycle 1. No patient had reduction of tumor metabolism. Serial biopsy in one patient showed alterations in polyamines consistent with SAMDC inhibition. Conclusions: Using the present dose and schedule of administration, SAM486A does not have significant therapeutic potential in patients with metastatic melanoma.