The aim of this research was to evaluate the performance of a new spectroscopic system in the diagnosis of melanoma. This study involves a consecutive series of 1278 patients with 1391 cutaneous pigmented lesions including 184 melanomas. In an attempt to approach the 'real world' of lesion population, a further set of 1022 not excised clinically reassuring lesions was also considered for analysis. Each lesion was imaged in vivo by a multispectral imaging system. The system operates at wavelengths between 483 and 950 nm by acquiring 15 images at equally spaced wavelength intervals. From the images, different lesion descriptors were extracted related to the colour distribution and morphology of the lesions. Data reduction techniques were applied before setting up a neural network classifier designed to perform automated diagnosis. The data set was randomly divided into three sets: train (696 lesions, including 90 melanomas) and verify (348 lesions, including 53 melanomas) for the instruction of a proper neural network, and an independent test set (347 lesions, including 41 melanomas). The neural network was able to discriminate between melanomas and non-melanoma lesions with a sensitivity of 80.4% and a specificity of 75.6% in the 1391 histologized cases data set. No major variations were found in classification scores when train, verify and test subsets were separately evaluated. Following receiver operating characteristic (ROC) analysis, the resulting area under the curve was 0.85. No significant differences were found among areas under train, verify and test set curves, supporting the good network ability to generalize for new cases. In addition, specificity and area under ROC curve increased up to 90% and 0.90, respectively, when the additional set of 1022 lesions without histology was added to the test set. Our data show that performance of an automated system is greatly population dependent, suggesting caution in the comparison with results reported in the literature. In our opinion, scientific reports should provide, at least, the median values of thickness and dimension of melanomas, as well as the number of small (6 mm) melanomas.

In an attempt to overcome the subjectiveness of clinical observation in the diagnosis of cutaneous melanoma, a computerized method is proposed. Reflectance images of 237 pigmented lesions (67 melanomas and 170 non-melanomas) were analysed using a telespectrophotometric technique. This device consists of a CCD camera with 17 interference filters. Images were acquired at selected wavelengths, from 420 to 1040 nm. Morphological and reflectance related parameters were extracted from the wavelength-dependent images of the lesions. The most significant features in the comparison between benign and malignant lesions were: lesion dimension (P < 10(-8) at 578 nm); mean value (P < 10(-7) at 940 nm) and standard deviation (P < 10(-4) at 904 nm) of lesion reflectance; lesion roundness (P < 10(-5) at 461 nm); and border irregularity (P < 10(-4) at 461 nm). Based on these parameters, a discriminant function between the two populations of lesions (naevi and melanomas) was obtained. By using the results of the analysis of the recruited lesions as 'training data', discriminant functions enabled the assignment of a score, or a 'risk probability', to each studied lesion. By imposing a sensitivity of 80% (a figure that mimics the diagnostic capability of an experienced clinician), entering or not entering the lesion dimension as input data in the discriminant analysis led to a specificity of 51% or 46% respectively. The high number of false-positive cases, which is a consequence of the selection criteria of the lesions, is, at present, the major limitation of the current technique. Nevertheless, our results suggest that an imaging-based computer-assisted device could be capable of discriminating malignant lesions mainly by evaluation of reflectance, especially in the infrared region, and shape properties. The dimension of a lesion should not be essential in the diagnosis of melanoma and, in our opinion, small melanomas should be recognized by a computer system as well as they are on clinical grounds.

The proposed technique allows to produce a stable and reproducible phantom, with accurately predictable optical properties, easy to make and to handle. This phantom is a useful tool for numerous applications involving light interaction with biologic tissue.

Various instruments based on acquisition and elaboration of images of pigmented skin lesions have been developed in an attempt to in vivo establish whether a lesion is a melanoma or not. Although encouraging, the response of these instruments, e.g. epiluminescence microscopy, reflectance spectrophotometry and fluorescence imaging, cannot currently replace the well-established diagnostic procedures. However, in place of the approach to instrumentally assess the diagnosis of the lesion, recent studies suggest that instruments should rather reproduce the assessment by an expert clinician of whether a lesion has to be excised or not. The aim of this study was to evaluate the performance of a spectrophotometric system to mimic such a decision. The study involved 1794 consecutively recruited patients with 1966 doubtful cutaneous pigmented lesions excised for histopathological diagnosis and 348 patients with 1940 non-excised lesions because clinically reassuring. Images of all these lesions were acquired in vivo with a multispectral imaging system. The data set was randomly divided into a train (802 reassuring and 1003 excision-needing lesions, including 139 melanomas), a verify (464 reassuring and 439 excision-needing lesions, including 72 melanomas) and a test set (674 reassuring and 524 excision-needing lesions, including 76 melanomas). An artificial neural network (ANN(1)) was set up to perform the classification of the lesions as excision-needing or reassuring, according to the expert clinicians' decision on how to manage each examined lesion. In the independent test set, the system was able to emulate the clinicians with a sensitivity of 88% and a specificity of 80%. Of the 462 correctly classified as excision-needing lesions, 72 (95%) were melanomas. No major variations in receiver operating characteristic curves were found between the test and the train/verify sets. On the same data set, a further artificial neural network (ANN(2)) was then architected to perform classification of the lesions as melanoma or non-melanoma, according to the histological diagnosis. Having set the sensitivity in recognizing melanoma to 95%, ANN(1) resulted to be significantly better in the classification of reassuring lesions than ANN(2). This study suggests that multispectral image analysis and artificial neural networks could be used to support primary care physicians or general practitioners in identifying pigmented skin lesions that require further investigations.

These results, although preliminary, suggest the potential of fluorescence measurements of blood plasma as an additional method for diagnostic application in colon cancer.