Biomedical subjects

Enrico Blanzieri

Publications and source records attributed to Enrico Blanzieri.

3 recordsLinked to original sources

PubMed2006

Detecting potential labeling errors in microarrays by data perturbation.

MOTIVATION: Classification is widely used in medical applications. However, the quality of the classifier depends critically on the accurate labeling of the training data. But for many medical applications, labeling a sample or grading a biopsy can be subjective. Existing studies confirm this phenomenon and show that even a very small number of mislabeled samples could deeply degrade the performance of the obtained classifier, particularly when the sample size is small. The problem we address in this paper is to develop a method for automatically detecting samples that are possibly mislabeled. RESULTS: We propose two algorithms, a classification-stability algorithm and a leave-one-out-error-sensitivity algorithm for detecting possibly mislabeled samples. For both algorithms, the key structure is the computation of the leave-one-out perturbation matrix. The classification-stability algorithm is based on measuring the stability of the label of a sample with respect to label changes of other samples and the version of this algorithm based on the support vector machine appears to be quite accurate for three real datasets. The suspect list produced by the version is of high quality. Furthermore, when human intervention is not available, the correction heuristic appears to be beneficial.

Artifacts↗

PubMed2004

Clinical validation of an automated system for supporting the early diagnosis of melanoma.

BACKGROUND: Early diagnosis and surgical excision is the most effective treatment of melanoma. Well-trained dermatologists reach a high level of diagnostic accuracy with good sensitivity and specificity. Their performances increase using some technical aids as digital epiluminescence microscopy. Several studies describe the development of computerized systems whose aim is supporting dermatologists in the early diagnosis of melanoma. In many cases, the performances of those systems were comparable to those of dermatologists. However, this cannot tell us whether a system is able to support dermatologists. Actually, the computerized system might correctly recognize the same lesions that the dermatologist does, without providing them any useful advice and therefore being useless in recognizing early malignant lesions. PURPOSE: We present a novel approach to enhance dermatologists' performances in the diagnosis of early melanoma. We provide results of our evaluation of a computerized system combined with dermatologists. METHODS: A Multiple-Classifier system was developed on a set of 152 cases and combined to a group of eight dermatologists to support them by improving their sensitivity. RESULTS: The eight dermatologists have average sensitivity and specificity values of 0.83 and 0.66, respectively. The Multiple-Classifier system performs as well as the eight dermatologists (sensitivity range: 0.75-0.86; specificity range: 0.64-0.89). The combination with the dermatologists shows an average improvement of 11% (P=0.022) of dermatologists' sensitivity. CONCLUSION: Our results suggest that an automated system can be effective in supporting dermatologists because it recognizes different malignant melanomas with respect to the dermatologists.

Dermatology↗

PubMed2003

A multiple classifier system for early melanoma diagnosis.

Melanoma is the most dangerous skin cancer and early diagnosis is the key factor in its successful treatment. Well-trained dermatologists reach a diagnosis via visual inspection, and reach sensitivity and specificity levels of about 80%. Several computerised diagnostic systems were reported in the literature using different classification algorithms. In this paper, we will illustrate a novel approach by which a suitable combination of different classifiers is used in order to improve the diagnostic performances of single classifiers. We used three different kinds of classifiers, namely linear discriminant analysis (LDA), k-nearest neighbour (k-NN) and a decision tree, the inputs of which are 38 geometric and colorimetric features automatically extracted from digital images of skin lesions. Multiple classifiers were generated by combining the diagnostic outputs of single classifiers with appropriate voting schemata. This approach was evaluated on a set of 152 digital skin images. We compared the performances of multiple classifiers (2- and 3-classifier groups) between them and with respect to single ones (1-classifier group). We further compared the classifiers' performances with those of eight dermatologists. Classifiers' performances were measured in terms of distance from the ideal classifier. Compared with 1- and 2-classifier groups, performances of 3-classifier systems were significantly higher (P<0.0005 and P<0.001, respectively). No statistically significant differences were found between the 1- and 2-classifier groups (P=0.352). While the dermatologists group showed a level of performances significantly higher than the 1-classifier systems (P<0.020), no differences were found between the multiple classifier groups and the dermatologists groups, indicating comparable performances. This work suggests that a suitable combination of different kinds of classifiers can improve the performances of an automatic diagnostic system.

Algorithms↗