This paper proposes a method to reduce the number of false-positives (FP) in a computer-aided detection (CAD) scheme for automated detection of architectural distortion (AD) in digital mammography. AD is a subtle contraction of breast parenchyma that may represent an early sign of breast cancer. Due to its subtlety and variability, AD is more difficult to detect compared to microcalcifications and masses, and is commonly found in retrospective evaluations of false-negative mammograms. Several computer-based systems have been proposed for automated detection of AD in breast images. The usual approach is automatically detect possible sites of AD in a mammographic image (segmentation step) and then use a classifier to eliminate the false-positives and identify the suspicious regions (classification step). This paper focus on the optimization of the segmentation step to reduce the number of FPs that is used as input to the classifier. The proposal is to use statistical measurements to score the segmented regions and then apply a threshold to select a small quantity of regions that should be submitted to the classification step, improving the detection performance of a CAD scheme. We evaluated 12 image features to score and select suspicious regions of 74 clinical Full-Field Digital Mammography (FFDM). All images in this dataset contained at least one region with AD previously marked by an expert radiologist. The results showed that the proposed method can reduce the false positives of the segmentation step of the CAD scheme from 43.4 false positives (FP) per image to 34.5 FP per image, without increasing the number of false negatives.
The interplay between photosensitivity and chemical sensitivity can give rise to a number of properties that can extend
the sensitivity in each separate context. Here we illustrate how the sensitivity to visble light of porphyrins coated ZnO
nanorods can modify the gas detection enhancing the sensitivity in particular towards electron donor species.
Reflectance anisotropy spectra of porphyrin thin films (30 monolayers) show a permanent change in their line shape when porphyrins are exposed to some specific analytes (e.g., amines). From this experimental evidence, we concluded that a molecular package adjustment occurred in the film upon interaction with the volatile compound, most likely in the outermost layers. This result is of paramount importance for the consequent application of these films in optical gas-sensors. Consequently, this system could be used as a prototype for optical gas-sensing of aggressive analytes or, more ambitiously, to investigate the porphyrin-analyte interaction.
Electronic Tongue systems have been widely used during last decades, reaching an high level of
performances in the detection and quantification of several matrices, such as for example waters, soft
and alcoholic drinks. Next step in research is represented by the miniaturization of these systems: it
is made possible by the integration of the knowledge on materials suitable for sensorial purpose and
the silicon technology, which allows the development of micro-dimensioned sensors. In this work
we report the development of a sensor array composed of 8 electro-polymerized porphyrin based
membranes, with an active area exposed to liquid of 0.5 mm2. The miniaturized system, integrated
on a single silicon wafer and completed by read-out electronics, was firstly tested towards standard
analytes and then applied on real white wine samples for the detection of some analytes mimicking
wine defects, namely H2S, SO2 and CH3CO2H.
An optical sensor for the detection of olive oil aroma is presented. It is capable of distinguishing different ageing levels of extra-virgin olive oils, and shows effective potential for achieving a non destructive olfactory perception of oil ageing. The sensor is an optical scanner, fitted with an array of metalloporphyrin-based sensors. The scanner provides exposure of the sensors to the flow of the oil vapor being tested, and their sequential spectral interrogation. Spectral data are then processed using chemometric methodologies.
A fiber optic multimeter is presented, consisting of a platform for interrogating an array of absorption-based chemical sensors. It has been validated on a set of porphyrin-based materials having gas-sensor potential. Discrimination between different kinds of gases has been demonstrated.