Search

Background An increase in naturally-occurring porphyrins has been described in the blood of subjects bearing different kinds of tumors, including colorectal, and this is probably related to a systemic alteration of heme metabolism induced by tumor cells. The aim of our study was to develop an artificial neural network (ANN) classifier for early detection of colorectal adenocarcinoma based on plasma porphyrin accumulation and risk factors. Methods We measured the endogenous fluorescence of blood plasma in 100 colorectal adenocarcinoma patients and 112 controls using a conventional spectrofluorometer. Height, weight, personal and family medical history, use of alcohol, red meat, vegetables and tobacco were all recorded. An ANN model was built up from demographic data and from the integral of the fluorescence emission peak in the range 610–650 nm. We used the Receiver Operating Characteristic (ROC) curve to assess performance in distinguishing colorectal adenocarcinoma patients and controls. A liquid chromatography-high resolution mass spectrometry (LC-HRMS) analytical method was employed to identify the agents responsible for native fluorescence. Results The fluorescence analysis indicated that the integral of the fluorescence emission peak in the range 610–650 nm was significantly higher in colorectal adenocarcinoma patients than controls (p

Rationale and Objectives This study evaluates the influence of the calibrated luminance level of medical displays in the detectability of microcalcifications and spiculated lesions in digital breast tomosynthesis images. Materials and Methods Four models of medical displays with calibrated maximum and minimum luminance, respectively, ranging from 500 to 1000 cd/m 2 and from 0.5 to 1.0 cd/m 2 , were investigated. Forty-eight studies were selected by a senior radiologist: 16 with microcalcifications, 16 with spiculated lesions, and 16 without lesions. All images were anonymized and blindly evaluated by one senior and two junior radiologists. For each study, lesion presence or absence and localization statements, interpretative difficulty level, and overall quality were reported. Cohen's kappa statistic was computed between monitors and within or between radiologists to estimate the reproducibility in correctly identifying lesions; for multireader-multicase analysis, the weighted jackknife alternative free-response receiver operating characteristic statistical tool was applied. Results Intraradiologist reproducibility ranged from 0.75 to 1.00. Interreader as well as reader-truth agreement values were >0.80 and higher with the two 1000 cd/m 2 luminance displays than with the lower luminance displays for each radiologist. Performances in the detectability of breast lesions were significantly greater with the 1000 cd/m 2 luminance displays when compared to the display with the lowest luminance value ( P value Conclusions Our findings highlight the role of display luminance level on the accuracy of detecting breast lesions.

In the present work we investigated the possible role of the native fluorescence of blood plasma in the management of colorectal cancer (CRC) and its feasibility as a new tumor marker. Sample of blood was collected from 248 asymptomatic blood donors and from 246 CRC patients. The native fluorescence of blood plasma was measured using a conventional spectrofluorimeter. The intensity of fluorescence of blood plasma at 623 nm (IF623), reasonably ascribed to endogenous porphyrins, was significantly higher in CRC patients than in healthy subjects. The diagnostic capability of IF623 in the discrimination between healthy subjects and CRC patients was tested by Receiving Operating Characteristic (ROC) curve analysis, which resulted in an Area Under the Curve (AUC) of 0.72+/-0.01. Fluorescence measurement of blood plasma might be considered diagnostically useful as a candidate for a new tumor marker for CRC management. The procedure is characterised by a great acceptability and by a very low cost, and might be used in a two-step screening wherein an IF623 positive result is followed by colonoscopy.

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.

Aims and background We designed a comparative planning study aimed at quantifying the advantages of intensity-modu-lated radiotherapy (IMRT) over the conventional 3-field technique (3FT) and a 5-field conformal technique (5FCT) for head and neck (HN) cancer. Methods We selected 9 patients treated at our institution with curative radiotherapy for a HN cancer. For all cases 4 plans were generated: 2 plans using the “standard” techniques (3FT and 5FCT), a third plan using IMRT, and a fourth “mixed” plan using IMRT followed by a conventional boost. Results Our study confirmed literature data on the ability of IMRT to significantly decrease the dose received by organs at risk, compared with previous techniques. Target coverage was systematically better with 5FCT and IMRT than with 3FT. However, the increase in coverage of both PTV2 and PTV1 was only about 3-5% and this was achieved at the price of a similar increase in maximum dose (D1%). Volumetric parameters (V100%, V95%) were much more sensitive in detecting the improvement with IMRT. Conclusions The improvement of target coverage attained by IMRT, as compared with conventional and conformal techniques, might be overestimated by data currently available in the medical literature. If treatment with conventional techniques is planned using all tools provided by currently available fully 3-D planning systems, excellent target coverage can be obtained.

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.

Amelanotic cutaneous melanoma (ACM) often defies clinical diagnosis because of the lack of pigmentation. In an attempt to find diagnostic clues, we retrospectively studied the clinical features of 15 thin (< 1 mm thick or Clark level I) ACM lesions. The clinical features of early ACMs are identified and illustrated to enable early diagnosis and cure of these lesions. The typical early lesion presents as an asymmetric macula, which may be uniformly pinkish or reddish or, more often, has faint light pigmentation (tan, brown or grey) at the periphery; it has borders that may be well- or ill-defined. In our study, these features suggested the correct clinical diagnosis in only a minority (40%) of cases. Nine cases in this series were also subjected to dermatoscopy. By this technique we identified, as constant feature, the presence of small red dots, evenly distributed or grouped on a whitish or pink-red background. Our results show the importance of dermatoscopy in the evaluation of equivocal pink or reddish lesions. Red dots seen with this technique can be an important sign for the diagnosis of thin ACM. Since this sign does not appear to be pathognomonic, the presence of an associated pigmentary network can be decisive in the differential diagnosis.

Our aim in the present research is to investigate the diagnostic performance of artificial neural networks (ANNs) applied to multispectral images of cutaneous pigmented skin lesions as well as to compare this approach to a standard traditional linear classification method, such as discriminant function analysis. This study involves a series of 534 patients with 573 cutaneous pigmented lesions (132 melanomas and 441 nonmelanoma lesions). Each lesion was analyzed by a telespectrophotometric system (TS) in vivo, before surgery. The system is able to acquire a set of 17 images at selected wavelengths from 400 to 1040 nm. For each wavelength, five lesion descriptors were extracted, related to the criteria of the ABCD (for asymmetry, border, color, and dimension) clinical guide for melanoma diagnosis. These variables were first reduced in dimension by the use of factor analysis techniques and then used as input data in an ANN. Multivariate discriminant analysis (MDA) was also performed on the same dataset. The whole dataset was split into two independent groups: i.e., train (the first 400 cases, 95 melanomas) and verification set (last 173 cases, 37 melanomas). Factor analysis was able to summarize the data structure into ten variables, accounting for at least 90% of the original parameters variance. After proper training, the ANN was able to classify the population with 80% sensitivity, 72% specificity, and 78% sensitivity, 76% specificity for the train and validation set, respectively. Following ROC analysis, area under curve (AUC) was 0.852 (train) and 0.847 (verify). Sensitivity and specificity values obtained by the standard discriminant analysis classifier resulted in a figure of 80% sensitivity, 60% specificity and 76% sensitivity, 57% specificity for the train and validation set, respectively. AUC for MDA was 0.810 and 0.764 for the train and verify set, respectively. Classification results were significantly different between the two methods both for diagnostic scores and model stability, which was worse for MDA.

Successful treatment of melanoma depends directly on early diagnosis. Such a diagnosis is based on clinical examination and dermatoscopy. Recently, automated instruments for melanoma detection are under development.To prospectively evaluate the diagnostic possibilities provided by clinical and dermatoscopic examinations and by a computerized telespectrophotometric system (TS).The study involves a consecutive series of 298 patients with 313 cutaneous pigmented lesions (66 melanomas and 247 non-melanoma lesions). Each lesion was subjected to the triple diagnostic evaluation, before surgery. Results were expressed in terms of sensitivity and specificity of each kind of evaluation.Clinical evaluation had sensitivity and specificity values of 86 and 77%, respectively, whereas dermatoscopy gave corresponding values of 91 and 74%. TS assessment resulted in a sensitivity of 80% and a specificity of 49%. Differences between clinical and dermatoscopic diagnoses lacked statistical significance (p = 0.22), whereas there was a significant difference comparing both clinical and TS evaluations (p0.01) and dermatoscopic and TS evaluations (p0.01). Combining clinical and dermatoscopic evaluations, a sensitivity of 97% was achieved. Addition of TS has not changed this figure.Results of this study confirm and stress the importance of dermatoscopy in the diagnosis of melanoma. Clinical evaluation coupled with dermatoscopy can be considered the cornerstone of such a diagnosis. Although TS is able to achieve interesting results, at present it cannot significantly compete with any of the other tested methods.

Aim and background Fluorescence spectroscopy of biomolecules is considered a promising method to discriminate in vivo normal tissue from malignant tissue at various sites including breast, cervix, lung, and colon. However, only few studies have been reported on the feasibility of exploiting fluorescence spectroscopy of blood to characterize pathological changes usable in diagnostic oncology. In this study, the fluorescence characteristics of human blood plasma have been studied in the visible spectral range in an attempt to discriminate patients with colorectal cancer from subjects of a control population. Patients and methods The study involved 341 subjects, including 169 blood donors with no evidence of disease, 143 patients bearing colorectal adenocarcinomas (36 in the colon, 38 in the sigmoid colon and 69 in the rectum), 11 patients with local relapse, 10 patients with familial adenomatous polyposis and 8 with single adenomas. Blood samples were collected from all subjects and plasma fluorescence spectrum was analyzed using a conventional spectrofluorometer. Results The intensity of a fluorescence emission peak around 615–635 nm, which could reasonably be ascribed to endogenous porphyrins, was significantly different between patients bearing colorectal cancer and blood donors. The diagnostic capacity of the method was tested by ROC analysis, which resulted in an area under the curve of 0.72, close to that reported for the CEA test. Conclusion These results, although preliminary, suggest the potential of fluorescence measurements of blood plasma as an additional method for diagnostic application in colon cancer.