Classification of prostatic carcinoma with artificial neural networks using comparative genomic hybridization and quantitative stereological data

Dimensional study of prostate cancer using stereological tools

This study analyzes the dimensional changes of the glands from prostate cancer by applying stereology to estimate the variations in volume, length, surface, and cellular densities of tumor acini. Normal and tumor acini were visualized using immunohistochemistry for cytokeratin18. On immunostained sections, parameters related to the dimensions and cell population of prostate acini were measured. The immunohistochemical expression of proliferative cell nuclear antigen was also measured to correlate the quantitative changes estimated with the proliferative activity of the epithelium. The average cell volume in normal and tumor epithelium was estimated using the method of the nucleator. The relative size of the acini was similar in the carcinoma compared with the normal prostate. Within the acini, the fraction of acinar volume occupied by the epithelium was significantly higher in cancer than in the nontumor prostate. Conversely, the glandular lumen of the cancer acini is lower than in the normal acini. The significant increase of acinar length density in the carcinoma indicates that the glandular tree's growth in the carcinoma is higher and with more branches than in the case of nonneoplastic glands. The basal surface density is higher in the carcinoma than in the controls. The number of epithelial cells per unit length of acini was significantly decreased in the neoplastic glands. This "dilution" of the cell population along the cancer acinus can be explained by the significant increase in the tumor cell's mean cell volume.

Prediction of metastasis in advanced colorectal carcinomas using CGH data

Logistic Regression Model (LRM) and artificial neural networks (ANNs) as two nonlinear models have been used to establish a novel two-stage hybrid modeling procedure for prediction of metastasis in advanced colorectal carcinomas. Two different datasets were used in training and testing procedures. For the first stage of hybrid modeling procedure, LRM was used to evaluate the contribution of DNA sequence copy number aberrations detected by Comparative Genomic Hybridization in advanced colorectal carcinoma and its metastasis. Then, the most effective parameters were selected by the LRM. Selected effective parameters among 565 detected chromosomal gains and losses were as follows: gain of 20q11.2, loss of 1q42, loss of 13q34, gain of 5q12, gain of 17p13, loss of 2q22, loss of 11q24 and gain of 2p11.2. Consequently, neural network models were constructed and fed by the parameters selected by LRM to build hybrid predictors on the two databases during self-consistency and jackknife tests, and performance of the hybrid model was verified. The results showed that our two-stage hybrid model approach is very promising for prediction of metastasis in advanced colorectal carcinomas.

The identification of gut neuroendocrine tumor disease by multiple synchronous transcript analysis in blood

Gastroenteropancreatic (GEP) neuroendocrine neoplasms (NENs) are increasing in both incidence and prevalence. A delay in correct diagnosis is common for these lesions. This reflects the absence of specific blood biomarkers to detect NENs. Measurement of the neuroendocrine secretory peptide Chromogranin A (CgA) is used, but is a single value, is non-specific and assay data are highly variable. To facilitate tumor detection, we developed a multi-transcript molecular signature for PCR-based blood analysis. NEN transcripts were identified by computational analysis of 3 microarray datasets: NEN tissue (n = 15), NEN peripheral blood (n = 7), and adenocarcinoma (n = 363 tumors). The candidate gene signature was examined in 130 blood samples (NENs: n = 63) and validated in two independent sets (Set 1 [n = 115, NENs: n = 72]; Set 2 [n = 120, NENs: n = 58]). Comparison with CgA (ELISA) was undertaken in 176 samples (NENs: n = 81). 51 significantly elevated transcript markers were identified. Gene-based classifiers detected NENs in independent sets with high sensitivity (85–98%), specificity (93–97%), PPV (95–96%) and NPV (87–98%). The AUC for the NEN gene-based classifiers was 0.95–0.98 compared to 0.64 for CgA (Z-statistic 6.97–11.42, p<0.0001). Overall, the gene-based classifier was significantly (χ² = 12.3, p<0.0005) more accurate than CgA. In a sub-analysis, pancreatic NENs and gastrointestinal NENs could be identified with similar efficacy (79–88% sensitivity, 94% specificity), as could metastases (85%). In patients with low CgA, 91% exhibited elevated transcript markers. A panel of 51 marker genes differentiates NENs from controls with a high PPV and NPV (>90%), identifies pancreatic and gastrointestinal NENs with similar efficacy, and confirms GEP-NENs when CgA levels are low. The panel is significantly more accurate than the CgA assay. This reflects its utility to identify multiple diverse biological components of NENs. Application of this sensitive and specific PCR-based blood test to NENs will allow accurate detection of disease, and potentially define disease progress enabling monitoring of treatment efficacy.

Stereological evaluation of the volume and volume fraction of newborns' brain compartment and brain in magnetic resonance images

PURPOSE

Brain development in early life is thought to be critical period in neurodevelopmental disorder. Knowledge relating to this period is currently quite limited. This study aimed to evaluate the volume relation of total brain (TB), cerebrum, cerebellum and bulbus+pons by the use of Archimedes' principle and stereological (point-counting) method and after that to compare these approaches with each other in newborns.

METHODS

This study was carried out on five newborn cadavers mean weighing 2.220 ± 1.056 g with no signs of neuropathology. The mean (±SD) age of the subjects was 39.7 (±1.5) weeks. The volume and volume fraction of the total brain, cerebrum, cerebellum and bulbus+pons were determined on magnetic resonance (MR) images using the point-counting approach of stereological methods and by the use of fluid displacement technique.

RESULTS

The mean (±SD) TB, cerebrum, cerebellum and bulbus+pons volumes by fluid displacement were 271.48 ± 78.3, 256.6 ± 71.8, 12.16 ± 6.1 and 2.72 ± 1.6 cm3, respectively. By the Cavalieri principle (point-counting) using sagittal MRIs, they were 262.01 ± 74.9, 248.11 ± 68.03, 11.68 ± 6.1 and 2.21 ± 1.13 cm3, respectively. The mean (± SD) volumes by point-counting technique using axial MR images were 288.06 ± 88.5, 275.2 ± 83.1, 19.75 ± 5.3 and 2.11 ± 0.7 cm3, respectively. There were no differences between the fluid displacement and point-counting (using axial and sagittal images) for all structures (p > 0.05).

CONCLUSION

This study presents the basic data for studies relative to newborn's brain volume fractions according to two methods. Stereological (point-counting) estimation may be accepted a beneficial and new tool for neurological evaluation in vivo research of the brain. Based on these techniques we introduce here, the clinician may evaluate the growth of the brain in a more efficient and precise manner.

A new method of assessing the size of mandibular cysts on orthopantomograms: projection area fraction

This study was carried out to describe a simple, accurate, and practical technique for assessing mandible cysts' area on routine orthopantomograms using digital planimetry.Forty orthopantomograms showing mandibular cysts were obtained. The digitalized images were used to measure the surface area of the half mandibles and cysts using ImageJ software by an observer. The projection area of the half mandibles and cysts was provided by the machine. The surface area fraction of the cysts within the half mandibles was estimated by using the projection area fraction (PAF) approach. Estimations were repeated on films 1 month later.The mean PAF (mean +/- SEM) obtained by the same observer in 2 sessions was 10.6% +/- 2.3% and 13.0% +/- 2.0% for the right and left sides, respectively. The estimation results of 2 sessions were compared using the Wilcoxon signed rank test. This study found no statistical difference between the estimated PAF values (P > 0.05). The estimation results of the same observer at 1-month intervals were analyzed statistically to check intraobserver variation using a correlation analysis test, which found a high degree of agreement for the results estimated using the planimetric method for the right and left sides (r = 0.994, P < 0.001 and r = 0.999, P < 0.001, respectively).The method described in this study is inexpensive and fast because planimetry can be performed within a couple of minutes per subject. This method can also be used to monitor the size difference of lesions evaluated for clinical follow-up and research.

Predicting neuroendocrine tumor (carcinoid) neoplasia using gene expression profiling and supervised machine learning

BACKGROUND

A more accurate taxonomy of small intestinal (SI) neuroendocrine tumors (NETs) is necessary to accurately predict tumor behavior and prognosis and to define therapeutic strategy. In this study, the authors identified a panel of such markers that have been implicated in tumorigenicity, metastasis, and hormone production and hypothesized that transcript levels of the genes melanoma antigen family D2 (MAGE-D2), metastasis-associated 1 (MTA1), nucleosome assembly protein 1-like (NAP1L1), Ki-67 (a marker of proliferation), survivin, frizzled homolog 7 (FZD7), the Kiss1 metastasis suppressor (Kiss1), neuropilin 2 (NRP2), and chromogranin A (CgA) could be used to define primary SI NETs and to predict the development of metastases.

METHODS

Seventy-three clinically and World Health Organization pathologically classified NET samples (primary tumor, n = 44 samples; liver metastases, n = 29 samples) and 30 normal human enterochromaffin (EC) cell preparations were analyzed using real-time polymerase chain reaction. Transcript levels were normalized to 3 NET housekeeping genes (asparagine-linked glycosylation 9 or ALG9, transcription factor CP2 or TFCP2, and zinc finger protein 410 or ZNF410) using geNorm analysis. A predictive gene-based model was constructed using supervised learning algorithms from the transcript expression levels.

RESULTS

Primary SI NETs could be differentiated from normal human EC cell preparations with 100% specificity and 92% sensitivity. Well differentiated NETs (WDNETs), well differentiated neuroendocrine carcinomas, and poorly differentiated NETs (PDNETs) were classified with a specificity of 78%, 78%, and 71%, respectively; whereas poorly differentiated neuroendocrine carcinomas were misclassified as either WDNETs or PDNETs. Metastases were predicted in all cases with 100% sensitivity and specificity.

CONCLUSIONS

The current results indicated that gene expression profiling and supervised machine learning can be used to classify SI NET subtypes and accurately predict metastasis. The authors believe that the application of this technique will facilitate accurate molecular pathologic delineation of NET disease, better define its extent, facilitate the assessment of prognosis, and provide a guide for the identification of appropriate strategies for individualized patient treatment.

A new classification method using array Comparative Genome Hybridization data, based on the concept of Limited Jumping Emerging Patterns

Background

Classification using aCGH data is an important and insufficiently investigated problem in bioinformatics. In this paper we propose a new classification method of DNA copy number data based on the concept of limited Jumping Emerging Patterns. We present the comparison of our limJEPClassifier to SVM which is considered the most successful classifier in the case of high-throughput data.

Results

Our results revealed that the classification performance using limJEPClassifier is significantly higher than other methods. Furthermore, we show that application of the limited JEP's can significantly improve classification, when strongly unbalanced data are given.

Conclusion

Nowadays, aCGH has become a very important tool, used in research of cancer or genomic disorders. Therefore, improving classification of aCGH data can have a great impact on many medical issues such as the process of diagnosis and finding disease-related genes. The performed experiment shows that the application of Jumping Emerging Patterns can be effective in the classification of high-dimensional data, including these from aCGH experiments.

Prostate magnetic resonance imaging: multiexponential T2 decay in prostate tissue

PURPOSE

To investigate the T2 decay in prostate tissue for multiexponentiality and to assess how the biexponential model relates to established T2W contrast.

MATERIALS AND METHODS

A 32-echo spin-echo sequence was performed on 16 volunteers. Six single-voxel decay curves were sampled from each prostate. Prediction accuracies were assessed by jackknifing for the mono-, bi-, and triexponential models. The differences were evaluated by cross-validated analysis of variance (CVANOVA). Multiple linear regression was performed to assess the relation between parameters in the biexponential model and the contrast in T2W images.

RESULTS

Mono-, bi-, and triexponential models were preferred in 8 (10%), 72 (86%), and 4 (5%) cases, respectively. The biexponential short T2 was 64 msec (range 43 to 92 msec) and the long T2 was 490 msec (range 161 to 1319 msec). The fitted signal fraction, f, of the long T2 component was 27% (range 3% to 80%). The adjusted R(2) was 75.1% for the full regression model and decreased by 0.9%, 1.3%, and 39.2% when short T2, long T2, and f were removed from the model, respectively.

CONCLUSION

Prostatic T2 decay was, in general, biexponential. The differences between the T2 components were large enough for accurate quantification. The T2W image contrast was primarily predicted by the biexponential signal fractions.

Morphometric signature differences in nuclei of Gleason pattern 4 areas in Gleason 7 prostate cancer with differing primary grades on needle biopsy

PURPOSE

Since clinically significant upgrading of the biopsy Gleason score has an adverse clinical impact, ancillary tools besides the visual determination of primary Gleason pattern are essential to aid in better risk stratification.

MATERIALS AND METHODS

A total of 61 prostate biopsies were selected in patients with a diagnosis of Gleason score 7 prostatic adenocarcinoma, including 41 with primary Gleason pattern 3 and 20 with primary Gleason pattern 4. Slides from these tissues were stained using Feulgen stain, a nuclear DNA stain. Areas of Gleason pattern in all cases were analyzed for 40 nuclear morphometric descriptors of size, shape and chromatin using a CAS-200 system (BD). The primary outcome analyzed was the ability of morphometric features to identify visually determined primary Gleason pattern 4 on the biopsy. Data were analyzed using logistic regression as well as a C4.5 decision tree with and without preselection.

RESULTS

Decision tree analysis yielded the best model. Automatic feature selection identified minimum nuclear diameter as the most discriminative feature in a 3-parameter model with 85% classification accuracy. Using a preselected 3-parameter model including minimum diameter, angularity and sum optical density the decision tree yielded a slightly lesser accuracy of around 79%. Bootstrap validation of logistic regression results revealed that there was no unique model that could significantly explain the variance in primary Gleason pattern status, although minimum nuclear diameter was the most frequently selected parameter.

CONCLUSIONS

In this small cohort of patients with Gleason score 7 disease we report that Gleason pattern 4 nuclei from those with primary Gleason pattern 4 are generally larger with coarser chromatin compared with the Gleason pattern 4 in patients with primary Gleason pattern 3. These findings may aid in better risk stratification of the Gleason score 7 group by supplementing visual estimation of the percent of primary Gleason pattern 3 and 4 in the biopsy.

On the classification of prostate carcinoma with methods from spatial statistics

Gleason grading is a common method used by pathologists to determine the aggressivity of prostate cancer on the basis of histological slide preparations. The advantage of this grading system is a good correlation with the biological behavior of the tumor, while its drawback is the subjectivity underlying the judgements of pathologists. Therefore, an automation of Gleason grading would be desirable. In this paper, we examined 780 digitized grayscale images of 78 different cases, which were split into a training and a test set. We developed two methods based on combinations of morphological characteristics like area fraction, line length, and Euler number to classify into the categories "Gleason score < 7" and "Gleason score > or = 7." In particular, the distinction between these two classes has great impact on the prognosis of patients. The agreement of each method with visual diagnosis was 87.18% and 92.31% within the training set and 66.67% and 64.10% within the test set, respectively.

Application of artificial intelligence to the management of urological cancer

PURPOSE

Artificial intelligence techniques, such as artificial neural networks, Bayesian belief networks and neuro-fuzzy modeling systems, are complex mathematical models based on the human neuronal structure and thinking. Such tools are capable of generating data driven models of biological systems without making assumptions based on statistical distributions. A large amount of study has been reported of the use of artificial intelligence in urology. We reviewed the basic concepts behind artificial intelligence techniques and explored the applications of this new dynamic technology in various aspects of urological cancer management.

MATERIALS AND METHODS

A detailed and systematic review of the literature was performed using the MEDLINE and Inspec databases to discover reports using artificial intelligence in urological cancer.

RESULTS

The characteristics of machine learning and their implementation were described and reports of artificial intelligence use in urological cancer were reviewed. While most researchers in this field were found to focus on artificial neural networks to improve the diagnosis, staging and prognostic prediction of urological cancers, some groups are exploring other techniques, such as expert systems and neuro-fuzzy modeling systems.

CONCLUSIONS

Compared to traditional regression statistics artificial intelligence methods appear to be accurate and more explorative for analyzing large data cohorts. Furthermore, they allow individualized prediction of disease behavior. Each artificial intelligence method has characteristics that make it suitable for different tasks. The lack of transparency of artificial neural networks hinders global scientific community acceptance of this method but this can be overcome by neuro-fuzzy modeling systems.

Prediction of Prognosis in Patients with Epidural Hematoma by a New Stereological Method

Epidural hematoma (EH) is a serious clinical event observed in 2% of head trauma patients. Studies regarding the effects of epidural hematoma volume (EHV) on prognosis are not sufficient. In this study, we applied the volume fraction approach of the stereological method to estimate the hematoma to brain volume fraction (HBVF), and investigated the relation between the HBVF and prognosis. Fifty-nine EH patients (46 male and 13 female subjects, with average age of 21 years) admitted to the emergency clinic were included. The HBVF was estimated on the printed films of cranial computed tomography scans. For this purpose, common point counting grids were superimposed over the scan frames. According to the clinical results, patients were divided into three groups as complete recovery (43), disability (8) and exitus (8). The HBVF was compared with the clinical results. HBVF was determined as 4.6% in the patients with recovery, 8.1% in disability, and 7.6% in exitus patients. The HBVF values were lowest in recovery patients, and the difference between the recovery and the other two groups was statistically significant (p=0.007). However, there was no statistically significant difference in HBVF between disability and exitus patients (p>0.05). In conclusion, the HBVF can be an important tool to determine prognosis, and it can be measured using the volume fraction approach of stereological methods as developed in the present study.

Prediction of the axillary lymph node status in mammary cancer on the basis of clinicopathological data and flow cytometry

Axillary lymph node status is a major prognostic factor in mammary carcinoma. It is clinically desirable to predict the axillary lymph node status from data from the mammary cancer specimen. In the study, the axillary lymph node status, routine histological parameters and flow-cytometric data were retrospectively obtained from 1139 specimens of invasive mammary cancer. The ten variables: age, tumour type, tumour grade, tumour size, skin infiltration, lymphangiosis carcinomatosa, pT4 category, percentage of tumour cells in G2/M- and S-phases of the cell cycle, and ploidy index were considered as predictor variables, and the single variable lymph node metastasis pN (0 for pN0, or 1 for pN1 or pN2) was used as an output variable. A stepwise logistic regression analysis, with the axillary lymph node as a dependent variable, was used for feature selection. Only lymphangiosis carcinomatosa and tumour size proved to be significant as independent predictor variables; the other variables were non-contributory. Three paradigms with supervised learning rules (multilayer perceptron, learning vector quantisation and support vector machines) were used for the purpose of prediction. If any of these paradigms was used with the information from all ten input variables, 73% of cases could be correctly predicted, with specificity ranging from 82 to 84% and sensitivity ranging from 60 to 63%. If only the two significant input variables were used, lymphangiosis carcinomatosa and tumour diameter, the prediction accuracy was no worse. Nearly identical results were obtained by two different techniques of cross-validation (leave-one-out against ten-fold cross validation). It was concluded that: artificial neural networks can be used for risk stratification on the basis of routine data in individual cases of mammary cancer; and lymphangiosis carcinomatosa and tumour size are independent predictors of axillary lymph node metastasis in mammary cancer.