Ultrasound elastography is a recent ultrasound method used for the calculation of tissue elasticity distribution in real-time . The method allows the reconstruction of tissue elasticity (i.e. the elasticity modulus) and reveals directly the physical properties of the tissue, consequently showing different tissue hardness patterns that are determined by diseases.
Elastography typically estimates the axial strain (along the direction of insonification / compression) by analyzing ultrasonic signals obtained with standard ultrasonographic systems . Thus, the RF signals returned from tissue structures before and after slight compression (about 1%) are compared. Tissue elastography can be easily performed real-time with conventional probes, including the linear EUS probes used for the examination of the pancreas. The calculation of tissue elasticity distribution is performed in real-time and the examination results are represented as transparent overlay colour images overimposed on the conventional gray-scale B-mode images.
This method thus allows the characterization of many tumors, because they are stiffer than normal tissues. Ultrasound elastography was previously used for the diagnosis of breast lesions , prostate cancer  and thyroid nodules . However, the value of endoscopic ultrasound elastography for the diagnosis of pancreatic focal masses is not clear for the current moment, as some authors couldn’t differentiate benign and malignant pancreatic tumors . Moreover, the intense fibrotic reaction and calcifications in chronic pancreatitis induce strain differences, and it is not clear if elastography is sensitive enough to detect them.
The study protocol is based on a semi-quantitative approach of EUS elastography data (movies) consisting of characterization of manually user-defined regions of interest, based on the hue histograms of the individual focal masses. Due to the inherent bias induced by selection of images from a dynamic sequence of EUS elastography, we have previously reported on the utility of using computer-aided diagnosis by averaging images from a dynamic sequence of EUS elastography . A special plugin (based on the ImageJ software, NIH, Bethesda, MD, USA) was used to compute hue histograms on average EUS elastography images, while the hue histograms values for each patient (0 to 255 values) were further used to classify the patients with benign and malignant lesions.
2. Aims of the study
The aim of the study is to assess elastography during EUS examinations of focal pancreatic masses, and to consequently differentiate benign vs malignant pancreatic masses in a prospective multicenter design.
3. Patients and methods
The study design is prospective, blinded and multi-center, comparing endoscopic ultrasound elastography (EUS-EG) results for the detection and characterization of focal pancreatic masses by using artificial intelligence techniques, in comparison with the gold standard represented by pathology. The study will be performed with the approval of the institutional board review of each center.
· Patients diagnosed with solid pancreatic tumor masses, with cytological / histological confirmation
· Age 30 to 75 years old, men or women
· Signed informed consent for EUS with elastography and FNA biopsy
· Prior surgical treatment with curative intent or chemo-radiotherapy
· Patients diagnosed with mucin producing tumors, pancreatic cystic tumors, etc.
4. Data collection
- Personal data (name, surname, age, admission date, SSN, diagnosis at admission)
5. Imaging tests
- All patients with a suspicion of pancreatic masses should undergo EUS and EUS-EG
- EUS with EUS-guided FNA and elastography
- Protocol of EUS with EUS-FNA should include linear EUS instruments with complete examinations of the pancreas.
- Tumor characteristics (echogenicity, echostructure, size) will be described as well as presence / absence of power Doppler signals.
- EUS-FNA will be performed in all pancreatic masses with at least three passes
- All examiners should be blinded for the results of pathology
- EUS-EG procedure:
- EUS-EG will be performed during an usual EUS examination (7.5 MHz frequency), with two movies of 10 seconds recorded on the embedded HDD in order to minimize variability and to increase repeatability of acquisition.
- A two panel image with the usual conventional gray-scale B-mode EUS image on the right side and with the elastography image on the left side will be used.
- The region of interest for EUS-EG will be preferably larger than the focal mass, in order to include the surrounding structures.
- In order to minimize the human bias, all the post-processing and computer analysis of digital movies will be performed within the IT Center in Craiova, with all programmers and statisticians being blinded to the clinical, pathological and imaging data, with the exception of the average hue histogram values calculated from a second region of interest manually traced around the focal mass.
6. Final diagnosis
- The diagnosis of chronic pancreatitis will be based on the clinical information (history of alcohol abuse, previous diagnosis of chronic pancreatitis or diabetes mellitus), as well as a combination of imaging methods (ultrasound, CT and EUS). At least four criteria of chronic pancreatitis during EUS will be considered for the positive diagnosis. The diagnosis of chronic pseudotumoral pancreatitis will always be confirmed by surgery or by a follow-up of at least six months used to exclude malignancy in the patients that will not be operated on.
- A positive cytological diagnosis will be taken as a final proof of malignancy of the pancreas mass. The diagnoses obtained by EUS-FNA will be further verified either by surgery or during a clinical follow-up of at least 6 months.
- Pathology samples obtained from duodeno-pancreatectomies or caudal pancreatectomies done with curative intent, as well as microhistological fragments obtained through EUS-FNA biopsy will be processed by paraffin embedding with usual colorations (haematoxylin-eosin), with subsequent immune-histochemistry at the discretion of the participating centers pathologists in order to exclude neuroendocrine tumors / pancreatic metastases.
- The patients will be followed-up for at least six months through clinical examination, biological exams and transabdominal ultrasound, eventually with a repeat spiral CT / EUS after six months.
7. Statistical analysis
· Descriptive statistics
o All results will be expressed as mean ± standard deviation (SD). Differences between the patients with pancreatic cancer and chronic pancreatitis will performed by the two-sample t-test (two independent samples). Since this parametric method makes assumptions about normality and similar variances, we will initially perform both the Kolmogorov-Smirnov and Shapiro-Wilk W normality tests and verify the equality of variances assumption with the F test. In the case of the two-sample t-test, we will also perform the non-parametric alternative given by the Mann-Whitney U test, since in some instances it may even offer greater power to reject the null hypothesis than the t-test.
o Since with more than two groups of observations it is far better to use a single analysis that enables us to look at all the data in the same time, we will also perform the one-way analysis of variance (ANOVA) method with the same baseline assumptions. A p-value less than 0.05 will be considered as statistically significant.
· Sensitivity, specificity, positive predictive value, negative predictive value and accuracy of EUS-EG will be determined in comparison with the final diagnosis
8. Computer–aided medical diagnosis
The use of the modern computer technology in medical decision support is now widespread and pervasive across a wide range of medical area. Thus, the Computer-Aided Medical Diagnosis (CAMD) is becoming an increasing important area for intelligent computer systems. Under these circumstances, there is a tremendous opportunity for the Artificial Intelligence, in general, and the Machine Learning, in particular, to assist the physicians deal with the flood of patient information and scientific knowledge. As a broad subfield of the Artificial Intelligence, the machine learningExploration and analysis by automatic means of large quantities of data in order to extract implicit, previously unknown and potentially useful information and discover meaningful patterns”). Machine learning can be viewed as an attempt to create a collaborative framework between human intuition and the huge computation power of the machines (computers). is concerned with the design and development of algorithms and techniques that allow computers to "learn". The major focus of the machine learning research is to extract information from data automatically, by computational and statistical methods and hence, machine learning is closely related to Data Mining (“
Common machine learning methods we shall use include:
· Classification and decision trees;
· Neural Networks;
· Evolutionary algorithms
· Support vector machines
8.1. Classification and decision tree
Classification and decision trees are used to predict membership of cases into two or more categories from their measurements on one or more predictor variables (making decisions algorithms). A distinctive characteristic of classification and decision trees is their flexibility. The ability of classification and decision trees to examine the effects of the predictor variables one at a time, rather than just all at once, is well-known. The ability of classification and decision trees to perform univariatesplits and examining the effects of predictors one at a time has implications for the variety of types of predictors that can be analyzed (categorical predictors, continuous predictors, or any mix of the two types of predictors).
Classification and decision trees are not limited to univariate splits on the predictor variables. When continuous predictors are indeed measured on at least an interval scale, linear combination splits, similar to the splits for linear discriminant analysis, can be computed for classification trees. The classification and decision trees can be used in any classification of patients, decision concerning diseases, tissues, tumors types etc. The tree graph presents all the information in a simple, straightforward way, and probably allows one to digest the information in much less time than it takes for the traditional taxonomic techniques.
8.2. Neural Networks
The artificial neural network, commonly referred to as neural network (NN), is an information processing paradigm that is inspired by the way the human brain processes information. The key of this paradigm is the novel architecture of the information processing system, consisting of a large number of highly interconnected processing elements (neurons) working together to solve specific problems. This complex processing system, storing experimental knowledge and making it available for use, offers efficient mechanisms to extract patterns and detect trends that are too complex to be noticed by humans.
There are two phases in neural information processing: the training phase and the testing phase. In the training phase, a training dataset is used to the progressive adjustments of the weighted interconnections (synaptic weights) that define the neural model. In this context, we speak of a training paradigm that refers to the process by which the free synaptic parameters of the NN are adapted to a process of stimulation by the environment in which the network is embedded. Afterwards, the trained neural model will be used in the testing phase to process testing patterns, yielding the true classification performance.
Basically, NN is trained to associate outputs with input patterns. When NN is used, it identifies the input pattern and tries to output the associated output pattern. If a pattern that has no output associated with it is given as an input, NN gives the output that corresponds to a taught input pattern that is least different from the given pattern. NN will be used to learn how to classify patients, diseases, tissues, tumors etc., based on a training dataset of known cases.
8.3. Evolutionary algorithms
Evolutionary algorithms presume the existence of a population of candidate solutions (individuals) to a problem to be solved that must adapt to the task requirements (fitness assignment). The natural selection, the recombination and mutation mechanisms and the survival of the fittest triggers the average fitness of passing generations of individuals to rise step by step until the optimal solution(s) is (are) reached.
In order to tackle diagnosis, evolutionary algorithms are applied under the form of an evolutionary classifier. The individuals are represented by decision rules that are evolved to fit the data samples and the aim is to achieve a complete rule set that models the decision making. The novel evolutionary classifiers are imagined in two distinct operating ways. The first direction involves the use of a multi-modal EA to discover the optimal rules for all classes of diagnosis. A second possibility regards the use of co-evolution to model the interaction between rules in solving the diagnosis task. On the one hand, population of rules, one for each diagnosis outcome, can cooperate towards completing an optimal rule set to fit to the data. On the other hand, a population of rules and a population of data samples can compete in an inverse fitness interaction that generates the evolution.
8.4. Support vector machines
Another way to target diagnosis through evolutionary algorithms is represented by hybridizations to classification-specific paradigms, such as support vector machines. The standard support vector machines regard diagnosis through the geometrical separation of positive and negative data samples. Despite the originality and performance of the learning vision, the inner training engine is intricate, constrained, rarely transparent and unable to offer convergence for any decision function. Therefore, an evolutionary resembling support vector machines technique is employed which considers the learning task as in support vector machines but uses an evolutionary algorithm to solve the optimization problem of determining the separation surface.
1. Frey H. Real-time elastography. A new ultrasound procedure for the reconstruction of tissue elasticity. Der Radiologe 2003; 43 (10): 850-855.
2. Ophir J, Alam KA, Garra B, et al. Elastography. Ultrasonic estimation and imaging of the elastic properties of tissues. Proceedings of the Institution of Mechanical Engineers, Part H. J Eng Med 1999; 213: 203-233.
6. Janssen J, Schlörer E, Greiner L. EUS elastography of the pancreas: feasability and pattern description of the normal pancreas, chronic pancreatitis, and focal pancreatic lesions. Gastrointest Endosc 2007; 65: 971-978.
7. Săftoiu A, Vilmann P, Ciurea T, Popescu GL, Iordache A, Hassan H, Gorunescu F, Iordache S. Dynamic analysis of endoscopic ultrasound (EUS) elastography used for the differentiation of benign and malignant lymph nodes. Gastrointest Endosc 2007; 66: 291-300.