Three-dimensional virtual colonoscopy for automatic polyps detection by artificial neural network approach: New tests on an enlarged cohort of polyps

Abstract

Introduction and objective

In computer aided diagnosis (CAD) tools searching for colonrectal polyps and based on three dimensions virtual colonoscopy (3DVC) using computed tomography (CT) images, the reduction of the occurrence of false-positives (FPs) still represents a challenge because they are source of unreliability. Following an encouraging previous supervised approach Bevilacqua et al., Three-dimensional Virtual Colonoscopy for Polyps Detection by Supervised Artificial Neural Networks D.-S. Huang et al. (Eds.): ICIC, LNBI 6840, Springer-Verlag, Berlin Heidelberg, (2011), pp. 596–603, the aim of this work is to discuss, in details, how the adopted strategies, designed and tested on an initial reduced data set, reveals good performance and robustness in terms of FPs reduction on an enlarged cohort of new cases.

Materials and methods

At the beginning, materials consisted only in 10 different polyps, diagnosed, by expert radiologists, in 6 different patients, scanning 16 rows helical CT multi slices with a resolution of 1 mm. Moreover from those 10 polyps only 7 polyps were initially used for the analysis, excluding 2 tumors with diameter bigger than 1 cm, and one polyp hardly recognizable due to fecal stool. In this paper, thanks to a new accurate phase of collecting data, materials grow impressively and then consist in total of 43 polyps all useful for the study. The whole data set was merged by using the former data set of colonrectal exams from the clinical operative unit called “Sezione di Diagnostica per Immagini” of Di.M.I.M.P. of Policlinico of Bari and the new ones coming from two new collaborations: the Oncology department of Faculty of Medicine of University of Pisa participating, as the former, to the IMPACT study (Italian Multicenter Polyps Accuracy CTC Study) Regge, Linear and nonlinear feedforward neural network classifiers: a comprehensive understanding, J. Intell. Syst., 9 (1) 1999, 1–38 and, more recently, the operative unit of radiology of the “Istituto Tumori Giovanni Paolo II” of Bari. Starting from computed tomography colonography (CTC) images, several volumes were scanned by means of three different supervised artificial neural networks (ANNs) architectures based on error back propagation training algorithm Huang and Ma, Linear and nonlinear feedforward neural network classifiers: a comprehensive understanding, J. Intell. Syst., 9 (1) 1999, 1–38. All the training sets were built by using polyps and non-polyps sub-volume samples, whose dimensions were correlated to the volume of the polyps to be detected.

Results

The performance of the best ANN architecture, trained by using a training set of 27 sessile polyps from the new 43 available dataset, were evaluated in terms of FPs and false-negatives and compared to the results shown in Bevilacqua et al., Three-dimensional Virtual Colonoscopy for Polyps Detection by Supervised Artificial Neural Networks D.-S. Huang et al. (Eds.): ICIC, LNBI 6840, Springer-Verlag, Berlin Heidelberg, (2011), pp. 596–603 where a cross validation strategy was used to overcome the small number of the old available dataset Huang, The bottleneck behaviour in linear feedforward neural network classifiers and their breakthrough, J. Comput. Sci. Technol., 14 (1) 1999, 34–43. Good performances in terms of generalization and robustness of the previous work, are then shown by the fact that the free-response operator characteristic analysis do not change significantly thanks to the enlargement of the available data.

Conclusions

This testing determined that the supervised ANN approach is consistent and reveals good performance; at the same time it is fairly intuitive that it is necessary to train a method by using polyps and non-polyps samples and that, for this reason, the overall performance could be improved by a larger dataset diagnosed by expert radiologists.

Introduction

The colon and rectal cancers are estimated to be the third carcinoma death cause in western countries, where their incidence is still growing. Every year approximately 678.000 new cases are diagnosed in the world and 150.000 in Europe [5]. Although this form of cancer is more curable than other forms of digestive apparatus carcinoma, the possibilities of 5 years surviving from the diagnosis stands at 40–50%, reaching 80–90% in early cases [6]. Polyp is a general term used to describe a benign (non-cancerous) growth on the lining, or inside, of a mucous membrane. This includes mucous membranes that are found in the digestive tract, including the colon, and the nasal passages. Other areas with mucous membranes, such as the mouth, uterus, bladder, and the genital areas can develop polyps as well. If the polyps are attached to the surface by a narrow elongated stalk, they are said to be pedunculated, where if no stalk is present, they are said to be sessile as shown in Fig. 1. Polyps are considered pre-cancerous, which means that they are not cancer, but if left untreated, they may develop into cancer, for this reason statistics show how important is to detect colorectal neoplasia at an early stage in order to ensure the effectiveness of the therapies and reduce the risk of death. Screening programs are, in this perspective, fundamental instruments of diagnosis. A traditionally diffused screening test is optical colonoscopy, performed by inserting an optical fiber probe into the patients intestine; this allows the visualization of the entire colon and the identification and removal of polyps. In most cases, the patient needs to be sedated, thus causing discomfort and a high risk for anesthetic complications, and in any case this is an expensive test and may take more than 1 h.

Computed tomography colonography (CTC), also known as virtual colonoscopy, is instead one of the most recent screening test techniques. It is based on the processing of digital images obtained via computed tomography (CT) scan or magnetic resonance, followed by a virtual reconstruction of the lumen used to navigate the whole colon [7]. This system is attracting the interests of the scientific community mainly because it is non-invasive, consequently not painful, and not hazardous to the patient. Moreover it allows the exploration of the entire colon lumen, even in cases of angles and other obstructions of the organ preventing the use of traditional optical colonoscopy but, therefore, involves specialized imaging software to elaborate volumetric CT data. The aim of this work is to develope a computer-aided diagnosis (CAD) system for CTC that could interact with the 3D reconstruction and rendering of the colon lumen. It refers to the possibility to automatically detect polyps and display them in order to fasten radiologists reviews. Although many CAD architectures have been investigated, the occurrence of false-positives (FPs) is still a problem that can lead to less confidence of behalf of technicians in the system and to the eventuality of non-distinction [8], [9].