Elena Casiraghi

Liver segmentation from computed tomography scans: A survey and a new algorithm

OBJECTIVE In the recent years liver segmentation from computed tomography scans has gained a lot of importance in the field of medical image processing since it is the first and fundamental step of any automated technique for the automatic liver disease diagnosis, liver volume measurement, and 3D liver volume rendering. METHODS In this paper we report a review study about the semi-automatic and automatic liver segmentation techniques, and we describe our fully automatized method. RESULTS The survey reveals that automatic liver segmentation is still an open problem since various weaknesses and drawbacks of the proposed works must still be addressed. Our gray-level based liver segmentation method has been developed to tackle all these problems; when tested on 40 patients it achieves satisfactory results, comparable to the mean intra- and inter-observer variation. CONCLUSIONS We believe that our technique outperforms those presented in the literature; nevertheless, a common test set with its gold standard traced by experts, and a generally accepted performance measure are required to demonstrate it.

A segmentation framework for abdominal organs from CT scans

OBJECTIVE Computed tomography images are becoming an invaluable mean for abdominal organ investigation. In the field of medical image processing, some of the current interests are the automatic diagnosis of liver, spleen, and kidney pathologies, and the 3D volume rendering of these abdominal organs. Their automatic segmentation is the first and fundamental step in all these studies, but it is still an open problem. METHODS In this paper we propose a fully automatic, gray-level based segmentation framework based on a multiplanar fast marching method. The proposed segmentation scheme is general, and employs only established and not critical anatomical knowledge. For this reason, it can be easily adapted to segment different abdominal organs, by overcoming problems due to the high inter- and intra-patient gray-level, and shape variabilities; the extracted volumes are then combined to produce the final results. RESULTS The system has been evaluated by computing the symmetric volume overlap (SVO) between the automatically segmented (liver and spleen) volumes and the volumes manually traced by radiological experts. The test dataset is composed of 60 images, where 40 images belong to a private dataset, and 20 images to a public one. Liver segmentation has achieved an average SVO congruent with94, which is comparable to the mean intra- and inter-personal variation (96). Spleen segmentation achieves similar, promising results (SVO congruent with93). The comparison of these results with those achieved by active contour models (SVO congruent with90), and topology adaptive snakes (SVO congruent with92) proves the efficacy of our system. CONCLUSIONS The described segmentation method is a general framework that can be adapted to segment different abdominal organs, achieving promising segmentation results. It has to be noted that its performance could be further improved by incorporating shape based rules.

Liver Segmentation from CT Scans: A Survey

In this paper we describe the state of the art of the semi-automatic and automatic techniques for liver volume extraction from abdominal CT. In the recent years this research focus has gained a lot of importance in the field of medical image processing since it is the first and fundamental step of any automated technique for the automatic liver disease diagnosis, liver volume measurement, and 3D liver volume rendering from CT images.

Automatic liver segmentation from abdominal CT scans

Abdominal CT images have been widely studied in the recent years as they are becoming an invaluable mean for abdominal organ investigation. In the field of medical image processing, some of the current interests are the automatic diagnosis of liver pathologies and its 3D volume rendering. The first and fundamental step in all these studies is the automatic liver segmentation, that is still an open problem. In this paper we describe two automatic methods to segment the liver from abdominal CT data. They have been evaluated on the data of 40 patients, by comparing the automatically detected liver volumes to the liver boundaries manually traced by three experts. The best performing method achieves a symmetric volume difference of 95%, which is comparable to the inter and intra-personal variability of the manual segmentation produced by experts.

Fully Automatic Segmentation of Abdominal Organs from CT Images Using Fast Marching Methods

Computed tomography (CT) images are becoming an invaluable mean for abdominal organ investigation. In the field of medical image processing, some of the current interests are the automatic diagnosis of liver, spleen, and kidney pathologies and the 3D volume rendering of the abdominal organs. The first and fundamental step in all these studies is the automatic organs segmentation, that is still an open problem. In this paper we propose a fully automatic gray level based segmentation framework that employs a fast marching technique; the proposed segmentation scheme is general, and employs only established and not critical anatomical knowledge. For this reason, it can be easily adapted to separately segment different abdominal organs, by overcoming problems due to the high inter and intra patient gray level and shape variabilities; the extracted volumes are then combined to achieve robust results. The system performance has been evaluated on the data of 40 patients, by comparing the automatically detected organ volumes to the organ boundaries manually traced by three experts. The good quality of the achieved results is proved by the fact that they are comparable to the inter and intra personal variability of the manual segmentation produced by experts.

IDEA: intrinsic dimension estimation algorithm

The high dimensionality of some real life signals makes the usage of the most common signal processing and pattern recognition methods unfeasible. For this reason, in literature a great deal of research work has been devoted to the development of algorithms performing dimensionality reduction. To this aim, an useful help could be provided by the estimation of the intrinsic dimensionality of a given dataset, that is the minimum number of parameters needed to capture, and describe, all the information carried by the data. Although many techniques have been proposed, most of them fail in case of noisy data or when the intrinsic dimensionality is too high. In this paper we propose a local intrinsic dimension estimator exploiting the statistical properties of data neighborhoods. The algorithm evaluation on both synthetic and real datasets, and the comparison with state of the art algorithms, proves that the proposed technique is promising.

DANCo: An intrinsic dimensionality estimator exploiting angle and norm concentration

Abstract In the past decade the development of automatic intrinsic dimensionality estimators has gained considerable attention due to its relevance in several application fields. However, most of the proposed solutions prove to be not robust on noisy datasets, and provide unreliable results when the intrinsic dimensionality of the input dataset is high and the manifold where the points are assumed to lie is nonlinearly embedded in a higher dimensional space. In this paper we propose a novel intrinsic dimensionality estimator ( DANCo ) and its faster variant ( FastDANCo ), which exploit the information conveyed both by the normalized nearest neighbor distances and by the angles computed on couples of neighboring points. The effectiveness and robustness of the proposed algorithms are assessed by experiments on synthetic and real datasets, by the comparative evaluation with state-of-the-art methodologies, and by significance tests.

Novel IPCA-Based Classifiers and Their Application to Spam Filtering

This paper proposes a novel two-class classifier, called IPCAC, based on the Isotropic Principal Component Analysis technique; it allows to deal with training data drawn from Mixture of Gaussian distributions, by projecting the data on the Fisher subspace that separates the two classes. The obtained results demonstrate that IPCAC is a promising technique; furthermore, to cope with training datasets being dynamically supplied, and to work with non-linearly separable classes, two improvements of this classifier are defined: a model merging algorithm, and a kernel version of IPCAC. The effectiveness of the proposed methods is shown by their application to the spam classification problem, and by the comparison of the achieved results with those obtained by Support Vector Machines SVM, and K-Nearest Neighbors KNN.

A Face Detection System Based on Color and Support Vector Machines

We describe a face detection algorithm, which characterizes and localizes skin regions and eyes in 2D images using color information and Support Vector Machine. The method is scale-independent, works on images of either frontal, rotated faces, with a single person or group of people, and does not require any manual setting or operator intervention. The algorithm can be used in face image database management systems both as a first step of a person identification, and to discriminate the images on the basis of the number of faces in them.

Intestinal interposition: the prevalence and clinical relevance of non-hepatodiaphragmatic conditions (non-Chilaiditi forms) documented by CT and review of the literature.

PurposeThis study was done to assess the prevalence and clinical impact of non-hepatodiaphragmatic interpositions in a sample of adult patients undergoing computed tomography (CT) for a variety of medical reasons.Materials and methodsFrom November 2008 to April 2009, two observers jointly examined the cases of intestinal interposition in 4,338 adults undergoing CT investigations. This study sought to identify not only hepatodiaphragmatic intestinal interpositions, defined as Chilaiditi, but also other forms of intestinal interposition, which we termed non-Chilaiditi. The latter were divided into five different classes on the basis of their anatomical relationships: splenorenal, retrogastric, hepatocaval, retrosplenic, and retrorenal. Moreover, a questionnaire investigating the clinical symptoms reported to be associated with Chilaiditi syndrome was given to patients exhibiting any form of intestinal interposition and to a control sample. Finally, clinical data related to the three groups were compared.ResultsOf the 4,338 patients examined, 130 (3%) were found to have intestinal interposition, for a total of 143 forms: 90 Chilaiditi and 53 non-Chilaiditi. Of the latter, 30 were splenorenal, 12 retrogastric, five hepatocaval, four retrosplenic and two retrorenal. Statistical analysis showed that the Chilaiditi group suffered most symptoms (24.4%), followed by the non-Chilaiditi group (18.9%) and control cases (10.8%). Our results were validated using the χ2 test of significance.ConclusionsThe number of non-Chilaiditi cases amounted to just over half the number of Chilaiditi cases, with the splenorenal form being by far the most frequent. Statistical analysis showed that patients with non-Chilaiditi forms of intestinal interposition had more symptoms than did controls.RiassuntoObiettivoScopo del nostro lavoro è stato valutare la prevalenza e l’impatto clinico delle forme di interposizione intestinale non epatodiaframmatiche in una popolazione adulta studiata con tomografia computerizzata (TC) per differenti indicazioni medico-chirurgiche.Materiali e metodiDa novembre 2008 ad aprile 2009, due autori hanno valutato insieme i casi di interposizione intestinale su 4338 pazienti adulti sottoposti a indagini TC. In tale studio, sono state evidenziate sia interposizioni di tipo epatodiaframmatico, che sono state definite Chilaiditi come da letteratura, sia altri tipi di interposizione definite secondo i diversi rapporti anatomici: splenorenale, retrogastrica, epatocavale, retrosplenica e retrorenale, che sono state raggruppate sotto il termine non-Chilaiditi. È stato successivamente sottoposto ai pazienti dei due gruppi e ad un gruppo controllo un questionario relativo ai disturbi clinici associati più frequentemente alla sindrome di Chilaiditi. Sono stati quindi comparati i dati clinici relativi ai tre gruppi.RisultatiSu 4338 pazienti sono stati osservati 130 (3%) pazienti con interposizione colica per un totale di 143 manifestazioni, 90 Chilaiditi e 53 non-Chilaiditi: 30 interposizioni di tipo splenorenale, 12 di tipo retrogastrico, 5 epatocavale, 4 retrosplenico e 2 retrorenale. L’analisi statistica ha evidenziato che le forme di Chilaiditi producono una maggiore sintomatologia (24,4%), seguite dalle forme non-Chilaiditi (18,9%) e infine dai casi controllo (10,8%). Tale analisi è stata validata dal test di significatività χ2.ConclusioniLe forme non-Chilaiditi hanno rappresentato più della metà delle forme Chilaiditi, con la manifestazione splenorenale di gran lunga la più frequente. Abbiamo inoltre evidenziato che anche le forme non-Chilaiditi sono statisticamente più sintomatiche dei casi controllo.