Average Jaccard Index Research Articles

Automatic Segmentation of Individual Tooth in Dental CBCT Images From Tooth Surface Map by a Multi-Task FCN

Accurate and automatic segmentation of individual tooth is critical for computer-aided analysis towards clinical decision support and treatment planning. Three-dimensional reconstruction of individual tooth after the segmentation also plays an important role in simulation in digital orthodontics. However, it is difficult to automatically segment individual tooth in cone beam computed tomography (CBCT) images due to the blurring boundaries of neighboring teeth and the similar intensities between teeth and mandible bone. In this work, we propose the use of a multi-task 3D fully convolutional network (FCN) and marker-controlled watershed transform (MWT) to segment individual tooth. The multi-task FCN learns to simultaneously predict the probability of tooth region and the probability of tooth surface. Through the combination of the tooth probability gradient map and the surface probability map as the input image, MWT is used to automatically separate and segment individual tooth. Twenty-five dental CBCT scans are used in the study. The average Dice similarity coefficient, Jaccard index, and relative volume difference are 0.936 (±0.012), 0.881 (±0.019), and 0.072 (±0.027), respectively, and the average symmetric surface distance is 0.363 (±0.145) mm for our method. The experimental results demonstrate that the multi-task 3D FCN combined with MWT can segment individual tooth of various types in dental CBCT images.

A Multi-Organ Nucleus Segmentation Challenge.

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Segmenting Cellular Retinal Images by Optimizing Super-pixels, Multi-level Modularity, and Cell Boundary Representation.

We introduce an interactive method for retina layer segmentation in gray-level and RGB images based on super-pixels, multi-level optimization of modularity, and boundary erosion. Our method produces highly accurate segmentation results and can segment very large images. We have evaluated our method with two datasets of 2D confocal microscopy (CM) images of a mammalian retina.We have obtained average Jaccard index values of 0.948 and 0.942 respectively, confirming the high-quality segmentation performance of our method relative to a known ground truth segmentation. Average processing time was two seconds.

An automatic method for lung segmentation and reconstruction in chest X-ray using deep neural networks

Background and ObjectiveChest X-ray (CXR) is one of the most used imaging techniques for detection and diagnosis of pulmonary diseases. A critical component in any computer-aided system, for either detection or diagnosis in digital CXR, is the automatic segmentation of the lung field. One of the main challenges inherent to this task is to include in the segmentation the lung regions overlapped by dense abnormalities, also known as opacities, which can be caused by diseases such as tuberculosis and pneumonia. This specific task is difficult because opacities frequently reach high intensity values which can be incorrectly interpreted by an automatic method as the lung boundary, and as a consequence, this creates a challenge in the segmentation process, because the chances of incomplete segmentations are increased considerably. The purpose of this work is to propose a method for automatic segmentation of lungs in CXR that addresses this problem by reconstructing the lung regions “lost” due to pulmonary abnormalities. MethodsThe proposed method, which features two deep convolutional neural network models, consists of four steps main steps: (1) image acquisition, (2) initial segmentation, (3) reconstruction and (4) final segmentation. ResultsThe proposed method was experimented on 138 Chest X-ray images from Montgomery County’s Tuberculosis Control Program, and has achieved as best result an average sensitivity of 97.54%, an average specificity of 96.79%, an average accuracy of 96.97%, an average Dice coefficient of 94%, and an average Jaccard index of 88.07%. ConclusionsWe demonstrate in our lung segmentation method that the problem of dense abnormalities in Chest X-rays can be efficiently addressed by performing a reconstruction step based on a deep convolutional neural network model.

Long-Term Spatiotemporal Variation in the Juvenile Fish Assemblage of the Tramandaí River Estuary (29°S) and Adjacent Coast in Southern Brazil

Based on a set of intermittent and seasonal data, covering a discontinuous 21-year period (1995 to 2016) and using a standard beach seine with replicates at several collection points inside the Tramandai River estuary (TRE) and outside in the marine adjacent coastal area (MACA), we evaluated connectivity between TRE and MACA and the spatiotemporal variations of fish associations. In the TRE (405 samples; 42,987 individuals) 55 species were captured. In the MACA (297 samples; 54,295 individuals) 41 species were captured. After data standardization the expected richness of the TRE [E(S) = 18.2] was significantly greater (p <0.05) than that of the MACA [E(S) = 14.4]. The fish association structure and distribution patterns in TRE and MACA are dynamic and interconnected but quite different in terms of species composition, especially due to the influence of local salinity. The TRE association is richer in a number of species but numerically dominated by marine estuarine-dependent juveniles. Freshwater species may eventually be carried in by heavy rains, bringing pulses of species richness. The MACA association is represented by a few typical marine species in addition to a couple of estuarine-related transient species who uses the surf-zone as a passageway to enter the estuaries. Even if there is a higher percentage of common species reported (30 out of 66), the monthly average Jaccard Index of similarity (JI = 28%) and the monthly average Percent Similarity Index (PSI=30%) was low, suggesting that the shallow water functional connectivity between MACA and TRE are represented by few species that occur equally in abundance in both environments. Juvenile of two species of mullets (Mugil liza and Mugil curema) add up to more than 70% of the total catches in both environments. The hypothesized signal of decadal diversity and abundance reduction seems to be muffled by seasonal environmental fluctuation revealing that fish assemblage of MACA and TRE are highly resilient through the years. The only observed interdecadal trend was the reduction in abundance of juvenile M. liza that seems to parallel the reduction in abundance of the adults fishing stocks in southern Brazil.

U-Net based deep learning bladder segmentation in CT urography.

To develop a U-Net-based deep learning approach (U-DL) for bladder segmentation in computed tomography urography (CTU) as a part of a computer-assisted bladder cancer detection and treatment response assessment pipeline. A dataset of 173 cases including 81 cases in the training/validation set (42 masses, 21 with wall thickening, 18 normal bladders), and 92 cases in the test set (43 masses, 36 with wall thickening, 13 normal bladders) were used with Institutional Review Board approval. An experienced radiologist provided three-dimensional (3D) hand outlines for all cases as the reference standard. We previously developed a bladder segmentation method that used a deep learning convolution neural network and level sets (DCNN-LS) within a user-input bounding box. However, some cases with poor image quality or with advanced bladder cancer spreading into the neighboring organs caused inaccurate segmentation. We have newly developed an automated U-DL method to estimate a likelihood map of the bladder in CTU. The U-DL did not require a user-input box and the level sets for postprocessing. To identify the best model for this task, we compared the following models: (a) two-dimensional (2D) U-DL and 3D U-DL using 2D CT slices and 3D CT volumes, respectively, as input, (b) U-DLs using CT images of different resolutions as input, and (c) U-DLs with and without automated cropping of the bladder as an image preprocessing step. The segmentation accuracy relative to the reference standard was quantified by six measures: average volume intersection ratio (AVI), average percent volume error (AVE), average absolute volume error (AAVE), average minimum distance (AMD), average Hausdorff distance (AHD), and the average Jaccard index (AJI). As a baseline, the results from our previous DCNN-LS method were used. In the test set, the best 2D U-DL model achieved AVI, AVE, AAVE, AMD, AHD, and AJI values of 93.4±9.5%, -4.2±14.2%, 9.2±11.5%, 2.7±2.5mm, 9.7±7.6mm, 85.0±11.3%, respectively, while the corresponding measures by the best 3D U-DL were 90.6±11.9%, -2.3±21.7%, 11.5±18.5%, 3.1±3.2mm, 11.4±10.0mm, and 82.6±14.2%, respectively. For comparison, the corresponding values obtained with the baseline method were 81.9±12.1%, 10.2±16.2%, 14.0±13.0%, 3.6±2.0mm, 12.8±6.1mm, and 76.2±11.8%, respectively, for the same test set. The improvement for all measures between the best U-DL and the DCNN-LS were statistically significant (P<0.001). Compared to a previous DCNN-LS method, which depended on a user-input bounding box, the U-DL provided more accurate bladder segmentation and was more automated than the previous approach.

Convolutional neural network-based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images.

Accurate three-dimensional (3D) segmentation of myocardial replacement fibrosis (i.e., scar) is emerging as a potentially valuable tool for risk stratification and procedural planning in patients with ischemic cardiomyopathy. The main purpose of this study was to develop a semiautomated method using a 3D convolutional neural network (CNN)-based for the segmentation of left ventricle (LV) myocardial scar from 3D late gadolinium enhancement magnetic resonance (LGE-MR) images. Our proposed CNN is built upon several convolutional and pooling layers aimed at choosing appropriate features from LGE-MR images to distinguish between myocardial scar and healthy tissues of the left ventricle. In contrast to previous methods that consider image intensity as the sole feature, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of unconventional features that separate scar from normal myocardium in the feature space. The first step of our pipeline was to manually delineate the left ventricular myocardium, which was used as the region of interest for scar segmentation. Our developed algorithm was trained using 265,220 volume patches extracted from ten 3D LGE-MR images, then was validated on 450,454 patches from a testing dataset of 24 3D LGE-MR images, all obtained from patients with chronic myocardial infarction. We evaluated our method in the context of several alternative methods by comparing algorithm-generated segmentations to manual delineations performed by experts. Our CNN-based method reported an average Dice similarity coefficient (DSC) and Jaccard Index (JI) of 93.63%±2.6% and 88.13%±4.70%. In comparison to several previous methods, including K-nearest neighbor (KNN), hierarchical max flow (HMF), full width at half maximum (FWHM), and signal threshold to reference mean (STRM), the developed algorithm reported significantly higher accuracy for DSC with a P-value less than 0.0001. Our experimental results demonstrated that our CNN-based proposed method yielded the highest accuracy of all contemporary LV myocardial scar segmentation methodologies, inclusive of the most widely used signal intensity-based methods, such as FWHM and STRM. To our knowledge, this is the first description of LV myocardial scar tissue segmentation from 3D LGE-MR images using a CNN-based method.

A Novel Deep Learning Based Auto Segmentation For Rectum Tumor On MRI Image

Manually contouring gross tumor volume (GTV) is a crucial and time-consuming process in rectum cancer radiotherapy. This study aims to develop a simple deep learning based rectum tumor auto segmentation algorithm on MRI T2 images. MRI scans (3T, T2-weighted) of 93 patients with locally advanced (cT3-4 and/or cN1-2) rectal cancer treated with neoadjuvant chemoradiotherapy followed by surgery were enrolled in this study. A very deep convolutional networks (VGG16) based full convolution network (FCN) was established as training model. The model was trained in two phases to increase efficiency, including tumor recognition and tumor segmentation. An opening (erosion and dilation) process was implemented to make contours smoother. Data were randomly separated into training (90%) and validation (10%) dataset for 10 folder cross-validation. Additionally, 20 patients were double contoured for performance evaluation. Four indices were calculated to evaluate the similarity of automated and manual segmentation, including Hausdorff distance (HD), average surface distance (ASD), Dice index (DSC) and Jaccard index (JSC). The DSC, JSC, HD, ASD (mean±SD) were 0.74±0.14, 0.60±0.16, 20.44±13.35mm and 3.25±1.69mm for validation dataset; And these indices were 0.71±0.13, 0.57±0.15, 14.91±7.62mm and 2.67±1.46mm between two human radiation oncologists. T-test suggested there is no statistically significant difference between automated segmentation and manual segmentation considering DSC (p=0.42), JSC (p=0.35), HD (p=0.079) and ASD (p=0.16). However, significant difference was found for HD (p=0.0027) without opening process. This study showed that a simple deep learning neural network can perform a human comparable segmentation for rectum cancer based on MRI T2 images.

Semantic segmentation of high-resolution remote sensing images using fully convolutional network with adaptive threshold

ABSTRACTSemantic segmentation is an important method to implement fine-grained semantically understand for high-resolution remote sensing images by dividing images into pixel groupings which can then be labelled and classified. In the field of computer vision (CV), the methods based on fully convolutional network (FCN) are the hotspot and have achieved state-of-the-art results. Compared with popular datasets in CV such as PASCAL and COCO, class imbalance is a problem for multiclass semantic segmentation in remote sensing datasets. In this paper, an FCN-based model is proposed to implement pixel-wise classifications for remote sensing image in an end-to-end way, and an adaptive threshold algorithm is proposed to adjust the threshold of Jaccard index in each class. Experiments on DSTL dataset show that the proposed method produces accurate classifications in an end-to-end way. Results show that the adaptive threshold algorithm can increase the score of average Jaccard index from 0.614 to 0.636 and achieve better segmentation results.

Computational Platform Based on Deep Learning for Segmenting Ventricular Endocardium in Long-axis Cardiac MR Imaging.

This paper presents an automated computational platform based on deep learning (DL) approach for left ventricular (LV) and right ventricular (RV) endocardium segmentation in long-axis cine cardiovascular magnetic resonance (CMR). The proposed method uses modified deep U-Net convolutional networks. We trained our model using 4800 images from 40 human subjects (20 healthy volunteers, 20 patients with various cardiac diseases) and validated the technique in 6000 images from 50 subjects (10 healthy volunteers, 40 patients). An average Dice metric of 0.929 ± 0.036 along with an average Jaccard index of 0.869 ± 0.059 were achieved for all the studied subjects. In addition, a high level of correlation and agreement with the ground truth contours for LV ejection fraction (R=0.975), LV fractional area change (R=0.959 to 0.971), and RV fractional area change (R=0.927) were observed. The proposed DL-based segmentation process took less than 3 seconds per subject (or < 30 milliseconds per image over 120 images for each subject). Therefore, our proposed framework offers a promising means to achieve fully automated and rapid segmentation for both LV and RV endocardium in long-axis cine CMR images using an appropriately trained deep convolutional neural network.

Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks

Background and objectiveAutomatic segmentation of skin lesions in dermoscopy images is still a challenging task due to the large shape variations and indistinct boundaries of the lesions. Accurate segmentation of skin lesions is a key prerequisite step for any computer-aided diagnostic system to recognize skin melanoma. MethodsIn this paper, we propose a novel segmentation methodology via full resolution convolutional networks (FrCN). The proposed FrCN method directly learns the full resolution features of each individual pixel of the input data without the need for pre- or post-processing operations such as artifact removal, low contrast adjustment, or further enhancement of the segmented skin lesion boundaries. We evaluated the proposed method using two publicly available databases, the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Challenge and PH2 datasets. To evaluate the proposed method, we compared the segmentation performance with the latest deep learning segmentation approaches such as the fully convolutional network (FCN), U-Net, and SegNet. ResultsOur results showed that the proposed FrCN method segmented the skin lesions with an average Jaccard index of 77.11% and an overall segmentation accuracy of 94.03% for the ISBI 2017 test dataset and 84.79% and 95.08%, respectively, for the PH2 dataset. In comparison to FCN, U-Net, and SegNet, the proposed FrCN outperformed them by 4.94%, 15.47%, and 7.48% for the Jaccard index and 1.31%, 3.89%, and 2.27% for the segmentation accuracy, respectively. Furthermore, the proposed FrCN achieved a segmentation accuracy of 95.62% for some representative clinical benign cases, 90.78% for the melanoma cases, and 91.29% for the seborrheic keratosis cases in the ISBI 2017 test dataset, exhibiting better performance than those of FCN, U-Net, and SegNet. ConclusionsWe conclude that using the full spatial resolutions of the input image could enable to learn better specific and prominent features, leading to an improvement in the segmentation performance.

Human Blastocyst's Zona Pellucida segmentation via boosting ensemble of complementary learning

Abstract Characteristics of Zona Pellucida (ZP), particularly its thickness, is a key indicator of human blastocyst (day-5 embryo) quality. Therefore, ZP segmentation is an important step towards achieving automatic embryo quality assessment. In this paper, a novel approach based on boosting ensemble of hybrid complementary learning is proposed to segment Zona Pellucida in human blastocyst images. First, an inner-ZP localization method is proposed to separate the ZP from the heavily textured area inside a blastocyst. Then, a deep Hierarchical Neural Network (HiNN) is proposed to segment ZP area. The hierarchical nature of the proposed network enables learning features with respect to their spatial location in the embryo. Finally, a Self-supervised Image-Specific Refinement (SISR) strategy is proposed as a complementary step to boost the performance. The proposed system is a hybrid approach in the sense that the HiNN learns the intra-correlation among images, while the SISR takes into account the inter-correlation within the query image. Experimental results confirm that the proposed method is capable of identifying ZP area with average Precision, Recall, Accuracy and Jaccard Index of 85.2 % , 92.0 % , 95.6 % and 78.1 % , respectively. The proposed HiNN system outperforms state of the art by 4.9 % in Precision, 11.2 % in Recall, 3.6 % in Accuracy and 10.7 % in Jaccard Index.

Improving Dermoscopic Image Segmentation with Enhanced Convolutional-Deconvolutional Networks.

Automatic skin lesion segmentation on dermoscopic images is an essential step in computer-aided diagnosis of melanoma. However, this task is challenging due to significant variations of lesion appearances across different patients. This challenge is further exacerbated when dealing with a large amount of image data. In this paper, we extended our previous work by developing a deeper network architecture with smaller kernels to enhance its discriminant capacity. In addition, we explicitly included color information from multiple color spaces to facilitate network training and thus to further improve the segmentation performance. We participated and extensively evaluated our method on the ISBI 2017 skin lesion segmentation challenge. By training with the 2000 challenge training images, our method achieved an average Jaccard Index (JA) of 0:765 on the 600 challenge testing images, which ranked itself in the first place among 21 final submissions in the challenge.

Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views.

Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972±0.003 and 0.985±0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5mm for all datasets. An average acceptable segmentation rate of ∼95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972±0.003 and 0.985±0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5mm for all datasets. An average acceptable segmentation rate of ∼95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.

Multi-atlas pancreas segmentation: Atlas selection based on vessel structure.

Automated organ segmentation from medical images is an indispensable component for clinical applications such as computer-aided diagnosis (CAD) and computer-assisted surgery (CAS). We utilize a multi-atlas segmentation scheme, which has recently been used in different approaches in the literature to achieve more accurate and robust segmentation of anatomical structures in computed tomography (CT) volume data. Among abdominal organs, the pancreas has large inter-patient variability in its position, size and shape. Moreover, the CT intensity of the pancreas closely resembles adjacent tissues, rendering its segmentation a challenging task. Due to this, conventional intensity-based atlas selection for pancreas segmentation often fails to select atlases that are similar in pancreas position and shape to those of the unlabeled target volume. In this paper, we propose a new atlas selection strategy based on vessel structure around the pancreatic tissue and demonstrate its application to a multi-atlas pancreas segmentation. Our method utilizes vessel structure around the pancreas to select atlases with high pancreatic resemblance to the unlabeled volume. Also, we investigate two types of applications of the vessel structure information to the atlas selection. Our segmentations were evaluated on 150 abdominal contrast-enhanced CT volumes. The experimental results showed that our approach can segment the pancreas with an average Jaccard index of 66.3% and an average Dice overlap coefficient of 78.5%.

Lung Field Segmentation in Chest Radiographs From Boundary Maps by a Structured Edge Detector

Lung field segmentation in chest radiographs (CXRs) is an essential preprocessing step in automatically analyzing such images. We present a method for lung field segmentation that is built on a high-quality boundary map detected by an efficient modern boundary detector, namely a structured edge detector (SED). A SED is trained beforehand to detect lung boundaries in CXRs with manually outlined lung fields. Then, an ultrametric contour map (UCM) is transformed from the masked and marked boundary map. Finally, the contours with the highest confidence level in the UCM are extracted as lung contours. Our method is evaluated using the public Japanese Society of Radiological Technology database of scanned films. The average Jaccard index of our method is 95.2%, which is comparable with those of other state-of-the-art methods (95.4%). The computation time of our method is less than 0.1 s for a CXR when executed on an ordinary laptop. Our method is also validated on CXRs acquired with different digital radiography units. The results demonstrate the generalization of the trained SED model and the usefulness of our method.

Automated liver segmentation from a postmortem CT scan based on a statistical shape model.

Automated liver segmentation from a postmortem computed tomography (PMCT) volume is a challenging problem owing to the large deformation and intensity changes caused by severe pathology and/or postmortem changes. This paper addresses this problem by a novel segmentation algorithm using a statistical shape model (SSM) for a postmortem liver. The location and shape parameters of a liver are directly estimated from a given volume by the proposed SSM-guided expectation-maximization (EM) algorithm without any spatial standardization that might fail owing to the large deformation and intensity changes. The estimated location and shape parameters are then used as a constraint of the subsequent fine segmentation process based on graph cuts. Algorithms with eight different SSMs were trained using 144 in vivo and 32 postmortem livers, and the segmentation algorithm was tested on 32 postmortem livers in a twofold cross validation manner. The segmentation performance is measured by the Jaccard index (JI) between the segmentation result and the true liver label. The average JI of the segmentation result with the best SSM was 0.8501, which was better compared with the results obtained using conventional SSMs and the results of the previous postmortem liver segmentation with statistically significant difference. We proposed an algorithm for automated liver segmentation from a PMCT volume, in which an SSM-guided EM algorithm estimated the location and shape parameters of a liver in a given volume accurately. We demonstrated the effectiveness of the proposed algorithm using actual postmortem CT volumes.

The effect of morphometric atlas selection on multi-atlas-based automatic brachial plexus segmentation.

PurposeThe present study aimed to measure the effect of a morphometric atlas selection strategy on the accuracy of multi-atlas-based BP autosegmentation using the commercially available software package ADMIRE® and to determine the optimal number of selected atlases to use. Autosegmentation accuracy was measured by comparing all generated automatic BP segmentations with anatomically validated gold standard segmentations that were developed using cadavers.Materials and methodsTwelve cadaver computed tomography (CT) atlases were included in the study. One atlas was selected as a patient in ADMIRE®, and multi-atlas-based BP autosegmentation was first performed with a group of morphometrically preselected atlases. In this group, the atlases were selected on the basis of similarity in the shoulder protraction position with the patient. The number of selected atlases used started at two and increased up to eight. Subsequently, a group of randomly chosen, non-selected atlases were taken. In this second group, every possible combination of 2 to 8 random atlases was used for multi-atlas-based BP autosegmentation. For both groups, the average Dice similarity coefficient (DSC), Jaccard index (JI) and Inclusion index (INI) were calculated, measuring the similarity of the generated automatic BP segmentations and the gold standard segmentation. Similarity indices of both groups were compared using an independent sample t-test, and the optimal number of selected atlases was investigated using an equivalence trial.ResultsFor each number of atlases, average similarity indices of the morphometrically selected atlas group were significantly higher than the random group (p < 0,05). In this study, the highest similarity indices were achieved using multi-atlas autosegmentation with 6 selected atlases (average DSC = 0,598; average JI = 0,434; average INI = 0,733).ConclusionsMorphometric atlas selection on the basis of the protraction position of the patient significantly improves multi-atlas-based BP autosegmentation accuracy. In this study, the optimal number of selected atlases used was six, but for definitive conclusions about the optimal number of atlases and to improve the autosegmentation accuracy for clinical use, more atlases need to be included.

Improving object segmentation by using EEG signals and rapid serial visual presentation

This paper extends our previous work on the potential of EEG-based brain computer interfaces to segment salient objects in images. The proposed system analyzes the Event Related Potentials (ERP) generated by the rapid serial visual presentation of windows on the image. The detection of the P300 signal allows estimating a saliency map of the image, which is used to seed a semi-supervised object segmentation algorithm. Thanks to the new contributions presented in this work, the average Jaccard index was improved from 0.47 to 0.66 when processed in our publicly available dataset of images, object masks and captured EEG signals. This work also studies alternative architectures to the original one, the impact of object occupation in each image window, and a more robust evaluation based on statistical analysis and a weighted F-score.

Localized Energy-Based Normalization of Medical Images: Application to Chest Radiography.

Automated quantitative analysis systems for medical images often lack the capability to successfully process images from multiple sources. Normalization of such images prior to further analysis is a possible solution to this limitation. This work presents a general method to normalize medical images and thoroughly investigates its effectiveness for chest radiography (CXR). The method starts with an energy decomposition of the image in different bands. Next, each band's localized energy is scaled to a reference value and the image is reconstructed. We investigate iterative and local application of this technique. The normalization is applied iteratively to the lung fields on six datasets from different sources, each comprising 50 normal CXRs and 50 abnormal CXRs. The method is evaluated in three supervised computer-aided detection tasks related to CXR analysis and compared to two reference normalization methods. In the first task, automatic lung segmentation, the average Jaccard overlap significantly increased from 0.72±0.30 and 0.87±0.11 for both reference methods to with normalization. The second experiment was aimed at segmentation of the clavicles. The reference methods had an average Jaccard index of 0.57±0.26 and 0.53±0.26; with normalization this significantly increased to . The third experiment was detection of tuberculosis related abnormalities in the lung fields. The average area under the Receiver Operating Curve increased significantly from 0.72±0.14 and 0.79±0.06 using the reference methods to with normalization. We conclude that the normalization can be successfully applied in chest radiography and makes supervised systems more generally applicable to data from different sources.