Search

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases., (© 2024. Springer Nature America, Inc.)

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training., (© 2022. The Author(s).)

Few-shot learning is an almost unexplored area in the field of medical image analysis. We propose a method for few-shot diagnosis of diseases and conditions from chest x-rays using discriminative ensemble learning. Our design involves a CNN-based coarse-learner in the first step to learn the general characteristics of chest x-rays. In the second step, we introduce a saliency-based classifier to extract disease-specific salient features from the output of the coarse-learner and classify based on the salient features. We propose a novel discriminative autoencoder ensemble to design the saliency-based classifier. The classification of the diseases is performed based on the salient features. Our algorithm proceeds through meta-training and meta-testing. During the training phase of meta-training, we train the coarse-learner. However, during the training phase of meta-testing, we train only the saliency-based classifier. Thus, our method is first-of-its-kind where the training phase of meta-training and the training phase of meta-testing are architecturally disjoint, making the method modular and easily adaptable to new tasks requiring the training of only the saliency-based classifier. Experiments show as high as ∼19% improvement in terms of F 1 score compared to the baseline in the diagnosis of chest x-rays from publicly available datasets., Competing Interests: Declaration of Competing Interest Ronald M. Summers receives royalties from PingAn, iCAD, ScanMed, Translation Holdings and Philips, research support from PingAn, and GPU card donations from NVIDIA., (Published by Elsevier B.V.)

Artificial intelligence (AI) continues to garner substantial interest in medical imaging. The potential applications are vast and include the entirety of the medical imaging life cycle from image creation to diagnosis to outcome prediction. The chief obstacles to development and clinical implementation of AI algorithms include availability of sufficiently large, curated, and representative training data that includes expert labeling (eg, annotations). Current supervised AI methods require a curation process for data to optimally train, validate, and test algorithms. Currently, most research groups and industry have limited data access based on small sample sizes from small geographic areas. In addition, the preparation of data is a costly and time-intensive process, the results of which are algorithms with limited utility and poor generalization. In this article, the authors describe fundamental steps for preparing medical imaging data in AI algorithm development, explain current limitations to data curation, and explore new approaches to address the problem of data availability., (© RSNA, 2020.)

Objective: To investigate a fully automated CT-based adiposity tool, applying it to a longitudinal adult screening cohort., Methods: A validated automated adipose tissue segmentation algorithm was applied to non-contrast abdominal CT scans in 8852 consecutive asymptomatic adults (mean age, 57.1 years; 3926 M/4926 F) undergoing colonography screening. The tool was also applied to follow-up CT scans in a subset of 1584 individuals undergoing longitudinal surveillance (mean interval, 5.6 years). Visceral and subcutaneous adipose tissue (VAT and SAT) volumes were segmented at levels T12-L5. Primary adipose results are reported herein for the L1 level as mean cross-sectional area. CT-based adipose measurements at initial CT and change over time were analyzed., Results: Mean VAT values were significantly higher in males (205.8 ± 107.5 vs 108.1 ± 82.4 cm 2 ; p < 0.001), whereas mean SAT values were significantly higher in females (171.3 ± 111.3 vs 124.3 ± 79.7 cm 2 ; p < 0.001). The VAT/SAT ratio at L1 was three times higher in males (1.8 ± 0.7 vs 0.6 ± 0.4; p < 0.001). At longitudinal follow-up CT, mean VAT/SAT ratio change was positive in males, but negative in females. Among the 502 individuals where the VAT/SAT ratio increased at follow-up CT, 333 (66.3%) were males. Half of patients (49.6%; 786/1585) showed an interval increase in both VAT and SAT at follow-up CT., Conclusion: This robust, fully automated CT adiposity tool allows for both individualized and population-based assessment of visceral and subcutaneous abdominal fat. Such data could be automatically derived at abdominal CT regardless of the study indication, potentially allowing for opportunistic cardiovascular risk stratification. Advances in knowledge: The CT-based adiposity tool described herein allows for fully automated measurement of visceral and subcutaneous abdominal fat, which can be used for assessing cardiovascular risk, metabolic syndrome, and for change over time.

Purpose To validate the dominant pulse sequence paradigm and limited role of dynamic contrast material-enhanced magnetic resonance (MR) imaging in the Prostate Imaging Reporting and Data System (PI-RADS) version 2 for prostate multiparametric MR imaging by using data from a multireader study. Materials and Methods This HIPAA-compliant retrospective interpretation of prospectively acquired data was approved by the local ethics committee. Patients were treatment-naïve with endorectal coil 3-T multiparametric MR imaging. A total of 163 patients were evaluated, 110 with prostatectomy after multiparametric MR imaging and 53 with negative multiparametric MR imaging and systematic biopsy findings. Nine radiologists participated in this study and interpreted images in 58 patients, on average (range, 56-60 patients). Lesions were detected with PI-RADS version 2 and were compared with whole-mount prostatectomy findings. Probability of cancer detection for overall, T2-weighted, and diffusion-weighted (DW) imaging PI-RADS scores was calculated in the peripheral zone (PZ) and transition zone (TZ) by using generalized estimating equations. To determine dominant pulse sequence and benefit of dynamic contrast-enhanced (DCE) imaging, odds ratios (ORs) were calculated as the ratio of odds of cancer of two consecutive scores by logistic regression. Results A total of 654 lesions (420 in the PZ) were detected. The probability of cancer detection for PI-RADS category 2, 3, 4, and 5 lesions was 15.7%, 33.1%, 70.5%, and 90.7%, respectively. DW imaging outperformed T2-weighted imaging in the PZ (OR, 3.49 vs 2.45; P = .008). T2-weighted imaging performed better but did not clearly outperform DW imaging in the TZ (OR, 4.79 vs 3.77; P = .494). Lesions classified as PI-RADS category 3 at DW MR imaging and as positive at DCE imaging in the PZ showed a higher probability of cancer detection than did DCE-negative PI-RADS category 3 lesions (67.8% vs 40.0%, P = .02). The addition of DCE imaging to DW imaging in the PZ was beneficial (OR, 2.0; P = .027), with an increase in the probability of cancer detection of 15.7%, 16.0%, and 9.2% for PI-RADS category 2, 3, and 4 lesions, respectively. Conclusion DW imaging outperforms T2-weighted imaging in the PZ; T2-weighted imaging did not show a significant difference when compared with DW imaging in the TZ by PI-RADS version 2 criteria. The addition of DCE imaging to DW imaging scores in the PZ yields meaningful improvements in probability of cancer detection. © RSNA, 2017 An earlier incorrect version of this article appeared online. This article was corrected on July 27, 2017. Online supplemental material is available for this article.

Purpose: Regional infarction identification is important for heart disease diagnosis and management, and myocardial deformation has been shown to be effective for this purpose. Although tagged and strain-encoded MR images can provide such measurements, they are uncommon in clinical routine. On the contrary, cardiac CT images are more available with lower costs, but they only provide motion of cardiac boundaries and additional constraints are required to obtain the myocardial strains. The goal of this study is to verify the potential of contrast-enhanced CT images on computer-aided regional infarction identification., Methods: We propose a biomechanical approach combined with machine learning algorithms. A hyperelastic biomechanical model is used with deformable image registration to estimate 3D myocardial strains from CT images. The regional strains and CT image intensities are input to a classifier for regional infarction identification. Cross-validations on ten canine image sequences with artificially induced infarctions were used to study the performances of using different feature combinations and machine learning algorithms., Results: Radial strain, circumferential strain, first principal strain, and image intensity were shown to be discriminative features. The highest identification accuracy ([Formula: see text] %) was achieved when combining radial strain with image intensity. Random forests gave better results than support vector machines on less discriminative features. Random forests also performed better when all strains were used together., Conclusion: Although CT images cannot directly measure myocardial deformation, with the use of a biomechanical model, the estimated strains can provide promising identification results especially when combined with CT image intensity.

A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention., (Copyright © 2016 Elsevier Ltd. All rights reserved.)

Point Distribution Models (PDM) are among the most popular shape description techniques and their usefulness has been demonstrated in a wide variety of medical imaging applications. However, to adequately characterize the underlying modeled population it is essential to have a representative number of training samples, which is not always possible. This problem is especially relevant as the complexity of the modeled structure increases, being the modeling of ensembles of multiple 3D organs one of the most challenging cases. In this paper, we introduce a new GEneralized Multi-resolution PDM (GEM-PDM) in the context of multi-organ analysis able to efficiently characterize the different inter-object relations, as well as the particular locality of each object separately. Importantly, unlike previous approaches, the configuration of the algorithm is automated thanks to a new agglomerative landmark clustering method proposed here, which equally allows us to identify smaller anatomically significant regions within organs. The significant advantage of the GEM-PDM method over two previous approaches (PDM and hierarchical PDM) in terms of shape modeling accuracy and robustness to noise, has been successfully verified for two different databases of sets of multiple organs: six subcortical brain structures, and seven abdominal organs. Finally, we propose the integration of the new shape modeling framework into an active shape-model-based segmentation algorithm. The resulting algorithm, named GEMA, provides a better overall performance than the two classical approaches tested, ASM, and hierarchical ASM, when applied to the segmentation of 3D brain MRI., (Copyright © 2015 Elsevier B.V. All rights reserved.)

The widespread use of CT imaging and the critical importance of early detection of epidural masses of the spinal canal generate a scenario ideal for the implementation of a computer-aided detection (CAD) system. Epidural masses can lead to paralysis, incontinence and loss of neurological function if not promptly detected. We present, to our knowledge, the first CAD system to detect epidural masses on CT scans. In this paper, spatially constrained Gaussian mixture model (GMM) and supervoxel-based method are proposed for epidural mass detection. The detection is performed on the Gaussian level or the supervoxel level rather than the voxel level. Cross-validation on 40 patients with epidural masses on body CT showed that the supervoxel-based method yielded a significant improvement of performance (82% at 3 false positives per patient) over the spatially constrained GMM method (55% at 3 false positives per patient)., (Published by Elsevier Ltd.)

Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. for mediastinal LN, by one-shot boosting on 3D HAAR features. In this paper, we first operate a preliminary candidate generation stage, towards -100% sensitivity at the cost of high FP levels (-40 per patient), to harvest volumes of interest (VOI). Our 2.5D approach consequently decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates. These random views are then used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign LN probabilities for all N random views that can be simply averaged (as a set) to compute the final classification probability per VOI. We validate the approach on two datasets: 90 CT volumes with 388 mediastinal LNs and 86 patients with 595 abdominal LNs. We achieve sensitivities of 70%/83% at 3 FP/vol. and 84%/90% at 6 FP/vol. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work.

Pleural effusion is an important biomarker for the diagnosis of many diseases. We develop an automated method to evaluate pleural effusion on CT scans, the measurement of which is prohibitively time consuming when performed manually. The method is based on parietal and visceral pleura extraction, active contour models, region growing, Bezier surface fitting, and deformable surface modeling. Twelve CT scans with three manual segmentations were used to validate the automatic segmentation method. The method was then applied on 91 additional scans for visual assessment. The segmentation method yielded a correlation coefficient of 0.97 and a Dice coefficient of 0.72±0.13 when compared to a professional manual segmentation. The visual assessment estimated 83% cases with negligible or small segmentation errors, 14% with medium errors, and 3% with large errors.

Rationale and Objectives: To define systematic volumetric thresholds to identify and grade splenomegaly and retrospectively evaluate the performance of radiologists to assess splenomegaly in computed tomography (CT) image data., Materials and Methods: A clinical tool was developed to segment spleens from 172 contrast-enhanced clinical CT studies. There were 45 normal and 127 splenomegaly cases confirmed by radiological reports. Spleen volumes were compared to manual measurements using overlap/error. Volumetric thresholds for mild/massive splenomegaly were defined at 1/2.5 standard deviations above the average splenic volume of the healthy population. The thresholds were validated against consensus reports. The performance of radiologists in assessing splenomegaly was retrospectively evaluated., Results: The automated segmentation of spleens was robust with volume overlap/error of 95.2/3.3%. There were no significant differences (P > .2) between manual and automated segmentations for either normal/splenomegaly subgroups. Comparable correlations between interobserver and manual-automated measurements were found (r = 0.99 for all). The average volume of normal spleens was 236.89 ± 77.58 mL. For splenomegaly, average volume was 1004.75 ± 644.27 mL. Volumetric thresholds of 314.47/430.84 mL were used to define mild/massive splenomegaly (±18.86 mL, 95% CI). Radiologists disagreed in 23.25% (n = 40) of the diagnosed cases. The area under the receiver operating characteristic curve of the volumetric criterion for splenomegaly detection was 0.96. Using the volumetric thresholds as the reference standard, the sensitivity of radiologists in detecting all/mild/massive splenomegaly was 95.0/66.6/99.0% at 78.0% specificity, respectively., Conclusion: Thresholds for the identification and grading of splenomegaly from automatic volumetric spleen assessment were introduced. The volumetric thresholds match well with clinical interpretations for splenomegaly and may improve splenomegaly detection compared with splenic cephalocaudal height measurements or visual inspection commonly used in current clinical practice., (Published by Elsevier Inc.)

In this work, we propose a visual phrase learning scheme to learn an optimal visual composite of anatomical components/parts from CT colonography images for computer-aided detection. The key idea is to utilize the anatomical parts of human body from medical images and associate them with biological targets of interest (organs, cancers, lesions, etc.) for joint detection and recognition. These anatomical parts of the human body are not necessarily near each other regarding their physical locations, and they serve more like a human body navigation system for detection and recognition. To show the effectiveness of the proposed learning scheme, we applied it to two sub-problems in computed tomographic colonography: teniae detection and classification of colorectal polyp candidates. Experimental results showed its efficacy.

Kidney lesions are important extracolonic findings at computed tomographic colonography (CTC). However, kidney lesion detection on non-contrast CTC images poses significant challenges due to low image contrast with surrounding tissues. In this paper, we treat the kidney surface as manifolds in Riemannian space and present an intrinsic manifold diffusion approach to identify lesion-caused protrusion while simultaneously removing geometrical noise on the manifolds. Exophytic lesions (those that deform the kidney surface) are detected by searching for surface points with local maximum diffusion response and using the normalized cut algorithm to extract them. Moreover, multi-scale diffusion response is a discriminative feature descriptor for the subsequent classification to reduce false positives: We validated the proposed method and compared it with a baseline method using shape index on CTC datasets from 49 patients. Free-response receiver operating characteristic analysis showed that at 7 false positives, the proposed method achieved 87% sensitivity while the baseline method achieved only 22% sensitivity. The proposed method showed far fewer false positives compared with the baseline method which makes it feasible for clinical practice.

Detection and segmentation of ovarian cancer metastases have great clinical impacts on women's health. However, the random distribution and weak boundaries of metastases significantly complicate this task. This paper presents a variational framework that combines region competition based level set propagation and image matching flow computation to jointly detect and segment metastases. Image matching flow not only detects metastases, but also creates shape priors to reduce over-segmentation. Accordingly, accurate segmentation helps to improve the detection accuracy by separating flow computation in metastasis and non-metastasis regions. Since all components in the image processing pipeline benefit from each other, our joint framework can achieve accurate metastasis detection and segmentation. Validation on 50 patient datasets demonstrated that our joint approach was superior to a sequential method with sensitivity 89.2% vs. 81.4% (Fisher exact test p = 0.046) and false positive per patient 1.04 vs. 2.04. The Dice coefficient of metastasis segmentation was 92 +/- 5.2% vs. 72 +/- 8% (paired t-test p = 0.022), and the average surface distance was 1.9 +/- 1.5mm vs. 4.5 +/- 2.2mm (paired t-test p = 0.004).

In this work we formulate vessel segmentation on contrast-enhanced CT angiogram images as a Bayesian tracking problem. To obtain posterior probability estimation of vessel location, we employ sequential Monte Carlo tracking and propose a new vessel segmentation method by fusing multiple cues extracted from CT images. These cues include intensity, vesselness, organ detection, and bridge information for poorly enhanced segments from global path minimization. By fusing local and global information for vessel tracking, we achieved high accuracy and robustness, with significantly improved precision compared to a traditional segmentation method (p = 0.0002). Our method was applied to the segmentation of the marginal artery of the colon, a small bore vessel of potential importance for colon segmentation and CT colonography. Experimental results indicate the effectiveness of the proposed method.

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers., (Copyright © 2012. Published by Elsevier B.V.)

Rationale and Objectives: The aims of this study were to develop and validate an automated method to segment the renal cortex on contrast-enhanced abdominal computed tomographic images from kidney donors and to track cortex volume change after donation., Materials and Methods: A three-dimensional fully automated renal cortex segmentation method was developed and validated on 37 arterial phase computed tomographic data sets (27 patients, 10 of whom underwent two computed tomographic scans before and after nephrectomy) using leave-one-out strategy. Two expert interpreters manually segmented the cortex slice by slice, and linear regression analysis and Bland-Altman plots were used to compare automated and manual segmentation. The true-positive and false-positive volume fractions were also calculated to evaluate the accuracy of the proposed method. Cortex volume changes in 10 subjects were also calculated., Results: The linear regression analysis results showed that the automated and manual segmentation methods had strong correlations, with Pearson's correlations of 0.9529, 0.9309, 0.9283, and 0.9124 between intraobserver variation, interobserver variation, automated and user 1, and automated and user 2, respectively (P < .001 for all analyses). The Bland-Altman plots for cortex segmentation also showed that the automated and manual methods had agreeable segmentation. The mean volume increase of the cortex for the 10 subjects was 35.1 ± 13.2% (P < .01 by paired t test). The overall true-positive and false-positive volume fractions for cortex segmentation were 90.15 ± 3.11% and 0.85 ± 0.05%. With the proposed automated method, the time for cortex segmentation was reduced from 20 minutes for manual segmentation to 2 minutes., Conclusions: The proposed method was accurate and efficient and can replace the current subjective and time-consuming manual procedure. The computer measurement confirms the volume of renal cortex increases after kidney donation., (Published by Elsevier Inc.)

The interpretation of medical images benefits from anatomical and physiological priors to optimize computer-aided diagnosis applications. Diagnosis also relies on the comprehensive analysis of multiple organs and quantitative measures of soft tissue. An automated method optimized for medical image data is presented for the simultaneous segmentation of four abdominal organs from 4D CT data using graph cuts. Contrast-enhanced CT scans were obtained at two phases: non-contrast and portal venous. Intra-patient data were spatially normalized by non-linear registration. Then 4D convolution using population training information of contrast-enhanced liver, spleen and kidneys was applied to multiphase data to initialize the 4D graph and adapt to patient-specific data. CT enhancement information and constraints on shape, from Parzen windows, and location, from a probabilistic atlas, were input into a new formulation of a 4D graph. Comparative results demonstrate the effects of appearance, enhancement, shape and location on organ segmentation. All four abdominal organs were segmented robustly and accurately with volume overlaps over 93.6% and average surface distances below 1.1mm., (Published by Elsevier B.V.)

Rationale and Objectives: The aims of this study were to define volumetric nomograms for identifying hepatomegaly and to retrospectively evaluate the performance of radiologists in assessing hepatomegaly., Materials and Methods: Livers were automatically segmented from 148 abdominal contrast-enhanced computed tomographic scans: 77 normal livers and 71 cases of hepatomegaly (diagnosed by visual inspection and/or linear liver height by radiologists). Quantified liver volumes were compared to manual measurements using volume overlap and error. Liver volumes were normalized to body surface area, from which hepatomegaly nomograms were defined (H scores) by analyzing the distribution of liver sizes in the healthy population. H scores were validated against consensus reports. The performance of radiologists in diagnosing hepatomegaly was retrospectively evaluated., Results: The automated segmentation of livers was robust, with volume overlap and error of 96.2% and 2.2%, respectively. There were no significant differences (P > .10) between manual and automated segmentation for either the normal or the hepatomegaly subgroup. The average volumes of normal and enlarged livers were 1.51 ± 0.25 and 2.32 ± 0.75 L, respectively. One-way analysis of variance found that body surface area (P = .004) and gender (P = .02), but not age, significantly affected normal liver volume. No significant effects were observed for two-way and three-way interactions among the three variables (P > .18). H-score cutoffs of 0.92 and 1.08 L/m2 were used to define mild and massive hepatomegaly (95% confidence interval, ± 0.02 L/m2). Using the H score as the reference standard, the sensitivity of radiologists in detecting all, mild, and massive hepatomegaly was 84.4%, 56.7%, and 100.0% at 90.1% specificity, respectively. Radiologists disagreed on 20.9% of the diagnosed cases (n = 31). The area under the receiver-operating characteristic curve of the H-score criterion for hepatomegaly detection was 0.98., Conclusions: Nomograms for the identification and grading of hepatomegaly from automatic volumetric liver assessment normalized to body surface area (H scores) are introduced. H scores match well with clinical interpretations for hepatomegaly and may improve hepatomegaly detection compared with height measurements or visual inspection, commonly used in current clinical practice., (Published by Elsevier Inc.)

Purpose: Computed tomographic colonography (CTC) is a minimally invasive technique for colonic polyps and cancer screening. Teniae coli are three bands of longitudinal smooth muscle on the colon surface. Teniae coli are important anatomically meaningful landmarks on human colon. In this paper, the authors propose an automatic teniae coli detection method for CT colonography., Methods: The original CTC slices are first segmented and reconstructed to a 3D colon surface. Then, the 3D colon surface is unfolded using a reversible projection technique. After that the unfolded colon is projected to a 2D height map. The teniae coli are detected using the height map and then reversely projected back to the 3D colon. Since teniae are located at the junctions where the haustral folds meet, the authors apply 2D Gabor filter banks to extract features of haustral folds. The maximum response of the filter banks is then selected as the feature image. The fold centers are then identified based on local maxima and thresholding on the feature image. Connecting the fold centers yields a path of the folds. Teniae coli are extracted as lines running between the fold paths. The authors used the spatial relationship between ileocecal valve (ICV) and teniae mesocolica (TM) to identify the TM, then the teniae omentalis (TO) and the teniae libera (TL) can be identified subsequently., Results: The authors tested the proposed method on 47 cases of 37 patients, 10 of the patients with both supine and prone CT scans. The proposed method yielded performance with an average normalized root mean square error (RMSE) ( ± standard deviation [95% confidence interval]) of 4.87% ( ± 2.93%, [4.05% 5.69%])., Conclusions: The proposed fully-automated teniae coli detection and identification method is accurate and promising for future clinical applications.

Assessment of trauma patients with multiple injuries can be one of the most clinically challenging situations dealt with by the radiologist. We propose a fully automated method to detect acute vertebral body fractures on trauma CT studies. The spine is first segmented and partitioned into vertebrae. Then the cortical shell of the vertebral body is extracted using deformable dual-surface models. The extracted cortical shell is unwrapped onto a 2D map effectively converting a complex 3D fracture detection problem into a pattern recognition problem of fracture lines on a 2D plane. Twenty-eight features are computed for each fracture line and sent to a committee of support vector machines for classification. The system was tested on 18 trauma CT datasets and achieved 95.3% sensitivity and 1.7 false positives per case by leave-one-out cross validation.

Purpose: To evaluate the performance of a computer-aided detection (CAD) system for detecting colonic polyps at noncathartic computed tomography colonography (CTC) in conjunction with an automated image-based colon cleansing algorithm., Methods: An automated colon cleansing algorithm was designed to detect and subtract tagged-stool, accounting for heterogeneity and poor tagging, to be used in conjunction with a colon CAD system. The method is locally adaptive and combines intensity, shape, and texture analysis with probabilistic optimization. CTC data from cathartic-free bowel preparation were acquired for testing and training the parameters. Patients underwent various colonic preparations with barium or Gastroview in divided doses over 48 h before scanning. No laxatives were administered and no dietary modifications were required. Cases were selected from a polyp-enriched cohort and included scans in which at least 90% of the solid stool was visually estimated to be tagged and each colonic segment was distended in either the prone or supine view. The CAD system was run comparatively with and without the stool subtraction algorithm., Results: The dataset comprised 38 CTC scans from prone and/or supine scans of 19 patients containing 44 polyps larger than 10 mm (22 unique polyps, if matched between prone and supine scans). The results are robust on fine details around folds, thin-stool linings on the colonic wall, near polyps and in large fluid/stool pools. The sensitivity of the CAD system is 70.5% per polyp at a rate of 5.75 false positives/scan without using the stool subtraction module. This detection improved significantly (p = 0.009) after automated colon cleansing on cathartic-free data to 86.4% true positive rate at 5.75 false positives/scan., Conclusions: An automated image-based colon cleansing algorithm designed to overcome the challenges of the noncathartic colon significantly improves the sensitivity of colon CAD by approximately 15%.

Purpose: Surface curvatures are important geometric features for the computer-aided analysis and detection of polyps in CT colonography (CTC). However, the general kernel approach for curvature computation can yield erroneous results for small polyps and for polyps that lie on haustral folds. Those erroneous curvatures will reduce the performance of polyp detection. This paper presents an analysis of interpolation's effect on curvature estimation for thin structures and its application on computer-aided detection of small polyps in CTC., Methods: The authors demonstrated that a simple technique, image interpolation, can improve the accuracy of curvature estimation for thin structures and thus significantly improve the sensitivity of small polyp detection in CTC., Results: Our experiments showed that the merits of interpolating included more accurate curvature values for simulated data, and isolation of polyps near folds for clinical data. After testing on a large clinical data set, it was observed that sensitivities with linear, quadratic B-spline and cubic B-spline interpolations significantly improved the sensitivity for small polyp detection., Conclusions: The image interpolation can improve the accuracy of curvature estimation for thin structures and thus improve the computer-aided detection of small polyps in CTC.

The interpretation of medical images benefits from anatomical and physiological priors to optimize computer-aided diagnosis (CAD) applications. Diagnosis also relies on the comprehensive analysis of multiple organs and quantitative measures of soft tissue. An automated method optimized for medical image data is presented for the simultaneous segmentation of four abdominal organs from 4D CT data using graph cuts. Contrast-enhanced CT scans were obtained at two phases: non-contrast and portal venous. Intra-patient data were spatially normalized by non-linear registration. Then 4D erosion using population historic information of contrast-enhanced liver, spleen, and kidneys was applied to multi-phase data to initialize the 4D graph and adapt to patient specific data. CT enhancement information and constraints on shape, from Parzen windows, and location, from a probabilistic atlas, were input into a new formulation of a 4D graph. Comparative results demonstrate the effects of appearance and enhancement, and shape and location on organ segmentation.

A multiobjective genetic algorithm is designed to optimize a computer-aided detection (CAD) system for identifying colonic polyps. Colonic polyps appear as elliptical protrusions on the inner surface of the colon. Curvature-based features for colonic polyp detection have proved to be successful in several CT colonography (CTC) CAD systems. Our CTC CAD program uses a sequential classifier to form initial polyp detections on the colon surface. The classifier utilizes a set of thresholds on curvature-based features to cluster suspicious colon surface regions into polyp candidates. The thresholds were previously chosen experimentally by using feature histograms. The chosen thresholds were effective for detecting polyps sized 10 mm or larger in diameter. However, many medium-sized polyps, 6-9 mm in diameter, were missed in the initial detection procedure. In this paper, the task of finding optimal thresholds as a multiobjective optimization problem was formulated, and a genetic algorithm to solve it was utilized by evolving the Pareto front of the Pareto optimal set. The new CTC CAD system was tested on 792 patients. The sensitivities of the optimized system improved significantly, from 61.68% to 74.71% with an increase of 13.03% (95% CI [6.57%, 19.5%], p = 7.78 x 10(-5)) for the size category of 6-9 mm polyps, from 65.02% to 77.4% with an increase of 12.38% (95% CI [6.23%, 18.53%], p = 7.95 x 10(-5)) for polyps 6 mm or larger, and from 82.2% to 90.58% with an increase of 8.38% (95% CI [0.75%, 16%], p = 0.03) for polyps 8 mm or larger at comparable false positive rates. The sensitivities of the optimized system are nearly equivalent to those of expert radiologists.

Initial placement of the models is an essential pre-processing step for model-based organ segmentation. Based on the observation that organs move along with the spine and their relative locations remain relatively stable, we built a statistical location model (SLM) and applied it to abdominal organ localization. The model is a point distribution model which learns the pattern of variability of organ locations relative to the spinal column from a training set of normal individuals. The localization is achieved in three stages: spine alignment, model optimization and location refinement. The SLM is optimized through maximum a posteriori estimation of a probabilistic density model constructed for each organ. Our model includes five organs: liver, left kidney, right kidney, spleen and pancreas. We validated our method on 12 abdominal CTs using leave-one-out experiments. The SLM enabled reduction in the overall localization error from 62.0 +/- 28.5 mm to 5.8 +/- 1.5 mm. Experiments showed that the SLM was robust to the reference model selection.

Computer-aided detection (CAD) has been shown to be feasible for polyp detection on computed tomography (CT) scans. After initial detection, the dataset of colonic polyp candidates has large-scale and high dimensional characteristics. In this article, we propose a nonlinear dimensionality reduction method based on diffusion map and locally linear embedding (DMLLE) for large-scale datasets. By selecting partial data as landmarks, we first map these points into a low dimensional embedding space using the diffusion map. The embedded landmarks can be viewed as a skeleton of whole data in the low dimensional space. Then by using the locally linear embedding algorithm, nonlandmark samples are mapped into the same low dimensional space according to their nearest landmark samples. The local geometry is preserved in both the original high dimensional space and the embedding space. In addition, DMLLE provides a faithful representation of the original high dimensional data at coarse and fine scales. Thus, it can capture the intrinsic distance relationship between samples and reduce the influence of noisy features, two aspects that are crucial to achieving high classifier performance. We applied the proposed DMLLE method to a colonic polyp dataset of 175 269 polyp candidates with 155 features. Visual inspection shows that true polyps with similar shapes are mapped to close vicinity in the low dimensional space. We compared the performance of a support vector machine (SVM) classifier in the low dimensional embedding space with that in the original high dimensional space, SVM with principal component analysis dimensionality reduction and SVM committee using feature selection technology. Free-response receiver operating characteristic analysis shows that by using our DMLLE dimensionality reduction method, SVM achieves higher sensitivity with a lower false positive rate compared with other methods. For 6-9 mm polyps (193 true polyps contained in test set), when the number of false positives per patient is 9, SVM with DMLLE improves the average sensitivity from 70% to 83% compared with that of an SVM committee classifier which is a state-of-the-art method for colonic polyp detection (p<0.001).

This retrospective study investigates the potential of image analysis to quantify for the presence and extent of pulmonary hypertension secondary to sickle cell disease (SCD). A combination of fast marching and geodesic active contours level sets were employed to segment the pulmonary artery from smoothed CT-Angiography images from 16 SCD patients and 16 matching controls. An algorithm based on fast marching methods was used to compute the centerline of the segmented arteries to measure automatically the diameters of the pulmonary trunk and first branches of the pulmonary arteries. Results show that the pulmonary trunk and arterial branches are significantly larger in diameter in SCD patients as compared to controls (p-values of 0.002 for trunk and 0.0003 for branches). For validation, the results were compared with manually measured values and did not demonstrate significant difference (mean p-values 0.71). CT with image processing shows great potential as a surrogate indicator of pulmonary hemodynamics or response to therapy, which could be an important tool for drug discovery and noninvasive clinical surveillance.

Objective: The purpose of this study was to validate automated quality assessment (QA) software for CT colonography (CTC) by comparing results obtained with the software with results of interpretation by radiologists in the assessment of colonic distention and surface area obscured by residual fluid., Materials and Methods: CTC scans of 30 patients were selected retrospectively to span ranges of luminal distention (well distended to poorly distended) and surface area covered by residual fluid (high amount of coverage to low amount of coverage). We used QA software developed in our laboratory to automatically measure the mean distention of each of five colonic segments (ascending, transverse, descending, sigmoid, and rectum). Three experienced radiologists visually graded each scan for distention and fluid coverage. Distention and fluid scores for specific segments were assessed with Bland-Altman analysis (mean difference with 95% limits of agreement) and the weighted kappa test. Interobserver and intraobserver variability was determined with the weighted kappa test., Results: For distention scoring, the mean difference between radiologists and the QA software was 0.1% (95% limits of agreement, -25.6% and 25.9%). For fluid scoring, the mean difference was -0.6% (95% limits of agreement, -8.2% and 7.1%). There was moderate to good agreement (weighted kappa value, 0.50-0.78) between the radiologists' mean scores and the scores obtained with the QA software and for interreader and intrareader assessments of distention and fluid coverage., Conclusion: Results with the QA software agreed with radiologists' assessment of colonic distention and residual fluid coverage but were a more objective assessment. Use of this QA software can help standardize two important factors, distention and residual fluid coverage, that affect the quality of CTC, reducing two known causes of poor CTC performance.

An automatic method to segment colonic polyps in computed tomography (CT) colonography is presented in this paper. The method is based on a combination of knowledge-guided intensity adjustment, fuzzy c-mean clustering, and deformable models. The computer segmentations were compared with manual segmentations to validate the accuracy of our method. An average 76.3% volume overlap percentage among 105 polyp detections was reported in the validation, which was very good considering the small polyp size. Several experiments were performed to investigate the intraoperator and interoperator repeatability of manual colonic polyp segmentation. The investigation demonstrated that the computer-human repeatability was as good as the interoperator repeatability. The polyp segmentation was also applied in computer-aided detection (CAD) to reduce the number of false positive (FP) detections and provide volumetric features for polyp classification. Our segmentation method was able to eliminate 30% of FP detections. The volumetric features computed from the segmentation can further reduce FP detections by 50% at 80% sensitivity.

Purpose: To eliminate false-positive (FP) polyp detections on the rectal tube (RT) in CT colonography (CTC) computer-aided detection (CAD)., Methods: We use a three-stage approach to detect the RT: detect the RT shaft, track the tube to the tip and label all the voxels that belong to the RT. We applied our RT detection algorithm on a CTC dataset consisting of 80 datasets (40 patients scanned in both prone and supine positions). Two different types of RTs were present, characterized by differences in shaft/bulb diameters, wall intensities, and shape of tip., Results: The algorithm detected 90% of RT shafts and completely tracked 72% of them. We labeled all the voxels belonging to the completely tracked RTs (72%) and in 11 out of 80 (14%) cases the RT voxels were partially labeled. We obtained a 9.2% reduction of the FPs in the initial polyp candidates' population, and a 7.9% reduction of the FPs generated by our CAD system. None of the true-positive detections were mislabeled., Conclusions: The algorithm detects the RTs with good accuracy, is robust with respect to the two different types of RT used in our study, and is effective at reducing the number of RT FPs reported by our CAD system.

Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study.

Purpose: To apply a computer-aided detection (CAD) algorithm to supine and prone multisection helical computed tomographic (CT) colonographic images to confirm if there is any added benefit provided by CAD over that of standard clinical interpretation., Materials and Methods: CT colonography (with patients in both supine and prone positions) was performed with a multisection helical CT scanner in 40 asymptomatic high-risk patients. There were two consecutive series of patients, 20 of whom had at least one polyp 1.0 cm in size or larger and 20 of whom had normal colons at conventional colonoscopy performed the same day. The CT colonographic images were interpreted with an automated CAD algorithm and by two radiologists who were blinded to colonoscopy findings., Results: For 25 polyps at least 1.0 cm in size ("large" polyps), sensitivity for detection by at least one radiologist was 48% (12 of 25). The sensitivity of CAD for detecting large polyps was also 48% (12 of 25), but the CAD algorithm detected four of 13 large polyps that were not detected by either radiologist (31%, 95% two-sided CI: 9, 61), increasing the potential sensitivity to 64% (16 of 25). For polyps identifiable retrospectively, sensitivity of CAD was 67% (12 of 18), and sensitivity of the combination of detection with the CAD algorithm or by at least one radiologist was 89% (16 of 18). There were an average of 11 false-positive detections per patient for CAD., Conclusion: In this series of patients in whom radiologists had difficulties detecting polyps (compared with sensitivities of 75%-90% reported in the literature), this CAD algorithm played a complementary role to conventional interpretation of CT colonographic images by detecting a number of large polyps missed by trained observers., (Copyright RSNA, 2002)

A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.

The vertebral body is the main axial load-bearing structure of the spinal vertebra. Assessment of acute injury and chronic deformity of the vertebral body is difficult to assess accurately and quantitatively by simple visual inspection. We propose a cortical shell unwrapping method to examine the vertebral body for injury such as fractures and degenerative osteophytes. The spine is first segmented and partitioned into vertebrae. Then the cortical shell of the vertebral body is extracted using deformable dual-surface models. The cortical shell is then unwrapped onto a 2D map and the complex 3D detection problem is effectively converted to a pattern recognition problem on a 2D plane. Characteristic features adapted for different applications are computed and sent to a committee of support vector machines for classification. The system was evaluated on two applications, one for fracture detection on trauma CT datasets and the other on degenerative osteophyte assessment on sodium fluoride PET/CT. The fracture CAD achieved 93.6% sensitivity at 3.2 false positive per patient and the degenerative osteophyte CAD achieved 82% sensitivity at 4.7 false positive per patient.

Objective: To investigate an automated aortic calcium segmentation and scoring tool at abdominal CT in an adult screening cohort. Methods: Using instance segmentation with convolutional neural networks (Mask R-CNN), a fully automated vascular calcification algorithm was applied to a data set of 9914 non-contrast CT scans from 9032 consecutive asymptomatic adults (mean age, 57.5 ± 7.8 years; 4467 M/5447F) undergoing colonography screening. Follow-up scans were performed in a subset of 866 individuals (mean interval, 5.4 years). Automated abdominal aortic calcium volume, mass, and Agatston score were assessed. In addition, comparison was made with a separate validated semi-automated approach in a subset of 812 cases. Results: Mean values were significantly higher in males for Agatston score (924.2 ± 2066.2 vs. 564.2 ± 1484.2, p < 0.001), aortic calcium mass (222.2 ± 526.0 mg vs. 144.5 ± 405.4 mg, p < 0.001) and volume (699.4 ± 1552.4 ml vs. 426.9 ± 1115.5 HU, p < 0.001). Overall age-specific Agatston scores increased an average of 10%/year for the entire cohort; males had a larger Agatston score increase between the ages of 40 to 60 than females (91.2% vs. 75.1%, p < 0.001) and had significantly higher mean Agatston scores between ages 50 and 80 (p < 0.001). For the 812-scan subset with both automated and semi-automated methods, median difference in Agatston score was 66.4 with an r2 agreement value of 0.84. Among the 866-patient cohort with longitudinal follow-up, the average Agatston score change was 524.1 ± 1317.5 (median 130.9), reflecting a mean increase of 25.5% (median 73.6%). Conclusion: This robust, fully automated abdominal aortic calcification scoring tool allows for both individualized and population-based assessment. Such data could be automatically derived at non-contrast abdominal CT, regardless of the study indication, allowing for opportunistic assessment of cardiovascular risk. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new registration method for prone and supine computed tomographic colonography scans using graph matching. We formulate 3-D colon registration as a graph matching problem and propose a new graph matching algorithm based on mean field theory. In the proposed algorithm, we solve the matching problem in an iterative way. In each step, we use mean field theory to find the matched pair of nodes with highest probability. During iterative optimization, one-to-one matching constraints are added to the system in a step-by-step approach. Prominent matching pairs found in previous iterations are used to guide subsequent mean field calculations. The proposed method was found to have the best performance with smallest standard deviation compared with two other baseline algorithms called the normalized distance along the colon centerline (NDACC) ( p = 0.17) with manual colon centerline correction and spectral matching ( p < 1e−5). A major advantage of the proposed method is that it is fully automatic and does not require defining a colon centerline for registration. For the latter NDACC method, user interaction is almost always needed for identifying the colon centerlines. [ABSTRACT FROM PUBLISHER]

In this paper, we present development and testing results for a novel colonic polyp classification method for use as part of a computed tomographic colonography (CTC) computer-aided detection (CAD) system. Inspired by the interpretative methodology of radiologists using 3-D fly-through mode in CTC reading, we have developed an algorithm which utilizes sequences of images (referred to here as videos) for classification of CAD marks. For each CAD mark, we created a video composed of a series of intraluminal, volume-rendered images visualizing the detection from multiple viewpoints. We then framed the video classification question as a multiple-instance learning (MIL) problem. Since a positive (negative) bag may contain negative (positive) instances, which in our case depends on the viewing angles and camera distance to the target, we developed a novel MIL paradigm to accommodate this class of problems. We solved the new MIL problem by maximizing a L2-norm soft margin using semidefinite programming, which can optimize relevant parameters automatically. We tested our method by analyzing a CTC data set obtained from 50 patients from three medical centers. Our proposed method showed significantly better performance compared with several traditional MIL methods. [ABSTRACT FROM PUBLISHER]

A multiobjective genetic algorithm is designed to optimize a computer-aided detection (CAD) system for identifying colonic polyps. Colonic polyps appear as elliptical protrusions on the inner surface of the colon. Curvature-based features for colonic polyp detection have proved to be successful in several CT colonography (CTC) CAD systems. Our CTC CAD program uses a sequential classifier to form initial polyp detections on the colon surface. The classifier utilizes a set of thresholds on curvature-based features to cluster suspicious colon surface regions into polyp candidates. The thresholds were previously chosen experimentally by using feature histograms. The chosen thresholds were effective for detecting polyps sized 10 mm or larger in diameter. However, many medium-sized polyps, 6–9 mm in diameter, were missed in the initial detection procedure. In this paper, the task of finding optimal thresholds as a multiobjective optimization problem was formulated, and a genetic algorithm to solve it was utilized by evolving the Pareto front of the Pareto optimal set. The new CTC CAD system was tested on 792 patients. The sensitivities of the optimized system improved significantly, from 61.68% to 74.71% with an increase of 13.03% (95% CI [6.57%, 19.5%], p=7.78×10-5) for the size category of 6–9 mm polyps, from 65.02% to 77.4% with an increase of 12.38% (95% CI [6.23%, 18.53%], p=7.95×10-5) for polyps 6 mm or larger, and from 82.2% to 90.58% with an increase of 8.38% (95%CI [0.75%, 16%], p=0.03) for polyps 8 mm or larger at comparable false positive rates. The sensitivities of the optimized system are nearly equivalent to those of expert radiologists. [ABSTRACT FROM AUTHOR]

Virtual colonoscopy (VC) is becoming a more prevalent method to detect and diagnose colorectal cancer. An essential component of using VC to detect cancerous polyps, especially in conjunction with computer-aided diagnosis, is the accurate calculation of the centerline of the colon. While the colon is often modeled as a simple cylinder, the amount of colonic distention may vary between patients and within the same patient often causing loops and multiple disconnected segments to be present in the colon segmentation. These variations have caused previous centerline algorithms to fail to capture a complete and accurate centerline for all colons. We have developed an automatic method to determine from a computed tomography (CT) VC a subvoxel precise centerline that is accurate even in cases of over-distended or under-distended colons. In this algorithm, the loops in the colon caused by over-distention are detected and removed when the centerline calculation is performed. Also, a newly developed method for the detection and segmentation of the outer wall of the colon is used to connect collapsed portions of the colon where the lumen segmentation fails to produce a continuous centerline. These two methods allow for a complete and accurate centerline to be calculated in uniformly distended colons as well as in colons containing segments which are over-distended and/or under-distended. We have demonstrated successfully the effectiveness of our algorithm on 50 cases, 25 of which resulted in erroneous solutions by previous centerline algorithms due to variability in the colon distention. [ABSTRACT FROM AUTHOR]