Marker-controlled watershed for lymphoma segmentation in sequential CT images

Gastric emptying performance of stomach-partitioning gastrojejunostomy versus conventional gastrojejunostomy for treating gastric outlet obstruction: A retrospective clinical and numerical simulation study

Purpose: This study evaluated the gastric emptying performance of stomach-partitioning gastrojejunostomy (SPGJ) versus conventional gastrojejunostomy (CGJ) for treating gastric outlet obstruction (GOO). Methods: First, 73 patients who underwent SPGJ (n = 48) or CGJ (n = 25) were involved. Surgical outcomes, postoperative recovery of gastrointestinal function, delayed gastric emptying, and nutritional status of both groups were compared. Second, a three-dimensional stomach model was constructed based on the gastric filling CT images from a GOO patient with a standard stature. The present study evaluated SPGJ numerically by comparing it with CGJ in terms of local flow parameters such as flow velocity, pressure, particle retention time, and particle retention velocity. Results: Clinical data found that SPGJ had significant advantages over CGJ in terms of time to pass gas (3 versus 4 days, p < 0.001), time to oral intake (3 versus 4 days, p = 0.001), postoperative hospitalization (7 versus 9 days, p < 0.001), the incidence of delay gastric emptying (DGE) (2.1% versus 36%, p < 0.001), DGE grading (p < 0.001), and complications (p < 0.001) for GOO patients. Moreover, numerical simulation revealed that the SPGJ model would induce contents in stomach discharge to the anastomosis at a higher speed, and only 5% of that flowed to the pylorus. SPGJ model also had a low-pressure drop as the flow from the lower esophagus to the jejunum, reducing the resistance to food discharge. Besides, the average retention time of particles in the CGJ model is 1.5 times longer than that in the SPGJ models, and the average instantaneous velocity in CGJ and SPGJ models are 22 mm/s and 29 mm/s, respectively. Conclusion: Compared with CGJ, patients after SPGJ had better gastric emptying performance and better postoperative clinical efficacy. Therefore, we think that SPGJ may be a better option for treating GOO.

PSR-Nets: Deep neural networks with prior shift regularization for PET/CT based automatic, accurate, and calibrated whole-body lymphoma segmentation

Lymphoma is a type of lymphatic tissue originated cancer. Automatic and accurate lymphoma segmentation is critical for its diagnosis and prognosis yet challenging due to the severely class-imbalanced problem. Generally, deep neural networks trained with class-observation-frequency based re-weighting loss functions are used to address this problem. However, the majority class can be under-weighted by them, due to the existence of data overlap. Besides, they are more mis-calibrated. To resolve these, we propose a neural network with prior-shift regularization (PSR-Net), which comprises a UNet-like backbone with re-weighting loss functions, and a prior-shift regularization (PSR) module including a prior-shift layer (PSL), a regularizer generation layer (RGL), and an expected prediction confidence updating layer (EPCUL). We first propose a trainable expected prediction confidence (EPC) for each class. Periodically, PSL shifts a prior training dataset to a more informative dataset based on EPCs; RGL presents a generalized informative-voxel-aware (GIVA) loss with EPCs and calculates it on the informative dataset for model finetuning in back-propagation; and EPCUL updates EPCs to refresh PSL and RRL in next forward-propagation. PSR-Net is trained in a two- stage manner. The backbone is first trained with re-weighting loss functions, then we reload the best saved model for the backbone and continue to train it with the weighted sum of the re-weighting loss functions, the GIVA regularizer and the L2 loss function of EPCs for regularization fine-tuning. Extensive experiments are performed based on PET/CT volumes with advanced stage lymphomas. Our PSR-Net achieves 95.12% sensitivity and 87.18% Dice coefficient, demonstrating the effectiveness of PSR-Net, when compared to the baselines and the state-of-the-arts.

Hemodynamic Impact of Stenting on Carotid Bifurcation: A Potential Role of the Stented Segment and External Carotid Artery

Carotid stenting near the bifurcation carina is associated with adverse events, especially in-stent restenosis, thrombosis, and side branch occlusion in clinical data. This study is aimed at determining the potential biomechanical mechanisms for these adverse events after carotid stenting. The patient-specific carotid models were constructed with different stenting scenarios to study the flow distribution and hemodynamic parameters, such as wall shear stress (WSS), flow velocity, relative residence time (RRT), and oscillating shear index (OSI) in the carotid bifurcation. The results suggested that the existing stents surely reduced blood flow to the external carotid artery (ECA) but enhanced local flow disturbance both in ECA and stented internal carotid artery (ICA), and the inner posterior wall of the stented ICA and the outer posterior wall of ECA might endure a relatively low level of WSS and remarkably elevated OSI and RRT. In addition, the implanted stent leads to more ECA adverse flow than ICA after stenting. While disturbed flow near the strut increased as stent length increased, blood flow and areas of local flow disturbance in ECA slightly decreased as stent length increased. In conclusion, the results revealed that ECA might be in relatively high levels of abnormal local hemodynamics after stenting, followed by stented ICA, leading to potential adverse events after intervention.

Machine learning for evolutive lymphoma and residual masses recognition in whole body diffusion weighted magnetic resonance images

BACKGROUND

After the treatment of the patients with malignant lymphoma, there may persist lesions that must be labeled either as evolutive lymphoma requiring new treatments or as residual masses. We present in this work, a machine learning-based computer-aided diagnosis (CAD) applied to whole-body diffusion-weighted magnetic resonance images.

METHODS

The database consists of a total of 1005 MRI images with evolutive lymphoma and residual masses. More specifically, we propose a novel approach that leverages: (1)-The complementarity of the functional and anatomical criteria of MRI images through a fusion step based on the discrete wavelet transforms (DWT). (2)- The automatic segmentation of the lesions, their localization, and their enumeration using the Chan-Vese algorithm. (3)- The generation of the parametric image which contains the apparent diffusion coefficient value named ADC map. (4)- The features selection through the application of the sequential forward selection (SFS), Entropy, Symmetric uncertainty and Gain Ratio algorithm on 72 extracted features. (5)- The classification of the lesions by applying five well known supervised machine learning classification algorithms: the back-propagation artificial neural network (ANN), the support vector machine (SVM), the K-nearest neighbours (K-NN), Relevance Vectors Machine (RVM), and the random forest (RF) compared to deep learning based on convolutional neural network (CNN). Moreover, this study is achieved with an evaluation of the classification using 335 DW-MR images where 80% of them are used for the training and the remaining 20% for the test.

RESULTS

The obtained accuracy for the five classifiers recorded a slight superiority to the proposed method based on the back-propagation 3-9-1 ANN model which reaches 96,5%. In addition, we compared the proposed method to five other works from the literature. The proposed method gives much better results in terms of SE, SP, accuracy, F₁-measure, and geometric-mean which reaches respectively 96.4%, 90.9%, 95.5%, 0.97, and 91.61%.

CONCLUSIONS

Our initial results suggest that Combining functional, anatomical, and morphological features of ROI's have very good accuracy (97.01%) for evolutive lymphoma and residual masses recognition when we based on the new proposed approach using the back-propagation 3-9-1 ANN model. Proposed method based on machine learning gives less than Deep learning CNN, which is 98.5%.

Marker-based watershed transform method for fully automatic mandibular segmentation from CBCT images

OBJECTIVES:

To propose a reliable and practical method for automatically segmenting the mandible from CBCT images.

METHODS:

The marker-based watershed transform is a region-growing approach that dilates or "floods" predefined markers onto a height map whose ridges denote object boundaries. We applied this method to segment the mandible from the rest of the CBCT image. The height map was generated to enhance the sharp decreases of intensity at the mandible/tissue border and suppress noise by computing the intensity gradient image of the CBCT itself. Two sets of markers, "mandible" and "background" were automatically placed inside and outside the mandible, respectively in a novel image using image registration. The watershed transform flooded the gradient image by dilating the markers simultaneously until colliding at watershed lines, estimating the mandible boundary. CBCT images of 20 adolescent subjects were chosen as test cases. Segmentation accuracy of the proposed method was evaluated by measuring overlap (Dice similarity coefficient) and boundary agreement against a well-accepted interactive segmentation method described in the literature.

RESULTS:

The Dice similarity coefficient was 0.97 ± 0.01 (mean ± SD), indicating almost complete overlap between the automatically and the interactively segmented mandibles. Boundary deviations were predominantly under 1 mm for most of the mandibular surfaces. The errors were mostly from bones around partially erupted wisdom teeth, the condyles and the dental enamels, which had minimal impact on the overall morphology of the mandible.

CONCLUSIONS:

The marker-based watershed transform method produces segmentation accuracy comparable to the well-accepted interactive segmentation approach.

Automatic segmentation of abnormal capillary nonperfusion regions in optical coherence tomography angiography images using marker-controlled watershed algorithm

Diabetic retinopathy (DR) is one of the most complications of diabetes. It is a progressive disease leading to significant vision loss in the patients. Abnormal capillary nonperfusion (CNP) regions are one of the important characteristics of DR increasing with its progression. Therefore, automatic segmentation and quantification of abnormal CNP regions can be helpful to monitor the patient's treatment process. We propose an automatic method for segmentation of abnormal CNP regions on the superficial and deep capillary plexuses of optical coherence tomography angiography (OCTA) images using the marker-controlled watershed algorithm. The proposed method has three main steps. In the first step, original images are enhanced using the vesselness filter and then foreground and background marker images are computed. In the second step, abnormal CNP region candidates are segmented using the marker-controlled watershed algorithm, and in the third step, the candidates are modeled using an undirected weighted graph and finally, by applying merging and removing procedures correct abnormal CNP regions are identified. The proposed method was evaluated on a dataset with 36 normal and diabetic subjects using the ground truth obtained by two observers. The results show the proposed method outperformed some of the state-of-the-art methods on the superficial and deep capillary plexuses according to the most important metrics.

Multi-Pass Fast Watershed for Accurate Segmentation of Overlapping Cervical Cells

The task of segmenting cell nuclei and cytoplasm in pap smear images is one of the most challenging tasks in automated cervix cytological analysis due to specifically the presence of overlapping cells. This paper introduces a multi-pass fast watershed-based method (MPFW) to segment both nucleus and cytoplasm from large cell masses of overlapping cervical cells in three watershed passes. The first pass locates the nuclei with barrier-based watershed on the gradient-based edge map of a pre-processed image. The next pass segments the isolated, touching, and partially overlapping cells with a watershed transform adapted to the cell shape and location. The final pass introduces mutual iterative watersheds separately applied to each nucleus in the largely overlapping clusters to estimate the cell shape. In MPFW, the line-shaped contours of the watershed cells are deformed with ellipse fitting and contour adjustment to give a better representation of cell shapes. The performance of the proposed method has been evaluated using synthetic, real extended depth-of-field, and multi-layers cervical cytology images provided by the first and second overlapping cervical cytology image segmentation challenges in ISBI 2014 and ISBI 2015. The experimental results demonstrate superior performance of the proposed MPFW in terms of segmentation accuracy, detection rate, and time complexity, compared with recent peer methods.

A Response Assessment Platform for Development and Validation of Imaging Biomarkers in Oncology

Quantitative imaging biomarkers are increasingly used in both oncology clinical trials and clinical practice aid evaluation of tumor response to novel therapies. To obtain these biomarkers, and to ensure smooth clinical adoption once they have been validated, it is critical to develop reliable computer-aided methods and a workflow-efficient imaging platform for integration in research and clinical settings. Here, we present a volumetric response assessment system developed based on an open-source image-viewing platform (WEASIS). Our response assessment system is designed using the Model–View–Controller concept, and it offers standard image-viewing and -manipulation functions, efficient tumor segmentation and quantification algorithms, and a reliable database containing tumor segmentation and measurement results. This prototype system is currently used in our research laboratory to foster the development and validation of new quantitative imaging biomarkers including the volumetric computed tomography technique as a more accurate and early assessment method of solid tumor response to targeted therapy and immunotherapy.

Semiautomatic segmentation of liver metastases on volumetric CT images

PURPOSE

Accurate segmentation and quantification of liver metastases on CT images are critical to surgery/radiation treatment planning and therapy response assessment. To date, there are no reliable methods to perform such segmentation automatically. In this work, the authors present a method for semiautomatic delineation of liver metastases on contrast-enhanced volumetric CT images.

METHODS

The first step is to manually place a seed region-of-interest (ROI) in the lesion on an image. This ROI will (1) serve as an internal marker and (2) assist in automatically identifying an external marker. With these two markers, lesion contour on the image can be accurately delineated using traditional watershed transformation. Density information will then be extracted from the segmented 2D lesion and help determine the 3D connected object that is a candidate of the lesion volume. The authors have developed a robust strategy to automatically determine internal and external markers for marker-controlled watershed segmentation. By manually placing a seed region-of-interest in the lesion to be delineated on a reference image, the method can automatically determine dual threshold values to approximately separate the lesion from its surrounding structures and refine the thresholds from the segmented lesion for the accurate segmentation of the lesion volume. This method was applied to 69 liver metastases (1.1-10.3 cm in diameter) from a total of 15 patients. An independent radiologist manually delineated all lesions and the resultant lesion volumes served as the "gold standard" for validation of the method's accuracy.

RESULTS

The algorithm received a median overlap, overestimation ratio, and underestimation ratio of 82.3%, 6.0%, and 11.5%, respectively, and a median average boundary distance of 1.2 mm.

CONCLUSIONS

Preliminary results have shown that volumes of liver metastases on contrast-enhanced CT images can be accurately estimated by a semiautomatic segmentation method.

Mediastinal lymph node detection and station mapping on chest CT using spatial priors and random forest

PURPOSE

To develop an automated system for mediastinal lymph node detection and station mapping for chest CT.

METHODS

The contextual organs, trachea, lungs, and spine are first automatically identified to locate the region of interest (ROI) (mediastinum). The authors employ shape features derived from Hessian analysis, local object scale, and circular transformation that are computed per voxel in the ROI. Eight more anatomical structures are simultaneously segmented by multiatlas label fusion. Spatial priors are defined as the relative multidimensional distance vectors corresponding to each structure. Intensity, shape, and spatial prior features are integrated and parsed by a random forest classifier for lymph node detection. The detected candidates are then segmented by the following curve evolution process. Texture features are computed on the segmented lymph nodes and a support vector machine committee is used for final classification. For lymph node station labeling, based on the segmentation results of the above anatomical structures, the textual definitions of mediastinal lymph node map according to the International Association for the Study of Lung Cancer are converted into patient-specific color-coded CT image, where the lymph node station can be automatically assigned for each detected node.

RESULTS

The chest CT volumes from 70 patients with 316 enlarged mediastinal lymph nodes are used for validation. For lymph node detection, their system achieves 88% sensitivity at eight false positives per patient. For lymph node station labeling, 84.5% of lymph nodes are correctly assigned to their stations.

CONCLUSIONS

Multiple-channel shape, intensity, and spatial prior features aggregated by a random forest classifier improve mediastinal lymph node detection on chest CT. Using the location information of segmented anatomic structures from the multiatlas formulation enables accurate identification of lymph node stations.

Comparison of CT volumetric measurement with RECIST response in patients with lung cancer

PURPOSE

To examine the correlations between uni-dimensional RECIST and volumetric measurements in patients with lung adenocarcinoma and to assess their association with overall survival (OS) and progression-free survival (PFS).

MATERIALS AND METHODS

In this study of patients receiving chemotherapy for lung cancer in the setting of a clinical trial, response was prospectively evaluated using RECIST 1.0. Retrospectively, volumetric measurements were recorded and response was assessed by two different volumetric methods at each followup CT scan using a semi-automated segmentation algorithm. We subsequently evaluated the correlation between the uni-dimensional RECIST measurements and the volumetric measurements and performed landmark analyses for OS and PFS at the completion of the first and second follow-ups. Kaplan-Meier curves together with log-rank tests were used to evaluate the association between the different response criteria and patient outcome.

RESULTS

Forty-two patients had CT scans at baseline, after the first follow up scan and second followup scan, and then every 8 weeks. The uni-dimensional RECIST measurements and volumetric measurements were strongly correlated, with a Spearman correlation coefficient (ρ) of 0.853 at baseline, ρ=0.861 at the first followup, ρ=0.843 at the 2nd followup, and ρ=0.887 overall between-subject. On first follow-up CT, partial responders and non responders as assessed by an "ellipsoid" volumetric criteria showed a significant difference in OS (p=0.008, 1-year OS of 70% for partial responders and 46% for non responders). There was no difference between the groups when assessed by RECIST criteria on first follow-up CT (p=0.841, 1-year OS rate of 64% for partial responders and 64% for non responders).

CONCLUSION

Volumetric response on first follow-up CT may better predict OS than RECIST response.

CLINICAL RELEVANCE STATEMENT

Assessment of tumor size and response is of utmost importance in clinical trials. Volumetric measurements may help to better predict OS than uni-dimensional RECIST criteria.

Region-based snake with edge constraint for segmentation of lymph nodes on CT images

Lymph nodes segmentation is a tedious process with large inter-user variability when performed manually. To facilitate lymph nodes assessment for lung cancer patient, we present an automatic and improved snake segmentation method for thoracic lymph nodes on CT images in this paper. We first investigated the performance of both edge-based and region-based snake algorithms for the segmentation task, using a B-spline contour parameterization. The effect of the number of B-spline control points on the snake performance was also examined. Both edge-based and region-based snakes were found to have their own advantages and disadvantages for lymph nodes segmentation. We further developed a method of region-based snake with edge constraint, which utilizes a self-adjusting mechanism to integrate both edge and region information in a constructive manner. The average Dice Similarity Coefficient obtained was 0.853 ± 0.059 and 0.841 ± 0.108 for the baseline and follow-up lymph nodes respectively using the proposed method. The method was found to be an effective lymph node segmentation method and would potentially be useful to help with treatment response evaluations in the clinical practice.

Image segmentation for integrated multiphoton microscopy and reflectance confocal microscopy imaging of human skin in vivo

BACKGROUND

Non-invasive cellular imaging of the skin in vivo can be achieved in reflectance confocal microscopy (RCM) and multiphoton microscopy (MPM) modalities to yield complementary images of the skin based on different optical properties. One of the challenges of in vivo microscopy is the delineation (i.e., segmentation) of cellular and subcellular architectural features.

METHODS

In this work we present a method for combining watershed and level-set models for segmentation of multimodality images obtained by an integrated MPM and RCM imaging system from human skin in vivo.

RESULTS

Firstly, a segmentation model based on watershed is introduced for obtaining the accurate structure of cell borders from the RCM image. Secondly,, a global region based energy level-set model is constructed for extracting the nucleus of each cell from the MPM image. Thirdly, a local region-based Lagrange Continuous level-set approach is used for segmenting cytoplasm from the MPM image.

CONCLUSIONS

Experimental results demonstrated that cell borders from RCM image and boundaries of cytoplasm and nucleus from MPM image can be obtained by our segmentation method with better accuracy and effectiveness. We are planning to use this method to perform quantitative analysis of MPM and RCM images of in vivo human skin to study the variations of cellular parameters such as cell size, nucleus size and other mophormetric features with skin pathologies.

Role of imaging in the staging and response assessment of lymphoma: consensus of the International Conference on Malignant Lymphomas Imaging Working Group

PURPOSE

Recent advances in imaging, use of prognostic indices, and molecular profiling techniques have the potential to improve disease characterization and outcomes in lymphoma. International trials are under way to test image-based response–adapted treatment guided by early interim positron emission tomography (PET)–computed tomography (CT). Progress in imaging is influencing trial design and affecting clinical practice. In particular, a five-point scale to grade response using PET-CT, which can be adapted to suit requirements for early- and late-response assessment with good interobserver agreement, is becoming widely used both in practice- and response-adapted trials. A workshop held at the 11th International Conference on Malignant Lymphomas (ICML) in 2011 concluded that revision to current staging and response criteria was timely.

METHODS

An imaging working group composed of representatives from major international cooperative groups was asked to review the literature, share knowledge about research in progress, and identify key areas for research pertaining to imaging and lymphoma.

RESULTS

A working paper was circulated for comment and presented at the Fourth International Workshop on PET in Lymphoma in Menton, France, and the 12th ICML in Lugano, Switzerland, to update the International Harmonisation Project guidance regarding PET. Recommendations were made to optimize the use of PET-CT in staging and response assessment of lymphoma, including qualitative and quantitative methods.

CONCLUSION

This article comprises the consensus reached to update guidance on the use of PET-CT for staging and response assessment for [18F]fluorodeoxyglucose-avid lymphomas in clinical practice and late-phase trials.

Building roof segmentation from aerial images using a lineand region-based watershed segmentation technique

In this paper, we present a novel strategy for roof segmentation from aerial images (orthophotoplans) based on the cooperation of edge- and region-based segmentation methods. The proposed strategy is composed of three major steps. The first one, called the pre-processing step, consists of simplifying the acquired image with an appropriate couple of invariant and gradient, optimized for the application, in order to limit illumination changes (shadows, brightness, etc.) affecting the images. The second step is composed of two main parallel treatments: on the one hand, the simplified image is segmented by watershed regions. Even if the first segmentation of this step provides good results in general, the image is often over-segmented. To alleviate this problem, an efficient region merging strategy adapted to the orthophotoplan particularities, with a 2D modeling of roof ridges technique, is applied. On the other hand, the simplified image is segmented by watershed lines. The third step consists of integrating both watershed segmentation strategies into a single cooperative segmentation scheme in order to achieve satisfactory segmentation results. Tests have been performed on orthophotoplans containing 100 roofs with varying complexity, and the results are evaluated with the VINETcriterion using ground-truth image segmentation. A comparison with five popular segmentation techniques of the literature demonstrates the effectiveness and the reliability of the proposed approach. Indeed, we obtain a good segmentation rate of 96% with the proposed method compared to 87.5% with statistical region merging (SRM), 84% with mean shift, 82% with color structure code (CSC), 80% with efficient graph-based segmentation algorithm (EGBIS) and 71% with JSEG.

Classification of thresholded regions based on selective use of PET, CT and PET-CT image features

Fluorodeoxyglucose positron emission tomography - computed tomography (FDG PET-CT) is the preferred image modality for lymphoma diagnosis. Sites of disease generally appear as foci of increased FDG uptake. Thresholding methods are often applied to robustly separate these regions. However, its main limitation is that it also includes sites of FDG excretion and physiological FDG uptake regions, which we define as FEPU - sites of FEPU include the bladder, renal, papillae, ureters, brain, heart and brown fat. FEPU can make image interpretation problematic. The ability to identify and label FEPU sites and separate them from abnormal regions is an important process that could improve image interpretation. We propose a new method to automatically separate and label FEPU sites from the thresholded PET images. Our method is based on the selective use of features extracted from data types comprising of PET, CT and PET-CT. Our FEPU classification of 43 clinical lymphoma patient studies revealed higher accuracy when compared to non-selective image features.

Snake model-based lymphoma segmentation for sequential CT images

The measurement of the size of lesions in follow-up CT examinations of cancer patients is important to evaluate the success of treatment. This paper presents an automatic algorithm for identifying and segmenting lymph nodes in CT images across longitudinal time points. Firstly, a two-step image registration method is proposed to locate the lymph nodes including coarse registration based on body region detection and fine registration based on a double-template matching algorithm. Then, to make the initial segmentation approximate the boundaries of lymph nodes, the initial image registration result is refined with intensity and edge information. Finally, a snake model is used to evolve the refined initial curve and obtain segmentation results. Our algorithm was tested on 26 lymph nodes at multiple time points from 14 patients. The image at the earlier time point was used as the baseline image to be used in evaluating the follow-up image, resulting in 76 total test cases. Of the 76 test cases, we made a 76 (100%) successful detection and 38/40 (95%) correct clinical assessment according to Response Evaluation Criteria in Solid Tumors (RECIST). The quantitative evaluation based on several metrics, such as average Hausdorff distance, indicates that our algorithm is produces good results. In addition, the proposed algorithm is fast with an average computing time 2.58s. The proposed segmentation algorithm for lymph nodes is fast and can achieve high segmentation accuracy, which may be useful to automate the tracking and evaluation of cancer therapy.

Harnessing technology to improve clinical trials: study of real-time informatics to collect data, toxicities, image response assessments, and patient-reported outcomes in a phase II clinical trial

PURPOSE

In clinical trials, traditional monitoring methods, paper documentation, and outdated collection systems lead to inaccuracies of study information and inefficiencies in the process. Integrated electronic systems offer an opportunity to collect data in real time.

PATIENTS AND METHODS

We created a computer software system to collect 13 patient-reported symptomatic adverse events and patient-reported Karnofsky performance status, semi-automated RECIST measurements, and laboratory data, and we made this information available to investigators in real time at the point of care during a phase II lung cancer trial. We assessed data completeness within 48 hours of each visit. Clinician satisfaction was measured.

RESULTS

Forty-four patients were enrolled, for 721 total visits. At each visit, patient-reported outcomes (PROs) reflecting toxicity and disease-related symptoms were completed using a dedicated wireless laptop. All PROs were distributed in batch throughout the system within 24 hours of the visit, and abnormal laboratory data were available for review within a median of 6 hours from the time of sample collection. Manual attribution of laboratory toxicities took a median of 1 day from the time they were accessible online. Semi-automated RECIST measurements were available to clinicians online within a median of 2 days from the time of imaging. All clinicians and 88% of data managers felt there was greater accuracy using this system.

CONCLUSION

Existing data management systems can be harnessed to enable real-time collection and review of clinical information during trials. This approach facilitates reporting of information closer to the time of events, and improves efficiency, and the ability to make earlier clinical decisions.

Hemodynamics analysis of patient-specific carotid bifurcation: a CFD model of downstream peripheral vascular impedance

The study of cardiovascular models was presented in this paper based on medical image reconstruction and computational fluid dynamics. Our aim is to provide a reality platform for the purpose of flow analysis and virtual intervention outcome predication for vascular diseases. By connecting two porous mediums with transient permeability at the downstream of the carotid bifurcation branches, a downstream peripheral impedance model was developed, and the effect of the downstream vascular bed impedance can be taken into consideration. After verifying its accuracy with a healthy carotid bifurcation, this model was implemented in a diseased carotid bifurcation analysis. On the basis of time-averaged wall shear stress, oscillatory shear index, and the relative residence time, fractions of abnormal luminal surface were highlighted, and the atherosclerosis was assessed from a hemodynamic point of view. The effect of the atherosclerosis on the transient flow division between the two branches because of the existence of plaque was also analysed. This work demonstrated that the proposed downstream peripheral vascular impedance model can be used for computational modelling when the outlets boundary conditions are not available, and successfully presented the potential of using medical imaging and numerical simulation to provide existing clinical prerequisites for diagnosis and therapeutic treatment.

Exploring intra- and inter-reader variability in uni-dimensional, bi-dimensional, and volumetric measurements of solid tumors on CT scans reconstructed at different slice intervals

OBJECTIVE

Understanding magnitudes of variability when measuring tumor size may be valuable in improving detection of tumor change and thus evaluating tumor response to therapy in clinical trials and care. Our study explored intra- and inter-reader variability of tumor uni-dimensional (1D), bi-dimensional (2D), and volumetric (VOL) measurements using manual and computer-aided methods (CAM) on CT scans reconstructed at different slice intervals.

MATERIALS AND METHODS

Raw CT data from 30 patients enrolled in oncology clinical trials was reconstructed at 5, 2.5, and 1.25 mm slice intervals. 118 lesions in the lungs, liver, and lymph nodes were analyzed. For each lesion, two independent radiologists manually and, separately, using computer software, measured the maximum diameter (1D), maximum perpendicular diameter, and volume (CAM only). One of them blindly repeated the measurements. Intra- and inter-reader variability for the manual method and CAM were analyzed using linear mixed-effects models and Bland-Altman method.

RESULTS

For the three slice intervals, the maximum coefficients of variation for manual intra-/inter-reader variability were 6.9%/9.0% (1D) and 12.3%/18.0% (2D), and for CAM were 5.4%/9.3% (1D), 11.3%/18.8% (2D) and 9.3%/18.0% (VOL). Maximal 95% reference ranges for the percentage difference in intra-reader measurements for manual 1D and 2D, and CAM VOL were (-15.5%, 25.8%), (-27.1%, 51.6%), and (-22.3%, 33.6%), respectively.

CONCLUSIONS

Variability in measuring the diameter and volume of solid tumors, manually and by CAM, is affected by CT slice interval. The 2.5mm slice interval provides the least measurement variability. Among the three techniques, 2D has the greatest measurement variability compared to 1D and 3D.

Assessing the effect of CT slice interval on unidimensional, bidimensional and volumetric measurements of solid tumours

Objectives: To study the magnitude of differences in tumour unidimensional (1D), bidimensional (2D) and volumetric (VOL) measurements determined from computed tomography (CT) images reconstructed at 5, 2.5 and 1.25 mm slice intervals. Materials and Methods: A total of 118 lesions in lung, liver and lymph nodes were selected from 30 patients enrolled in early phase clinical trials. Each CT scan was reconstructed at 5, 2.5 and 1.25 mm slice intervals during the image acquisition. Lesions were semi-automatically segmented on each interval image series and supervised by a radiologist. 1D, 2D and VOL were computed based on the final segmentation results. Average measurement differences across different slice intervals were obtained using linear mixed-effects analysis of variance models. Results: Lesion diameters ranged from 6.1 to 80.1 mm (median 18.4 mm). The largest difference was seen between 1.25 and 5 mm (mean difference of 7.6% for 1D [P < 0.0001], 13.1% for 2D [P < 0.0001], −5.7% for VOL [P = 0.0001]). Mean differences between 1.25 and 2.5 mm were all within ±3.5% (within ±6% confidence interval). For VOL, there was a larger average difference between measurements on different slice intervals for the smaller lesions (<10 mm) compared with the larger lesions. Conclusions: Different slice intervals may give different 1D, 2D and VOL measurements. In clinical practice, it would be prudent to use the same slice interval for consecutive measurements.

How to share underground reservoirs

Many resources, such as oil, gas, or water, are extracted from porous soils and their exploration is often shared among different companies or nations. We show that the effective shares can be obtained by invading the porous medium simultaneously with various fluids. Partitioning a volume in two parts requires one division surface while the simultaneous boundary between three parts consists of lines. We identify and characterize these lines, showing that they form a fractal set consisting of a single thread spanning the medium and a surrounding cloud of loops. While the spanning thread has fractal dimension 1.55 ± 0.03, the set of all lines has dimension 1.69 ± 0.02. The size distribution of the loops follows a power law and the evolution of the set of lines exhibits a tricritical point described by a crossover with a negative dimension at criticality.

A multistage discriminative model for tumor and lymph node detection in thoracic images

Analysis of primary lung tumors and disease in regional lymph nodes is important for lung cancer staging, and an automated system that can detect both types of abnormalities will be helpful for clinical routine. In this paper, we present a new method to automatically detect both tumors and abnormal lymph nodes simultaneously from positron emission tomography-computed tomography thoracic images. We perform the detection in a multistage approach, by first detecting all potential abnormalities, then differentiate between tumors and lymph nodes, and finally refine the detected tumors for false positive reduction. Each stage is designed with a discriminative model based on support vector machines and conditional random fields, exploiting intensity, spatial and contextual features. The method is designed to handle a wide and complex variety of abnormal patterns found in clinical datasets, consisting of different spatial contexts of tumors and abnormal lymph nodes. We evaluated the proposed method thoroughly on clinical datasets, and encouraging results were obtained.

Semi-automatic analysis of standard uptake values in serial PET/CT studies in patients with lung cancer and lymphoma

BACKGROUND

Changes in maximum standardised uptake values (SUVmax) between serial PET/CT studies are used to determine disease progression or regression in oncologic patients. To measure these changes manually can be time consuming in a clinical routine. A semi-automatic method for calculation of SUVmax in serial PET/CT studies was developed and compared to a conventional manual method. The semi-automatic method first aligns the serial PET/CT studies based on the CT images. Thereafter, the reader selects an abnormal lesion in one of the PET studies. After this manual step, the program automatically detects the corresponding lesion in the other PET study, segments the two lesions and calculates the SUVmax in both studies as well as the difference between the SUVmax values. The results of the semi-automatic analysis were compared to that of a manual SUVmax analysis using a Philips PET/CT workstation. Three readers did the SUVmax readings in both methods. Sixteen patients with lung cancer or lymphoma who had undergone two PET/CT studies were included. There were a total of 26 lesions.

RESULTS

Linear regression analysis of changes in SUVmax show that intercepts and slopes are close to the line of identity for all readers (reader 1: intercept = 1.02, R2 = 0.96; reader 2: intercept = 0.97, R2 = 0.98; reader 3: intercept = 0.99, R2 = 0.98). Manual and semi-automatic method agreed in all cases whether SUVmax had increased or decreased between the serial studies. The average time to measure SUVmax changes in two serial PET/CT examinations was four to five times longer for the manual method compared to the semi-automatic method for all readers (reader 1: 53.7 vs. 10.5 s; reader 2: 27.3 vs. 6.9 s; reader 3: 47.5 vs. 9.5 s; p < 0.001 for all).

CONCLUSIONS

Good agreement was shown in assessment of SUVmax changes between manual and semi-automatic method. The semi-automatic analysis was four to five times faster to perform than the manual analysis. These findings show the feasibility of using semi-automatic methods for calculation of SUVmax in clinical routine and encourage further development of programs using this type of methods.

Fracturing ranked surfaces

Discretized landscapes can be mapped onto ranked surfaces, where every element (site or bond) has a unique rank associated with its corresponding relative height. By sequentially allocating these elements according to their ranks and systematically preventing the occupation of bridges, namely elements that, if occupied, would provide global connectivity, we disclose that bridges hide a new tricritical point at an occupation fraction p = p_c, where p_c is the percolation threshold of random percolation. For any value of p in the interval p_c < p ≤ 1, our results show that the set of bridges has a fractal dimension d_BB ≈ 1.22 in two dimensions. In the limit p → 1, a self-similar fracture is revealed as a singly connected line that divides the system in two domains. We then unveil how several seemingly unrelated physical models tumble into the same universality class and also present results for higher dimensions.

Marker-controlled watershed for lesion segmentation in mammograms

Lesion segmentation, which is a critical step in computer-aided diagnosis system, is a challenging task as lesion boundaries are usually obscured, irregular, and low contrast. In this paper, an accurate and robust algorithm for the automatic segmentation of breast lesions in mammograms is proposed. The traditional watershed transformation is applied to the smoothed (by the morphological reconstruction) morphological gradient image to obtain the lesion boundary in the belt between the internal and external markers. To automatically determine the internal and external markers, the rough region of the lesion is identified by a template matching and a thresholding method. Then, the internal marker is determined by performing a distance transform and the external marker by morphological dilation. The proposed algorithm is quantitatively compared to the dynamic programming boundary tracing method and the plane fitting and dynamic programming method on a set of 363 lesions (size range, 5-42 mm in diameter; mean, 15 mm), using the area overlap metric (AOM), Hausdorff distance (HD), and average minimum Euclidean distance (AMED). The mean ± SD of the values of AOM, HD, and AMED for our method were respectively 0.72 ± 0.13, 5.69 ± 2.85 mm, and 1.76 ± 1.04 mm, which is a better performance than two other proposed segmentation methods. The results also confirm the potential of the proposed algorithm to allow reliable segmentation and quantification of breast lesion in mammograms.

Automated 3-dimensional segmentation of pelvic lymph nodes in magnetic resonance images

PURPOSE

Computer aided diagnosis (CAD) of lymph node metastases may help reduce reading time and improve interpretation of the large amount of image data in a 3-D pelvic MRI exam. The purpose of this study was to develop an algorithm for automated segmentation of pelvic lymph nodes from a single seed point, as part of a CAD system for the classification of normal vs metastatic lymph nodes, and to evaluate its performance compared to other algorithms.

METHODS

The authors' database consisted of pelvic MR images of 146 consecutive patients, acquired between January 2008 and April 2010. Each dataset included four different MR sequences, acquired after infusion of a lymph node specific contrast medium based on ultrasmall superparamagnetic particles of iron oxide. All data sets were analyzed by two expert readers who, reading in consensus, annotated and manually segmented the lymph nodes. The authors compared four segmentation algorithms: confidence connected region growing (CCRG), extended CCRG (ECC), graph cut segmentation (GCS), and a segmentation method based on a parametric shape and appearance model (PSAM). The methods were ranked based on spatial overlap with the manual segmentations, and based on diagnostic accuracy in a CAD system, with the experts' annotations as reference standard.

RESULTS

A total of 2347 manually annotated lymph nodes were included in the analysis, of which 566 contained a metastasis. The mean spatial overlap (Dice similarity coefficient) was: 0.35 (CCRG), 0.57 (ECC), 0.44 (GCS), and 0.46 (PSAM). When combined with the classification system, the area under the ROC curve was: 0.805 (CCRG), 0.890 (ECC), 0.807 (GCS), 0.891 (PSAM), and 0.935 (manual segmentation).

CONCLUSIONS

We identified two segmentation methods, ECC and PSAM, that achieve a high diagnostic accuracy when used in conjunction with a CAD system for classification of normal vs metastatic lymph nodes. The manual segmentations still achieve the highest diagnostic accuracy.

Automated temporal tracking and segmentation of lymphoma on serial CT examinations

PURPOSE

It is challenging to reproducibly measure and compare cancer lesions on numerous follow-up studies; the process is time-consuming and error-prone. In this paper, we show a method to automatically and reproducibly identify and segment abnormal lymph nodes in serial computed tomography (CT) exams.

METHODS

Our method leverages initial identification of enlarged (abnormal) lymph nodes in the baseline scan. We then identify an approximate region for the node in the follow-up scans using nonrigid image registration. The baseline scan is also used to locate regions of normal, non-nodal tissue surrounding the lymph node and to map them onto the follow-up scans, in order to reduce the search space to locate the lymph node on the follow-up scans. Adaptive region-growing and clustering algorithms are then used to obtain the final contours for segmentation. We applied our method to 24 distinct enlarged lymph nodes at multiple time points from 14 patients. The scan at the earlier time point was used as the baseline scan to be used in evaluating the follow-up scan, resulting in 70 total test cases (e.g., a series of scans obtained at 4 time points results in 3 test cases). For each of the 70 cases, a "reference standard" was obtained by manual segmentation by a radiologist. Assessment according to response evaluation criteria in solid tumors (RECIST) using our method agreed with RECIST assessments made using the reference standard segmentations in all test cases, and by calculating node overlap ratio and Hausdorff distance between the computer and radiologist-generated contours.

RESULTS

Compared to the reference standard, our method made the correct RECIST assessment for all 70 cases. The average overlap ratio was 80.7 ± 9.7% s.d., and the average Hausdorff distance was 3.2 ± 1.8 mm s.d. The concordance correlation between automated and manual segmentations was 0.978 (95% confidence interval 0.962, 0.984). The 100% agreement in our sample between our method and the standard with regard to RECIST classification suggests that the true disagreement rate is no more than 6%.

CONCLUSIONS

Our automated lymph node segmentation method achieves excellent overall segmentation performance and provides equivalent RECIST assessment. It potentially will be useful to streamline and improve cancer lesion measurement and tracking and to improve assessment of cancer treatment response.

CT-PET weighted image fusion for separately scanned whole body rat

PURPOSE

The limited resolution and lack of spatial information in positron emission tomography (PET) images require the complementary anatomic information from the computed tomography (CT) and/or magnetic resonance imaging (MRI). Therefore, multimodality image fusion techniques such as PET/CT are critical in mapping the functional images to structural images and thus facilitate the interpretation of PET studies. In our experimental situation, the CT and PET images are acquired in separate scanners at different times and the inherent differences in the imaging protocols produce significant nonrigid changes between the two acquisitions in addition to dissimilar image characteristics. The registration conditions are also poor because CT images have artifacts due to the limitation of current scanning settings, while PET images are very blurry (in transmission-PET) and have vague anatomical structure boundaries (in emission-PET).

METHODS

The authors present a new method for whole body small animal multimodal registration. In particular, the authors register whole body rat CT image and PET images using a weighted demons algorithm. The authors use both the transmission-PET and the emission-PET images in the registration process emphasizing particular regions of the moving transmission-PET image using the emission-PET image. After a rigid transformation and a histogram matching between the CT and the transmission-PET images, the authors deformably register the transmission-PET image to the CT image with weights based on the intensity-normalized emission-PET image. For the deformable registration process, the authors develop a weighted demons registration method that can give preferences to particular regions of the input image using a weight image.

RESULTS

The authors validate the results with nine rat image sets using the M-Hausdorff distance (M-HD) similarity measure with different outlier-suppression parameters (OSP). In comparison with standard methods such as the regular demons and the normalized mutual information (NMI)-based nonrigid free-form deformation (FFD) registration, the proposed weighted demons registration method shows average M-HD errors: 3.99 ± 1.37 (OSP = 10), 5.04 ± 1.59 (OSP = 20) and 5.92 ± 1.61 (OSP = ∞) with statistical significance (p < 0.0003) respectively, while NMI-based nonrigid FFD has average M-HD errors: 5.74 ± 1.73 (OSP = 10), 7.40 ± 7.84 (OSP = 20) and 9.83 ± 4.13 (OSP = ∞), and the regular demons has average M-HD errors: 6.79 ± 0.83 (OSP = 10), 9.19 ± 2.39 (OSP = 20) and 11.63 ± 3.99 (OSP = ∞), respectively. In addition to M-HD comparisons, the visual comparisons on the faint-edged region between the CT and the aligned PET images also show the encouraging improvements over the other methods.

CONCLUSIONS

In the whole body multimodal registration between CT and PET images, the utilization of both the transmission-PET and the emission-PET images in the registration process by emphasizing particular regions of the transmission-PET image using an emission-PET image is effective. This method holds promise for other image fusion applications where multiple (more than two) input images should be registered into a single informative image.

Identifying weak linear features with the "coalescing shortest path image transform"

The detection of line-like features in images finds many applications in microanalysis. Actin fibers, microtubules, neurites, pilis, DNA, and other biological structures all come up as tenuous curved lines in microscopy images. A reliable tracing method that preserves the integrity and details of these structures is particularly important for quantitative analyses. We have developed a new image transform called the "Coalescing Shortest Path Image Transform" with very encouraging properties. Our scheme efficiently combines information from an extensive collection of shortest paths in the image to delineate even very weak linear features.

CASE-BASED-REASONING FOR IMAGE SEGMENTATION

This paper proposes to use case-based-reasoning for grey-level image segmentation. Different approaches to image segmentation have been proposed in the literature. The selection of the segmentation approach and the assignment of the values to the parameters involved in the selected algorithm depend on image domain and on the specific application. Case-based-reasoning seems a promising way to make the above selection automatic. In this paper, we describe the results of a preliminary study done in this respect. In particular, we refer to the automatic selection of the values of the parameters for a new watershed image segmentation algorithm.

Longitudinal volume analysis from computed tomography: Reproducibility using adrenal glands as surrogate tumors

This study aims to determine the precision (reproducibility) of volume assessment in routine clinical computed tomography (CT) using adrenal glands as surrogate tumors. Seven patients at our institution were identified retrospectively as having received numerous abdominal CT scans (average 13.1, range 5 to 20). The adrenal glands were used as surrogate tumors, assuming no actual volume change. Left and right adrenal gland volumes were assessed by hand segmentation for each patient scan. Over 1240 regions of interest were outlined in total. The reproducibility, expressed as the coefficient of variation (COV), was used to characterize measurement precision. The average volumes were 5.9 and 4.5 cm³ for the left and right adrenal gland, respectively, with COVs of 17.8% and 18.9%, respectively. Using one patient’s data (20 scans) as an example surrogate for a spherical tumor, it was calculated that a 13% change in volume (4.2% change in diameter) could be determined with statistical significance at P=0.05. For this case, cursor positioning error in linear measurement of object size, by even 1 pixel on the CT image, corresponded to a significant change in volume (P=0.05). The precision of volume determination was dependent on total volume. Precision improved with increasing object size (r² =0.367). Given the small dimensions of the adrenal glands, the ~18% COV is likely to be a high estimate compared to larger tumors. Modern CT scanners working with thinner sections (i.e. <1 mm) are likely to produce better measurement precision. The use of volume measurement to quantify changing tumor size is supported as a more precise metric than linear measurement.

Mediastinal atlas creation from 3-D chest computed tomography images: application to automated detection and station mapping of lymph nodes

One important aspect of lung cancer staging is the assessment of mediastinal lymph nodes in 3-D chest computed tomography (CT) images. In the current clinical routine this is done manually by analyzing the 3-D CT image slice by slice to find nodes, evaluate them quantitatively, and assign labels to them for describing the clinical and pathologic extent of metastases. In this paper we present a method to automate the process of lymph node detection and labeling by creation of a mediastinal average image and a novel lymph node atlas containing probability maps for mediastinal, aortic, and N1 nodes. Utilizing a fast deformable registration approach to match the atlas with CT images of new patients, our method can maintain an acceptable runtime. In comparison to previously published methods for mediastinal lymph node detection and labeling it also shows a good sensitivity and positive predictive value.

Automated detection of white matter changes in elderly people using fuzzy, geostatistical, and information combining models

Detection of white matter changes of the brain using magnetic resonance imaging (MRI) has increasingly been an active and challenging research area in computational neuroscience. There have rarely been any single image analysis methods that can effectively address the issue of automated quantification of neuroimages, which are subject to different interests of various medical hypotheses. This paper presents new image segmentation models for automated detection of white matter changes of the brain in an elderly population. The methods are based on the computational models of fuzzy clustering, possibilistic clustering, geostatistics, and knowledge combination. Experimental results on MRI data have shown that the proposed image analysis methodology can be applied as a very useful computerized tool for the validation of our particular medical question, where white matter changes of the brain are thought to be the most important social medical evidence.

Malignant lesion segmentation in contrast-enhanced breast MR images based on the marker-controlled watershed

Breast tumor volume measured on MRI has been used to assess response to neoadjuvant chemotherapy. However, accurate and reproducible delineation of breast lesions can be challenging, since the lesions may have complicated topological structures and heterogeneous intensity distributions. In this article, the authors present an advanced computerized method to semiautomatically segment tumor volumes on T1-weighted, contrast-enhanced breast MRI. The method starts with manual selection of a region of interest (ROI) that contains the lesion to be segmented in a single image, followed by automated separation of the lesion volume from its surrounding breast parenchyma by using a unique combination of the image processing techniques including Gaussian mixture modeling and a marker-controlled watershed transform. Explicitly, the Gaussian mixture modeling is applied to an intensity histogram of the pixels inside the ROI to distinguish the tumor class from other tissues. Based on the ROI and the intensity distribution of the tumor, internal and external markers are determined and the tumor contour is delineated using the marker-controlled watershed transform. To obtain the tumor volume, the segmented tumor in one slice is propagated to the adjacent slice to form an ROI in that slice. The marker-controlled watershed segmentation is then used again to obtain a tumor contour in the propagated slice. This procedure is terminated when there is no lesion in an adjacent slice. To reduce measurement variations possibly caused by the manual selection of the ROI, the segmentation result is refined based on an automatically determined ROI based on the segmented volume. The algorithm was applied to 13 patients with breast cancer, prospectively accrued prior to beginning neoadjuvant chemotherapy. Each patient had two MRI scans, a baseline MRI examination prior to commencing neoadjuvant chemotherapy and a 1 week follow-up after receiving the first dose of neoadjuvant chemotherapy. Blinded to the computer segmentation results, two experienced radiologists manually delineated all tumors independently. The computer results were then compared with the manually generated results using the volume overlap ratio, defined as the intersection of the computer- and radiologist-generated tumor volumes divided by the union of the two. The algorithm reached overall overlap ratios of 62.6% +/- 9.1% and 61.0% +/- 11.3% in comparison to the two manual segmentation results, respectively. The overall overlap ratio between the two radiologists' manual segmentations was 64.3% +/- 10.4%. Preliminary results suggest that the proposed algorithm is a promising method for assisting in tumor volume measurement in contrast-enhanced breast MRI.

Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics

In this work the authors compare the accuracy of two-dimensional (2D) and three-dimensional (3D) implementations of a computer-aided image segmentation method to that of physician observers (using manual outlining) for volume measurements of liver tumors visualized with diagnostic contrast-enhanced and PET/CT-based non-contrast-enhanced (PET-CT) CT scans. The method assessed is a hybridization of the watershed method using observer-set markers with a gradient vector flow approach. This method is known as the iterative watershed segmentation (IWS) method. Initial assessments are performed using software phantoms that model a range of tumor shapes, noise levels, and noise qualities. IWS is then applied to CT image sets of patients with identified hepatic tumors and compared to the physicians' manual outlines on the same tumors. The repeatability of the physicians' measurements is also assessed. IWS utilizes multiple levels of segmentation performed with the use of "fuzzy regions" that could be considered part of a selected tumor. In phantom studies, the outermost volume outline for level 1 (called level 1_1 consisting of inner region plus fuzzy region) was generally the most accurate. For in vivo studies, the level 1_1 and the second outermost outline for level 2 (called level 2_2 consisting of inner region plus two fuzzy regions) typically had the smallest percent error values when compared to physician observer volume estimates. Our data indicate that allowing the operator to choose the "best result" level iteration outline from all generated outlines would likely give the more accurate volume for a given tumor rather than automatically choosing a particular level iteration outline. The preliminary in vivo results indicate that 2D-IWS is likely to be more accurate than 3D-IWS in relation to the observer volume estimates.

3D Axon structure extraction and analysis in confocal fluorescence microscopy images

The morphological properties of axons, such as their branching patterns and oriented structures, are of great interest for biologists in the study of the synaptic connectivity of neurons. In these studies, researchers use triple immunofluorescent confocal microscopy to record morphological changes of neuronal processes. Three-dimensional (3D) microscopy image analysis is then required to extract morphological features of the neuronal structures. In this article, we propose a highly automated 3D centerline extraction tool to assist in this task. For this project, the most difficult part is that some axons are overlapping such that the boundaries distinguishing them are barely visible. Our approach combines a 3D dynamic programming (DP) technique and marker-controlled watershed algorithm to solve this problem. The approach consists of tracking and updating along the navigation directions of multiple axons simultaneously. The experimental results show that the proposed method can rapidly and accurately extract multiple axon centerlines and can handle complicated axon structures such as cross-over sections and overlapping objects.

A multichannel watershed-based segmentation method for multispectral chromosome classification

Multiplex fluorescent in situ hybridization (M-FISH) is a recently developed chromosome imaging technique where each chromosome class appears to have a distinct color. This technique not only facilitates the detection of subtle chromosomal aberrations but also makes the analysis of chromosome images easier; both for human inspection and computerized analysis. In this paper, a novel method for segmentation and classification of M-FISH chromosome images is presented. The segmentation is based on the multichannel watershed transform in order to define regions of similar spatial and spectral characteristics. Then, a Bayes classifier, task-specific on region classification, is applied. Our method consists of four basic steps: 1) computation of the gradient magnitude of the image, 2) application of the watershed transform to decompose the image into a set of homogenous regions, 3) classification of each region, and 4) merging of similar adjacent regions. The method is evaluated using a publicly available chromosome image database and the obtained overall accuracy is 82.4%. By introducing the classification of each watershed region, the proposed method achieves substantially better results compared to other methods at a lower computational cost. The combination of the multichannel segmentation and the region-based classification is found to improve the overall classification accuracy compared to pixel-by-pixel approaches.

Automated matching and segmentation of lymphoma on serial CT examinations

In patients with lymphoma, identification and quantification of the tumor extent on serial CT examinations is critical for assessing tumor response to therapy. In this paper, we present a computer method to automatically match and segment lymphomas in follow-up CT images. The method requires that target lymph nodes in baseline CT images be known. A fast, approximate alignment technique along the x, y, and axial directions is developed to provide a good initial condition for the subsequent fast free form deformation (FFD) registration of the baseline and the follow-up images. As a result of the registration, the deformed lymph node contours from the baseline images are used to automatically determine internal and external markers for the marker-controlled watershed segmentation performed in the follow-up images. We applied this automated registration and segmentation method retrospectively to 29 lymph nodes in 9 lymphoma patients treated in a clinical trial at our cancer center. A radiologist independently delineated all lymph nodes on all slices in the follow-up images and his manual contours served as the "gold standard" for evaluation of the method. Preliminary results showed that 26/29 (89.7%) lymph nodes were correctly matched; i.e., there was a geometrical overlap between the deformed lymph node from the baseline and its corresponding mass in the follow-up images. Of the matched 26 lymph nodes, 22 (84.6%) were successfully segmented; for these 22 lymph nodes, several metrics were calculated to quantify the method's performance. Among them, the average distance and the Hausdorff distance between the contours generated by the computer and those generated by the radiologist were 0.9 mm (stdev. 0.4 mm) and 3.9 mm (stdev. 2.1 mm), respectively.