Anatomic attention regions via optimal anatomy modeling and recognition for DL-based image segmentation.

Organ segmentation is a crucial task in various medical imaging applications. Many deep learning models have been developed to do this, but they are slow and require a lot of computational resources. To solve this problem, attention mechanisms are used which can locate important objects of interest within medical images, allowing the model to segment them accurately even when there is noise or artifact. By paying attention to specific anatomical regions, the model becomes better at segmentation. Medical images have unique features in the form of anatomical information, which makes them different from natural images. Unfortunately, most deep learning methods either ignore this information or do not use it effectively and explicitly. Combined natural intelligence with artificial intelligence, known as hybrid intelligence, has shown promising results in medical image segmentation, making models more robust and able to perform well in challenging situations. In this paper, we propose several methods and models to find attention regions in medical images for deep learning-based segmentation via non-deep-learning methods. We developed these models and trained them using hybrid intelligence concepts. To evaluate their performance, we tested the models on unique test data and analyzed metrics including false negatives quotient and false positives quotient. Our findings demonstrate that object shape and layout variations can be explicitly learned to create computational models that are suitable for each anatomic object. This work opens new possibilities for advancements in medical image segmentation and analysis.

Optimal computed tomography-based biomarkers for prediction of incisional hernia formation.

PURPOSE: Unstructured data are an untapped source for surgical prediction. Modern image analysis and machine learning (ML) can harness unstructured data in medical imaging. Incisional hernia (IH) is a pervasive surgical disease, well-suited for prediction using image analysis. Our objective was to identify optimal biomarkers (OBMs) from preoperative abdominopelvic computed tomography (CT) imaging which are most predictive of IH development. METHODS: Two hundred and twelve rigorously matched colorectal surgery patients at our institution were included. Preoperative abdominopelvic CT scans were segmented to derive linear, volumetric, intensity-based, and textural features. These features were analyzed to find a small subset of OBMs, which are maximally predictive of IH. Three ML classifiers (Ensemble Boosting, Random Forest, SVM) trained on these OBMs were used for prediction of IH. RESULTS: Altogether, 279 features were extracted from each CT scan. The most predictive OBMs found were: (1) abdominopelvic visceral adipose tissue (VAT) volume, normalized for height; (2) abdominopelvic skeletal muscle tissue volume, normalized for height; and (3) pelvic VAT volume to pelvic outer aspect of body wall skeletal musculature (OAM) volume ratio. Among ML prediction models, Ensemble Boosting produced the best performance with an AUC of 0.85, accuracy of 0.83, sensitivity of 0.86, and specificity of 0.81. CONCLUSION: These OBMs suggest increased intra-abdominopelvic volume/pressure as the salient pathophysiologic driver and likely mechanism for IH formation. ML models using these OBMs are highly predictive for IH development. The next generation of surgical prediction will maximize the utility of unstructured data using advanced image analysis and ML.

Three-dimensional kinematic stress magnetic resonance image analysis shows promise for detecting altered anatomical relationships of tissues in the cervical spine associated with painful radiculopathy.

For some patients with radiculopathy a source of nerve root compression cannot be identified despite positive electromyography (EMG) evidence. This discrepancy hampers the effective clinical management for these individuals. Although it has been well-established that tissues in the cervical spine move in a three-dimensional (3D) manner, the 3D motions of the neural elements and their relationship to the bones surrounding them are largely unknown even for asymptomatic normal subjects. We hypothesize that abnormal mechanical loading of cervical nerve roots during pain-provoking head positioning may be responsible for radicular pain in those cases in which there is no evidence of nerve root compression on conventional cervical magnetic resonance imaging (MRI) with the neck in the neutral position. This biomechanical imaging proof-of-concept study focused on quantitatively defining the architectural relationships between the neural and bony structures in the cervical spine using measurements derived from 3D MR images acquired in neutral and pain-provoking neck positions for subjects: (1) with radicular symptoms and evidence of root compression by conventional MRI and positive EMG, (2) with radicular symptoms and no evidence of root compression by MRI but positive EMG, and (3) asymptomatic age-matched controls. Function and pain scores were measured, along with neck range of motion, for all subjects. MR imaging was performed in both a neutral position and a pain-provoking position. Anatomical architectural data derived from analysis of the 3D MR images were compared between symptomatic and asymptomatic groups, and the symptomatic groups with and without imaging evidence of root compression. Several differences in the architectural relationships between the bone and neural tissues were identified between the asymptomatic and symptomatic groups. In addition, changes in architectural relationships were also detected between the symptomatic groups with and without imaging evidence of nerve root compression. As demonstrated in the data and a case study the 3D stress MR imaging approach provides utility to identify biomechanical relationships between hard and soft tissues that are otherwise undetected by standard clinical imaging methods. This technique offers a promising approach to detect the source of radiculopathy to inform clinical management for this pathology.

Relation of vision to global and regional brain MRI in multiple sclerosis.

OBJECTIVE: To examine the relation between low-contrast letter acuity, an emerging visual outcome for multiple sclerosis (MS) clinical trials, and brain MRI abnormalities in an MS cohort. METHODS: T2 lesion volume and brain parenchymal fraction were determined for whole brain and within visual pathway regions of interest. Magnetization transfer ratio histograms were examined. Vision testing was performed binocularly using low-contrast letter acuity (2.5%, 1.25% contrast) and high-contrast visual acuity (VA). Linear regression, accounting for age and disease duration, was used to assess the relation between vision and MRI measures. RESULTS: Patients (n = 45) were aged 44 +/- 11 years, with disease duration of 5 years (range <1 to 21), Expanded Disability Status Scale score of 2.0 (0 to 6.0), and binocular Snellen acuity of 20/16 (20/12.5 to 20/25). The average T2 lesion volume was 18.5 mm(3). Patients with lower (worse) low-contrast letter acuity and high-contrast VA scores had greater T2 lesion volumes in whole brain (2.5% contrast: p = 0.004; 1.25%: p = 0.002; VA: p = 0.04), Area 17 white matter (2.5%: p < 0.001; 1.25%: p = 0.02; VA: p = 0.01), and optic radiations (2.5%: p = 0.001; 1.25%: p = 0.02; VA: p = 0.007). Within whole brain, a 3-mm(3) increase in lesion volume corresponded, on average, to a 1-line worsening of low-contrast acuity, whereas 1-line worsening of high-contrast acuity corresponded to a 5.5-mm(3) increase. CONCLUSIONS: Low-contrast letter acuity scores correlate well with brain MRI lesion burden in multiple sclerosis (MS), supporting validity for this vision test as a candidate for clinical trials. Disease in the postgeniculate white matter is a likely contributor to visual dysfunction in MS that may be independent of acute optic neuritis history.

Cartilage anlagen adapt in response to static deformation.

Connective tissue adaptation, including the development of cartilaginous anlagen into bones, is widely believed to be related to dynamic, intermittent load and stress histories. Static stresses, on the other hand, are generally believed deleterious in tissue adaptation. Using serial MRI in a natural human experiment (manipulation and corrective casting of infant clubfoot), we have observed casting produces two effects: (1) the well recognized change in relative positions of the hindfoot anlagen; (2) a newly recognized immediate shape change in the anlagen. These changes seemingly enhance the rate of growth of the anlagen and of the ossific nucleus. The shape change or deformation in the anlagen would occur as a result of alterations in the magnitudes and directions of loading from soft tissue attachments and muscle activity and would necessarily be associated with changes in the stress states within the anlagen and, when present, the ossific nuclei. Given the known role of load and stress history in tissue adaptation, we presume the reduced stress histories influence the enhanced growth rates. These observations contradict some current theories of tissue adaptation since static, rather than dynamic stresses play a crucial role in accelerating the growth and development of anlagen in the infant clubfoot.

The effect of ankle ligament damage and surgical reconstructions on the mechanics of the ankle and subtalar joints revealed by three-dimensional stress MRI.

Common image-based diagnostic techniques used to detect ankle ligament injuries or the effects of those injuries (e.g., mechanical instability) include magnetic resonance imaging (MRI) and stress radiography. Each of these techniques has limitations. The interpretation of the results obtained through stress radiography, a two-dimensional technique, is highly controversial. MRI can facilitate visualization of soft tissue, but three-dimensional visualization of the full length of the ligaments or detecting partial ligament damage is difficult. This work is part of a long-term study aimed at improving the diagnostic ability of MRI by utilizing it not only to visualize the ligaments but also to detect the mechanical instability produced at the ankle and subtalar joints due to ligament damage. The goal of the present study was to evaluate the ability of a previously developed technique called 3D stress MRI (sMRI) to detect in vitro the effect of damage to the lateral collateral ligaments and the stabilizing effect produced by two common surgical reconstruction techniques. MRI data were collected from eight cadaver limbs in a MR compatible ankle-loading device in neutral, inversion, and anterior drawer. Each specimen was tested intact, after cutting the anterior talo-fibular ligament followed by the calcaneo-fibular ligament and after applying two reconstructions. Ligament injuries produced significant changes in the response of the ankle and subtalar joints to load as detected by the 3D stress MRI technique. Both surgical procedures restored mechanical stability to the joints but they differed in the amount and type of stabilization achieved. We concluded that 3D sMRI can extend the diagnostic power of MRI from the current practice of slice-by-slice visualization to the assessment of mechanical function, the compromise in this function due to injury, and the effects of surgery.

Mechanics of the ankle and subtalar joints revealed through a 3D quasi-static stress MRI technique.

A technique to study the three-dimensional (3D) mechanical characteristics of the ankle and of the subtalar joints in vivo and in vitro is described. The technique uses an MR scanner compatible 3D positioning and loading linkage to load the hindfoot with precise loads while the foot is being scanned. 3D image processing algorithms are used to derive from the acquired MR images bone morphology, hindfoot architecture, and joint kinematics. The technique was employed to study these properties both in vitro and in vivo. The ankle and subtler joint motion and the changes in architecture produced in response to an inversion load and an anterior drawer load were evaluated. The technique was shown to provide reliable measures of bone morphology. The left-to-right variations in bone morphology were less than 5%. The left-to-right variations in unloaded hindfoot architecture parameters were less than 10%, and these properties were only slightly affected by inversion and anterior drawer loads. Inversion and anterior drawer loads produced motion both at the ankle and at the subtalar joint. In addition, high degree of coupling, primarily of internal rotation with inversion, was observed both at the ankle and at the subtalar joint. The in vitro motion produced in response to inversion and anterior drawer load was greater than the in vivo motion. Finally, external motion, measured directly across the ankle complex, produced in response to load was much greater than the bone movements measured through the 3D stress MRI technique indicating the significant effect of soft tissue and skin interference.

Scale-based diffusive image filtering preserving boundary sharpness and fine structures.

Image acquisition techniques often suffer from low signal-to-noise ratio (SNR) and/or contrast-to-noise ratio (CNR). Although many acquisition techniques are available to minimize these, post acquisition filtering is a major off-line image processing technique commonly used to improve the SNR and CNR. A major drawback of filtering is that it often diffuses/blurs important structures along with noise. In this paper, we introduce two scale-based filtering methods that use local structure size or "object scale" information to arrest smoothing around fine structures and across even low-gradient boundaries. The first of these methods uses a weighted average over a scale-dependent neighborhood while the other employs scale-dependent diffusion conductance to perform filtering. Both methods adaptively modify the degree of filtering at any image location depending on local object scale. Object scale allows us to accurately use a restricted homogeneity parameter for filtering in regions with fine details and in the vicinity of boundaries while a generous parameter in the interiors of homogeneous regions. Qualitative experiments based on both phantoms and patient magnetic resonance images show significant improvements using the scale-based methods over the extant anisotropic diffusive filtering method in preserving fine details and sharpness of object boundaries. Quantitative analyses utilizing 25 phantom images generated under a range of conditions of blurring, noise, and background variation confirm the superiority of the new scale-based approaches.

A sensor array processing approach to object region detection.

This paper presents a new approach for medical image analysis. It translates the object region-detection problem into a sensor array processing framework and detects the number of object regions based on the signal eigenstructure of the converted array system. The theoretical and experimental results obtained by using this approach on various medical images were in good agreement.

Multiprotocol MR image segmentation in multiple sclerosis: experience with over 1,000 studies.

RATIONALE AND OBJECTIVES: Multiple sclerosis (MS) is an acquired disease of the central nervous system. Several clinical measures are commonly used to express the severity of the disease, including the Expanded Disability Status Scale and the ambulation index. These measures are subjective and may be difficult to reproduce. The aim of this research is to investigate the possibility of developing more objective measures derived from MR imaging. MATERIALS AND METHODS: Various magnetic resonance (MR) imaging protocols are being investigated for the study of MS. Seeking to replace the Expanded Disability Status Scale and ambulation index with an objective means to assess the natural course of the disease and its response to therapy, the authors have developed multiprotocol MR image segmentation methods based on fuzzy connectedness to quantify both macrosopic features of the disease (lesions, gray matter, white matter, cerebrospinal fluid, and brain parenchyma) and the microscopic appearance of diseased white matter. Over 1,000 studies have been processed to date. RESULTS: By far the strongest correlations with the clinical measures were demonstrated by the magnetization transfer ratio histogram parameters obtained for the various segmented tissue regions. These findings emphasize the importance of considering the microscopic and diffuse nature of the disease in the individual tissue regions. Brain parenchymal volume also demonstrated a strong correlation with clinical measures, which suggests that brain atrophy is an important disease indicator. CONCLUSION: Fuzzy connectedness is a viable, highly reproducible segmentation method for studying MS.

Artery-vein separation via MRA--an image processing approach.

This paper presents a near-automatic process for separating vessels from background and other clutter as well as for separating arteries and veins in contrast-enhanced magnetic resonance angiographic (CE-MRA) image data, and an optimal method for three-dimensional visualization of vascular structures. The separation process utilizes fuzzy connected object delineation principles and algorithms. The first step of this separation process is the segmentation of the entire vessel structure from the background and other clutter via absolute fuzzy connectedness. The second step is to separate artery from vein within this entire vessel structure via iterative relative fuzzy connectedness. After seed voxels are specified inside artery and vein in the CE-MRA image, the small regions of the bigger aspects of artery and vein are separated in the initial iterations, and further detailed aspects of artery and vein are included in later iterations. At each iteration, the artery and vein compete among themselves to grab membership of each voxel in the vessel structure based on the relative strength of connectedness of the voxel in the artery and vein. This approach has been implemented in a software package for routine use in a clinical setting and tested on 133 CE-MRA studies of the pelvic region and two studies of the carotid system from six different hospitals. In all studies, unified parameter settings produced correct artery-vein separation. When compared with manual segmentation/separation, our algorithms were able to separate higher order branches, and therefore produced vastly more details in the segmented vascular structure. The total operator and computer time taken per study is on the average about 4.5 min. To date, this technique seems to be the only image processing approach that can be routinely applied for artery and vein separation.

Breast tissue density quantification via digitized mammograms.

Studies reported in the literature indicate that breast cancer risk is associated with mammographic densities. An objective, repeatable, and a quantitative measure of risk derived from mammographic densities will be of considerable use in recommending alternative screening paradigms and/or preventive measures. However, image processing efforts toward this goal seem to be sparse in the literature, and automatic and efficient methods do not seem to exist. In this paper, we describe and validate an automatic and reproducible method to segment dense tissue regions from fat within breasts from digitized mammograms using scale-based fuzzy connectivity methods. Different measures for characterizing mammographic density are computed from the segmented regions and their robustness in terms of their linear correlation across two different projections--cranio-caudal and medio-lateral-oblique--are studied. The accuracy of the method is studied by computing the area of mismatch of segmented dense regions using the proposed method and using manual outlining. A comparison between the mammographic density parameter taking into account the original intensities and that just considering the segmented area indicates that the former may have some advantages over the latter.

Brain atrophy in relapsing-remitting multiple sclerosis: fractional volumetric analysis of gray matter and white matter.

PURPOSE: To determine the fractional brain tissue volume changes in the gray matter and white matter of patients with relapsing-remitting multiple sclerosis (MS) and to correlate these measurements with clinical disability and total lesion load. MATERIALS AND METHODS: Thirty patients with relapsing-remitting MS and 25 healthy control subjects underwent magnetic resonance imaging. Fractional brain tissue volumes (tissue volume relative to total intracranial volume) were obtained from the total segmented gray matter and white matter in each group and were analyzed. RESULTS: The fractional volume of white matter versus that of gray matter was significantly lower (-6.4%) in patients with MS (P <.0001) than in control subjects. Neither gray matter nor white matter fractional volume measurements correlated with clinical disability in the patients with MS. CONCLUSION: Loss of brain parenchymal volume in patients with relapsing-remitting MS is predominantly confined to white matter. Analysis of fractional brain tissue volumes provides additional information useful in characterizing MS and may have potential in evaluating treatment strategies.

An in vivo analysis of the motion of the peri-talar joint complex based on MR imaging.

The purpose of this work is to characterize the three-dimensional (3-D) motion of the peritalar joint complex in vivo using magnetic resonance imaging (MRI). Each image data set utilized in this study is made of 60 longitudinal MR slices of the foot in each of eight positions from extreme pronation to extreme supination. We acquired and analyzed ten such data sets from normal subjects, seven data sets from pathological joints and two postoperative data sets. We segmented and formed the surfaces of the calcaneus, talus, cuboid and navicular from all data sets. About 30 geometrical parameters are computed for each joint in each position. The results present features of normal motion and show how normal and abnormal motion can be distinguished. They also show the consequences of surgery on the motion. This non- invasive method offers a unique tool to characterize and quantify the 3-D motion of the rearfoot in vivo from MR images.

Magnetization transfer ratio histogram analysis of gray matter in relapsing-remitting multiple sclerosis.

BACKGROUND AND PURPOSE: Gray matter may be affected by multiple sclerosis (MS), a white matter disease. Magnetization transfer ratio (MTR) is a sensitive and quantitative marker for structural abnormalities, and has been used frequently in the imaging of MS. In this study, we evaluated the amount of MTR of gray matter among patients with relapsing-remitting MS and healthy control subjects as well as the correlation between gray matter MTR abnormality and neurologic disability associated with relapsing-remitting MS. METHODS: We obtained fast spin-echo dual-echo and magnetization transfer (with and without MT saturation pulses) images from eighteen patients with relapsing-remitting MS and 18 age-matched healthy control subjects. Gray matter was segmented using a semiautomated system. Gray matter MTR histogram parameters, Kurtzke Expanded Disability Status Scale (EDSS), total T2 lesion volume, and gray matter volumes were obtained for statistical analysis. RESULTS: A significant difference was found in gray matter MTR between patients with relapsing-remitting MS and healthy subjects (mean and median). Gray matter MTR histogram normalized peak heights in patients inversely correlated with EDSS (r = -0.65, P =.01). There was also an inverse correlation between mean MTR of gray matter and total T2 lesion volume. CONCLUSION: The MTR of gray matter significantly differed between patients with relapsing-remitting MS and healthy control subjects, suggesting that MS is a more diffuse disease affecting the whole brain, and neuronal damage accumulates in step with T2 lesion volume. Our finding of the relationship between gray matter MTR and EDSS indicates that measurement of gray matter abnormality may be a potentially useful tool for assessing clinical disability in MS.

Numerical tissue characterization in MS via standardization of the MR image intensity scale.

Image intensity standardization is a recently developed postprocessing method that is capable of correcting the signal intensity variations in MR images. We evaluated signal intensity of healthy and diseased tissues in 10 multiple sclerosis (MS) patients based on standardized dual fast spin-echo MR images using a numerical postprocessing technique. The main idea of this technique is to deform the volume image histogram of each study to match a standard histogram and to utilize the resulting transformation to map the image intensities into standard scale. Upon standardization, the coefficients of variation of signal intensities for each segmented tissue (gray matter, white matter, lesion plaques, and diffuse abnormal white matter) in all patients were significantly smaller (2.3-9.2 times) than in the original images, and the same tissues from different patients looked alike, with similar intensity characteristics. Numerical tissue characterizability of different tissues in MS achieved by standardization offers a fixed tissue-specific meaning for the numerical values and can significantly facilitate image segmentation and analysis.

Multiple sclerosis: magnetization transfer histogram analysis of segmented normal-appearing white matter.

PURPOSE: To investigate and characterize the global distribution of magnetization transfer (MT) ratio values of normal-appearing white matter (NAWM) in patients with relapsing-remitting multiple sclerosis (MS) and test the hypothesis that the MT histogram for NAWM reflects disease progression. MATERIALS AND METHODS: Conventional and MT magnetic resonance (MR) images were obtained in 23 patients and 25 healthy volunteers. Clinical tests for comparison with the MT histogram parameters included the Extended Disability Status Scale and the ambulation index. Lesion load calculated with T2-weighted MR images and whole-brain and white matter volumes were measured. RESULTS: The location of the MT histogram peak and the mean MT ratio for NAWM were significantly lower in patients with MS than in control subjects. In longitudinal studies, the histogram peak location and mean MT ratio shifted in the direction of normal values as the duration of disease increased. A mean of 26.5% of the volume of new lesions identified on the later studies were demonstrated to have originated in NAWM corresponding to "lost" pixels on the histogram. CONCLUSION: MT histogram analysis of NAWM, including longitudinal analysis, may provide new prognostic information regarding lesion formation and increase understanding of the course of the disease.

The effect of gadolinium-enhancing lesions on whole brain atrophy in relapsing-remitting MS.

OBJECTIVE: To determine the relationship between gadolinium-enhancing lesions and changes in whole brain parenchymal volume in patients with relapsing-remitting MS, and to test the hypothesis that gadolinium enhancement is a predictor of whole brain atrophy. METHODS: Twenty-four patients with clinically definite MS were imaged over 2 years. A computer-assisted segmentation technique based on high-resolution MRI was used to quantify gadolinium-enhancing T1 lesion volume and brain parenchyma and CSF volumes. Percent brain parenchymal volume (PBV) relative to the total intracranial volume was calculated, and changes in PBV were used to represent the degree of whole brain atrophy over 2 years. RESULTS: PBV at baseline was dependent on duration of MS, and a significant decrease in PBV was observed over the course of the study. Changes in enhanced T1 lesion load failed to correlate with changes in PBV, and multiple regression analyses determined that enhanced T1 lesion load at baseline was not a significant predictor of subsequent change in PBV. CONCLUSIONS: MR visible inflammation as demonstrated by enhanced T1 lesions is not a significant factor in the pathogenesis of whole brain atrophy in relapsing-remitting MS, suggesting that a more global pathologic process is responsible for the loss of brain parenchymal volume.

Magnetization transfer histogram analysis of monosymptomatic episodes of neurologic dysfunction: preliminary findings.

BACKGROUND AND PURPOSE: Patients presenting with a monosymptomatic episode of neurologic dysfunction (MEND) have a high probability of developing multiple sclerosis (MS). Our study was designed to determine whether magnetization transfer (MT) histogram analysis could predict the development of MS for a cohort of patients presenting with a MEND. METHODS: Eleven patients with a MEND and 21 age-matched control volunteers underwent MR imaging. Six patients underwent serial MR examinations. MT ratio histogram peak height (MTRHPH) and the location of the MT ratio histogram peak (LOC MTRHP) were determined for patients and control volunteers. T2 lesion volume was also calculated. Patients were clinically followed up for 587 +/- 308 days to determine or rule out the development of MS. RESULTS: Three patients went on to develop MS. There was no statistically significant difference in the MTRHPH (P = .65) and the LOC MTRHP (P = .71) between patients and control volunteers. For those patients who underwent multiple examinations, no statistically significant differences in the MTRHPH (P = .64), LOC MTRHP (P =.58), and T2 lesion volume (P = .47) were seen. There were no statistically significant correlations between any of the parameters studied. CONCLUSION: We found no difference in MT histogram parameters among control volunteers, patients with a MEND without MS, and patients with a MEND who went on to a diagnosis of MS. Our preliminary findings suggest that there may not be a substrate of disease in the normal-appearing white matter that is predictive of the development of MS.

An ultra-fast user-steered image segmentation paradigm: live wire on the fly.

We have been developing general user steered image segmentation strategies for routine use in applications involving a large number of data sets. In the past, we have presented three segmentation paradigms: live wire, live lane, and a three-dimensional (3-D) extension of the live-wire method. In this paper, we introduce an ultra-fast live-wire method, referred to as live wire on the fly, for further reducing user's time compared to the basic live-wire method. In live wire, 3-D/four-dimensional (4-D) object boundaries are segmented in a slice-by-slice fashion. To segment a two-dimensional (2-D) boundary, the user initially picks a point on the boundary and all possible minimum-cost paths from this point to all other points in the image are computed via Dijkstra's algorithm. Subsequently, a live wire is displayed in real time from the initial point to any subsequent position taken by the cursor. If the cursor is close to the desired boundary, the live wire snaps on to the boundary. The cursor is then deposited and a new live-wire segment is found next. The entire 2-D boundary is specified via a set of live-wire segments in this fashion. A drawback of this method is that the speed of optimal path computation depends on image size. On modestly powered computers, for images of even modest size, some sluggishness appears in user interaction, which reduces the overall segmentation efficiency. In this work, we solve this problem by exploiting some known properties of graphs to avoid unnecessary minimum-cost path computation during segmentation. In live wire on the fly, when the user selects a point on the boundary the live-wire segment is computed and displayed in real time from the selected point to any subsequent position of the cursor in the image, even for large images and even on low-powered computers. Based on 492 tracing experiments from an actual medical application, we demonstrate that live wire on the fly is 1.3-31 times faster than live wire for actual segmentation for varying image sizes, although the pure computational part alone is found to be about 120 times faster.