Mean Dice Similarity Index Research Articles

Deep learning-based cerebral aneurysm segmentation and morphological analysis with three-dimensional rotational angiography

BackgroundThe morphological assessment of cerebral aneurysms based on cerebral angiography is an essential step when planning strategy and device selection in endovascular treatment, but manual evaluation by human raters only...

A portable multispectral vein imaging system

Abstract Phlebotomy may cause unnecessary injuries to a patient whose veins are not easily visible to a healthcare professional. To mitigate this problem we designed a new system to image subcutaneous veins. Multispectral images were obtained using a microprocessor, an IR (infrared) camera, different wavelengths of NIR (near-infrared) sources, and an IR band-pass filter. Raw vein images were enhanced, colored, and displayed on a monitor using an easy-to-use interface. The mean dice similarity index (DSI) between the vein border specified by a doctor on the raw images manually and the automated segmented by the proposed system is determined as 0.92 ± 2.1 for 20 subjects. Also, the average peak signal-to-noise ratio (PSNR) obtained a high value of 68.37 ± 1.56 from the enhanced image. Phlebotomists can easily observe the subcutaneous veins in real-time with the three different options using the proposed device. As a result, this study advances the vein imaging field which has the potential to reduce injury to the patient during venipuncture.

Automated volumetric and statistical shape assessment of cam-type morphology of the femoral head-neck region from clinical 3D magnetic resonance images.

BackgroundFemoroacetabular impingement (FAI) cam morphology is routinely assessed using manual measurements of two-dimensional (2D) alpha angles which are prone to high rater variability and do not provide direct three-dimensional (3D) data on these osseous formations. We present CamMorph, a fully automated 3D pipeline for segmentation, statistical shape assessment and measurement of cam volume, surface area and height from clinical magnetic resonance (MR) images of the hip in FAI patients.MethodsThe novel CamMorph pipeline involves two components: (I) accurate proximal femur segmentation generated by combining the 3D U-net to identify both global (region) and local (edge) features in clinical MR images and focused shape modelling to generate a 3D anatomical model for creating patient-specific proximal femur models; (II) patient-specific anatomical information from 3D focused shape modelling to simulate ‘healthy’ femoral bone models with cam-affected region constraints applied to the anterosuperior femoral head-neck region to quantify cam morphology in FAI patients. The CamMorph pipeline, which generates patient-specific data within 5 min, was used to analyse multi-site clinical MR images of the hip to measure and assess cam morphology in male (n=56) and female (n=41) FAI patients.ResultsThere was excellent agreement between manual and CamMorph segmentations of the proximal femur as demonstrated by the mean Dice similarity index (DSI; 0.964±0.006), 95% Hausdorff distance (HD; 2.123±0.876 mm) and average surface distance (ASD; 0.539±0.189 mm) values. Compared to female FAI patients, male patients had a significantly larger median cam volume (969.22 vs. 272.97 mm3, U=240.0, P<0.001), mean surface area [657.36 vs. 306.93 mm2, t(95)=8.79, P<0.001], median maximum-height (3.66 vs. 2.15 mm, U=407.0, P<0.001) and median average-height (1.70 vs. 0.86 mm, U=380.0, P<0.001).ConclusionsThe fully automated 3D CamMorph pipeline developed in the present study successfully segmented and measured cam morphology from clinical MR images of the hip in male and female patients with differing FAI severity and pathoanatomical characteristics.

Functional connectivity of the irritative zone identified by electrical source imaging, and EEG-correlated fMRI analyses

The irritative zone - the area generating epileptic spikes - can be studied non-invasively during the interictal period using Electrical Source Imaging (ESI) and simultaneous electroencephalography-functional magnetic resonance imaging (EEG-fMRI). Although the techniques yield results which may overlap spatially, differences in spatial localization of the irritative zone within the same patient are consistently observed. To investigate this discrepancy, we used Blood Oxygenation Level Dependent (BOLD) functional connectivity measures to examine the underlying relationship between ESI and EEG-fMRI findings. Fifteen patients (age 20-54), who underwent presurgical epilepsy investigation, were scanned using a single-session resting-state EEG-fMRI protocol. Structural MRI was used to obtain the electrode localisation of a high-density 64-channel EEG cap. Electrical generators of interictal epileptiform discharges were obtained using a distributed local autoregressive average (LAURA) algorithm as implemented in Cartool EEG software. BOLD activations were obtained using both spike-related and voltage-map EEG-fMRI analysis. The global maxima of each method were used to investigate the temporal relationship of BOLD time courses and to assess the spatial similarity using the Dice similarity index between functional connectivity maps. ESI, voltage-map and spike-related EEG-fMRI methods identified peaks in 15 (100%), 13 (67%) and 8 (53%) of the 15 patients, respectively. For all methods, maxima were localised within the same lobe, but differed in sub-lobar localisation, with a median distance of 22.8mm between the highest peak for each method. The functional connectivity analysis showed that the temporal correlation between maxima only explained 38% of the variance between the time course of the BOLD response at the maxima. The mean Dice similarity index between seed-voxel functional connectivity maps showed poor spatial agreement. Non-invasive methods for the localisation of the irritative zone have distinct spatial and temporal sensitivity to different aspects of the local cortical network involved in the generation of interictal epileptiform discharges.

Volume Delineation in Cervical Cancer With T2 and Diffusion-weighted MRI: Agreement on Volumes Between Observers.

To delineate cervical cancer gross tumor volume (GTV) on T2-magnetic resonance imaging (MRI) and apparent diffusion coefficient (ADC) maps, assessing volumes and inter-observer agreement between two observers. A radiologist and a radiation oncologist delineated GTV on T2 (T2GTV) and ADC (ADCGTV) sequences. Dice similarity index (DICE) and Bland-Altman analysis were used to estimated concordance. Mean T2GTV and ADCGTV volumes were 43.84±71.47 cc and 37.28±68.92 cc according to the radiologist, and 43.4±70.44 cc and 36.65±69.21 cc according to the radiation oncologist. ADC led to statistically significantly smaller volumes compared to T2. The mean DICE index was 0.86 for T2GTV and 0.84 for ADCGTV The Bland-Altman plots globally showed concordance. GTV delineation was smaller in the ADC maps compared to T2-MRI, reaching an almost perfect agreement between observers. Thanks to this acceptable variability, adding functional imaging might provide more information for tumor delineation, improving reproducibility for image-guided adaptive radiotherapy.

Auto-segmentation of head and neck organs at risk in radiotherapy and its dependence on anatomic similarity.

PurposeThe aim is to study the dependence of deformable based auto-segmentation of head and neck organs-at-risks (OAR) on anatomy matching for a single atlas based system and generate an acceptable set of contours.MethodsA sample of ten patients in neutral neck position and three atlas sets consisting of ten patients each in different head and neck positions were utilized to generate three scenarios representing poor, average and perfect anatomy matching respectively and auto-segmentation was carried out for each scenario. Brainstem, larynx, mandible, cervical oesophagus, oral cavity, pharyngeal muscles, parotids, spinal cord, and trachea were the structures selected for the study. Automatic and oncologist reference contours were compared using the dice similarity index (DSI), Hausdroff distance and variation in the centre of mass (COM).ResultsThe mean DSI scores for brainstem was good irrespective of the anatomy matching scenarios. The scores for mandible, oral cavity, larynx, parotids, spinal cord, and trachea were unacceptable with poor matching but improved with enhanced bony matching whereas cervical oesophagus and pharyngeal muscles had less than acceptable scores for even perfect matching scenario. HD value and variation in COM decreased with better matching for all the structures.ConclusionImproved anatomy matching resulted in better segmentation. At least a similar setup can help generate an acceptable set of automatic contours in systems employing single atlas method. Automatic contours from average matching scenario were acceptable for most structures. Importance should be given to head and neck position during atlas generation for a single atlas based system.

Inter-observer variability of clinical target volume delineation in definitive radiotherapy of neck lymph node metastases from unknown primary. A cooperative study of the Italian Association of Radiotherapy and Clinical Oncology (AIRO) Head and Neck Group.

This study, promoted by Italian Association of Radiotherapy and Clinical Oncology (AIRO) Head and Neck Group, aimed to assess the current national practice of target volume delineation on a case of neck lymph node metastases from unknown primary evaluating inter-observer variability, in a setting of primary radiotherapy. A case of metastatic neck lymph node from occult primary was proposed to 17 radiation oncologists. A national reference RT center was identified and considered as benchmark. Participants were requested to delineate target volumes. A structured questionnaire was administered. A comparison between following parameters of the CTVs was performed: centroids distances, Dice similarity index (DSI), Jaccard index and mean distance to agreement (MDA). Volume expressed in cubic centimeters and CTVs cranio-caudal extension were evaluated. Sixteen of 17 radiation oncologists recommended three CTVs dose levels. (CTV HD, CTV ID and CTV LD); CTV ID was not delineated by one of the participants and by the reference center. The distance between the reference centroid and the mean centroid of CTVs HD was 1.09cm (0.36-3.99cm); for CTV LD, a mean centroids distance of 2.45 (0.27-4.83cm) was found, and for CTV HD, mean DSI is 0.48 and mean Jaccard index is 0.32 and MDA was 8.89mm. CTV LD showed a mean DSI of 0.46, mean Jaccard index of 0.31 and MDA of 14.87 when compared to the reference. Many aspects concerning treatment optimization of cervical nodes metastases from occult primary remain unclear, and we found a notable heterogeneity of global radiotherapy management reporting discordances both in target volume delineation and volume prescription.

Development of delineation for the left anterior descending coronary artery region in left breast cancer radiotherapy: An optimized organ at risk

Background and purposeThe left anterior descending coronary artery (LAD) and diagonal branches (DBs) are blurred on computed tomography (CT). We aimed to define the LAD region (LADR) with adequate inclusion of the LAD and DBs and contouring consistency. Methods and materialsThe LADR was defined using coronary CT angiograms. The inclusion ratio was used to assess the LAD and DBs inclusion by the LADR. Four radiation oncologists delineated the LAD and LADR, using contrast-enhanced CT of 15 patients undergoing left breast radiotherapy. The Sørensen–Dice similarity index (DSI), Jaccard similarity index (JSI), and Hausdorff distance (HD) were calculated to assess similarity. The mean dose (Dmean) and maximum dose (Dmax) to the LAD and LADR were calculated to compare consistency. Correlations were evaluated using Pearson’s correlation coefficient. ResultsThe inclusion ratio of the LAD by the LADR was 96%. The mean DSI, JSI, and HD values were respectively 27.9%, 16.7%, and 0.42mm for the LAD, and 83.1%, 73.0%, and 0.18mm for the LADR. The Dmean between the LAD and LADR were strongly correlated (r=0.93). ConclusionDelineation of the LADR significantly improved contouring similarity and consistency for dose reporting. This could optimize dose estimation for breast radiotherapy.

Feasibility of offline head & neck adaptive radiotherapy using deformed planning CT electron density mapping on weekly cone beam computed tomography.

The purpose of the study was to use deformable mapping of planning CT (pCT) electron density values on weekly cone-beam CT (CBCT) to quantify the anatomical changes and determine the dose-volume relationship in offline adaptive volumetric-modulated arc therapy. 10 patients treated with RapidArc plans who had weekly CBCTs were selected retrospectively. The pCT was deformed to weekly CBCTs and the deformed contours were checked for any discrepancies. Clinical target volume 66 Gy and 60 Gy (CTV66 and CTV60), parotids and spinal cord were the structures selected for analysis. Volume reduction and dice similarity index (DSI) were determined. Hybrid RapidArc plans were created and the cumulative dose-volume histograms for selected structures were analyzed. Results showed a mean volume reduction of 18.82 ± 6.08% and 18.22 ± 6.1% for Clinical target volume 66 Gy and 60 Gy (CTV66 and CTV60), respectively, and their corresponding DSI values were 0.94 ± 0.03 and 0.95 ± 0.01. Mean volume reductions of left and right parotids were 32.79 ± 10.28% and 29.46 ± 8.78%, respectively, and their corresponding mean DSI values were 0.90 ± 0.05 and 0.89 ± 0.05. The cumulative mean dose difference for Planning target volume 66 Gy (PTV66) was -1.35 ± 1.71% and for Planning target volume 60 Gy (PTV60), it was -0.69 ± 1.37%. Spinal cord doses varied for all patients over the course. The results from the study showed that it is clinically feasible to estimate the dose-volume relationship using deformed pCT. Monitoring of patient anatomic changes and incorporating patient-specific replanning strategy are necessary to avoid critical structure complications. Advances in knowledge: Deformable mapping of pCT electron density values on weekly CBCTs has been performed to establish the volumetric and dosimetric changes. The anatomical changes differ among the patients and hence, the choice for adaptive radiotherapy should be strictly patient specific rather than time specific.

Neural-network based autocontouring algorithm for intrafractional lung-tumor tracking using Linac-MR.

To develop a neural-network based autocontouring algorithm for intrafractional lung-tumor tracking using Linac-MR and evaluate its performance with phantom and in-vivo MR images. An autocontouring algorithm was developed to determine both the shape and position of a lung tumor from each intrafractional MR image. A pulse-coupled neural network was implemented in the algorithm for contrast improvement of the tumor region. Prior to treatment, to initiate the algorithm, an expert user needs to contour the tumor and its maximum anticipated range of motion in pretreatment MR images. During treatment, however, the algorithm processes each intrafractional MR image and automatically generates a tumor contour without further user input. The algorithm is designed to produce a tumor contour that is the most similar to the expert's manual one. To evaluate the autocontouring algorithm in the author's Linac-MR environment which utilizes a 0.5 T MRI, a motion phantom and four lung cancer patients were imaged with 3 T MRI during normal breathing, and the image noise was degraded to reflect the image noise at 0.5 T. Each of the pseudo-0.5 T images was autocontoured using the author's algorithm. In each test image, the Dice similarity index (DSI) and Hausdorff distance (HD) between the expert's manual contour and the algorithm generated contour were calculated, and their centroid positions were compared (Δd centroid). The algorithm successfully contoured the shape of a moving tumor from dynamic MR images acquired every 275 ms. From the phantom study, mean DSI of 0.95-0.96, mean HD of 2.61-2.82 mm, and mean Δd centroid of 0.68-0.93 mm were achieved. From the in-vivo study, the author's algorithm achieved mean DSI of 0.87-0.92, mean HD of 3.12-4.35 mm, as well as Δd centroid of 1.03-1.35 mm. Autocontouring speed was less than 20 ms for each image. The authors have developed and evaluated a lung tumor autocontouring algorithm for intrafractional tumor tracking using Linac-MR. The autocontouring performance in the Linac-MR environment was evaluated using phantom and in-vivo MR images. From the in-vivo study, the author's algorithm achieved 87%-92% of contouring agreement and centroid tracking accuracy of 1.03-1.35 mm. These results demonstrate the feasibility of lung tumor autocontouring in the author's laboratory's Linac-MR environment.

Inter-observer variability of clinical target volume delineation in radiotherapy treatment of pancreatic cancer: a multi-institutional contouring experience.

BackgroundAn observational multi-institutional study has been conducted aimed to evaluate the inter-observer variability in clinical target volume (CTV) delineation among different radiation oncologists in radiotherapy treatment of pancreatic cancer.MethodsA multi-institutional contouring dummy-run of two different cases of pancreatic cancer treated by postoperative and preoperative radiotherapy (RT) was performed. Clinical history, diagnostics, and planning CT imaging were available on AIRO website (http://www.radioterapiaitalia.it). Participants were requested to delineate CTVs according to their skills and knowledge. Aiming to quantify interobserver variability of CTVs delineations, the total volume, craniocaudal, laterolateral, and anteroposterior diameters were calculated. Descriptive statistic was calculated. The 95% Confidence Interval (95% CI) for coefficient of variation (CV) was estimated. The Dice Similarity Index (DSI) was used to evaluate the spatial overlap accuracy of the different CTVs compared with the CTVs of a national reference Centre considered as a benchmark. The mean DSI (mDSI) was calculated and reported.ResultsA total of 18 radiation oncologists from different Institutes submitted the targets. Less variability was observed for the Elective CTV rather than the Boost CTV, in both cases. The estimated CV were 28.8% (95% CI: 21.2 - 45.0%) and 20.0% (95% CI: 14.9 - 30.6%) for the Elective CTV, in adjuvant (Case 1) and neoadjuvant (Case 2) case, respectively. The mDSI value was 0.68 for the Elective CTVs in both cases (range 0.19 - 0.79 in postoperative vs range 0.35 - 0.79 in preoperative case). The mDSI was increased to 0.71 (Case 1) and 0.72 (Case 2) if the observers with a worse agreement have been excluded. On the other hand, a CV of 42.4% (95% CI: 30.1 - 72.4%) and 63.8% (95% CI: 43.9 - 119.2%) with a mDSI value of 0.44 and 0.52, were calculated for the Boost CTV in Case 1 and Case 2, respectively.ConclusionsThe CV and mDSI obtained values for Elective CTVs showed an acceptable agreement among participants either in postoperative as well in preoperative setting. Additional strategies to reduce the variability in Boost CTV delineation need to be found and promoted.

Evaluation of an Atlas-Based Segmentation Method for High-Risk Prostate Cancer With RTOG-Defined Pelvic Lymph Node Levels

Intensity modulated radiation therapy (IMRT) for high risk prostate cancer requires careful contouring and segmentation of at risk pelvic lymph nodes. However, this process can be very time consuming and difficult compared to traditional prostate only fields. One possible solution to improve target volume contouring efficiency is to use atlas based segmentation software. For this pilot study, we compiled a prostate target atlas database and sought to develop an atlas based segmentation method. Institutional review board approval was obtained to retrospectively analyze patient CT simulation scans to develop an atlas database. Atlas contours included prostate, seminal vesicles, and RTOG-defined pelvic lymph node levels for treatment volumes. Lymph node levels were contoured using RTOG guidelines by following the internal/external iliac vessels and its associated lymph nodes from the L5-S1 vertebral level to obturator nodes at the pubic symphysis. A total of 23 patients with contours reviewed by three different physicians were included in our atlas database. Once this database was compiled we tested the feasibility of developing an atlas based segmentation algorithm and tested it using Dice similarity index (DICE) scores. Atlas segmentation was designed using a leave-one-out analysis (subject being tested was excluded from the atlas). Then the 5 best-matched atlas subjects were automatically chosen and deformed to the test subject. The atlas segmentation method included an additional automatic registration approximation component to influence the intensity-based deformable registration. The 5 sets of auto contours were combined using majority vote where 3 of 5 contours overlapped. Final auto contours were then compared to the manually defined contours using DICE. Using this algorithm for all 23 atlas subjects, the mean DICE score was 0.67 +/- 0.14 for the prostate target volume and 0.74 +/- 0.05 for the pelvic lymph node target volume. Our atlas segmentation method provided accurate contours for high risk prostate cancer. This segmentation method has may have potential for greater accuracy and less variance than traditional inter-individual user contours. In particular, the accuracy of our atlas based segmentation algorithm for pelvic lymph nodes was very good. This is likely due to their association with rigid structures and reduced motion compared to other structures such as the prostate and seminal vesicles. Therefore, our results demonstrate, that atlas based auto-contouring of the pelvic nodes could both help increase consistency for treatment volumes in high risk patients between different cancer centers as well as decrease time related to treatment planning for radiation oncologist.

Automatic delineation for replanning in nasopharynx radiotherapy: What is the agreement among experts to be considered as benchmark?

Background and purpose. Anatomic changes during head and neck radiotherapy require replanning. The primary aim of this study is the definition of the agreement among experts in the head and neck automatic delineation frame to use as benchmark. The secondary goal is to assess the reliability of automatic delineation for nasopharynx radiotherapy and time saving. Material and methods. A computed tomography (CT) scan was acquired in 10 nasopharynx patients along intensity-modulated radiotherapy (IMRT) treatment for replanning. Deformable registration with replanning autocontouring of the structures was performed using VelocityAI 2.3© software defining Structure Set A. The optimization of these contours was obtained through revision by a skilled operator, drawing Structure Set B. An ex novo Structure Set C was segmented on the replanning CT-scan by an expert delineation team. The mean Dice's Similarity Index (mDSI) was calculated between Structure Set A and B, A and C, and between B and C for each volume. All segmentation times for organs at risk (OARs) and clinical target volume (CTV) were recorded and compared. Results. We validated the replanning autocontoured Structure Sets for 10 patients. For volumetric analysis we observed mDSI values of 0.87 for the OARs, 0.70 for nodes, 0.90 for CTV in the Structure Set A-B comparison and respectively of 0.74, 0.63 and 0.78 for the Structure Set A-C one, and 0.78, 0.78 and 0.85 for Structure Set B-C, which represents the existing expert based benchmark. We calculated a mean saved time in Structure Set B of 30 minutes. Conclusions. Autocontouring procedures offer considerable segmentation time saving with acceptable reliability of the contours, even if an independent check procedure for their optimization is still required to increase their adherence to referential benchmark gold standard among experts, which stands at a 0.80 DSI value.

Improved detection of synovial boundaries in ultrasound examination by using a cascade of active-contours

Rheumatoid arthritis (RA) is a chronic multisystemic autoimmune disease, with an unclear etiopathogenesis. Its early diagnosis and activity assessment are essential to adjust the proper therapy. Among the different imaging techniques, ultrasonography (US) allows direct visualization of early inflammatory joint changes as synovitis, being also rapidly performed and easily accepted by patients. We propose an algorithm to semi-automatically detect synovial boundaries on US images, requiring minimal user interaction. In order to identify the synovia-bone and the synovia-soft tissues interfaces, and to tackle the morphological variability of diseased joints, a cascade of two different active contours is developed, whose composition corresponds to the whole synovial boundary.The algorithm was tested on US images acquired from proximal interphalangeal (PIP) and metacarpophalangeal (MCP) finger joints of 34 subjects. The results have been compared with a consensus manual segmentation. We obtained an overall mean sensitivity of 85±13%, and a mean Dice's similarity index of 80±8%, with a mean Hausdorff distance from the manual segmentation of 28±10 pixels (approximately 1.4±0.5mm), that are a better performance than those obtained by the raters with respect to the consensus.

TU‐B‐204B‐05: Quantitative Evaluation and Optimization of an Algorithm for Non‐Rigidly Registering Serial CT Images to the Planning CT during Prostate‐Cancer Radiation Therapy

Purpose: To identify the optimal parameters for a non‐rigid registration algorithm and to assess its accuracy for deformably registering serial prostate cancer CT images acquired during radiation therapy. Such registrations are needed to map organ segmentations from the planning CT onto daily replanning CTs and for cumulative dose reconstruction. Method and Material: Data sets were provided by the Netherlands Cancer Institute and consisted of multislice CT images of 17 prostate cancer patients each scanned 10–12 times during radiation therapy. One physician contoured bladder, rectum, and prostate on all images. The small‐deformation, inverse‐consistent linear‐elastic (SICLE) registration algorithm (TMI 20: 568, 2001) was used to estimate the deformation vector field (DVF) that simultaneously matched CT intensity (intensity matching, IM) and the three segmented regions (contour matching, or CM). IM was used to find DVFs mapping the first image (source) to each of the other subsequent images (target images) for all patients. IM + CM and CM was assessed for a pair of images for each of 10 patients. Endpoints included comparing deformed source contours to manually drawn target contours via the Dice similarity Index (DSI) and Pearson Correlation Coefficient (CC). CC and difference images (deformed source‐target) were used to quantify IM accuracy. Results: IM+CM vs. IM increased mean DSI from 0.78 to 0.95, 0.84 to 0.92, and 0.77 to 0.90 for rectum, prostate, and bladder, respectively, with CC improvements of 14%, 9%, 12%. Compared to CM, IM+CM produced better soft‐tissue registration outside contoured regions, with minimal IM loss relative to IM alone. Conclusion: IM registrations failed to produce acceptable registrations in about 1/3 of the cases, with accurate rectal deformation proving to be especially challenging. Simultaneously contour and intensity matching gave the best overall registration accuracy. Supported by Grant P01 CA 116602.