Dice Coefficient Values Research Articles

Atlas based segmentation in prone breast cancer radiation therapy

The evidence supporting atlas based contour generation is growing and includes breast, prostate, central nervous system, gastrointestinal, gynecologic, and head and neck cancer patient populations. We sought to investigate atlas based segmentation (ABS) in patients with early stage breast cancer status post breast conserving surgery treated with adjuvant radiation therapy in the prone position. An initial atlas library was generated by uploading 20 previously treated patients. Subsequently, a group of 20 consecutive patients underwent treatment planning. Heart, right lung, left lung, total lungs, and breast clinical target volume (CTV) targets were manually contoured per our standard workflow. ABS was then incorporated into our radiation planning workflow and differences in contouring time were recorded, including time needed for ABS volume refinement. ABS generated volumes were compared subjectively in the unedited and edited stages by an independent radiation oncologist to reduce bias by incorporating an interobserver quality analysis. Various objective measurements were used to compare target volume quality including mean distance to agreement (MDA), Dice Coefficient (DC), logit transformation of DC (logit(DC)). The contouring physician edited 88.75% of organ at risk (OAR) volumes on average per patient, whereas the independent reviewing physician recommended revision of 27.5% OAR on average volumes per patient. CTV editing was performed in 20/20 (100%) of cases by the contouring physician, whereas CTV revision was recommended by the independent reviewing physician in 4/20 (20%) of cases. Our atlas performed well with DC values of >0.909 and logit(DC) of >2.344 across heart, lung, and breast volumes when compared to manually generated volumes. All objective measurements demonstrated improvement with physician refinement of ABS generated volumes. The largest absolute improvement was seen in the heart and breast CTV targets. There was 100% acceptance of the edited ABS generated volumes by the independent reviewing physician. The average time saved using ABS was 6.27 minutes (56.92%) per patient. This study confirms ABS offers improvements in efficiency without sacrificing contour quality in the early stage breast cancer patient population and demonstrates the functionality of ABS with prone patient positioning.

Automated contour detection in spine radiographs and computed tomography reconstructions for forensic comparative identification.

This study was conducted to test an automated method to identify unknown individuals. It relies on a previous radiographic file and uses an edge-based comparison of lumbar CT/PMCT reconstructions and radiographs. The living group was composed of 15 clinical lumbar spine CT scans and 15 paired radiographs belonging to the same patients. The deceased group consisted of 5 lumbar spine PMCT scans and 5 paired antemortem radiographs of deceased individuals plus the 15 unpaired radiographs belonging to the living. An automated method using image filtering (anisotropic diffusion) and edge detection (Canny filter) provided image contours. Cross comparisons of all the exams in each group were performed using similarity measurements under the affine registration hypothesis. The Dice coefficient and Hausdorff distance values were significantly linked (p < 0.001 and p = 0.001 respectively) to the matched examinations in the living group (p < 0.001; pseudo-R2 = 0.70). 12 of the 15 examinations were correctly paired, 2 were wrongly paired and 3 were not paired when they must have been. In the deceased group, the Hausdorff distance was significantly linked (p = 0.018) to the matched examinations (p < 0.001; pseudo-R2 = 0.62; Dice coefficient p = 0.138). The paired examinations were all correctly found, but one was wrongly paired. The negative predictive value was above 98% for both groups. We highlighted the feasibility of comparative radiological identification using automated edge detection in cross-modality (CT/PMCT scan and radiographs) examinations. This method could be of significant help to a radiologist or coroner in identifying unknown cadavers.

Single patient convolutional neural networks for real-time MR reconstruction: a proof of concept application in lung tumor segmentation for adaptive radiotherapy

Investigate 3D (spatial and temporal) convolutional neural networks (CNNs) for real-time on-the-fly magnetic resonance imaging (MRI) reconstruction. In particular, we investigated the applicability of training CNNs on a patient-by-patient basis for the purpose of lung tumor segmentation.Data were acquired with our 3 T Philips Achieva system. A retrospective analysis was performed on six non-small cell lung cancer patients who received fully sampled dynamic acquisitions consisting of 650 free breathing images using a bSSFP sequence. We retrospectively undersampled the six patient’s data by 5× and 10× acceleration. The retrospective data was used to quantitatively compare the CNN reconstruction to gold truth data via the Dice coefficient (DC) and centroid displacement to compare the tumor segmentations. Reconstruction noise was investigated using the normalized mean square error (NMSE). We further validated the technique using prospectively undersampled data from a volunteer and motion phantom.The retrospectively undersampled data at 5× and 10× acceleration was reconstructed using patient specific trained CNNs. The patient average DCs for the tumor segmentation at 5× and 10× acceleration were 0.94 and 0.92, respectively. These DC values are greater than the inter- and intra-observer segmentations acquired by radiation oncologist experts as reported in a previous study of ours. Furthermore, the patient specific CNN can be trained in under 6 h and the reconstruction time was 65 ms per image. The prospectively undersampled CNN reconstruction data yielded qualitatively acceptable images.We have shown that 3D CNNs can be used for real-time on-the-fly dynamic image reconstruction utilizing both spatial and temporal data in this proof of concept study. We evaluated the technique using six retrospectively undersampled lung cancer patient data sets, as well as prospectively undersampled data acquired from a volunteer and motion phantom. The reconstruction speed achieved for our current implementation was 65 ms per image.

Spectral mixture analysis in Google Earth Engine to model and delineate fire scars over a large extent and a long time-series in a rainforest-savanna transition zone

Fire is used worldwide to clear natural vegetation areas for economic activities and to manage the regeneration of already opened sites. In Brazil, fire has been traditionally used to convert natural vegetation areas to agricultural lands (slash and burn) and to manage pastures for livestock. We developed the Burned Area Spectral Mixture Analysis (BASMA) algorithm in Google Earth Engine, which is designed to process Landsat data to produce a multi-temporal fire scar database representing annual burned area for an extent of 362,000 km2 in the transition zone between the Amazon forest and the Cerrado biome. This region is considered a conservation hotspot, given its high deforestation rates over the last four decades. We digitally processed a 32-year time-series (1985 to 2017) of Landsat 5 Thematic Mapper, Landsat 7 Enhanced Thematic Mapper+, and Landsat 8 Operational Land Imager data to map fire scars based on sub-pixel char fraction, aiming to generate a consistent burned area product at a finer scale and covering a longer period than those currently available for the region. Manually interpreted reference burned area polygons for each annual mosaic was used to guide the definition of the best fire scar endmember and its fraction threshold. To assess our BASMA-delineated fire scar, they were compared to independent datasets of manually delineated burned area produced by visual analysis of finer spatial resolution imagery, returning an average Dice Coefficient value of 0.86. Accuracy was also measured against the 30-meter Burned Area product available at the ‘Queimadas’ data portal. A total of 11,106,258 ha was mapped as having been affected by fire during the annual dry season over the 32 years, which represents 30.7% of the study region. Results showed a decreasing trend in the annual amount of burned area over the time-series. It reflects a similar pattern shown in the deforestation rate for the Legal Amazon, measured by the Brazilian National Institute for Space Research - INPE. Moreover, the Cerrado biome subset of the study region consistently showed higher burned area when compared to the Amazon forest subset. Our findings provide robust evidence that our approach is a consistent method to identify and delineate fire scars for large areas over a long time-series in a very efficient fashion, given the digital processing power of Google Earth Engine, which reduces the time necessary to analyze such big amount of data.

Automatic segmentation of hyperreflective foci in OCT images

Background and ObjectiveThe leading cause of vision loss in the Western World is Age-related Macular Degeneration (AMD), but together with modern medicines, tracking the number of Hyperreflective Foci (HF) on Optical Coherence Tomography (OCT) images should assist the treatment of patients. Here, we developed a framework based on deep learning for the automatic segmentation of HF in OCT images. MethodsWe collected OCT images and annotated them, then these images underwent image preprocessing, and feature extraction steps. Using the prepared data we trained different types of Conventional-, Deep- and Convolutional Neural Networks to perform the task of the automatic segmentation of HF. ResultsWe evaluated the various Neural Networks, by performing HF segmentation of clinical data belonging to patients, whose data were excluded from the training process. The results suggest that our systems can achieve reasonably high Dice Coefficient values, and they are comparable with (i.e., in most cases above 95%) the similarity between manual annotations performed by different physicians. ConclusionFrom the results, it can be concluded that neural networks can be used to accurately segment HF in OCT images. The results are sufficiently accurate for us to incorporate them into the next phase of the research, building a decision support system for everyday clinical practice.

A Novel Neutrosophic Method for Automatic Seed Point Selection in Thyroid Nodule Images.

The thyroid nodule is one of the endocrine issues caused by an irregular cell development. This rate of survival can be improved by earlier nodule detection. Accordingly, the accurate recognition of the nodule is of the utmost importance in providing powerful results in building the survival rate. The reduction in the accuracy of manual or semiautomatic segmentation methods for thyroid nodule detection is due to many factors, basically, the lack of experience of the sonographer and latency of operation. Most lesion regions in ultrasound images are homogeneous. Therefore, the value of entropy in these regions is high compared to its neighbours. Based on this criterion, a novel procedure for automatically selecting the seed point in thyroid nodule images is proposed. The proposed system consists of three components: neutrosophic image enhancement and speckle reduction to reduce speckle noise and automatic seed selection algorithm extracted from the centre of candidate block in ultrasound thyroid images based on the principle that most of its Higher Order Spectra Entropies (HOSE) from Radon Transform (RT) at different angles are within the range between average and maximum entropies, and the region growing image segmentation is applied with the constant threshold. The performance of proposed automatic segmentation method is compared with other methods in terms of calculating, True Positive (TP) value (96.44 ± 3.01%), False Positive (FP) value (3.55 ± 1.45%), Dice Coefficient (DC) value (92.24 ± 6.47%), Similarity Index (SI) (80.57 ± 1.06%), and Hausdroff Distance (HD) (0.42 ± 0.24 pixels). The proposed system can be considered as an added value to the malignancy diagnosis in thyroid nodule by an endocrinologist.

Burn image segmentation based on Mask Regions with Convolutional Neural Network deep learning framework: more accurate and more convenient

BackgroundBurns are life-threatening with high morbidity and mortality. Reliable diagnosis supported by accurate burn area and depth assessment is critical to the success of the treatment decision and, in some cases, can save the patient’s life. Current techniques such as straight-ruler method, aseptic film trimming method, and digital camera photography method are not repeatable and comparable, which lead to a great difference in the judgment of burn wounds and impede the establishment of the same evaluation criteria. Hence, in order to semi-automate the burn diagnosis process, reduce the impact of human error, and improve the accuracy of burn diagnosis, we include the deep learning technology into the diagnosis of burns.MethodThis article proposes a novel method employing a state-of-the-art deep learning technique to segment the burn wounds in the images. We designed this deep learning segmentation framework based on the Mask Regions with Convolutional Neural Network (Mask R-CNN). For training our framework, we labeled 1150 pictures with the format of the Common Objects in Context (COCO) data set and trained our model on 1000 pictures. In the evaluation, we compared the different backbone networks in our framework. These backbone networks are Residual Network-101 with Atrous Convolution in Feature Pyramid Network (R101FA), Residual Network-101 with Atrous Convolution (R101A), and InceptionV2-Residual Network with Atrous Convolution (IV2RA). Finally, we used the Dice coefficient (DC) value to assess the model accuracy.ResultThe R101FA backbone network gains the highest accuracy 84.51% in 150 pictures. Moreover, we chose different burn depth pictures to evaluate these three backbone networks. The R101FA backbone network gains the best segmentation effect in superficial, superficial thickness, and deep partial thickness. The R101A backbone network gains the best segmentation effect in full-thickness burn.ConclusionThis deep learning framework shows excellent segmentation in burn wound and extremely robust in different burn wound depths. Moreover, this framework just needs a suitable burn wound image when analyzing the burn wound. It is more convenient and more suitable when using in clinics compared with the traditional methods. And it also contributes more to the calculation of total body surface area (TBSA) burned.

Application of aSi-kVCBCT for Volume Assessment and Dose Estimation: An Offline Adaptive Study for Prostate Radiotherapy

Objective:The purpose of this study is to develop a method to estimate the dose using amorphous silicon detector panel cone beam computed tomography (aSi-kVCBCT) for the OARs and targets in prostate radiotherapy and to compare with the actual planned dose.Methods:The aSi-kVCBCT is used widely in radiotherapy to verify the patient position before treatment. The advancement in aSi-kVCBCT combined with adaptive software allows us to verify the dose distribution in daily acquired CBCT images. CBCT images from 10 patients undergoing radical prostate radiotherapy were included in this study. Patients received total dose of 65Gy in 25 fractions using volumetric modulated arc therapy (VMAT). aSi-kVCBCT scans were acquired before daily treatment and exported to smart adapt software for image adaptation. The planning CT is adapted to daily aSi-kVCBCT images in terms of HU mapping. The primary VMAT plans were copied on to the adapted planning CT images and dose was calculated using Anisotropic Analytic Algorithm (AAA). The DVH is then used to evaluate the volume changes of organs at risk (OAR), the actual dose received by OARs, CTV and PTV during a single fraction.Results:The normalized volume of the bladder and rectum ranged from 0.70–1.66 and 0.70–1.16 respectively. The cumulative mean Sorensen–Dice coefficient values of bladder and rectum were 0.89±0.04 and 0.79±0.06 respectively. The maximum dose differences for CTV and PTV were 2.5% and -4.7% and minimum were 0.1% and 0.1% respectively.Conclusion:The adapted planning CT obtained from daily imaging using aSi-kVCBCT and SmartAdapt® can be used as an effective tool to estimate the volume changes and dose difference in prostate radiotherapy.

Fully automated organ segmentation in male pelvic CT images

Accurate segmentation of prostate and surrounding organs at risk is important for prostate cancer radiotherapy treatment planning. We present a fully automated workflow for male pelvic CT image segmentation using deep learning. The architecture consists of a 2D organ volume localization network followed by a 3D segmentation network for volumetric segmentation of prostate, bladder, rectum, and femoral heads. We used a multi-channel 2D U-Net followed by a 3D U-Net with encoding arm modified with aggregated residual networks, known as ResNeXt. The models were trained and tested on a pelvic CT image dataset comprising 136 patients. Test results show that 3D U-Net based segmentation achieves mean (±SD) Dice coefficient values of 90 (±2.0)%, 96 (±3.0)%, 95 (±1.3)%, 95 (±1.5)%, and 84 (±3.7)% for prostate, left femoral head, right femoral head, bladder, and rectum, respectively, using the proposed fully automated segmentation method.

An efficient multiple sclerosis segmentation and detection system using neural networks

In this work, an efficient multiple sclerosis (MS) segmentation technique is proposed to simplify pre-processing steps and diminish processing time using heterogeneous single-channel magnetic resonance imaging (MRI). A spatial-filtering image mapping, histogram reference image, and histogram matching techniques are effectively applied to possess a local threshold per image using the global threshold algorithm. Feature extraction is performed using mathematical and morphological operations, and a multilayer feed-forward neural network (MLFFNN) is used identify multiple sclerosis’ tissues. Fluid-attenuated inversion recovery (FLAIR) series are used to integrate a faster system while maintaining reliability and accuracy. A sagittal (SAG) FLAIR-based system is proposed for the first time in MS detection systems, which reduces the number of utilized images, and decreases the processing time by nearly one-third. Our detection system provided a significant recognition rate of up to 98.5%. Moreover, a relatively high dice coefficient (DC) value (0.71 ± 0.18) was observed upon testing new images.

Automated skin lesion segmentation of dermoscopic images using GrabCut and k‐means algorithms

Skin cancer is the most common type of cancer in the world and the incidents of skin cancer have been rising over the past decade. Even with a dermoscopic imaging system, which magnifies the lesion region, detecting and classifying skin lesions by visual examination is laborious due to the complex structures of the lesions. This necessitates the need for an automated skin lesion diagnosis system to enhance the diagnostic capability of dermatologists. In this study, the authors propose an automatic skin lesion segmentation method which can be used as a preliminary step for lesion classification. The proposed method comprises two major steps, namely preprocessing and segmentation. In the preprocessing step, noise such as illumination, hair and rulers are removed using filtering techniques and in the segmentation phase, skin lesions are segmented using the GrabCut segmentation algorithm. The k‐means clustering algorithm is then used along with the colour features learnt from the training images to improve the boundaries of the segments. To evaluate the authors’ proposed method, they have used ISIC 2017 challenge dataset and dataset. They have obtained Dice coefficient values of 0.8236 and 0.9139 for ISIC 2017 test dataset and dataset, respectively.

Ischemic stroke lesion segmentation using stacked sparse autoencoder

Automatic segmentation of ischemic stroke lesion volumes from multi-spectral Magnetic Resonance Imaging (MRI) sequences plays a vital role in quantifying and locating the lesion region. Most existing methods mainly rely on designing hand-crafted features followed by a classifier model for ischemic stroke lesion segmentation. Design of these features requires complex domain knowledge and often lacks the ability to differentiate between the stroke lesions and the normal classes. In this work, we propose an unsupervised featured learning approach based on stacked sparse autoencoder (SSAE) framework for automatically learning the features for accurate segmentation of stroke lesions from brain MR images. A deep architecture is designed using sparse autoencoder (SAE) layers, followed by support vector machine (SVM) classifier for classifying the patches into normal or lesions. We validated our approach on a publicly available Ischemic Stroke Lesion Segmentation (ISLES) 2015 dataset, with a mean precision of 0.968, mean dice coefficient (DC) of 0.943, mean recall of 0.924 and mean accuracy of 0.904. The experimental results show that our proposed approach significantly outperforms the state-of-the-art methods in terms of precision, DC, and recall. Quantitative evaluation was carried out and compared with the existing approaches, which demonstrates that the proposed method is 25.71%, 36.67%, and 16.96% higher in terms of precision, DC and recall values, respectively. The unsupervised features learned via SSAE framework performs better than the hand-crafted features and can be easily trained on large datasets.

Computer aided thyroid nodule detection system using medical ultrasound images

Abstract Thyroid nodule is one of the endocrine problem caused due to abnormal growth of cells. This survival rate can be enhanced by earlier detection of nodules. Thus, the accurate detection of nodule is of utmost importance in providing effective diagnosis to increase the survival rate. However, accuracy of nodule detection from ultrasound images is suffered due to speckle noise. It considerably deteriorates the image quality and makes the differentiation of fine details quite difficult. Most of the detection systems for the thyroid nodules are semi-automated entailing manual intervention to draw rough outline of the nodule at some level or require manual segmentation in training or testing phases that increase the inaccuracies and evaluation time. To handle this, a fully Computer-Aided Detection system is presented for speckle reduction and segmentation of nodules from thyroid ultrasound images. The proposed system has three components: speckle reduction to reduce speckle noise and preserve the diagnostic features of ultrasound image, automatic generation of Region of interest (ROI) that identifies suspicious regions and fully automatic segmentation of nodule in processed ROI image. The proposed segmentation method outperformed other methods by gaining high True Positive (TP) value (95.92 ± 3.70%), False Positive (FP) value (7.04 ± 4.21%), Dice Coefficient (DC) value (93.88 ± 2.59%), Overlap Metric (OM) (91.18 ± 7.04 pixels) and Hausdroff Distance (HD) (0.52 ± 0.20 pixels). This system can facilitate the endocrinologists by providing second opinion to improve diagnosis of nodules as benign or malignant.

Segmentation of Retinal Cysts From Optical Coherence Tomography Volumes Via Selective Enhancement.

Automated and accurate segmentation of cystoid structures in optical coherence tomography (OCT) is of interest in the early detection of retinal diseases. It is, however, a challenging task. We propose a novel method for localizing cysts in 3-D OCT volumes. The proposed work is biologically inspired and based on selective enhancement of the cysts, by inducing motion to a given OCT slice. A convolutional neural network is designed to learn a mapping function that combines the result of multiple such motions to produce a probability map for cyst locations in a given slice. The final segmentation of cysts is obtained via simple clustering of the detected cyst locations. The proposed method is evaluated on two public datasets and one private dataset. The public datasets include the one released for the OPTIMA cyst segmentation challenge (OCSC) in MICCAI 2015 and the DME dataset. After training on the OCSC train set, the method achieves a mean dice coefficient (DC) of 0.71 on the OCSC test set. The robustness of the algorithm was examined by cross validation on the DME and AEI (private) datasets and a mean DC values obtained were 0.69 and 0.79, respectively. Overall, the proposed system has the highest performance on all the benchmarks. These results underscore the strengths of the proposed method in handling variations in both data acquisition protocols and scanners.

Computer aided thyroid nodule detection system using medical ultrasound images

Abstract Thyroid nodule is one of the endocrine problem caused due to abnormal growth of cells. This survival rate can be enhanced by earlier detection of nodules. Thus, the accurate detection of nodule is of utmost importance in providing effective diagnosis to increase the survival rate. However, accuracy of nodule detection from ultrasound images is suffered due to speckle noise. It considerably deteriorates the image quality and makes the differentiation of fine details quite difficult. Most of the detection systems for the thyroid nodules are semi-automated entailing manual intervention to draw rough outline of the nodule at some level or require manual segmentation in training or testing phases that increase the inaccuracies and evaluation time. To handle this, a fully Computer-Aided Detection system is presented for speckle reduction and segmentation of nodules from thyroid ultrasound images. The proposed system has three components: speckle reduction to reduce speckle noise and preserve the diagnostic features of ultrasound image, automatic generation of Region of interest (ROI) that identifies suspicious regions and fully automatic segmentation of nodule in processed ROI image. The proposed segmentation method outperformed other methods by gaining high True Positive (TP) value (95.92 ± 3.70%), False Positive (FP) value (7.04 ± 4.21%), Dice Coefficient (DC) value (93.88 ± 2.59%), Overlap Metric (OM) (91.18 ± 7.04 pixels) and Hausdroff Distance (HD) (0.52 ± 0.20 pixels). This system can facilitate the endocrinologists by providing second opinion to improve diagnosis of nodules as benign or malignant.

A Simple Image Processing Approach To Abnormal Slices Detection From MRI Tumor Volumes

This paper proposed a method for brain tumor detection from the magnetic resonance imaging (MRI) of human head scans. The proposed work explained the tumor detection process by means of image processing transformations and thresholding technique. The MRI images are preprocessed by transformation techniques and thus enhance the tumor region. Then the images are checked for abnormality using fuzzy symmetric measure (FSM). If abnormal, then Otsu’s thresholding is used to extract the tumor region. Experiments with the proposed method were done on 17 datasets. Various evaluation parameters were used to validate the proposed method. The predictive accuracy (PA) and dice coefficient (DC) values of proposed method reached maximum.

Optical mammography: bilateral breast symmetry in hemoglobin saturation maps.

We present a study of the bilateral symmetry of human breast hemoglobin saturation maps measured with a broadband optical mammography instrument. We have imaged 21 patients with unilateral breast cancer, 32 patients with unilateral benign lesions, and 27 healthy patients. An image registration process was applied to the bilateral hemoglobin saturation (SO 2 SO2 ) images by assigning each pixel to the low, middle, or high range of SO 2 SO2 values, where the thresholds for the categories were the 15th and 85th percentiles of the individual saturation range. The Dice coefficient, which is a measure of similarity, was calculated for each patient’s pair of right and left breast SO 2 SO2 images. The invasive cancer patients were found to have an average Dice coefficient value of 0.55±0.07 0.55±0.07 , which was significantly lower than the benign and healthy groups (0.61±0.11 0.61±0.11 and 0.62±0.12 0.62±0.12 , respectively). Although differences were seen in a group analysis, the healthy patient Dice coefficients spanned a wide range, limiting the diagnostic capabilities of this SO 2 SO2 symmetry analysis on an individual basis. Our results suggest that for assessing the SO 2 SO2 contrast of breast lesions, it may be better to select a reference tissue in the ipsilateral rather than the contralateral breast.

Small Animal In Vivo X-Ray Tomosynthesis: Anatomical Relevance of the Reconstructed Images.

Whole body X-ray micro-Digital Tomosynthesis (micro-DT) for small animal imaging is introduced in this work. Such a system allows to deal with geometrical constraints that do not allow to use a micro-CT system as well as to reduce the radiological dose compared to a micro-CT scan. Data was simulated using the Digimouse anatomical model of the mouse with the designed system. An algebraic reconstruction algorithm regularized by Total Variation norm (TV) minimization was used to reconstruct images. Parameters for the reconstruction were optimized and the algorithm performance was evaluated quantitatively. High contrast tissues were subsequently segmented by thresholding the image. Quantitative analysis of the segmented domains indicates that a relevant anatomical information can possibly be extracted from micro-DT images. Indeed the Dice's coefficient values are greater than 0.8 for the segmented High Contrast Tissues compared to the phantom, which indicates an important overlap between the domains. The volume of the segmented tissues is over-estimated for the bones and skin-with 1.313 and 1.113 ratios of the estimated over reference volumes, respectively-and under-estimated in the case of the lungs with a 0.762 ratio. The mean point to surface distance is inferior to the voxel size of 400 μm, for the three segmented tissues. These results are very encouraging and let us consider micro-DT as an alternative to micro-CT to deal with geometrical constraints.

A rapid automatic brain tumor detection method for MRI images using modified minimum error thresholding technique

ABSTRACTThis proposed work is aimed to develop a rapid automatic method to detect the brain tumor from T2‐weighted MRI brain images using the principle of modified minimum error thresholding (MET) method. Initially, modified MET method is applied to produce well segmented and sub‐structural clarity for MRI brain images. Further, using FCM clustering the appearance of tumor area is refined. The obtained results are compared with corresponding ground truth images. The quantitative measures of results were compared with the results of those conventional methods using the metrics predictive accuracy (PA), dice coefficient (DC), and processing time. The PA and DC values of the proposed method attained maximum value and processing time is minimum while compared to conventional FCM and k‐means clustering techniques. This proposed method is more efficient and faster than the existing segmentation methods in detecting the tumor region from T2‐weighted MRI brain images. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 77–85, 2015

An alternative approach to histopathological validation of PET imaging for radiation therapy image-guidance: A proof of concept

PurposeIn radiotherapy, PET images can be used to guide the delivery of selectively escalated doses to biologically relevant tumour subvolumes. Validation of PET for such applications requires demonstration of spatial coincidence between PET tracer uptake pattern and the histopathologically confirmed target. This study introduces a novel approach to histopathological validation of PET image segmentation for radiotherapy guidance. Methods and materialsSequential tissue sections from surgically excised whole-tumour specimens were used to acquire full 3D-sets of both histopathological images (microscopy) and PET tracer distribution images (autoradiography). After these datasets were accurately registered, a full 3D autoradiographic distribution of PET tracer was reconstructed and used to obtain synthetic PET images (sPET) by simulating the image deterioration induced by processes involved in PET image formation. To illustrate the method, sPET images were used in this study to investigate spatial coincidence between high FDG uptake areas and the distribution of viable tissue in two small animal tumour models. ResultsThe reconstructed 3D autoradiographic distribution of the PET tracer was spatially coherent, as indicated by the high average value of the normalised pixel-by-pixel correlation of intensities between successive slices (0.84±0.05 and 0.94±0.02). The loss of detail in the sPET images versus the 3D autoradiography was significant as indicated by Dice coefficient values corresponding to the two tumours (0 and 0.1 at 70% threshold). The maximum overlap between the FDG segmented volumes and the extent of the viable tissue as indicated by Dice coefficient values, was 0.8 for one tumour (for the image thresholded at 22% of max intensity) and 0.88 for the other (threshold of 14% of max intensity). ConclusionIt was demonstrated that the use of synthetic PET images for histopathological validation allows for bypassing a technically challenging and error-prone step of registering non-invasive PET images with histopathology.