Rotationally resliced 3D prostate segmentation of MR images using Bhattacharyya similarity and active band theory

PurposeIn this article, we propose a novel, semi-automatic segmentation method to process 3D MR images of the prostate using the Bhattacharyya coefficient and active band theory with the goal of providing technical support for computer-aided diagnosis and surgery of the prostate.MethodsOur method consecutively segments a stack of rotationally resectioned 2D slices of a prostate MR image by assessing the similarity of the shape and intensity distribution in neighboring slices. 2D segmentation is first performed on an initial slice by manually selecting several points on the prostate boundary, after which the segmentation results are propagated consecutively to neighboring slices. A framework of iterative graph cuts is used to optimize the energy function, which contains a global term for the Bhattacharyya coefficient with the help of an auxiliary function. Our method does not require previously segmented data for training or for building statistical models, and manual intervention can be applied flexibly and intuitively, indicating the potential utility of this method in the clinic.ResultsWe tested our method on 3D T2-weighted MR images from the ISBI dataset and PROMISE12 dataset of 129 patients, and the Dice similarity coefficients were 90.34 ± 2.21% and 89.32 ± 3.08%, respectively. The comparison was performed with several state-of-the-art methods, and the results demonstrate that the proposed method is robust and accurate, achieving similar or higher accuracy than other methods without requiring training.ConclusionThe proposed algorithm for segmenting 3D MR images of the prostate is accurate, robust, and readily applicable to a clinical environment for computer-aided surgery or diagnosis.     

Epithelium segmentation and automated Gleason grading of prostate cancer via deep learning in label‐free multiphoton microscopic images

In the current clinical care practice, Gleason grading system is one of the most powerful prognostic predictors for prostate cancer (PCa). The grading system is based on the architectural pattern of cancerous epithelium in histological images. However, the standard procedure of histological examination often involves complicated tissue fixation and staining, which are time‐consuming and may delay the diagnosis and surgery. In this study, label‐free multiphoton microscopy (MPM) was used to acquire subcellular‐resolution images of unstained prostate tissues. Then, a deep learning architecture (U‐net) was introduced for epithelium segmentation of prostate tissues in MPM images. The obtained segmentation results were then merged with the original MPM images to train a classification network (AlexNet) for automated Gleason grading. The developed method achieved an overall pixel accuracy of 92.3% with a mean F1 score of 0.839 for epithelium segmentation. By merging the segmentation results with the MPM images, the accuracy of Gleason grading was improved from 72.42% to 81.13% in hold‐out test set. Our results suggest that MPM in combination with deep learning holds the potential to be used as a fast and powerful clinical tool for PCa diagnosis.     

Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network

Precise liver segmentation in abdominal MRI images is one of the most important steps for the computer-aided diagnosis of liver pathology. The first and essential step for diagnosis is automatic liver segmentation, and this process remains challenging. Extensive research has examined liver segmentation; however, it is challenging to distinguish which algorithm produces more precise segmentation results that are applicable to various medical imaging techniques. In this paper, we present a new automatic system for liver segmentation in abdominal MRI images. The system includes several successive steps. Preprocessing is applied to enhance the image (edge-preserved noise reduction) by using mathematical morphology. The proposed algorithm for liver region extraction is a combined algorithm that utilizes MLP neural networks and watershed algorithm. The traditional watershed transformation generally results in oversegmentation when directly applied to medical image segmentation. Therefore, we use trained neural networks to extract features of the liver region. The extracted features are used to monitor the quality of the segmentation using the watershed transform and adjust the required parameters automatically. The process of adjusting parameters is performed sequentially in several iterations. The proposed algorithm extracts liver region in one slice of the MRI images and the boundary tracking algorithm is suggested to extract the liver region in other slices, which is left as our future work. This system was applied to a series of test images to extract the liver region. Experimental results showed positive results for the proposed algorithm.     

MR 脑图像海马自动分割法在AD 早期诊断中的应用研究

目的:研究磁共振(Magnetic resonance,MR)脑图像中海马的自动分割方法及海马的形态学分析方法,为阿尔茨海默病(Alzheimer’s disease,AD)的早期诊断提供依据。方法:对20例AD患者和60名正常对照者行MRI T1 WI 3D容积扫描,建立海马的三维主动表观模型,并以此模型对每个个体脑部磁共振图像上的海马进行自动识别和三维分割,分别建立正常对照组和AD组的海马统计形状模型,比较AD组与正常对照组间海马形状的差异性。结果:海马三维分割方法与手动分割方法在海马体积测量上无统计学差别(P>0.05);AD患者海马头部发生萎缩(P<0.05)。结论:基于主动表观模型的MR脑图像海马自动识别和三维分割法是准确可靠的;海马头部萎缩可作为AD诊断的依据之一。     

Récidive biologique de cancer de la prostate : intérêt de la TEP/TDM à la fluorocholine (18F) du corps entier

Case reportA patient was referred to fluorocholine (18F) PET/CT to restage a biological recurrence of his prostate cancer. There was a doubt on local and lymph node recurrence on MRI.ResultPET/CT showed several pelvic foci evocative of local and lymph node recurrence, more extensive than the MRI anomaly without bone lesion; this recurrence was treated by hormone therapy. But FCH PET/CT also revealed a left cerebral focus. Cerebral MRI was therefore performed which confirmed an anomaly evocative of a grade II brain lesion.ConclusionThis observation illustrates the fact that, in case of prostate cancer, a whole-body imaging, including the skull, is useful, even when foci are detected in the pelvis. Several types of cancer take-up fluorocholine (18F): in case of a visceral distant focus in a patient with prostate cancer, the hypothesis of a second primary cancer should be considered.     

Susceptibility Weighted Imaging: A New Tool in the Diagnosis of Prostate Cancer and Detection of Prostatic Calcification

Background

Susceptibility weighted imaging (SWI) is a new MRI technique which has been proved very useful in the diagnosis of brain diseases, but few study was performed on its value in prostatic diseases. The aim of the present study was to investigate the value of SWI in distinguishing prostate cancer from benign prostatic hyperplasia and detecting prostatic calcification.

Methodology/Principal Findings

23 patients with prostate cancer and 53 patients with benign prostatic hyperplasia proved by prostate biopsy were scanned on a 3.0T MR and a 16-row CT scanner. High-resolution SWI, conventional MRI and CT were performed on all patients. The MRI and CT findings, especially SWI, were analyzed and compared. The analyses revealed that 19 out of 23 patients with prostate cancer presented hemorrhage within tumor area on SWI. However, in 53 patients with benign prostatic hyperplasia, hemorrhage was detected only in 1 patient in prostate by SWI. When comparing SWI, conventional MRI and CT in detecting prostate cancer hemorrhage, out of the 19 patients with prostate cancer who had prostatic hemorrhage detected by SWI, the prostatic hemorrhage was detected in only 7 patients by using conventional MRI, and none was detected by CT. In addition, CT demonstrated calcifications in 22 patients which were all detected by SWI whereas only 3 were detected by conventional MRI. Compared to CT, SWI showed 100% in the diagnostic sensitivity, specificity, accuracy, positive predictive value(PPV) and negative predictive value(NPV) in detecting calcifications in prostate but conventional MRI demonstrated 13.6% in sensitivity, 100% in specificity, 75% in accuracy, 100% in PPV and 74% in NPV.

Conclusions

More apparent prostate hemorrhages were detected on SWI than on conventional MRI or CT. SWI may provide valuable information for the differential diagnosis between prostate cancer and prostatic hyperplasia. Filtered phase images can identify prostatic calcifications as well as CT.     

Imagerie moléculaire de la maladie de Parkinson : données actuelles

During the last years, knowledge and concepts concerning Parkinson's disease and other parkinsonian syndromes have progressed: a concept of network pathology with different clinical presentations and evolutions, involving several neurotransmission pathways succeeeded the single dopaminergic lesion concept. Imaging also changed with the development of MRI. In this context, the aim of this work is to bring up-to-date methodology and clinical contribution of dopaminergic neuron imaging. Nigrostriatal neuron imaging (dopamine transporter imaging) contributes to diagnosis of Parkinson's disease and Lewy body dementia. Dopamine receptor imaging mainly helps in differential diagnosis of parkinsonian syndromes (Parkinson's disease and Parkinson plus syndromes). The ongoing development of dopaminergic, cholinergic, serotoninergic tracers and the recent emergence of amyloid plaques and neurofibrillary tangles imaging open perspectives for molecular imaging and care of neurodegenerative diseases.     

Magnetic resonance imaging for prostate cancer radiotherapy

For radiotherapy of prostate cancer, MRI is used increasingly for delineation of the prostate gland. For focal treatment of low-risk prostate cancer or focal dose escalation for intermediate and high-risk cancer, delineation of the tumor is also required. While multi-parametric MRI is well established for detection of tumors and for staging of the disease, delineation of the tumor inside the prostate is not common practice.Guidelines, such as the PI-RADS classification, exist for tumor detection and staging, but no such guidelines are available for tumor delineation. Indeed, interobserver studies show substantial variation in tumor contours. Computer-aided tumor detection and delineation may help improve the robustness of the interpretation of multi-parametric MRI data. Comparing the performance of an earlier developed model for tumor segmentation with expert delineations, we found a significant correlation between tumor probability in a voxel and the number of experts identifying this voxel as tumor. This suggests that the model agrees with ‘the wisdom of the crowd’, and thus could serve as a reference for individual physicians in their decision making.With multi-parametric MRI it becomes feasible to revisit the GTV-CTV concept in radiotherapy of prostate cancer. While detection of index lesions is quite reliable, contouring variability and the low sensitivity to small lesions suggest that the remainder of the prostate should be treated as CTV. Clinical trials that investigate the options for dose differentiation, for example with dose escalation to the visible tumor or dose reduction to the CTV, are therefore warranted.     

Apport de la médecine nucléaire dans la prise en charge du cancer de la prostate : analyse de 360 cas en milieu camerounais

Prostate cancer is the most frequent neoplasm affecting males above 50 years old in developed countries. Previous studies carried out in Cameroon have shown that, this condition is not infrequent. Late diagnosis is equally common. The advent of nuclear medicine technology in the year 2000 has enabled the possibility of prostate specific antigen (PSA) assay and imaging by bone scintigraphy. In this study, we aimed at assessing the contributions of PSA assay and bone scintigraphy in the management of prostate cancer in Cameroon. Within a 5 years period (January 2003–December 2007) 360 patients had biopsy proven (Gleason score) prostate adenocarcinoma. The age ranged from 50 to 85 years with a mean of 67 years. Those aged between 60 to 69 years were more affected. The patients were divided into 2 groups: a first one accruing of 250 patients with a previous bone scintigraphy carried out before treatment and a second group of patients who underwent a bone scintigraphy during treatment. Clinical features digital rectal examination, endorectal echography were noted. PSA levels and bone scintigraphy results were also noted. Most of these patients (80.56%) presented with advanced lesions with metastases. Orchiectomy and hormonotherapy were the most used methods of treatment due to late diagnosis. Bone scintigraphy-evidenced lesions were mainly located (92.25%) at the dorso-lombar region of the spine. There is a correlation between the following variables: clinical features, namely, digital rectal examinations, PSA blood levels, ultrasound, histology and bone scintigraphy. Therefore, we can conclude that, PSA is an important marker of prostate cancer. Its association with bone scintigraphy is appropriate for the detection of bone metastases.     

A diabetic retinopathy detection method using an improved pillar K-means algorithm

The paper presents a new approach for medical image segmentation. Exudates are a visible sign of diabetic retinopathy that is the major reason of vision loss in patients with diabetes. If the exudates extend into the macular area, blindness may occur. Automated detection of exudates will assist ophthalmologists in early diagnosis. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system applies K-means clustering to the image segmentation after getting optimized by Pillar algorithm; pillars are constructed in such a way that they can withstand the pressure. Improved pillar algorithm can optimize the K-means clustering for image segmentation in aspects of precision and computation time. This evaluates the proposed approach for image segmentation by comparing with Kmeans and Fuzzy C-means in a medical image. Using this method, identification of dark spot in the retina becomes easier and the proposed algorithm is applied on diabetic retinal images of all stages to identify hard and soft exudates, where the existing pillar K-means is more appropriate for brain MRI images. This proposed system help the doctors to identify the problem in the early stage and can suggest a better drug for preventing further retinal damage.     

Quantification automatisée de la transmuralité de l’infarctus du myocarde sur des images de rehaussement tardif en IRM

MRI is an important technique to follow up myocardial infarction, allowing studying in only one examination the contraction and the viability through delayed enhancement (DE). This study proposes to automate the segmentation of the myocardium on images prior to the estimation of the extent of infarcted tissue. Indeed the segmentation of the myocardium was performed using cine contraction images which present a high contrast between cavity and myocardium before reporting resulting segmentation on DE images. After the segmentation, the segmental transmurality is estimated on a conventional five point scale, using the fuzzy k-mean classification algorithm. A head-to-head comparison was performed between visual and quantitative analysis of the infarct transmural extent on DE-MR imaging. Results on nine patients showed an absolute agreement of 80% and a relative agreement (with one point difference) of 97%.     

miRNA Expression Analyses in Prostate Cancer Clinical Tissues

A critical challenge in prostate cancer (PCa) clinical management is posed by the inadequacy of currently used biomarkers for disease screening, diagnosis, prognosis and treatment. In recent years, microRNAs (miRNAs) have emerged as promising alternate biomarkers for prostate cancer diagnosis and prognosis. However, the development of miRNAs as effective biomarkers for prostate cancer heavily relies on their accurate detection in clinical tissues. miRNA analyses in prostate cancer clinical specimens is often challenging owing to tumor heterogeneity, sampling errors, stromal contamination etc. The goal of this article is to describe a simplified workflow for miRNA analyses in archived FFPE or fresh frozen prostate cancer clinical specimens using a combination of quantitative real-time PCR (RT-PCR) and in situ hybridization (ISH). Within this workflow, we optimize the existing methodologies for miRNA extraction from FFPE and frozen prostate tissues and expression analyses by Taqman-probe based miRNA RT-PCR. In addition, we describe an optimized method for ISH analyses formiRNA detection in prostate tissues using locked nucleic acid (LNA)- based probes. Our optimized miRNA ISH protocol can be applied to prostate cancer tissue slides or prostate cancer tissue microarrays (TMA).     

Cancer de la prostate : les niveaux de preuve des biomarqueurs de la détection précoce

As part of an overall review on the role of PSA and other emerging biomarkers in the detection, diagnosis and treatment of prostate cancer, we present here a part of a review of the literature made by the working group Biologie de la Prostate (AFU, CNBH, SFBC, SFMN) on the use of PSA and other biomarkers in the early detection of prostate cancer with an assessment of the level of evidence.     

磁共振成像联合血清前列腺特异抗原、上皮钙黏蛋白、早期前列腺癌抗原-2诊断前列腺癌的临床价值探讨

摘要 目的：探究磁共振成像（MRI）联合血清前列腺特异抗原（PSA）、上皮钙黏蛋白（sE-cadherin）、早期前列腺癌抗原-2（EPCA-2）诊断前列腺癌的临床价值。方法：选取潍坊市人民医院2020年1月-2021年7月期间经病理证实的50例前列腺癌患者（前列腺组）以及50例前列腺增生患者（前列腺增生组）展开回顾性研究。100例研究对象均完善了MRI检查并测定血清PSA、EPCA-2、sE-cadherin水平,分析两组患者的MRI影像学特征,比较两组患者的PSA、EPCA-2、sE-cadherin水平以及各项检查方法的诊断准确性差异。结果：前列腺癌的MRI影像学特征为病灶主要位于外周带,外周带T2W呈低信号,病变侵及包膜、膀胱及周围组织具有T1加权消失或者不对称,具有信号异常、肌肉增厚的表现,盆腔淋巴结转移具有淋巴结部分融合或增大表现;前列腺增生的MRI影像学特征为边界清晰、包膜完整并且中央带增生、不均匀信号结节;前列腺癌、前列腺增生均存在不同程度的前列腺体积增大。相比于前列腺增生组,前列腺癌组患者的PSA、sE-cadherin、EPCA-2水平明显更高（P<0.05）。MRI、PSA、sE-cadherin、EPCA-2四项联合鉴别前列腺癌、前列腺增生的诊断符合率为96.00%,明显高于四项单独诊断的88.00%、79%、81%、82%（P<0.05）。结论：MRI联合PSA、sE-cadherin、EPCA-2鉴别诊断前列腺癌的准确性较高,具有作为临床前列腺癌早期诊断指导方案的潜力。     

Apport de l’imagerie hybride TEMP-TDM dans le suivi d’un cancer différencié de la thyroïde

In the management of patients with differentiated thyroid cancer (DTC), abnormalities detected on planar whole body scan and ¹³¹I-SPECT are difficult to interpret because of a lack of anatomical landmarks and limited specificity. Integrated ¹³¹I-SPECT-CT imaging has an additional value for characterization of equivocal tracer uptake seen on planar imaging as well as for precise localization. We illustrate through an observation the incremental diagnostic value of ¹³¹I-SPECT-CT images in the diagnosis of a cervical lymph node mimicking a physiological uptake on planar views. A 35-year-old Tunisian female was followed for papillary thyroid carcinoma, for which she underwent total thyroidectomy and iratherapy. Three years after a complete remission, the thyroglobulin (Tg) level on TSH stimulation increased. Diagnostic planar images with ¹³¹I did not disclose any obvious pathological foci. Furthermore, we noticed an increased ¹³¹I-uptake in the left sub-mandibulary area, which suggested a salivary physiological activity. SPECT-CT of the neck and chest were then performed with a Symbia T camera. Fused images demonstrate that this activity corresponds to a cervical lymph node closely adjacent to sub-mandibulary gland. Management of the patient was then changed. In selected patients with DTC, hybrid imaging should be used as a complementary to planar imaging in terms of diagnostic accuracy, because of superior focus localization and additional anatomic information derived from the CT component. Integrated SPECT-CT is then a useful tool, especially in cases of unclear diagnoses, precising anatomical localization of areas of increased ¹³¹I-uptake and distinguishing malignant lesions from normal physiological uptakes. This is particularly important in an oncologic center, as ours, where we don’t yet have a positron emission tomography (PET) camera is not yet available.     

A pipeline to quantify spinal cord atrophy with deep learning: Application to differentiation of MS and NMOSD patients

PurposeQuantitative measurement of various anatomical regions of the brain and spinal cord (SC) in MRI images are used as unique biomarkers to consider progress and effects of demyelinating diseases of the central nervous system. This paper presents a fully-automated image processing pipeline which quantifies the SC volume of MRI images.MethodsIn the proposed pipeline, after conducting some pre-processing tasks, a deep convolutional network is utilized to segment the spinal cord cross-sectional area (SCCSA) of each slice. After full segmentation, certain extra slices interpolate between each two adjacent slices using the shape-based interpolation method. Then, a 3D model of the SC is reconstructed, and, by counting the voxels of it, the SC volume is calculated. The performance of the proposed method for the SCCSA segmentation is evaluated on 140 MRI images. Subsequently, to demonstrate the application of the proposed pipeline, we study the differentiations of SC atrophy between 38 Multiple Sclerosis (MS) and 25 Neuromyelitis Optica Spectrum Disorder (NMOSD) patients.ResultsThe experimental results of the SCCSA segmentation indicate that the proposed method, adapted by Mask R-CNN, presented the most satisfactory result with the average Dice coefficient of 0.96. For this method, statistical metrics including sensitivity, specificity, accuracy, and precision are 97.51%, 99.98%, 99.92%, and 98.04% respectively. Moreover, the t-test result (p-value = 0.00089) verified a significant difference between the SC atrophy of MS and NMOSD patients.ConclusionThe pipeline efficiently quantifies the SC volume of MRI images and can be utilized as an affordable computer-aided tool for diagnostic purposes.     

Application of a semi-automatic cartilage segmentation method for biomechanical modeling of the knee joint

Manual segmentation of articular cartilage from knee joint 3D magnetic resonance images (MRI) is a time consuming and laborious task. Thus, automatic methods are needed for faster and reproducible segmentations. In the present study, we developed a semi-automatic segmentation method based on radial intensity profiles to generate 3D geometries of knee joint cartilage which were then used in computational biomechanical models of the knee joint. Six healthy volunteers were imaged with a 3T MRI device and their knee cartilages were segmented both manually and semi-automatically. The values of cartilage thicknesses and volumes produced by these two methods were compared. Furthermore, the influences of possible geometrical differences on cartilage stresses and strains in the knee were evaluated with finite element modeling. The semi-automatic segmentation and 3D geometry construction of one knee joint (menisci, femoral and tibial cartilages) was approximately two times faster than with manual segmentation. Differences in cartilage thicknesses, volumes, contact pressures, stresses, and strains between segmentation methods in femoral and tibial cartilage were mostly insignificant (p > 0.05) and random, i.e. there were no systematic differences between the methods. In conclusion, the devised semi-automatic segmentation method is a quick and accurate way to determine cartilage geometries; it may become a valuable tool for biomechanical modeling applications with large patient groups.     

Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.     

Synergy between anti‐CCL2 and docetaxel as determined by DW‐MRI in a metastatic bone cancer model

Metastatic prostate cancer continues to be the second leading cause of cancer death in American men with an estimated 28,660 deaths in 2008. Recently, monocyte chemoattractant protein‐1 (MCP‐1, CCL2) has been identified as an important factor in the regulation of prostate metastasis. CCL2, shown to attract macrophages to the tumor site, has a direct promotional effect on tumor cell proliferation, migration, and survival. Previous studies have shown that anti‐CCL2 antibodies given in combination with docetaxel were able to induce tumor regression in a pre‐clinical prostate cancer model. A limitation for evaluating new treatments for metastatic prostate cancer to bone is the inability of imaging to objectively assess response to treatment. Diffusion‐weighted MRI (DW‐MRI) assesses response to anticancer therapies by quantifying the random (i.e., Brownian) motion of water molecules within the tumor mass, thus identifying cells undergoing apoptosis. We sought to measure the treatment response of prostate cancer in an osseous site to docetaxel, an anti‐CCL2 agent, and combination treatments using DW‐MRI. Measurements of tumor apparent diffusion coefficient (ADC) values were accomplished over time during a 14‐day treatment period and compared to response as measured by bioluminescence imaging and survival studies. The diffusion data provided early predictive evidence of the most effective therapy, with survival data results correlating with the DW‐MRI findings. DW‐MRI is under active investigation in the pre‐clinical and clinical settings to provide a sensitive and quantifiable means for early assessment of cancer treatment outcome. J. Cell. Biochem. 107: 58–64, 2009. © 2009 Wiley‐Liss, Inc.     

A coarse-to-fine approach to prostate boundary segmentation in ultrasound images

Background  

In this paper a novel method for prostate segmentation in transrectal ultrasound images is presented.