An Efficient Capsule-based Network for 2D Left Ventricle Segmentation in Echocardiography Images.

The segmentation of cardiac chambers is essential for the clinical diagnosis and treatment of cardiovascular diseases. It is demonstrated that in cardiac disease, the left ventricle (LV) is extensively involved. Therefore, segmentation of the LV in echocardiographic images is critical for the precise evaluation of factors that influence cardiac function such as LV volume, ejection fraction, and LV mass. Although these measurements could be obtained by manual segmentation of the LV, it would be time-consuming and inaccurate because of the poor quality and low contrast of these images. Convolutional neural networks, commonly referred to as CNNs, have emerged as a highly favored deep learning technique for medical image segmentation. Despite their popularity, the pooling layers in CNNs ignore the spatial information and do not consider the part-whole hierarchy relationships. Furthermore, they require a large training dataset and a large number of parameters. Therefore, Capsule Networks are proposed to address the CNNs limitations. In this study, for the first time, an optimized capsule-based network for object segmentation called SegCaps is proposed to achieve accurate LV segmentation on echocardiography images applied to the CAMUS dataset. The result was compared against the standard 2D-UNet. The modified SegCaps and 2D-UNet achieved an average Dice similarity coefficient (DSC) of 84.48% and 83.28% on LV segmentation, respectively. The capabilities of the CapsNet led to an improvement of 1.44% in DSC with 92.77% fewer parameters than the U-Net. The results indicate that the proposed method leads to accurate and efficient LV segmentation.Clinical Relevance- From a clinical point of view, our findings lead to more precise evaluations of critical cardiac parameters, including ejection fraction as well as left ventricle volume at end-diastole and end-systole.

A Hybrid Capsule Network for Automatic 3D Mandible Segmentation applied in Virtual Surgical Planning.

Automatic mandible segmentation of CT images is an essential step to achieve an accurate preoperative prediction of an intended target in three-dimensional (3D) virtual surgical planning. Segmentation of the mandible is a challenging task due to the complexity of the mandible structure, imaging artifacts, and metal implants or dental filling materials. In recent years, utilizing convolutional neural networks (CNNs) have made significant improvements in mandible segmentation. However, aggregating data at pooling layers in addition to collecting and labeling a large volume of data for training CNNs are significant issues in medical practice. We have optimized data-efficient 3D-UCaps to achieve the advantages of both the capsule network and the CNN, for accurate mandible segmentation on volumetric CT images. A novel hybrid loss function based on a weighted combination of the focal and margin loss functions is also proposed to handle the problem of voxel class imbalance. To evaluate the performance of our proposed method, a similar experiment was conducted with the 3D-UNet. All experiments are performed on the public domain database for computational anatomy (PDDCA). The proposed method and 3D-UNet achieved an average dice coefficient of 90% and 88% on the PDDCA, respectively. The results indicate that the proposed method leads to accurate mandible segmentation and outperforms the popular 3D-UNet model. It is concluded that the proposed approach is very effective as it requires more than 50% fewer parameters than the 3D-UNet.

Clinical standards for the diagnosis, treatment and prevention of TB infection.

BACKGROUND: Tuberculosis (TB) preventive therapy (TPT) decreases the risk of developing TB disease and its associated morbidity and mortality. The aim of these clinical standards is to guide the assessment, management of TB infection (TBI) and implementation of TPT.METHODS: A panel of global experts in the field of TB care was identified; 41 participated in a Delphi process. A 5-point Likert scale was used to score the initial standards. After rounds of revision, the document was approved with 100% agreement.RESULTS: Eight clinical standards were defined: Standard 1, all individuals belonging to at-risk groups for TB should undergo testing for TBI; Standard 2, all individual candidates for TPT (including caregivers of children) should undergo a counselling/health education session; Standard 3, testing for TBI: timing and test of choice should be optimised; Standard 4, TB disease should be excluded prior to initiation of TPT; Standard 5, all candidates for TPT should undergo a set of baseline examinations; Standard 6, all individuals initiating TPT should receive one of the recommended regimens; Standard 7, all individuals who have started TPT should be monitored; Standard 8, a TBI screening and testing register should be kept to inform the cascade of care.CONCLUSION: This is the first consensus-based set of Clinical Standards for TBI. This document guides clinicians, programme managers and public health officers in planning and implementing adequate measures to assess and manage TBI.

Accurate Automatic Glioma Segmentation in Brain MRI images Based on CapsNet.

Glioma is a highly invasive type of brain tumor with an irregular morphology and blurred infiltrative borders that may affect different parts of the brain. Therefore, it is a challenging task to identify the exact boundaries of the tumor in an MR image. In recent years, deep learning-based Convolutional Neural Networks (CNNs) have gained popularity in the field of image processing and have been utilized for accurate image segmentation in medical applications. However, due to the inherent constraints of CNNs, tens of thousands of images are required for training, and collecting and annotating such a large number of images poses a serious challenge for their practical implementation. Here, for the first time, we have optimized a network based on the capsule neural network called SegCaps, to achieve accurate glioma segmentation on MR images. We have compared our results with a similar experiment conducted using the commonly utilized U-Net. Both experiments were performed on the BraTS2020 challenging dataset. For U-Net, network training was performed on the entire dataset, whereas a subset containing only 20% of the whole dataset was used for the SegCaps. To evaluate the results of our proposed method, the Dice Similarity Coefficient (DSC) was used. SegCaps and U-Net reached DSC of 87.96% and 85.56% on glioma tumor core segmentation, respectively. The SegCaps uses convolutional layers as the basic components and has the intrinsic capability to generalize novel viewpoints. The network learns the spatial relationship between features using dynamic routing of capsules. These capabilities of the capsule neural network have led to a 3% improvement in results of glioma segmentation with fewer data while it contains 95.4% fewer parameters than U-Net.

Evaluation of multi-wavelengths LED-based photoacoustic imaging for maximum safe resection of glioma: a proof of concept study.

PURPOSE: A real-time intra-operative imaging modality is required to update the navigation systems during neurosurgery, since precise localization and safe maximal resection of gliomas are of utmost clinical importance. Different intra-operative imaging modalities have been proposed to delineate the resection borders, each with advantages and disadvantages. This preliminary study was designed to simulate the photoacoustic imaging (PAI) to illustrate the brain tumor margin vessels for safe maximal resection of glioma. METHODS: In this study, light emitting diode (LED)-based PAI was selected because of its lower cost, compact size and ease of use. We developed a simulation framework based on multi-wavelength LED-based PAI to further facilitate PAI during neurosurgery. This framework considers a multilayer model of the tumoral and normal brain tissue. The simulation of the optical fluence and absorption map in tissue at different depths was computed by Monte Carlo. Then, the propagation of initial photoacoustic pressure was simulated by using k-wave toolbox. RESULTS: To evaluate the LED-based PAI, we used three evaluation criteria: signal-to-noise ratio (SNR), contrast ratio (CR) and full width of half maximum (FWHM). Results showed that by using proper wavelengths, the vessels were recovered with the same axial and lateral FWHM. Furthermore, by increasing the wavelength from 532 to 1064 nm, SNR and CR were increased in the deep region. The results showed that vessels with larger diameters at same wavelength have a higher CR with average improvement 28%. CONCLUSION: Multi-wavelength LED-based PAI provides detailed images of the blood vessels which are crucial for detection of the residual glioma: The longer wavelengths like 1064 nm can be used for the deeper tumor margins, and the shorter wavelengths like 532 nm for tumor margins closer to the surface. LED-based PAI may be considered as a promising intra-operative imaging modality to delineate tumor margins.

Co-Sparse Analysis Model Based Image Registration to Compensate Brain Shift by Using Intra-Operative Ultrasound Imaging.

Notwithstanding the widespread use of image guided neurosurgery systems in recent years, the accuracy of these systems is strongly limited by the intra-operative deformation of the brain tissue, the so-called brain shift. Intra-operative ultrasound (iUS) imaging as an effective solution to compensate complex brain shift phenomena update patients coordinate during surgery by registration of the intra-operative ultrasound and the pre-operative MRI data that is a challenging problem.In this work a non-rigid multimodal image registration technique based on co-sparse analysis model is proposed. This model captures the interdependency of two image modalities; MRI as an intensity image and iUS as a depth image. Based on this model, the transformation between the two modalities is minimized by using a bimodal pair of analysis operators which are learned by optimizing a joint co-sparsity function using a conjugate gradient.Experimental validation of our algorithm confirms that our registration approach outperforms several of other state-of-the-art registration methods quantitatively. The evaluation was performed using seven patient dataset with the mean registration error of only 1.83 mm. Our intensity-based co-sparse analysis model has improved the accuracy of non-rigid multimodal medical image registration by 15.37% compared to the curvelet based residual complexity as a powerful registration method, in a computational time compatible with clinical use.

Curvelet based residual complexity objective function for non-rigid registration of pre-operative MRI with intra-operative ultrasound images.

Intra-operative ultrasound as an imaging based method has been recognized as an effective solution to compensate non rigid brain shift problem in recent years. Measuring brain shift requires registration of the pre-operative MRI images with the intra-operative ultrasound images which is a challenging task. In this study a novel hybrid method based on the matching echogenic structures such as sulci and tumor boundary in MRI with ultrasound images is proposed. The matching echogenic structures are achieved by optimizing the Residual Complexity (RC) in the curvelet domain. At the first step, the probabilistic map of the MR image is achieved and the residual image as the difference between this probabilistic map and intra-operative ultrasound is obtained. Then curvelet transform as a sparse function is used to minimize the complexity of residual image. The proposed method is a compromise between feature-based and intensity-based approaches. Evaluation was performed using 14 patients data set and the mean of registration error reached to 1.87 mm. This hybrid method based on RC improves accuracy of nonrigid multimodal image registration by 12.5% in a computational time compatible with clinical use.

Brain-shift compensation by non-rigid registration of intra-operative ultrasound images with preoperative MR images based on residual complexity.

PURPOSE: Compensation for brain shift is often necessary for image-guided neurosurgery, requiring registration of intra-operative ultrasound (US) images with preoperative magnetic resonance images (MRI). A new image similarity measure based on residual complexity (RC) to overcome challenges of registration of intra-operative US and preoperative MR images was developed and tested. METHOD: A new two-stage method based on the matching echogenic structures such as sulci is achieved by optimizing the residual complexity value in the wavelet domain between the ultrasound image and the probabilistic map of the MR image. The proposed method is a compromise between feature-based and intensity-based approaches. Evaluation was performed using a specially designed brain phantom and an in vivo patient data set. RESULT: The results of the phantom data set registration confirmed that the proposed objective function outperforms the accuracy of adapted RC for multi-modal cases by 48 %. The mean fiducial registration error reached 1.17 and 2.14 mm when the method was applied on phantom and clinical data sets, respectively. CONCLUSION: This improved objective function based on RC in the wavelet domain enables accurate non-rigid multi-modal (US and MRI) image registration which is robust to noise. This technology is promising for compensation of intra-operative brain shift in neurosurgery.

A hybrid method for non-rigid registration of intra-operative ultrasound images with pre-operative MR images.

In recent years intra-operative ultrasound images have been used for many procedures in neurosurgery. The registration of intra-operative ultrasound images with preoperative magnetic resonance images is still a challenging problem. In this study a new hybrid method based on residual complexity is proposed for this problem. A new two stages method based on the matching echogenic structures such as sulci is achieved by optimizing the residual complexity (RC) value with quantized coefficients between the ultrasound image and the probabilistic map of MR image. The proposed method is a compromise between feature-based and intensity-based approaches. The evaluation is performed on both a brain phantom and patient data set. The results of the phantom data set confirmed that the proposed method outperforms the accuracy of conventional RC by 39%. Also the mean of fiducial registration errors reached to 1.45, 1.94 mm when the method was applied on phantom and clinical data set, respectively. This hybrid method based on RC enables non-rigid multimodal image registration in a computational time compatible with clinical use as well as being accurate.

A shape based rotation invariant method for ultrasound-MR image registration: A phantom study.

In this work, a new shape based method to improve the accuracy of Brain Ultrasound-MRI image registration is proposed. The method is based on modified Shape Context (SC) descriptor in combination with CPD algorithm. An extensive experiment was carried out to evaluate the robustness of this method against different initialization conditions. As the results prove, the overall performance of the proposed algorithm outperforms both SC and CPD methods. In order to have control over the registration procedure, we simulated the deformations, missing points and outliers according to our Phantom MRI images.

Rapid identification of extensively and extremely drug resistant tuberculosis from multidrug resistant strains; using PCR-RFLP and PCR-SSCP.

BACKGROUND AND OBJECTIVES: Resistance in Mycobacterium tuberculosis is caused by mutations in genes encoding drug targets. Investigators have already demonstrated the existence of mutations in codons 88 to 94 in the gyrA gene and also in codons 1400, 1401, and 1483 of rrs gene among extensively and extremely drug resistant tuberculosis (XDR & XXDR-TB) strains. The aim of this study was to identify the XDR and XXDR-TB stains based on their mutational analysis. MATERIALS AND METHODS: Susceptibility testing against first and second-line anti-tuberculosis drugs was performed by the proportional method. Based on susceptibility results, samples were later analyzed, using PCR-SSCP and PCR-RFLP for detection of mutation in gyrA and rrs genes. RESULTS: Overall, using proportional method, sixty-three strains (64.9%) were identified as MDR, 8(8.2%) as non-MDR and 26 strains (26.8%) were susceptible. Thirty-one cases (31.9%) were amikacin-resistant and 18 (18.5%) samples were ciprofloxacin-resistant. Using PCR-SSCP and PCR-RFLP, we identified 6(6.2%) and 7(7.2%) resistant strains, respectively. Discrepancy in strains was cross-checked by sequencing. The results showed no mutation in 66.6% and 77.4% of CIP and AMK- resistant strains. CONCLUSION: Rapid detection of drug-resistant Mycobacterium tuberculosis using molecular techniques could be effective in determining therapeutic regimen and preventing the spread of XDR and MDR TB in the community. We should still keep in mind that a high number of resistant strains may have no mutation in proposed candidate genes.

Treatment outcome, mortality and their predictors among HIV-associated tuberculosis patients.

The risk of death is significantly higher in HIV-infected patients with tuberculosis (TB). This study aims to evaluate the impact of demographic, clinical and laboratory characteristics on the treatment outcome and mortality of TB/HIV co-infected patients in a tertiary TB centre in Iran. In total, 111 patients were recruited from 2004 to 2007. Mycobacteriological studies and demographic, clinical, and laboratory data from all patients were analysed and predictors of unsuccessful outcomes as well as mortality were determined. The mean age for all 111 TB-HIV patients was 38 ± 9 years (range 22-70) and 107 (96.3%) were men; 104 (93.7%) had a history of drug abuse and 96 (86.4%) had a history of imprisonment. The method of HIV transmission was intravenous drug use in 88 (79.3%). Twenty-three (20.7%) had a history of Category 1 (CAT I) TB treatment and six (5.4%) Category 2 (CAT II) treatment. Combination antiretroviral therapy (cART) was given to 48 (43.2%). No significant associations were found between treatment outcomes or mortality and gender, smoking, drug and alcohol abuse, imprisonment, method of transmission, history of CAT I and CAT II treatments, CD4 counts or adverse effects (P > 0.05). Administration of cART led to significantly better outcomes (P < 0.001). Lower serum albumin levels and low body weight were significantly associated with mortality.

Susceptibility to pulmonary tuberculosis in Iranian individuals is not affected by compound KIR/HLA genotype.

Natural killer (NK) cells have distinctive functional capacities that are likely to contribute both to innate and adaptive immunity to Mycobacterium tuberculosis. Killer cell immunoglobulin-like receptors (KIR) and their ligands, i.e. human leukocyte antigen (HLA) class I molecules contribute partly in regulation of NK cell activity. In this study, the impact of compound KIR/HLA genotype on susceptibility to pulmonary tuberculosis (TB) has been evaluated in Iranian individuals. A total of 107 TB patients and 100 matched healthy controls were genotyped for 17 KIR genes and their three major HLA class I ligand groups (-C1, -C2 and -Bw4: -B Bw4(Ile80) , -B Bw4(Thr80) and -A Bw4) by a polymerase chain reaction-sequence-specific primers assay. Various analyses including distribution of KIR and HLA ligand genes and genotypes, frequency of inhibitory and activating KIR+HLA combinations and compound genotype status regarding balance of inhibitory and activating components showed no significant difference between patient and control groups. These findings may suggest that compound KIR/HLA genotype has no major impact on limiting Mycobacterium tuberculosis infection.

Standardised second-line treatment of multidrug-resistant tuberculosis during pregnancy.

We describe the efficacy and outcome of standardised second-line anti-tuberculosis (TB) medications during pregnancy. Treatment outcomes of five pregnant women with documented multidrug-resistant TB (MDR-TB) referred to the National Research Institute of Tuberculosis and Lung Diseases from 2003 to 2009 were analysed in two categories, maternal and neonatal. Patients became pregnant during treatment for MDR-TB without any changes in their anti-tuberculosis regimen. None of them had any adverse effects during pregnancy and delivery. No adverse effects were observed in mothers or neonates. The treatment of MDR-TB during pregnancy with a standardised second-line regimen in this study population was safe, with an acceptable rate of treatment success.

Association between TNF-Alpha (-857) Gene Polymorphism and Susceptibility to Tuberculosis.

BACKGROUND: TNF-α as a pro-inflammatory cytokine plays a key role in host defense against tuberculosis (TB). Presence of mutation in TNF-α gene can influence the effectiveness, performance and capability of immune responses against this infection. The Aim of this study was to investigate the frequency of TNF-α alleles and its relationship with susceptibility to TB and TNF-α gene variations. METHODS: A case-control study was conducted and 103 healthy controls and 93 TB patients were enrolled. Genotype of TNF-238, TNF -244, TNF-308, TNF -857 and TNF-863 were distinguished using PCR-RFLP method. RESULTS: TNF-857 and TNF-863 were in high frequency mutation regions in a population level, and a significant difference at TNF-857 was noticed between the two groups of case and control. CONCLUSION: Presence of mutation in TNF-857 region probably increases the host susceptibility to mycobacterial infection. Genotyping of these regions in combination with other factors can be used for screening of high risk persons. According to high distribution of mutations in TNF-857 and TNF-863 regions, further studies on association of these regions is suggested.

Human infections due to Mycobacterium lentiflavum: first report in Iran.

Non-tuberculosis mycobacteria (NTM), as certain species of mycobacteria, can affect human in several ways. In the preceding years, the rate of NTM detection has risen in both immunocompromised and immunocompetent patients. On the other hand, several reports have debated the possibility of co-infection of both Mycobcateriu tuberculosis (MTB) and NTM in individuals that puts the role of NTM in disease manifestations under question. Moreover, it is now proven that some of the cases that are identified as anti-TB treatment failure or suspected for drug resistance are actually NTM.

Phospholipase C in Beijing strains of Mycobacterium tuberculosis.

BACKGROUND AND OBJECTIVES: Phospholipase of Mycobacterium tuberculosis plays an important role in pathogenesis through breaking up phospholipids and production of diacylglycerol. In this study, we examined the Beijing strains of Mycobacterium tuberculosis isolated from Iranian patients for the genes encoding this enzyme. MATERIALS AND METHODS: DNA extraction was performed using CTAB (cetyltrimethylammonium bromide) from positive culture specimens in tuberculosis patients. PCR was then used to amplify the plcA, plcB, plcC genes of Beijing strain, and non-Beijing strains were identified by spoligotyping. RESULTS: Of 200 specimens, 19 (9.5%) were Beijing strain and 181 (90.5%) were non-Beijing strains. The results of PCR for Beijing strains were as follows: 16 strains (84.2%) were positive for plcA, 17 (89.4%) were positive for plcB and 17 (89.4%) were positive for plcC genes. The standard strain (H37RV) was used as control. CONCLUSION: The majority of Beijing strains have phospholipase C genes which can contribute to their pathogenesis but we need complementary studies to confirm the role of phospholipase C in pathogenecity of Mycobacterium tuberculosis.

Beijing genotype and other predominant Mycobacterium tuberculosis spoligotypes observed in Mashhad city, Iran.

PURPOSE: The purpose of this study was to understand the molecular epidemiology of tuberculosis in Khorasan province of Iran was studied by spoligotyping 113 Mycobacterium tuberculosis isolates. The spoligotyping results were in comparison to the word Spoligotyping Database of Institute Pasteur de Guadeloupe (SpolDB4). Spoligotyping data from Iran has rarely been described and there is limited information on the major circulating clades of M. tuberculosis in Iran. MATERIALS AND METHODS: Spoligotyping was performed on 113 M. tuberculosis isolates from Mashhad patients between November 2004 and September 2005. RESULTS: The study found 57 spoligopatterns. 17 clusters and 32 true orphan genotype. The biggest cluster with 13 isolates had not been previously reported. The Beijing genotype was seen in eight (7.1%) isolates. CONCLUSIONS: Genotyping and Spoligotyping gives a unifying framework for both epidemiology and evolutionary analysis of M. tuberculosis populations.