Lesion-preserving unpaired image-to-image translation between MRI and CT from ischemic stroke patients

PURPOSE

Multiple medical imaging modalities are used for clinical follow-up ischemic stroke analysis. Mixed-modality datasets are challenging, both for clinical rating purposes and for training machine learning models. While image-to-image translation methods have been applied to harmonize stroke patient images to a single modality, they have only been used for paired data so far. In the more common unpaired scenario, the standard cycle-consistent generative adversarial network (CycleGAN) method is not able to translate the stroke lesions properly. Thus, the aim of this work was to develop and evaluate a novel image-to-image translation regularization approach for unpaired 3D follow-up stroke patient datasets.

METHODS

A modified CycleGAN was used to translate images between 238 non-contrast computed tomography (NCCT) and 244 fluid-attenuated inversion recovery (FLAIR) MRI datasets, two of the most relevant follow-up modalities in clinical practice. We introduced an additional attention-guided mechanism to encourage an improved translation of the lesion and a gradient-consistency loss to preserve structural brain morphology.

RESULTS

The proposed modifications were able to preserve the overall quality provided by the CycleGAN translation. This was confirmed by the FID score and gradient correlation results. Furthermore, the lesion preservation was significantly improved compared to a standard CycleGAN. This was evaluated for location and volume with segmentation models, which were trained on real datasets and applied to the translated test images. Here, the Dice score coefficient resulted in 0.81 and 0.62 for datasets translated to FLAIR and NCCT, respectively, compared to 0.57 and 0.50 for the corresponding datasets translated using a standard CycleGAN. Finally, an analysis of the distribution of mean lesion intensities showed substantial improvements.

CONCLUSION

The results of this work show that the proposed image-to-image translation method is effective at preserving stroke lesions in unpaired modality translation, supporting its potential as a tool for stroke image analysis in real-life scenarios.

Dementia in Convolutional Neural Networks: Using Deep Learning Models to Simulate Neurodegeneration of the Visual System

Although current research aims to improve deep learning networks by applying knowledge about the healthy human brain and vice versa, the potential of using such networks to model and study neurodegenerative diseases remains largely unexplored. In this work, we present an in-depth feasibility study modeling progressive dementia in silico with deep convolutional neural networks. Therefore, networks were trained to perform visual object recognition and then progressively injured by applying neuronal as well as synaptic injury. After each iteration of injury, network object recognition accuracy, saliency map similarity between the intact and injured networks, and internal activations of the degenerating models were evaluated. The evaluation revealed that cognitive function of the network progressively decreased with increasing injury load whereas this effect was much more pronounced for synaptic damage. The effects of neurodegeneration found for the in silico model are especially similar to the loss of visual cognition seen in patients with posterior cortical atrophy.

An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction

OBJECTIVE

Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.

MATERIALS AND METHODS

2025 T1-weighted magnetic resonance imaging scans were used to investigate the effect of sample sizes on FL and TM for brain age prediction. We evaluated models across 18 scenarios varying the number of samples per site (1, 2, 5, 10, and 20) and the number of training rounds (20, 40, and 200).

RESULTS

Our results demonstrate that the TM outperforms FL, for every sample size examined. In the extreme case when each site provided only one sample, FL achieved a mean absolute error (MAE) of 18.9 ± 0.13 years, while the TM achieved a MAE of 6.21 ± 0.50 years, comparable to central learning (MAE = 5.99 years).

DISCUSSION

Although FL is more commonly used, our study demonstrates that TM is the best implementation for small sample sizes.

CONCLUSION

The TM offers new opportunities to apply machine learning models in rare diseases and pediatric research but also allows even small hospitals to contribute small datasets.

The use of acrylic yarn modified with amidoxime and carboxylate-containing polymer for lead removal from drinking water

Amidoxime and carboxylate-containing polymer adsorbents derived from acrylic yarn exhibit high adsorption capacity for lead (Pb2+) ions in water.

Modeling Neurodegeneration in silico With Deep Learning

Deep neural networks, inspired by information processing in the brain, can achieve human-like performance for various tasks. However, research efforts to use these networks as models of the brain have primarily focused on modeling healthy brain function so far. In this work, we propose a paradigm for modeling neural diseases in silico with deep learning and demonstrate its use in modeling posterior cortical atrophy (PCA), an atypical form of Alzheimer’s disease affecting the visual cortex. We simulated PCA in deep convolutional neural networks (DCNNs) trained for visual object recognition by randomly injuring connections between artificial neurons. Results showed that injured networks progressively lost their object recognition capability. Simulated PCA impacted learned representations hierarchically, as networks lost object-level representations before category-level representations. Incorporating this paradigm in computational neuroscience will be essential for developing in silico models of the brain and neurological diseases. The paradigm can be expanded to incorporate elements of neural plasticity and to other cognitive domains such as motor control, auditory cognition, language processing, and decision making.

Supervised machine learning tools: a tutorial for clinicians

In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.

Encapsulation-free controlled release: Electrostatic adsorption eliminates the need for protein encapsulation in PLGA nanoparticles

Encapsulation of therapeutic molecules within polymer particles is a well-established method for achieving controlled release, yet challenges such as low loading, poor encapsulation efficiency, and loss of protein activity limit clinical translation. Despite this, the paradigm for the use of polymer particles in drug delivery has remained essentially unchanged for several decades. By taking advantage of the adsorption of protein therapeutics to poly(lactic-co-glycolic acid) (PLGA) nanoparticles, we demonstrate controlled release without encapsulation. In fact, we obtain identical, burst-free, extended-release profiles for three different protein therapeutics with and without encapsulation in PLGA nanoparticles embedded within a hydrogel. Using both positively and negatively charged proteins, we show that short-range electrostatic interactions between the proteins and the PLGA nanoparticles are the underlying mechanism for controlled release. Moreover, we demonstrate tunable release by modifying nanoparticle concentration, nanoparticle size, or environmental pH. These new insights obviate the need for encapsulation and offer promising, translatable strategies for a more effective delivery of therapeutic biomolecules.

Correlation of bone marrow aspiration and biopsy findings in diagnosing hematological disorders - a study of 89 cases

Background: Bone marrow examination is an important diagnostic tool to evaluate various disorders which includes both neoplastic and non- neoplastic hematological diseases. Few studies have compared the relative value of aspirate with trephine biopsy. The present study was conducted to compare the role of bone marrow aspirate and trephine biopsy to formulate an effective and rapid method for diagnosing wide spectrum of hematological diseases. Materials and Methods: This is a three year retrospective study done from July 2010 to June 2013. A total of 95 cases presented with clinical haematological disorders; of which only 89 were biopsied and the correlation done. All the smears and sections were reviewed for morphological details and findings on aspirate and biopsy and compared to each other. Results: Out of the 89 cases selected for study; bone marrow aspiration revealed diagnostic materials in 75 cases and 14 cases were inconclusive for a definite diagnosis. The diagnostic accuracy of the bone marrow aspiration cytology was 84.26%. Eighty eight cases were diagnosed on trephine biopsy of bone marrow with diagnostic accuracy of 98.87%. Conclusion: Both the aspiration cytology and trephine biopsy complement each other for evaluating any haematological disorder. Though cellular morphology is better understood in marrow aspirates and is equally effective to biopsy in diagnosing various anemias and leukemias; however it is the histopathological study of trephine biopsy that gives well preserved marrow architecture with its all cellular and stromal components. modalities including radiological, microbiological and serological tests. DOI: http://dx.doi.org/10.3126/jpn.v4i7.10294 Journal of Pathology of Nepal (2014) Vol. 4, 534-538

HLA antigen distribution in renal transplant recipients and donors

BACKGROUND

HLA typing analysis is important in renal transplant patient. This study is the first report from Nepal to find out distribution of HLA A, B, DR antigen in live related renal transplant recipients and donors from Nepal. The aim of this study was to investigate the distribution of HLA in the live related renal transplant recipients and donors of Nepal.

METHODS

In a retrospective study, HLA patterns were defined in 100 live related renal transplant recipients and donors. One year study is done from June 2011 to May 2012. The study was done by using sequence specific oligonucleotides primers and polymerase chain reaction and assay. Allele frequencies were obtained by direct counting.

RESULTS

A total of 12 HLA-A, 15 HLA-B and 13 HLA-DRB1 alleles were identified at the four-digit level in the live related renal transplant recipients and donors of Nepal. High frequency alleles were HLA-A*11 (34.5%), A*24 (17%), A*33 (13%); HLA-B*15(27%), B*35(19%), B*40 (10%); HLA-DRB1*15 (33.5%), DRB1*12 (21.4%) and DRB1*04 (7.32%).

CONCLUSIONS

These results showed considerable heterogeneity in both HLA class I and class II antigens. To reduce the risk of allograft rejection, transplantation from HLA matched donors is recommended.

Histomorphological spectrum of masses of the nasal cavity, paranasal sinuses and nasopharynx

Background: Swellings of nasal cavity, paranasal sinuses and nasopharynx have infl icted man from time immemorial. Nose is the most prominent part of the face with substantial aesthetic and functional signifi cance. A variety of non-neoplastic and neoplastic conditions involve the nasal cavity, paranasal sinuses and nasophaynx, and these are very common lesions encountered in clinical practice. Materials and Methods: This retrospective cross-sectional study was done in the Department of Pathology, Kathmandu Model Hospital for a period of 5 years from August 2007 to August 2012. Demographic data including age, sex and clinical presentation were obtained from the histopathology records. Results: A total of 148 samples of tissue sent for histopathology were studied, out of which 119 were nonneoplastic and 29 were neoplastic lesions. A slight female preponderance was observed. Infl ammatory nasal polyp was the most common non-neoplastic lesions encountered accounting for a total of 106 cases (89%). Similarly, inverted papilloma was the most common benign lesion (6 cases) and nasopharyngeal carcinoma was the most common malignant lesion (5 cases). Conclusion: Sino-nasal masses have various differential diagnoses. Malignancy should be distinguished from non-malignant lesions. A detailed history, clinical examination and most importantly, thorough histopathological evaluation are essential components of workup of patients for timely medical intervention. Journal of Pathology of Nepal (2013) Vol. 3, No.1, Issue 5, 351-355 DOI: http://dx.doi.org/10.3126/jpn.v3i5.7857

A hydrogel composite system for sustained epi-cortical delivery of Cyclosporin A to the brain for treatment of stroke

Stimulation of endogenous neural stem/progenitor cells (NSPCs) with therapeutic factors holds potential for the treatment of stroke. Cyclosporin A (CsA) is a particularly promising candidate molecule because it has been shown to act as a survival factor for these cells over a period of weeks both in vitro and in vivo; however, systemically-delivered CsA compromises the entire immune system, necessitating sustained localized delivery. Herein we describe a local delivery strategy for CsA using an epi-cortical hydrogel of hyaluronan-methylcellulose (HAMC) as the drug reservoir. Three methods of incorporating the drug into the hydrogel (solubilized, particulate, and poly(lactic-co-glycolic) acid (PLGA) microsphere-encapsulated) resulted in tunable release, spanning a period of hours to weeks. Importantly, PLGA-encapsulated CsA released from the hydrogel had equivalent bioactivity to fresh drug as measured by the neurosphere assay. Moreover, when CsA was released from the PLGA/HAMC composite that was injected on the cortex of adult mice, CsA was detected in the NSPC niche at a constant concentration for at least 24days post-implant. Thus this hydrogel composite system may be promising for the treatment of stroke.

Sonographic assessment of placental migration in second trimester low lying placenta

To assess the migration of low lying placenta diagnosed in the second trimester ultrasonogram (USG). All the women attending antenatal OPD clinic had undergone routine obstetric USG in the second trimester (14 weeks onwards). Those cases who had low lying placenta lower edge of placenta within 3.0 cms from the cervical internal os were included in the study. These cases were subjected to be followed up at 4 weekly interval to repeated serial ultrasonogram by Transabdominal and/or Transvaginal USG well through 3rd trimester of pregnancy or delivery which ever was earlier. Of the total 1229 second trimester USG, 312 (25.3%) women had low lying placenta in the second trimester. Follow up of this 312 cases indicated that in 288 (92.4%) cases it had migrated to upper segment by 3rd trimester. The migration of placenta was 92.4% and 68.0 % where the distance between the leading edge of placenta and cervical internal os was more than 2.0 cm or less than 2 cm respectively. Migration was not observed in women where the distance was less than 1.5 cm. Placental migration was 94.5% in anteriorly situated placenta and 90.2% in posteriorly situated placenta. The rate of placental migration was 95.1%, 77.7%, 55.5% in women who had previous normal delivery, previous caesarean delivery and prior history of dilatation and curettage (D & C) or manual removal of placenta (MRP), respectively. The prevalence of low lying placenta in 2nd trimester is 25.3%, which reduces to 7.3% at term. The rate of placental migration was over 90.0%. Factor like initial distance between the lower edge of the placental and cervical internal os. placental position and previous birth by caesarean section influence the placental migration.

Co-expression vs. co-infection using baculovirus expression vectors in insect cell culture: Benefits and drawbacks

The baculovirus expression vector system (BEVS) is a versatile and powerful platform for protein expression in insect cells. With the ability to approach similar post-translational modifications as in mammalian cells, the BEVS offers a number of advantages including high levels of expression as well as an inherent safety during manufacture and of the final product. Many BEVS products include proteins and protein complexes that require expression from more than one gene. This review examines the expression strategies that have been used to this end and focuses on the distinguishing features between those that make use of single polycistronic baculovirus (co-expression) and those that use multiple monocistronic baculoviruses (co-infection). Three major areas in which researchers have been able to take advantage of co-expression/co-infection are addressed, including compound structure-function studies, insect cell functionality augmentation, and VLP production. The core of the review discusses the parameters of interest for co-infection and co-expression with time of infection (TOI) and multiplicity of infection (MOI) highlighted for the former and the choice of promoter for the latter. In addition, an overview of modeling approaches is presented, with a suggested trajectory for future exploration. The review concludes with an examination of the gaps that still remain in co-expression/co-infection knowledge and practice.

Estimation of mental effort in learning visual search by measuring pupil response

Perceptual learning refers to the improvement of perceptual sensitivity and performance with training. In this study, we examined whether learning is accompanied by a release from mental effort on the task, leading to automatization of the learned task. For this purpose, we had subjects conduct a visual search for a target, defined by a combination of orientation and spatial frequency, while we monitored their pupil size. It is well known that pupil size reflects the strength of mental effort invested in a task. We found that pupil size increased rapidly as the learning proceeded in the early phase of training and decreased at the later phase to a level half of its maximum value. This result does not support the simple automatization hypothesis. Instead, it suggests that the mental effort and behavioral performance reflect different aspects of perceptual learning. Further, mental effort would be continued to be invested to maintain good performance at a later stage of training.

The effect of retinal illuminance on visual motion priming

The perceived direction of a directionally ambiguous stimulus is influenced by the moving direction of a preceding priming stimulus. Previous studies have shown that a brief priming stimulus induces positive motion priming, in which a subsequent directionally ambiguous stimulus is perceived to move in the same direction as the primer, while a longer priming stimulus induces negative priming, in which the following ambiguous stimulus is perceived to move in the opposite direction of the primer. The purpose of this study was to elucidate the underlying mechanism of motion priming by examining how retinal illuminance and velocity of the primer influences the perception of priming. Subjects judged the perceived direction of 180-deg phase-shifted (thus directionally ambiguous) sine-wave gratings displayed immediately after the offset of a primer stimulus. We found that perception of motion priming was greatly modulated by the retinal illuminance and velocity of the primer. Under low retinal illuminance, positive priming nearly disappeared even when the effective luminance contrast was equated between different conditions. Positive priming was prominent when the velocity of the primer was low, while only negative priming was observed when the velocity was high. These results suggest that the positive motion priming is induced by a higher-order mechanism that tracks prominent features of the visual stimulus, while a directionally selective motion mechanism induces negative motion priming.

Deep-seated thoracic and abdominal lesions: usefulness of ultrasound guided fine needle aspiration cytology, a 3 year experience

Three hundred twenty patients were subjected to ultrasound guided fine needle aspiration cytology (FNAC) over a 3 year period (April 2006 - March 2009). These included liver (125 cases), lung (81 cases), abdominal and mediastinal lymph nodes (29 cases), ovary (14 cases), omentum (12 cases), pancreas (10 cases), kidney (10 cases), mediastinum (8 cases), gall bladder (8 cases) etc. The aim of this study was to evaluate the overall utility of ultrasonographic guided FNAC in the diagnosis of abdominal and thoracic lesions. In 264 cases (82.5%), FNAC was diagnostic with commonest diagnosis being malignant neoplasm (70.0%). 14 cases (4.4%) were suspicious of malignancy and remaining 42 (13.1%) cases either didn't reveal diagnostic material or they were inconclusive. In liver, Metastatic adenocarcinoma is the commonest tumor, while in lung; the commonest lesion is non-small cell carcinoma. Benign neoplasm (3.1%) and non neoplastic lesion (9.4%) were also diagnosed by FNAC. Rare sites like oesophagus and duodenum were also aspirated. Complication rate was too low (0.9%) in this study. USG guided FNAC, in conjunction with clinico-radiological parameters are accurate and safe in diagnosing deep-seated mass lesions in the thorax and abdomen.

Comparative analyses of cytohistologic techniques in diagnoses of lung lesions

Background: The use of cytological methods in the diagnosis of malignant lesions of the respiratory tract has been generally acclaimed as one of its most successful applications. Flexible fiberoptic bronchoscopy revolutionized respiratory cytology, as bronchial brushings, broncho-alveolar lavage and bronchial forceps biopsy became more easy, accessible and popular, shifting the emphasis from diagnosis of advanced malignancy in inoperable patients to the use of cytology as a first line diagnostic and management tool. Respiratory tract cytology is well established throughout the world as a diagnostic procedure in the evaluation of patient with suspected lung malignancy. Materials and Methods: A prospective study was conducted on 50 patients divided in two groups who underwent fiberoptic bronchoscopy during the period from November 2007 to October 2008 at the Department of Cardiovascular and Thoracic Unit, Bir Hospital. Group I consisted of 35 cases of suspected lung malignancy on clinical and radiological examination, while group II consisted of 15 cases of non-neoplastic lung diseases. Results: Bronchial brushing and forceps biopsy showed a sensitivity of 50% and 84.21% respectively in the diagnosis of malignancy. Broncho-alveolar lavage revealed malignancy in 66.7% patients. Transthoracic needle aspiration had the highest sensitivity of 100% whereas bronchial wash was revealed malignancy only in 17.4% of the cases. Conclusion: Combination of various cytohistological techniques complements each other and enhances the diagnostic efficacy of various neoplastic and non-neoplastic lung diseases. Bronchial brushing, forceps biopsy and transthoracic needle aspiration are complimentary in diagnosis of various lung malignancies whereas broncho-alveolar lavage is a useful procedure in detection of infections diseases. Keywords: Fiberoptic bronchoscopy; Lund cancer; Infection; Cytohistologic technique DOI: http://dx.doi.org/10.3126/jpn.v1i2.5407 JPN 2011; 1(2): 126-130

Ultrasound and computed tomography guided fine needle aspiration cytology in diagnosing intra-abdominal and intra-thoracic lesions

Background: Ultrasonography and computed tomography guided fine needle aspiration cytology has an important role in diagnosing intraabdominal and intrathoracic mass lesions. It has an accuracy of 70-90%, depending on the site under evaluation. Materials and Methods: This retrospective study was done in the Department of Pathology, Kathmandu Model Hospital, between June 2006 and November 2010. The study included 53 abdominal and 47 thoracic masses. The cytological diagnosis was correlated with clinical and radiological data to arrive at a final diagnosis. Results: Fine needle aspiration cytology was performed in various anatomic sites: liver (28 cases), pancreas (8 cases), lymph nodes (7 cases), ovary and gall bladder (3 cases each) and 2 cases each of gastrointestinal tract and omentum. Thoracic aspirations were done from the lung (44 cases) and mediastinum (3 cases). The most common malignancy encountered in the abdomen was hepatocellular carcinoma (12 cases). Non-small cell carcinoma was the most common diagnoses amongst the lung lesions (15 cases). Conclusion: Ultrasonography and computed tomography guided fine needle aspiration cytology had a high sensitivity and specificity in diagnosing deep seated lesions. Keywords: Computed tomography; Deep-seated masses; Fine needle aspiration; Ultrasound DOI: 10.3126/jpn.v1i1.4444 Journal of Pathology of Nepal (2011) Vol.1, 17-21

Ileo-psoas muscle metastasis from pulmonary carcinoma

Metastatic disease to muscle is rare and may be misdiagnosed when it is the presenting symptom, particularly in the absence of a known primary tumor. Skeletal muscle metastasis as a mode of presentation of primary lung cancer is an unusual phenomenon. Here, we report a case of ileo-psoas muscle metastasis from lung cancer as the initial clinical manifestation in a 58 year-old male with a personal history of heavy smoking. Excisional biopsy of the mass in the ileo-psoas muscle revealed metastatic adenocarcinoma. Computed tomography scan of the chest for a primary search was done and found to be pulmonary carcinoma. DOI: http://dx.doi.org/10.3126/jpn.v2i3.6033 JPN 2012; 2(3): 251-253