Effect of high frequency repetitive transcranial magnetic stimulation (rTMS) on the balance and the white matter integrity in patients with relapsing-remitting multiple sclerosis: A long-term follow-up study

OBJECTIVES

Repetitive Transcranial Magnetic Stimulation (rTMS) is considered as a safe and non-invasive developing technique used as a therapeutic method for patients with Relapsing-Remitting Multiple Sclerosis (RRMS) who suffer from disturbances in gait and balance. The aim of our study is to evaluate the long-term effect of high frequency rTMS as a therapeutic option for truncal ataxia in RRMS patients and to assess its impact on the integrity of the white matter (WMI), measured in the form of anisotropy metrics using diffusion tensor imaging (DTI).

METHODS

The study was conducted in two phases: phase I; a randomized, single-blind, sham-controlled phase and phase II was a 12 months longitudinal open-label prospective phase. Phase I of the trial involved the randomization of 43 patients with RRMS and truncal ataxia to either real (n = 20) or sham (n = 19) rTMS (2 participants from each treatment group were excluded from the study; one developed a relapse before treatment, 2 declined to participate, and one did not show up). Phase II involved providing 12 actual treatments cycles to all patients; each cycle length is 4 weeks, repeated four times on a trimonthly basis, forming a total of 48 sessions. DTI was used for assessment of the WMI. All patients performed DTI 3 times: Imaging sessions were conducted at the screening visit, at the end of phase I, and after the last session in phase II for the first, second and third sessions respectively. A figure-of-8-shape coil, employing rTMS protocol and located over the cerebellum, was used. rTMS protocol is formed of 20 trains formed of 50 stimuli with 20 s apart (5 Hz of 80 % of resting Motor Threshold "MT"). The Berg Balance Scale (BBS), Time up and go (TUG) test, and 10-m walk test (10MWT) were first evaluated at the start of each cycle and just after the final rTMS session.

RESULTS

The genuine rTMS group's 10MWT, TUG, and BBS showed substantial improvement (p < 0.01), which is continued to be improved throughout the study Timeline, with a significant difference observed following the final rTMS session (P< 0.001). A longitudinal increase in FA was observed in both the Cerebello-Thalamo-Cortical (CTC) and Cortico-Ponto-Cerebellar (CPC) bilateral, as indicated by means of Fractional Anisotropy (FA) measures (p < 0.05).

CONCLUSION

In ataxic RRMS patients, high frequency rTMS over the cerebellum has a long-term beneficial impact on both balance and WMI.

Center-Focused Affinity Loss for Class Imbalance Histology Image Classification

Early-stage cancer diagnosis potentially improves the chances of survival for many cancer patients worldwide. Manual examination of Whole Slide Images (WSIs) is a time-consuming task for analyzing tumor-microenvironment. To overcome this limitation, the conjunction of deep learning with computational pathology has been proposed to assist pathologists in efficiently prognosing the cancerous spread. Nevertheless, the existing deep learning methods are ill-equipped to handle fine-grained histopathology datasets. This is because these models are constrained via conventional softmax loss function, which cannot expose them to learn distinct representational embeddings of the similarly textured WSIs containing an imbalanced data distribution. To address this problem, we propose a novel center-focused affinity loss (CFAL) function that exhibits 1) constructing uniformly distributed class prototypes in the feature space, 2) penalizing difficult samples, 3) minimizing intra-class variations, and 4) placing greater emphasis on learning minority class features. We evaluated the performance of the proposed CFAL loss function on two publicly available breast and colon cancer datasets having varying levels of imbalanced classes. The proposed CFAL function shows better discrimination abilities as compared to the popular loss functions such as ArcFace, CosFace, and Focal loss. Moreover, it outperforms several SOTA methods for histology image classification across both datasets.

Clinical outcomes of peripheral nerve interfaces for rehabilitation in paralysis and amputation: a literature review

Peripheral nerve interfaces (PNIs) are electrical systems designed to integrate with peripheral nerves in patients, such as following central nervous system (CNS) injuries to augment or replace CNS control and restore function. We review the literature for clinical trials and studies containing clinical outcome measures to explore the utility of human applications of PNIs. We discuss the various types of electrodes currently used for PNI systems and their functionalities and limitations. We discuss important design characteristics of PNI systems, including biocompatibility, resolution and specificity, efficacy, and longevity, to highlight their importance in the current and future development of PNIs. The clinical outcomes of PNI systems are also discussed. Finally, we review relevant PNI clinical trials that were conducted, up to the present date, to restore the sensory and motor function of upper or lower limbs in amputees, spinal cord injury patients, or intact individuals and describe their significant findings. This review highlights the current progress in the field of PNIs and serves as a foundation for future development and application of PNI systems.

Spinal cord stimulation for chronic pain treatment following sacral chordoma resection: illustrative case

BACKGROUND

Cancer-related or postoperative pain can occur following sacral chordoma resection. Despite a lack of current recommendations for cancer pain treatment, spinal cord stimulation (SCS) has demonstrated effectiveness in addressing cancer-related pain.

OBSERVATIONS

A 76-year-old female with a sacral chordoma underwent anterior osteotomies and partial en bloc sacrectomy. She subsequently presented with chronic pain affecting both buttocks and posterior thighs and legs, significantly impeding her daily activities. She underwent a staged epidural SCS paddle trial and permanent system placement using intraoperative neuromonitoring. The utilization of percutaneous leads was not viable because of her history of spinal fluid leakage, multiple lumbosacral surgeries, and previous complex plastic surgery closure. The patient reported a 62.5% improvement in her lower-extremity pain per the modified Quadruple Visual Analog Scale and a 50% improvement in the modified Pain and Sleep Questionnaire 3-item index during the SCS trial. Following permanent SCS system placement and removal of her externalized lead extenders, she had an uncomplicated postoperative course and reported notable improvements in her pain symptoms.

LESSONS

This case provides a compelling illustration of the successful treatment of chronic pain using SCS following radical sacral chordoma resection. Surgeons may consider this treatment approach in patients presenting with refractory pain following spinal tumor resection.

Tomato maturity recognition with convolutional transformers

Tomatoes are a major crop worldwide, and accurately classifying their maturity is important for many agricultural applications, such as harvesting, grading, and quality control. In this paper, the authors propose a novel method for tomato maturity classification using a convolutional transformer. The convolutional transformer is a hybrid architecture that combines the strengths of convolutional neural networks (CNNs) and transformers. Additionally, this study introduces a new tomato dataset named KUTomaData, explicitly designed to train deep-learning models for tomato segmentation and classification. KUTomaData is a compilation of images sourced from a greenhouse in the UAE, with approximately 700 images available for training and testing. The dataset is prepared under various lighting conditions and viewing perspectives and employs different mobile camera sensors, distinguishing it from existing datasets. The contributions of this paper are threefold: firstly, the authors propose a novel method for tomato maturity classification using a modular convolutional transformer. Secondly, the authors introduce a new tomato image dataset that contains images of tomatoes at different maturity levels. Lastly, the authors show that the convolutional transformer outperforms state-of-the-art methods for tomato maturity classification. The effectiveness of the proposed framework in handling cluttered and occluded tomato instances was evaluated using two additional public datasets, Laboro Tomato and Rob2Pheno Annotated Tomato, as benchmarks. The evaluation results across these three datasets demonstrate the exceptional performance of our proposed framework, surpassing the state-of-the-art by 58.14%, 65.42%, and 66.39% in terms of mean average precision scores for KUTomaData, Laboro Tomato, and Rob2Pheno Annotated Tomato, respectively. This work can potentially improve the efficiency and accuracy of tomato harvesting, grading, and quality control processes.

Neural Graph Refinement for Robust Recognition of Nuclei Communities in Histopathological Landscape

Accurate classification of nuclei communities is an important step towards timely treating the cancer spread. Graph theory provides an elegant way to represent and analyze nuclei communities within the histopathological landscape in order to perform tissue phenotyping and tumor profiling tasks. Many researchers have worked on recognizing nuclei regions within the histology images in order to grade cancerous progression. However, due to the high structural similarities between nuclei communities, defining a model that can accurately differentiate between nuclei pathological patterns still needs to be solved. To surmount this challenge, we present a novel approach, dubbed neural graph refinement, that enhances the capabilities of existing models to perform nuclei recognition tasks by employing graph representational learning and broadcasting processes. Based on the physical interaction of the nuclei, we first construct a fully connected graph in which nodes represent nuclei and adjacent nodes are connected to each other via an undirected edge. For each edge and node pair, appearance and geometric features are computed and are then utilized for generating the neural graph embeddings. These embeddings are used for diffusing contextual information to the neighboring nodes, all along a path traversing the whole graph to infer global information over an entire nuclei network and predict pathologically meaningful communities. Through rigorous evaluation of the proposed scheme across four public datasets, we showcase that learning such communities through neural graph refinement produces better results that outperform state-of-the-art methods.

Transformers for autonomous recognition of psychiatric dysfunction via raw and imbalanced EEG signals

Early identification of mental disorders, based on subjective interviews, is extremely challenging in the clinical setting. There is a growing interest in developing automated screening tools for potential mental health problems based on biological markers. Here, we demonstrate the feasibility of an AI-powered diagnosis of different mental disorders using EEG data. Specifically, this work aims to classify different mental disorders in the following ecological context accurately: (1) using raw EEG data, (2) collected during rest, (3) during both eye open, and eye closed conditions, (4) at short 2-min duration, (5) on participants with different psychiatric conditions, (6) with some overlapping symptoms, and (7) with strongly imbalanced classes. To tackle this challenge, we designed and optimized a transformer-based architecture, where class imbalance is addressed through focal loss and class weight balancing. Using the recently released TDBRAIN dataset (n= 1274 participants), our method classifies each participant as either a neurotypical or suffering from major depressive disorder (MDD), attention deficit hyperactivity disorder (ADHD), subjective memory complaints (SMC), or obsessive-compulsive disorder (OCD). We evaluate the performance of the proposed architecture on both the window-level and the patient-level. The classification of the 2-min raw EEG data into five classes achieved a window-level accuracy of 63.2% and 65.8% for open and closed eye conditions, respectively. When the classification is limited to three main classes (MDD, ADHD, SMC), window level accuracy improved to 75.1% and 69.9% for eye open and eye closed conditions, respectively. Our work paves the way for developing novel AI-based methods for accurately diagnosing mental disorders using raw resting-state EEG data.

Specialty Impact on Patient Outcomes: Paving a Way for an Integrated Approach to Spinal Disorders

Spinal surgical procedures are steadily increasing globally due to broad indications of certain techniques encompassing a wide spectrum of conditions, including degenerative spine disorders, congenital anomalies, spinal metastases, and traumatic spinal fractures. The two specialties, neurosurgery (NS) and orthopedic surgery (OS), both possess the clinical adeptness to perform these procedures. With the advancing focus on comparative effectiveness research, it is vital to compare patient outcomes in spine surgeries performed by orthopedic surgeons and neurosurgeons, given their distinct approaches and training backgrounds to guide hospital programs and physicians to consider surgeon specialty when making informed decisions. Our review of the available literature revealed no significant difference in postoperative outcomes in terms of blood loss, neurological deficit, dural injury, intraoperative complications, and postoperative wound dehiscence in procedures performed by neurosurgeons and orthopedic surgeons. An increase in blood transfusion rates among patients operated by orthopedic surgeons and a longer operative time of procedures performed by neurosurgeons was a consistent finding among several studies. Other findings include a prolonged hospital stay, higher hospital readmission rates, and lower cost of procedures in patients operated on by orthopedic surgeons. A few studies revealed lower sepsis rates unplanned intubation rates and higher incidence of urinary tract infections (UTIs) and pneumonia postoperatively among patient cohorts operated by neurosurgeons. Certain limitations were identified in the studies including the use of large databases with incomplete information related to patient and surgeon demographics. Hence, it is imperative to account for these confounding variables in future studies to alleviate any biases. Nevertheless, it is essential to embrace a multidisciplinary approach integrating the surgical expertise of the two specialties and develop standardized management guidelines and techniques for spinal disorders to mitigate complications and enhance patient outcomes.

Orbital Exenteration for Craniofacial Lesions: A Systematic Review and Meta-Analysis of Patient Characteristics and Survival Outcomes

BACKGROUND

The outcomes of orbital exenteration (OE) in patients with craniofacial lesions (CFLs) remain unclear. The present review summarizes the available literature on the clinical outcomes of OE, including surgical outcomes and overall survival (OS).

METHODS

Relevant articles were retrieved from Medline, Scopus, and Cochrane according to PRISMA guidelines. A systematic review and meta-analysis were conducted on the clinical characteristics, management, and outcomes.

RESULTS

A total of 33 articles containing 957 patients who underwent OE for CFLs were included (weighted mean age: 64.3 years [95% CI: 59.9-68.7]; 58.3% were male). The most common lesion was squamous cell carcinoma (31.8%), and the most common symptom was disturbed vision/reduced visual acuity (22.5%). Of the patients, 302 (31.6%) had total OE, 248 (26.0%) had extended OE, and 87 (9.0%) had subtotal OE. Free flaps (33.3%), endosseous implants (22.8%), and split-thickness skin grafts (17.2%) were the most used reconstructive methods. Sino-orbital or sino-nasal fistula (22.6%), flap or graft failure (16.9%), and hyperostosis (13%) were the most reported complications. Regarding tumor recurrences, 38.6% were local, 32.3% were distant, and 6.7% were regional. The perineural invasion rate was 17.4%, while the lymphovascular invasion rate was 5.0%. Over a weighted mean follow-up period of 23.6 months (95% CI: 13.8-33.4), a weighted overall mortality rate of 39% (95% CI: 28-50%) was observed. The 5-year OS rate was 50% (median: 61 months [95% CI: 46-83]). The OS multivariable analysis did not show any significant findings.

CONCLUSIONS

Although OE is a disfiguring procedure with devastating outcomes, it is a viable option for carefully selected patients with advanced CFLs. A patient-tailored approach based on tumor pathology, extension, and overall patient condition is warranted.

Healthcare lobbying and campaign finance activities of vision-related professional societies, 2015 to 2022

Purpose

To compare the lobbying expenditures and political action committee (PAC) campaign finance activities of the American Academy of Ophthalmology (AAO), American Society of Cataract and Refractive Surgery (ASCRS), and American Optometric Association (AOA) from 2015 to 2022.

Methods

Financial data were collected from the Federal Election Commission and OpenSecrets database. Analysis was performed to characterize and compare financial activity among the organizations. P < 0.05 was considered significant and all analyses were two-sided.

Results

From 2015 to 2022, the AAO, ASCRS, and AOA spent $6,745,000, $5,354,406, and $13,335,000 on lobbying, respectively. The AOA's annual lobbying expenditure (median, $1,725,000) was significantly greater than AAO's ($842,500, P = 0.03) and ASCRS's ($694,289, P < 0.001). In PAC donations, OPHTHPAC, affiliated with AAO, received $3,221,737 from 2079 donors (median, $900); eyePAC, affiliated with ASCRS, received $506,255 from 349 donors ($500); and AOA-PAC received $6,642,588 from 3641 donors ($825). Compared to eyePAC, median donations to OPHTHPAC (P = 0.01) and AOA-PAC (P = 0.04) were significantly higher. In campaign spending, OPHTHPAC contributed $2,728,500 to 326 campaigns (median, $5000), eyePAC contributed $293,500 to 58 campaigns ($3000), and AOA-PAC contributed $5,128,673 to 617 campaigns ($5500). eyePAC's median campaign contribution was significantly lower than the AOA's (P < 0.001) and AAO's (P = 0.007). Every PAC directed most of its contributions toward Republican campaigns; eyePAC donated the highest proportion (64.9%).

Conclusions

AOA was more assertive in shaping policy by increasing lobbying expenditures, fundraising, and donating to a greater number of election campaigns.

Internal iliac artery aneurysm masquerading as a sciatic nerve schwannoma: illustrative case

BACKGROUND

Schwannomas are common peripheral nerve sheath tumors. Imaging techniques such as magnetic resonance imaging (MRI) and computed tomography (CT) can help to distinguish schwannomas from other types of lesions. However, there have been several reported cases describing the misdiagnosis of aneurysms as schwannomas.

OBSERVATIONS

A 70-year-old male with ongoing pain despite spinal fusion surgery underwent MRI. A lesion was noted along the left sciatic nerve, which was believed to be a sciatic nerve schwannoma. During the surgery for planned neurolysis and tumor resection, the lesion was noted to be pulsatile. Electromyography mapping and intraoperative ultrasound confirmed vascular pulsations and turbulent flow within the aneurysm, so the surgery was aborted. A formal CT angiogram revealed the lesion to be an internal iliac artery (IIA) branch aneurysm. The patient underwent coil embolization with complete obliteration of the aneurysm.

LESSONS

The authors report the first case of an IIA aneurysm misdiagnosed as a sciatic nerve schwannoma. Surgeons should be aware of this potential misdiagnosis and potentially use other imaging modalities to confirm the lesion before proceeding with surgery.

HNF1α upregulation and promoter hypermethylation as a cause of glucose dysregulation: a case-control study of Kashmiri MODY population

AIM

HNF1α transcription factor regulates a network of genes involved in the development of β-cells and also serves as a model for transcription defects in pancreatic β-cells; mutations in this gene cause MODY. The goal of this study was to assess the promoter methylation and expression profile of the most common MODY causing gene, HNF1α, in Kashmiri MODY patients, as factors responsible for glucose dysregulation, as no such study had been performed on MODY patients in Kashmir previously.

METHODS

The study included 85 Kashmiri subjects. Samples were extracted for DNA and RNA using standard protocols. The HNF1α promoter methylation profile was assessed by bisulfite conversion of the DNA followed by MSP, whereas qPCR was used for expression analysis.

RESULTS

The expression of HNF1α was found to be upregulated (p value 0.0349*) in majority of MODY (60%) and T1D (72%) cases (p value 0.0349*). HNF1α expression was 1.33-fold higher in MODY cases with hypermethylated HNF1α promoters (p value 0.0360*). HNF1α expression was upregulated by 2.3-fold in MODY patients with HbA1c levels > 7% (p value 0.0025**). MODY cases with FBS levels > 7.7 mmol/l were upregulated by 0.646-fold than those with FBS levels ≤ 7.7 mmol/l (p value 0.0161*).

CONCLUSION

In this study, we found that as glucose dysregulation progresses, blood FBS, RBS, and HbA1c levels rise, and that at higher levels, HNF1α expression rises as well. From the results obtained, we may conclude that HNF1α is strongly upregulated in MODY, thus indicating the deleterious effect of over expression of HNF1α gene on glucose regulation.

Search for Gamma-Ray Spectral Lines from Dark Matter Annihilation up to 100 TeV toward the Galactic Center with MAGIC

Linelike features in TeV γ rays constitute a "smoking gun" for TeV-scale particle dark matter and new physics. Probing the Galactic Center region with ground-based Cherenkov telescopes enables the search for TeV spectral features in immediate association with a dense dark matter reservoir at a sensitivity out of reach for satellite γ-ray detectors, and direct detection and collider experiments. We report on 223 hours of observations of the Galactic Center region with the MAGIC stereoscopic telescope system reaching γ-ray energies up to 100 TeV. We improved the sensitivity to spectral lines at high energies using large-zenith-angle observations and a novel background modeling method within a maximum-likelihood analysis in the energy domain. No linelike spectral feature is found in our analysis. Therefore, we constrain the cross section for dark matter annihilation into two photons to ⟨σv⟩≲5×10^{-28}  cm^{3} s^{-1} at 1 TeV and ⟨σv⟩≲1×10^{-25}  cm^{3} s^{-1} at 100 TeV, achieving the best limits to date for a dark matter mass above 20 TeV and a cuspy dark matter profile at the Galactic Center. Finally, we use the derived limits for both cuspy and cored dark matter profiles to constrain supersymmetric wino models.

Knowledge distillation driven instance segmentation for grading prostate cancer

Prostate cancer (PCa) is one of the deadliest cancers in men, and identifying cancerous tissue patterns at an early stage can assist clinicians in timely treating the PCa spread. Many researchers have developed deep learning systems for mass-screening PCa. These systems, however, are commonly trained with well-annotated datasets in order to produce accurate results. Obtaining such data for training is often time and resource-demanding in clinical settings and can result in compromised screening performance. To address these limitations, we present a novel knowledge distillation-based instance segmentation scheme that allows conventional semantic segmentation models to perform instance-aware segmentation to extract stroma, benign, and the cancerous prostate tissues from the whole slide images (WSI) with incremental few-shot training. The extracted tissues are then used to compute majority and minority Gleason scores, which, afterward, are used in grading the PCa as per the clinical standards. The proposed scheme has been thoroughly tested on two datasets, containing around 10,516 and 11,000 WSI scans, respectively. Across both datasets, the proposed scheme outperforms state-of-the-art methods by 2.01% and 4.45%, respectively, in terms of the mean IoU score for identifying prostate tissues, and 10.73% and 11.42% in terms of F1 score for grading PCa according to the clinical standards. Furthermore, the applicability of the proposed scheme is tested under a blind experiment with a panel of expert pathologists, where it achieved a statistically significant Pearson correlation of 0.9192 and 0.8984 with the clinicians' grading.

Forensic psychiatry in Pakistan: Where next following the Supreme Court judgement

Introduction

No statutory mental health services exist for justice-involved individuals in Pakistan. The lack of expertise in forensic psychiatry serves to deny individuals with mental illness the critical support needed for mental healthcare and adequate court dispositions with serious unintended consequences including capital punishment for those who could otherwise be deemed treatment and not punishment worthy. A landmark judgement by the Supreme Court of Pakistan in February 2021 criticized the lack of forensic psychiatry expertise in Pakistan and directing the development of forensic mental health services and forensic psychiatry training in Pakistan.

Objectives

The key objectives are: 1. Understanding the timeline of how justice invloved individuals are manged by psychiatric services 2. The importance of the Supreme Court of Pakistan Judgement in affecting change 3. Highlights on how Queen’s University will enhance forensic psychiatry in Pakistan

Methods

A literature review and personal networking facilitated the collection of important data in how justice invloved individuals are supported in Pakistan. The author has published and presented to Pakistani psychiatrists and the Pakistani judiciary on this topic. Queen’s University is aiming to implement a 3-year plan to develop an online curriculum and certificate course to help train the trainers.

Results

In the Pakistan’s most populous province, Punjab, prevalence rates for psychotic illnesses (3.7%), major depression (10%), and personality disorders (65%) among men with higher rates for psychotic disorders (4.0%) and major depression (12%) among women.

Conclusions

In conclusion there is a dire need to develop forensic psychiatry in Pakistan and other low/middle income countries.

Disclosure

No significant relationships.

Treatment and comorbidities of patients with erectile dysfunction before and during COVID-19 in the United States: A real-world data analysis

Introduction

Objectives

Methods

Results

Conclusions

Disclosure

Deep learning based joint segmentation and characterization of multi-class retinal fluid lesions on OCT scans for clinical use in anti-VEGF therapy

BACKGROUND

In anti-vascular endothelial growth factor (anti-VEGF) therapy, an accurate estimation of multi-class retinal fluid (MRF) is required for the activity prescription and intravitreal dose. This study proposes an end-to-end deep learning-based retinal fluids segmentation network (RFS-Net) to segment and recognize three MRF lesion manifestations, namely, intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED), from multi-vendor optical coherence tomography (OCT) imagery. The proposed image analysis tool will optimize anti-VEGF therapy and contribute to reducing the inter- and intra-observer variability.

METHOD

The proposed RFS-Net architecture integrates the atrous spatial pyramid pooling (ASPP), residual, and inception modules in the encoder path to learn better features and conserve more global information for precise segmentation and characterization of MRF lesions. The RFS-Net model is trained and validated using OCT scans from multiple vendors (Topcon, Cirrus, Spectralis), collected from three publicly available datasets. The first dataset consisted of OCT volumes obtained from 112 subjects (a total of 11,334 B-scans) is used for both training and evaluation purposes. Moreover, the remaining two datasets are only used for evaluation purposes to check the trained RFS-Net's generalizability on unseen OCT scans. The two evaluation datasets contain a total of 1572 OCT B-scans from 1255 subjects. The performance of the proposed RFS-Net model is assessed through various evaluation metrics.

RESULTS

The proposed RFS-Net model achieved the mean F₁ scores of 0.762, 0.796, and 0.805 for segmenting IRF, SRF, and PED. Moreover, with the automated segmentation of the three retinal manifestations, the RFS-Net brings a considerable gain in efficiency compared to the tedious and demanding manual segmentation procedure of the MRF.

CONCLUSIONS

Our proposed RFS-Net is a potential diagnostic tool for the automatic segmentation of MRF (IRF, SRF, and PED) lesions. It is expected to strengthen the inter-observer agreement, and standardization of dosimetry is envisaged as a result.

An incremental learning approach to automatically recognize pulmonary diseases from the multi-vendor chest radiographs

The human respiratory network is a vital system that provides oxygen supply and nourishment to the whole body. Pulmonary diseases can cause severe respiratory problems, leading to sudden death if not treated timely. Many researchers have utilized deep learning systems (in both transfer learning and fine-tuning modes) to diagnose pulmonary disorders using chest X-rays (CXRs). However, such systems require exhaustive training efforts on large-scale (and well-annotated) data to effectively diagnose chest abnormalities (at the inference stage). Furthermore, procuring such large-scale data (in a clinical setting) is often infeasible and impractical, especially for rare diseases. With the recent advances in incremental learning, researchers have periodically tuned deep neural networks to learn different classification tasks with few training examples. Although, such systems can resist catastrophic forgetting, they treat the knowledge representations (which the network learns periodically) independently of each other, and this limits their classification performance. Also, to the best of our knowledge, there is no incremental learning-driven image diagnostic framework (to date) that is specifically designed to screen pulmonary disorders from the CXRs. To address this, we present a novel framework that can learn to screen different chest abnormalities incrementally (via few-shot training). In addition to this, the proposed framework is penalized through an incremental learning loss function that infers Bayesian theory to recognize structural and semantic inter-dependencies between incrementally learned knowledge representations to diagnose the pulmonary diseases effectively (at the inference stage), regardless of the scanner specifications. We tested the proposed framework on five public CXR datasets containing different chest abnormalities, where it achieved an accuracy of 0.8405 and the F1 score of 0.8303, outperforming various state-of-the-art incremental learning schemes. It also achieved a highly competitive performance compared to the conventional fine-tuning (transfer learning) approaches while significantly reducing the training and computational requirements.

RAG-FW: A Hybrid Convolutional Framework for the Automated Extraction of Retinal Lesions and Lesion-Influenced Grading of Human Retinal Pathology

The identification of retinal lesions plays a vital role in accurately classifying and grading retinopathy. Many researchers have presented studies on optical coherence tomography (OCT) based retinal image analysis over the past. However, to the best of our knowledge, there is no framework yet available that can extract retinal lesions from multi-vendor OCT scans and utilize them for the intuitive severity grading of the human retina. To cater this lack, we propose a deep retinal analysis and grading framework (RAG-FW). RAG-FW is a hybrid convolutional framework that extracts multiple retinal lesions from OCT scans and utilizes them for lesion-influenced grading of retinopathy as per the clinical standards. RAG-FW has been rigorously tested on 43,613 scans from five highly complex publicly available datasets, containing multi-vendor scans, where it achieved the mean intersection-over-union score of 0.8055 for extracting the retinal lesions and the accuracy of 98.70% for the correct severity grading of retinopathy.

Meta-Transfer Learning Driven Tensor-Shot Detector for the Autonomous Localization and Recognition of Concealed Baggage Threats

Screening baggage against potential threats has become one of the prime aviation security concerns all over the world, where manual detection of prohibited items is a time-consuming and hectic process. Many researchers have developed autonomous systems to recognize baggage threats using security X-ray scans. However, all of these frameworks are vulnerable against screening cluttered and concealed contraband items. Furthermore, to the best of our knowledge, no framework possesses the capacity to recognize baggage threats across multiple scanner specifications without an explicit retraining process. To overcome this, we present a novel meta-transfer learning-driven tensor-shot detector that decomposes the candidate scan into dual-energy tensors and employs a meta-one-shot classification backbone to recognize and localize the cluttered baggage threats. In addition, the proposed detection framework can be well-generalized to multiple scanner specifications due to its capacity to generate object proposals from the unified tensor maps rather than diversified raw scans. We have rigorously evaluated the proposed tensor-shot detector on the publicly available SIXray and GDXray datasets (containing a cumulative of 1,067,381 grayscale and colored baggage X-ray scans). On the SIXray dataset, the proposed framework achieved a mean average precision (mAP) of 0.6457, and on the GDXray dataset, it achieved the precision and F₁ score of 0.9441 and 0.9598, respectively. Furthermore, it outperforms state-of-the-art frameworks by 8.03% in terms of mAP, 1.49% in terms of precision, and 0.573% in terms of F₁ on the SIXray and GDXray dataset, respectively.

Clinically Verified Hybrid Deep Learning System for Retinal Ganglion Cells Aware Grading of Glaucomatous Progression

OBJECTIVE

Glaucoma is the second leading cause of blindness worldwide. Glaucomatous progression can be easily monitored by analyzing the degeneration of retinal ganglion cells (RGCs). Many researchers have screened glaucoma by measuring cup-to-disc ratios from fundus and optical coherence tomography scans. However, this paper presents a novel strategy that pays attention to the RGC atrophy for screening glaucomatous pathologies and grading their severity.

METHODS

The proposed framework encompasses a hybrid convolutional network that extracts the retinal nerve fiber layer, ganglion cell with the inner plexiform layer and ganglion cell complex regions, allowing thus a quantitative screening of glaucomatous subjects. Furthermore, the severity of glaucoma in screened cases is objectively graded by analyzing the thickness of these regions.

RESULTS

The proposed framework is rigorously tested on publicly available Armed Forces Institute of Ophthalmology (AFIO) dataset, where it achieved the F₁ score of 0.9577 for diagnosing glaucoma, a mean dice coefficient score of 0.8697 for extracting the RGC regions and an accuracy of 0.9117 for grading glaucomatous progression. Furthermore, the performance of the proposed framework is clinically verified with the markings of four expert ophthalmologists, achieving a statistically significant Pearson correlation coefficient of 0.9236.

CONCLUSION

An automated assessment of RGC degeneration yields better glaucomatous screening and grading as compared to the state-of-the-art solutions.

SIGNIFICANCE

An RGC-aware system not only screens glaucoma but can also grade its severity and here we present an end-to-end solution that is thoroughly evaluated on a standardized dataset and is clinically validated for analyzing glaucomatous pathologies.

Data on fundus images for vessels segmentation, detection of hypertensive retinopathy, diabetic retinopathy and papilledema

This paper presents a dataset that contains 100 high quality fundus images which are acquired from Armed Forces Institute of Ophthalmology (AFIO), Rawalpindi Pakistan. The dataset has been marked by four expert ophthalmologists to aid clinicians and researchers in screening hypertensive retinopathy, diabetic retinopathy and papilledema cases. Moreover, it contains highly detailed annotations for retinal blood vascular patterns, arteries and veins to calculate arteriovenous ratio (AVR), optic nerve head (ONH) region and other retinal anomalies such as hard exudates and cotton wool spots etc. The dataset is extremely useful for the researchers who are working in the ophthalmic image analysis.

Multilayered Deep Structure Tensor Delaunay Triangulation and Morphing Based Automated Diagnosis and 3D Presentation of Human Macula

Maculopathy is the group of diseases that affects central vision of a person and they are often associated with diabetes. Many researchers reported automated diagnosis of maculopathy from optical coherence tomography (OCT) images. However, to the best of our knowledge there is no literature that presents a complete 3D suite for the extraction as well as diagnosis of macula. Therefore, this paper presents a multilayered convolutional neural networks (CNN) structure tensor Delaunay triangulation and morphing based fully autonomous system that extracts up to nine retinal and choroidal layers along with the macular fluids. Furthermore, the proposed system utilizes the extracted retinal information for the automated diagnosis of maculopathy as well as for the robust reconstruction of 3D macula of retina. The proposed system has been validated on 41,921 retinal OCT scans acquired from different OCT machines and it significantly outperformed existing state of the art solutions by achieving the mean accuracy of 95.27% for extracting retinal and choroidal layers, mean dice coefficient of 0.90 for extracting fluid pathology and the overall accuracy of 96.07% for maculopathy diagnosis. To the best of our knowledge, the proposed framework is first of its kind that provides a fully automated and complete 3D integrated solution for the extraction of candidate macula along with its fully automated diagnosis against different macular syndromes.

Fully Automated Robust System to Detect Retinal Edema, Central Serous Chorioretinopathy, and Age Related Macular Degeneration from Optical Coherence Tomography Images

Maculopathy is the excessive damage to macula that leads to blindness. It mostly occurs due to retinal edema (RE), central serous chorioretinopathy (CSCR), or age related macular degeneration (ARMD). Optical coherence tomography (OCT) imaging is the latest eye testing technique that can detect these syndromes in early stages. Many researchers have used OCT images to detect retinal abnormalities. However, to the best of our knowledge, no research that presents a fully automated system to detect all of these macular syndromes is reported. This paper presents the world's first ever decision support system to automatically detect RE, CSCR, and ARMD retinal pathologies and healthy retina from OCT images. The automated disease diagnosis in our proposed system is based on multilayered support vector machines (SVM) classifier trained on 40 labeled OCT scans (10 healthy, 10 RE, 10 CSCR, and 10 ARMD). After training, SVM forms an accurate decision about the type of retinal pathology using 9 extracted features. We have tested our proposed system on 2819 OCT scans (1437 healthy, 640 RE, and 742 CSCR) of 502 patients from two different datasets and our proposed system correctly diagnosed 2817/2819 subjects with the accuracy, sensitivity, and specificity ratings of 99.92%, 100%, and 99.86%, respectively.

Fully automated diagnosis of papilledema through robust extraction of vascular patterns and ocular pathology from fundus photographs

Rapid development in the field of ophthalmology has increased the demand of computer aided diagnosis of various eye diseases. Papilledema is an eye disease in which the optic disc of the eye is swelled due to an increase in intracranial pressure. This increased pressure can cause severe encephalic complications like abscess, tumors, meningitis or encephalitis, which may lead to a patient's death. Although there have been several papilledema case studies reported from a medical point of view, only a few researchers have presented automated algorithms for this problem. This paper presents a novel computer aided system which aims to automatically detect papilledema from fundus images. Firstly, the fundus images are preprocessed by going through optic disc detection and vessel segmentation. After preprocessing, a total of 26 different features are extracted to capture possible changes in the optic disc due to papilledema. These features are further divided into four categories based upon their color, textural, vascular and disc margin obscuration properties. The best features are then selected and combined to form a feature matrix that is used to distinguish between normal images and images with papilledema using the supervised support vector machine (SVM) classifier. The proposed method is tested on 160 fundus images obtained from two different data sets i.e. structured analysis of retina (STARE), which is a publicly available data set, and our local data set that has been acquired from the Armed Forces Institute of Ophthalmology (AFIO). The STARE data set contained 90 and our local data set contained 70 fundus images respectively. These annotations have been performed with the help of two ophthalmologists. We report detection accuracies of 95.6% for STARE, 87.4% for the local data set, and 85.9% for the combined STARE and local data sets. The proposed system is fast and robust in detecting papilledema from fundus images with promising results. This will aid physicians in clinical assessment of fundus images. It will not take away the role of physicians, but will rather help them in the time consuming process of screening fundus images.

Automated diagnosis of macular edema and central serous retinopathy through robust reconstruction of 3D retinal surfaces

BACKGROUND AND OBJECTIVES

Macular diseases tend to damage macula within human retina due to which the central vision of a person is affected. Macular edema (ME) and central serous retinopathy (CSR) are two of the most common macular diseases. Many researchers worked on automated detection of ME from optical coherence tomography (OCT) and fundus images, whereas few researchers have worked on diagnosing central serous retinopathy. But this paper proposes a fully automated method for the classification of ME and CSR through robust reconstruction of 3D OCT retinal surfaces.

METHODS

The proposed system uses structure tensors to extract retinal layers from OCT images. The 3D retinal surface is then reconstructed by extracting the brightness scan (B-scan) thickness profile from each coherent tensor. The proposed system extracts 8 distinct features (3 based on retinal thickness profile of right side, 3 based on thickness profile of left side and 2 based on top surface and cyst spaces within retinal layers) from 30 labeled volumes (10 healthy, 10 CSR and 10 ME) which are used to train the supervised support vector machines (SVM) classifier.

RESULTS

In this research we have considered 90 OCT volumes (30 Healthy, 30 CSR and 30 ME) of 73 patients to test the proposed system where our proposed system correctly classified 89 out of 90 cases and has promising receiver operator characteristics (ROC) ratings with accuracy, sensitivity and specificity of 98.88%, 100%, and 96.66% respectively.

CONCLUSION

The proposed system is quite fast and robust in detecting all the three types of retinal pathologies from volumetric OCT scans. The proposed system is fully automated and provides an early and on fly diagnosis of ME and CSR syndromes. 3D macular thickness surfaces can further be used as decision support parameter in clinical studies to check the volume of cyst.

Structure tensor based automated detection of macular edema and central serous retinopathy using optical coherence tomography images

Macular edema (ME) and central serous retinopathy (CSR) are two macular diseases that affect the central vision of a person if they are left untreated. Optical coherence tomography (OCT) imaging is the latest eye examination technique that shows a cross-sectional region of the retinal layers and that can be used to detect many retinal disorders in an early stage. Many researchers have done clinical studies on ME and CSR and reported significant findings in macular OCT scans. However, this paper proposes an automated method for the classification of ME and CSR from OCT images using a support vector machine (SVM) classifier. Five distinct features (three based on the thickness profiles of the sub-retinal layers and two based on cyst fluids within the sub-retinal layers) are extracted from 30 labeled images (10 ME, 10 CSR, and 10 healthy), and SVM is trained on these. We applied our proposed algorithm on 90 time-domain OCT (TD-OCT) images (30 ME, 30 CSR, 30 healthy) of 73 patients. Our algorithm correctly classified 88 out of 90 subjects with accuracy, sensitivity, and specificity of 97.77%, 100%, and 93.33%, respectively.

[External Dacryocystorhinostomy--Analysis of Patient Material of the University Hospital Halle from 2000 to 2011]

BACKGROUND

The aim of this retrospective study was to collect additional data on the long-term success (LTS) of external dacryocystorhinostomy (ext-DCR) and the impact of pre-, intra- and postoperative factors on the surgical outcome. This was intended to increase the precision of the indication for DCR.

METHOD

A retrospective, non-comparative study was conducted on 637 ext-DCR due to dacryocystitis performed at the Department of Ophthalmology, University Hospital Halle. This included all surgical interventions on patients of at least 11 years of age. Using standardised questionnaires and patient records, 60.75 % (n = 387) of patients were surveyed. Follow-up was 1.0 to 12.0 years (mean, 4.0 years).

RESULTS

Analysis of patient satisfaction showed satisfactory (20.2 %) and very satisfactory (74.2 %) results. LTS was 94.4 % (n = 365). Factors negatively influencing postoperative outcome were prior surgical interventions of nose and/or sinus, previous ext-DCR and transcanalicular lacrimal surgery. Surgical outcome was positively influenced by lacrimal sac size and lacrimal stenting. Large saccus lacrimales and use of monocanalicular intubates improved LTS.

CONCLUSIONS

LTS of ext-DCR shows very good results, thus underlining its superiority to other surgical approaches. Special attention should be paid to diseases and previous surgical interventions on the nose and/or sinus that effect the lacrimal duct system. Therefore, a special committee of ENT physicians and ophthalmologists has been established at the Department of Ophthalmology, University Hospital Halle. From the surgical point of view, it is important to create an adequate mucosal anastomosis using lacrimal and nasal mucosa. Restoration is possible with lacrimal stent materials. The indication for ext-DCR was restricted by competition with transcanalicular endoscopic interventions to preserve physiological lacrimal drainage.

Automated segmentation of subretinal layers for the detection of macular edema

Macular edema (ME) is considered as one of the major indications of proliferative diabetic retinopathy and it is commonly caused due to diabetes. ME causes retinal swelling due to the accumulation of protein deposits within subretinal layers. Optical coherence tomography (OCT) imaging provides an early detection of ME by showing the cross-sectional view of macular pathology. Many researchers have worked on automated identification of macular edema from fundus images, but this paper proposes a fully automated method for extracting and analyzing subretinal layers from OCT images using coherent tensors. These subretinal layers are then used to predict ME from candidate images using a support vector machine (SVM) classifier. A total of 71 OCT images of 64 patients are collected locally in which 15 persons have ME and 49 persons are healthy. Our proposed system has an overall accuracy of 97.78% in correctly classifying ME patients and healthy persons. We have also tested our proposed implementation on spectral domain OCT (SD-OCT) images of the Duke dataset consisting of 109 images from 10 patients and it correctly classified all healthy and ME images in the dataset.

The oxysterol receptor LXRβ protects against DSS- and TNBS-induced colitis in mice

We examined the function of the oxysterol receptors (LXRs) in inflammatory bowel disease (IBD) through studying dextran sodium sulfate (DSS)- and 2,4,6-trinitrobenzene sulfonic acid (TNBS)-induced colitis in mice and by elucidating molecular mechanisms underlying their anti-inflammatory action. We observed that Lxr-deficient mice are more susceptible to colitis. Clinical indicators of colitis including weight loss, diarrhea and blood in feces appeared earlier and were more severe in Lxr-deficient mice and particularly LXRβ protected against symptoms of colitis. Addition of an LXR agonist led to faster recovery and increased survival. In contrast, Lxr-deficient mice showed slower recovery and decreased survival. In Lxr-deficient mice, inflammatory cytokines and chemokines were increased together with increased infiltration of immune cells in the colon epithelium. Activation of LXRs strongly suppressed expression of inflammatory mediators including TNFα. While LXRα had anti-inflammatory effects in CD11b(+) immune cell populations, LXRβ in addition had anti-inflammatory effects in colon epithelial cells. Lack of LXRβ also induced CD4(+)/CD3(+) immune cell recruitment to the inflamed colon. Expression of both LXRA and LXRB was significantly suppressed in inflamed colon from subjects with IBD compared with non-inflamed colon. Taken together, our observations suggest that the LXRs could provide interesting targets to reduce the inflammatory responses in IBD.

Identification of patients with low-risk pulmonary embolism suitable for outpatient treatment using the pulmonary embolism severity index (PESI)

BACKGROUND

There is increasing evidence that outpatient treatment of patients with low-risk stable pulmonary embolism (PE) is safe, effective and potentially reduces costs. It is not clear how many patients presenting to an Irish Emergency Department (ED) are potentially suitable for outpatient management.

AIMS

To identify how many patients presenting to our ED over a 1-year period who were diagnosed with acute PE are potentially suitable for outpatient treatment.

METHODS

A retrospective observational study was conducted over a 1-year period. Clinical notes for patients who had a positive computed tomographic pulmonary angiogram (CTPA) within 24 h of presentation to the ED were examined to risk stratify the patients according to the pulmonary embolism severity index (PESI).

RESULTS

Forty-seven patients who presented to our ED were diagnosed with a PE. Clinical notes were missing for 3 cases, and 44 cases were analysed further. The mean age was 64.3 (±16.8 SD) years and 24 (54.5 %, 95 % CI 40-68.3 %) were males. Six patients (13.6 %, 95 % CI 6.4-26.7 %) had a background of cancer. Fifteen cases (34.1 %, 95 % CI 21.9-48.7 %) were deemed to be low risk as they were categorised as PESI risk class I or II. Our study found that 61/420 (14.5 %, 95 % CI 11.5-18.2) of CTPAs done were positive for PE.

CONCLUSION

This study suggests that a significant percentage of patients diagnosed with acute PE are low risk as per PESI and therefore potentially suitable for outpatient management.

Evaluation of Balloon Occlusion Test for Giant Brain Aneurysms under Local Anaesthesia

We describe our experience in balloon test occlusion for giant carotid or basilar aneurysms under hypotension. Twenty-four patients underwent balloon test occlusion (BTO) during the year 2008. Only patients showed absence of any neurological deficits after 20 minutes under normal tension then another 20 minutes under hypotension were considered tolerable for occlusion of the parent artery. Of the 24 patients, four (16.67%) had deficits at normal tension and two (8.33%) had deficits at hypotensive phase. None of the 18 (75%) patients who clinically tolerated test occlusion and had parent artery sacrifice show any complication at follow-up period of two years. Two patients with clinical intolerability underwent carotid artery sacrifice after STA-MCA bypass without sequelae. Balloon test occlusion with hypotension is a useful, competent and simple technique in the evaluation of tolerance to parent artery occlusion in case of giant and complex intracranial aneurysms.

Prenatal diagnosis of chorionicity in twins

The aim of this audit was to assess the accuracy of transabdominal ultrasound scan in predicting chorionicity in twin pregnancies in our unit. The presence or absence of lambda sign, T-sign, dividing membrane thickness and number of placentae were used to determine chorionicity. We retrospectively analysed these antenatal markers in 268 sets of twins delivered over a 5 year period and compared it with the postpartum placental histology and neonatal gender. Of 268 twin deliveries, 204 (76%) had both chorionicity and placental histology to compare. 67 of 84 (80%) were correctly diagnosed antenatally as monochorionic and 137 of 151 (91%) as dichorionic. In 31 cases (15%) the ultrasound diagnosis of chorionicity didn't match placental histology. Seventeen were thought to be monochorionic antenatally but were confirmed dichorionic on placental histology. Overall chorionicity was correctly diagnosed in 171/204 (84%) using transabdominal ultrasound scan (USS) in all trimesters. However the sensitivity and specificity of USS was much higher for dichorionic twins when carried out before 14 weeks of gestation.