A Hybrid Deep Learning Model for Enhanced Structural Damage Detection: Integrating ResNet50, GoogLeNet, and Attention Mechanisms.

Quick and accurate structural damage detection is essential for maintaining the safety and integrity of infrastructure, especially following natural disasters. Traditional methods of damage assessment, which rely on manual inspections, can be labor-intensive and subject to human error. This paper introduces a hybrid deep learning model that combines the capabilities of ResNet50 and GoogLeNet, further enhanced by a convolutional block attention module (CBAM), proposed to improve both the accuracy and performance in detecting structural damage.

Diaphragmatic Myopathy Associated with Dual Immune Checkpoint Inhibitors in a Patient with Renal Cell Carcinoma.

Immune-related adverse events (irAEs) have become increasingly prevalent with immune checkpoint inhibitor (ICI) cancer treatment. We present a 79-year-old man with metastatic renal cell carcinoma who developed shortness of breath and hypercapnic respiratory insufficiency after his first cycle of nivolumab and ipilimumab. Laboratory data showed elevated creatinine kinase, troponins, and transaminases.

Chronic shoulder pain due to spinal accessory nerve palsies present opportunities for improved care integration.

Chronic shoulder pain due to iatrogenic spinal accessory nerve (SAN) injury continues to be under-recognized, resulting in delayed time-to-diagnosis and poorer outcomes. Solutions are needed to improve the management of this condition, which can be challenging as care needs to be coordinated across pain management, neurophysiology, rehabilitation and reconstructive surgery. We present a series of six patients with shoulder pain refractory to conservative pain treatments to highlight how SAN injuries continued to be missed and treatment delayed, even at advanced care centers.

Neurofilament light chain in serum of cancer patients with acute neurological complications.

Neurofilament light chain (NfL) is a nonspecific sensitive biomarker of axonal damage. This case series identified cancer patients with neurological complications who had serum NfL measurements and paired these results to outcomes. NfL serum levels were available in 15 patients with hematological malignancies or solid tumors.

Cerebral clues: serum neurofilament light chain (sNfL) as a novel biomarker for immune check point inhibitor (ICI) mediated seronegative encephalitis.

Immune checkpoint inhibitor (ICI) mediated encephalitides are increasingly being recognized in the literature, but atypical cases may be missed or misdiagnosed. Recent efforts are directed to identify biomarkers to help elucidate early diagnosis and treatment. Herein, we describe two cases of antibody negative ICI-mediated encephalitis with elevated serum Neurofilament light chain (sNfL) levels.

Molecular Pathways and Cellular Subsets Associated with Adverse Clinical Outcomes in Overlapping Immune-Related Myocarditis and Myositis.

Immune checkpoint therapies (ICT) can induce life-threatening immune-related adverse events, including myocarditis and myositis, which are rare but often concurrent. The molecular pathways and immune subsets underlying these toxicities remain poorly understood. To address this need, we performed single-cell RNA sequencing of heart and skeletal muscle biopsies obtained from living patients with cancers treated with ICTs and admitted to the hospital with myocarditis and/or myositis (overlapping myocarditis plus myositis, n = 10; myocarditis-only, n = 1) or ICT-exposed patients ruled out for toxicity utilized as controls (n = 9).

A 3D Sparse Autoencoder for Fully Automated Quality Control of Affine Registrations in Big Data Brain MRI Studies.

This paper presents a fully automated pipeline using a sparse convolutional autoencoder for quality control (QC) of affine registrations in large-scale T1-weighted (T1w) and T2-weighted (T2w) magnetic resonance imaging (MRI) studies. Here, a customized 3D convolutional encoder-decoder (autoencoder) framework is proposed and the network is trained in a fully unsupervised manner. For cross-validating the proposed model, we used 1000 correctly aligned MRI images of the human connectome project young adult (HCP-YA) dataset.

Intraoperative language mapping guided by real-time visualization of gamma band modulation electrocorticograms: Case report and proof of concept.

Background: Electrocorticography (ECoG) language mapping is often performed extraoperatively, frequently involves offline processing, and relationships with direct cortical stimulation (DCS) remain variable. We sought to determine the feasibility and preliminary utility of an intraoperative language mapping approach guided by real-time visualization of electrocorticograms.

Methods: A patient with astrocytoma underwent awake craniotomy with intraoperative language mapping, utilizing a dual iPad stimulus presentation system coupled to a real-time neural signal processing platform capable of both ECoG recording and delivery of DCS.

Management of respiratory failure in immune checkpoint inhibitors-induced overlap syndrome: a case series and review of the literature.

Background: Checkpoint inhibitor-induced overlap syndrome ([OS] myocarditis, and myositis with or without myasthenia gravis) is rare but life-threatening.

Cases Presentation: Here we present a case series of four cancer patients that developed OS. High troponinemia raised the concern for myocarditis in all the cases.

Decoding the clinical effects of low-grade glioma-induced cortical excitability.

Objective: Patients with low-grade glioma (LGG) in eloquent regions often present with seizures, and findings on detailed neuropsychological testing are often abnormal. This study evaluated the association between cortical excitability, seizures, and cognitive function in patients with LGG.

Methods: LGG patients who underwent transcranial magnetic stimulation (TMS) from January 2021 to December 2022 were studied.

An Explainable Classification Method Based on Complex Scaling in Histopathology Images for Lung and Colon Cancer.

Lung and colon cancers are among the leading causes of human mortality and morbidity. Early diagnostic work up of these diseases include radiography, ultrasound, magnetic resonance imaging, and computed tomography. Certain blood tumor markers for carcinoma lung and colon also aid in the diagnosis.

EfficientNetV2 Based Ensemble Model for Quality Estimation of Diabetic Retinopathy Images from DeepDRiD.

Diabetic retinopathy (DR) is one of the major complications caused by diabetes and is usually identified from retinal fundus images. Screening of DR from digital fundus images could be time-consuming and error-prone for ophthalmologists. For efficient DR screening, good quality of the fundus image is essential and thereby reduces diagnostic errors.

Few-shot learning using explainable Siamese twin network for the automated classification of blood cells.

Automated classification of blood cells from microscopic images is an interesting research area owing to advancements of efficient neural network models. The existing deep learning methods rely on large data for network training and generating such large data could be time-consuming. Further, explainability is required via class activation mapping for better understanding of the model predictions.

Ulnar fascicle to brachialis branch of musculocutaneous nerve for restoration of elbow flexion associated with spinal cord tumor and radiation-induced lower motor neuron disease.

Transfer of the ulnar fascicle to the biceps branch of the musculocutaneous nerve, or Oberlin transfer, has been widely used for the treatment of elbow flexion weakness in the setting of upper trunk brachial plexus palsy. The authors present a modified application of this technique for restoration of functional elbow flexion in a 30-year-old woman with a history of recurrent upper cervical spinal cord pilocytic astrocytoma, complex spinal deformity, and radiation-induced lower motor neuron disease. The video can be found here: https://stream.

Comparative study of preoperative functional imaging combined with tractography for prediction of iatrogenic motor deficits.

Objective: Robust preoperative imaging can improve the extent of resection in patients with brain tumors while minimizing postoperative neurological morbidity. Both structural and functional imaging techniques can provide helpful preoperative information. A recent study found that transcranial magnetic stimulation (TMS) tractography has significant predictive value for permanent deficits.

Long-latency gamma modulation after median nerve stimulation delineates the central sulcus and contrasts the states of consciousness.

Objective: To evaluate the functional use of sub-band modulations in somatosensory evoked potentials (SSEPs) to discriminate between the primary somatosensory (S1) and motor (M1) areas and contrast the states of consciousness.

Methods: During routine intraoperative cortical mapping, SSEPs were recorded with electrocorticography (ECoG) grids from the sensorimotor cortex of eight patients in the anesthetized and awake states. We conducted a time-frequency analysis on the SSEP trace to extract the spectral modulations in each state and visualize their spatial topography.

Transcranial magnetic stimulation tractography and the facilitation of gross total resection in a patient with a motor eloquent glioblastoma: illustrative case.

Background: In patients with perieloquent tumors, neurosurgeons must use a variety of techniques to maximize survival while minimizing postoperative neurological morbidity. Recent publications have shown that conventional anatomical features may not always predict postoperative deficits. Additionally, scientific conceptualizations of complex brain function have shifted toward more dynamic, neuroplastic theories instead of traditional static, localizationist models.

Classification of Brain Tumor from Magnetic Resonance Imaging Using Vision Transformers Ensembling.

The automated classification of brain tumors plays an important role in supporting radiologists in decision making. Recently, vision transformer (ViT)-based deep neural network architectures have gained attention in the computer vision research domain owing to the tremendous success of transformer models in natural language processing. Hence, in this study, the ability of an ensemble of standard ViT models for the diagnosis of brain tumors from T1-weighted (T1w) magnetic resonance imaging (MRI) is investigated.

Transcranial magnetic stimulation (TMS) seeded tractography provides superior prediction of eloquence compared to anatomic seeded tractography.

Background: For patients with brain tumors, maximizing the extent of resection while minimizing postoperative neurological morbidity requires accurate preoperative identification of eloquent structures. Recent studies have provided evidence that anatomy may not always predict eloquence. In this study, we directly compare transcranial magnetic stimulation (TMS) data combined with tractography to traditional anatomic grading criteria for predicting permanent deficits in patients with motor eloquent gliomas.

Real-Time Delineation of the Central Sulcus with the Spatial Profile of SSEPs Captured with High-Density Ecog Grid.

Cortical mapping is widely employed to define the sensorimotor area and delineate the central sulcus (CS) during awake craniotomies. The approach involves the gold standard somatosensory evoked potentials (SSEPs) recorded with electrocorticogram (ECoG) strip electrodes. However, the evoked response can be misconstrued from the manual peak interpretation due to the poor spatial resolution of the strip electrode or when the electrode does not precisely cover the desired cortical area.