The Lung Cancer Prediction Model "Stress Test": Assessment of Models' Performance in a High-Risk Prospective Pulmonary Nodule Cohort.

BACKGROUND: Pulmonary nodules represent a growing health care burden because of delayed diagnosis of malignant lesions and overtesting for benign processes. Clinical prediction models were developed to inform physician assessment of pretest probability of nodule malignancy but have not been validated in a high-risk cohort of nodules for which biopsy was ultimately performed. RESEARCH QUESTION: Do guideline-recommended prediction models sufficiently discriminate between benign and malignant nodules when applied to cases referred for biopsy by navigational bronchoscopy? STUDY DESIGN AND METHODS: We assembled a prospective cohort of 322 indeterminate pulmonary nodules in 282 patients referred to a tertiary medical center for diagnostic navigational bronchoscopy between 2017 and 2019. We calculated the probability of malignancy for each nodule using the Brock model, Mayo Clinic model, and Veterans Affairs (VA) model. On a subset of 168 patients who also had PET-CT scans before biopsy, we also calculated the probability of malignancy using the Herder model. The performance of the models was evaluated by calculating the area under the receiver operating characteristic curves (AUCs) for each model. RESULTS: The study cohort contained 185 malignant and 137 benign nodules (57% prevalence of malignancy). The malignant and benign cohorts were similar in terms of size, with a median longest diameter for benign and malignant nodules of 15 and 16 mm, respectively. The Brock model, Mayo Clinic model, and VA model showed similar performance in the entire cohort (Brock AUC, 0.70; 95% CI, 0.64-0.76; Mayo Clinic AUC, 0.70; 95% CI, 0.64-0.76; VA AUC, 0.67; 95% CI, 0.62-0.74). For 168 nodules with available PET-CT scans, the Herder model had an AUC of 0.77 (95% CI, 0.68-0.85). INTERPRETATION: Currently available clinical models provide insufficient discrimination between benign and malignant nodules in the common clinical scenario in which a patient is being referred for biopsy, especially when PET-CT scan information is not available.

Curating retrospective multimodal and longitudinal data for community cohorts at risk for lung cancer.

BACKGROUND: Large community cohorts are useful for lung cancer research, allowing for the analysis of risk factors and development of predictive models. OBJECTIVE: A robust methodology for (1) identifying lung cancer and pulmonary nodules diagnoses as well as (2) associating multimodal longitudinal data with these events from electronic health record (EHRs) is needed to optimally curate cohorts at scale. METHODS: In this study, we leveraged (1) SNOMED concepts to develop ICD-based decision rules for building a cohort that captured lung cancer and pulmonary nodules and (2) clinical knowledge to define time windows for collecting longitudinal imaging and clinical concepts. We curated three cohorts with clinical data and repeated imaging for subjects with pulmonary nodules from our Vanderbilt University Medical Center. RESULTS: Our approach achieved an estimated sensitivity 0.930 (95% CI: [0.879, 0.969]), specificity of 0.996 (95% CI: [0.989, 1.00]), positive predictive value of 0.979 (95% CI: [0.959, 1.000]), and negative predictive value of 0.987 (95% CI: [0.976, 0.994]) for distinguishing lung cancer from subjects with SPNs. CONCLUSION: This work represents a general strategy for high-throughput curation of multi-modal longitudinal cohorts at risk for lung cancer from routinely collected EHRs.

Lung CT harmonization of paired reconstruction kernel images using generative adversarial networks.

BACKGROUND: The kernel used in CT image reconstruction is an important factor that determines the texture of the CT image. Consistency of reconstruction kernel choice is important for quantitative CT-based assessment as kernel differences can lead to substantial shifts in measurements unrelated to underlying anatomical structures. PURPOSE: In this study, we investigate kernel harmonization in a multi-vendor low-dose CT lung cancer screening cohort and evaluate our approach's validity in quantitative CT-based assessments. METHODS: Using the National Lung Screening Trial, we identified CT scan pairs of the same sessions with one reconstructed from a soft tissue kernel and one from a hard kernel. In total, 1000 pairs of five different paired kernel types (200 each) were identified. We adopt the pix2pix architecture to train models for kernel conversion. Each model was trained on 100 pairs and evaluated on 100 withheld pairs. A total of 10 models were implemented. We evaluated the efficacy of kernel conversion based on image similarity metrics including root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) as well as the capability of the models to reduce measurement shifts in quantitative emphysema and body composition measurements. Additionally, we study the reproducibility of standard radiomic features for all kernel pairs before and after harmonization. RESULTS: Our approach effectively converts CT images from one kernel to another in all paired kernel types, as indicated by the reduction in RMSE (p < 0.05) and an increase in the PSNR (p < 0.05) and SSIM (p < 0.05) for both directions of conversion for all pair types. In addition, there is an increase in the agreement for percent emphysema, skeletal muscle area, and subcutaneous adipose tissue (SAT) area for both directions of conversion. Furthermore, radiomic features were reproducible when compared with the ground truth features. CONCLUSIONS: Kernel conversion using deep learning reduces measurement variation in percent emphysema, muscle area, and SAT area.

Kirigami electronics for long-term electrophysiological recording of human neural organoids and assembloids.

Realizing the full potential of organoids and assembloids to model neural development and disease will require improved methods for long-term, minimally invasive recording of electrical activity. Current technologies, such as patch clamp, penetrating microelectrodes, planar electrode arrays and substrate-attached flexible electrodes, do not allow chronic recording of organoids in suspension, which is necessary to preserve architecture. Inspired by kirigami art, we developed flexible electronics that transition from a two-dimensional to a three-dimensional basket-like configuration with either spiral or honeycomb patterns to accommodate the long-term culture of organoids in suspension. Here we show that this platform, named kirigami electronics (KiriE), integrates with and enables chronic recording of cortical organoids for up to 120 days while preserving their morphology, cytoarchitecture and cell composition. We demonstrate integration of KiriE with optogenetic and pharmacological manipulation and modeling phenotypes related to a genetic disease. Moreover, KiriE can capture corticostriatal connectivity in assembloids following optogenetic stimulation. Thus, KiriE will enable investigation of disease and activity patterns underlying nervous system assembly.

Safety and efficacy of laquinimod for Huntington's disease (LEGATO-HD): a multicentre, randomised, double-blind, placebo-controlled, phase 2 study.

BACKGROUND: Laquinimod modulates CNS inflammatory pathways thought to be involved in the pathology of Huntington's disease. Studies with laquinimod in transgenic rodent models of Huntington's disease suggested improvements in motor function, reduction of brain volume loss, and prolonged survival. We aimed to evaluate the safety and efficacy of laquinimod in improving motor function and reducing caudate volume loss in patients with Huntington's disease. METHODS: LEGATO-HD was a multicentre, double-blind, placebo-controlled, phase 2 study done at 48 sites across ten countries (Canada, Czech Republic, Germany, Italy, Netherlands, Portugal, Russia, Spain, UK, and USA). Patients aged 21-55 years with a cytosine-adenosine-guanine (CAG) repeat length of between 36 and 49 who had symptomatic Huntington's disease with a Unified Huntington's Disease Rating Scale-Total Motor Score (UHDRS-TMS) of higher than 5 and a Total Functional Capacity score of 8 or higher were randomly assigned (1:1:1:1) by centralised interactive response technology to laquinimod 0·5 mg, 1·0 mg, or 1·5 mg, or to matching placebo, administered orally once daily over 52 weeks; people involved in the randomisation had no other role in the study. Participants, investigators, and study personnel were masked to treatment assignment. The 1·5 mg group was discontinued before recruitment was finished because of cardiovascular safety concerns in multiple sclerosis studies. The primary endpoint was change from baseline in the UHDRS-TMS and the secondary endpoint was percent change in caudate volume, both comparing the 1·0 mg group with the placebo group at week 52. Primary and secondary endpoints were assessed in the full analysis set (ie, all randomised patients who received at least one dose of study drug and had at least one post-baseline UHDRS-TMS assessment). Safety measures included adverse event frequency and severity, and clinical and laboratory examinations, and were assessed in the safety analysis set (ie, all randomised patients who received at least one dose of study drug). This trial is registered with ClinicalTrials.gov, NCT02215616, and EudraCT, 2014-000418-75, and is now complete. FINDINGS: Between Oct 28, 2014, and June 19, 2018, 352 adults with Huntington's disease (179 [51%] men and 173 [49%] women; mean age 43·9 [SD 7·6] years and 340 [97%] White) were randomly assigned: 107 to laquinimod 0·5 mg, 107 to laquinimod 1·0 mg, 30 to laquinimod 1·5 mg, and 108 to matching placebo. Least squares mean change from baseline in UHDRS-TMS at week 52 was 1·98 (SE 0·83) in the laquinimod 1·0 mg group and 1·2 (0·82) in the placebo group (least squares mean difference 0·78 [95% CI -1·42 to 2·98], p=0·4853). Least squares mean change in caudate volume was 3·10% (SE 0·38) in the 1·0 mg group and 4·86% (0·38) in the placebo group (least squares mean difference -1·76% [95% CI -2·67 to -0·85]; p=0·0002). Laquinimod was well tolerated and there were no new safety findings. Serious adverse events were reported by eight (7%) patients on placebo, seven (7%) on laquinimod 0·5 mg, five (5%) on laquinimod 1·0 mg, and one (3%) on laquinimod 1·5 mg. There was one death, which occurred in the placebo group and was unrelated to treatment. The most frequent adverse events in all laquinimod dosed groups (0·5 mg, 1·0 mg, and 1·5 mg) were headache (38 [16%]), diarrhoea (24 [10%]), fall (18 [7%]), nasopharyngitis (20 [8%]), influenza (15 [6%]), vomiting (13 [5%]), arthralgia (11 [5%]), irritability (ten [4%]), fatigue (eight [3%]), and insomnia (eight [3%]). INTERPRETATION: Laquinimod did not show a significant effect on motor symptoms assessed by the UHDRS-TMS, but significantly reduced caudate volume loss compared with placebo at week 52. Huntington's disease has a chronic and slowly progressive course, and this study does not address whether a longer duration of laquinimod treatment could have produced detectable and meaningful changes in the clinical assessments. FUNDING: Teva Pharmaceutical Industries.

Effectiveness of a Maintenance and Reliever Digihaler System in Asthma: 24-Week Randomized Study (CONNECT2).

BACKGROUND: Digital health tools have been shown to help address challenges in asthma control, including inhaler technique, treatment adherence, and short-acting ß2-agonist overuse. The maintenance and reliever Digihaler System (DS) comprises 2 Digihaler inhalers (fluticasone propionate/salmeterol and albuterol) with an associated patient App and web-based Dashboard. Clinicians can review patients' inhaler use and Digihaler inhalation parameter data to support clinical decision-making. OBJECTIVE: CONNECT2 evaluated asthma control in participants using the DS versus standard-of-care (SoC) maintenance and reliever inhalers. METHODS: Participants (13 years or older) with uncontrolled asthma (Asthma Control Test [ACT] score <19) were randomized 4:3 (open-label) to the DS (n = 210) or SoC (n = 181) for 24 weeks. The primary endpoint was the proportion of patients achieving well-controlled asthma (ie, an ACT score ≥20 or increase from baseline of ≥3 units at week 24). RESULTS: There was an 88.7% probability that participants using the DS would have greater odds of achieving improvement in asthma control compared with SoC after 24 weeks. The mean odds ratio (95% credible interval) for DS versus SoC was 1.35 (0.846-2.038), indicating a 35% higher odds of improved asthma control with the DS. The DS group had more clinician-participant interactions versus SoC, mainly addressing a poor inhaler technique. DS participants' maintenance treatment adherence was good (month 1: 79.2%; month 6: 68.6%); reliever use decreased by 38.2% versus baseline. App and Dashboard usability was rated "good." CONCLUSION: The positive results in asthma control in this study after 24 weeks demonstrate the effectiveness of the DS in asthma management.

Age-related Muscle Fat Infiltration in Lung Screening Participants: Impact of Smoking Cessation.

Rationale: Skeletal muscle fat infiltration progresses with aging and is worsened among individuals with a history of cigarette smoking. Many negative impacts of smoking on muscles are likely reversible with smoking cessation. Objectives: To determine if the progression of skeletal muscle fat infiltration with aging is altered by smoking cessation among lung cancer screening participants. Methods: This was a secondary analysis based on the National Lung Screening Trial. Skeletal muscle attenuation in Hounsfield unit (HU) was derived from the baseline and follow-up low-dose CT scans using a previously validated artificial intelligence algorithm. Lower attenuation indicates greater fatty infiltration. Linear mixed-effects models were constructed to evaluate the associations between smoking status and the muscle attenuation trajectory. Measurements and Main Results: Of 19,019 included participants (age: 61 years, 5 [SD]; 11,290 males), 8,971 (47.2%) were actively smoking cigarettes. Accounting for body mass index, pack-years, percent emphysema, and other confounding factors, actively smoking predicted a lower attenuation in both males (ß0 =-0.88 HU, P<.001) and females (ß0 =-0.69 HU, P<.001), and an accelerated muscle attenuation decline-rate in males (ß1=-0.08 HU/y, P<.05). Age-stratified analyses indicated that the accelerated muscle attenuation decline associated with smoking likely occurred at younger age, especially in females. Conclusions: Among lung cancer screening participants, active cigarette smoking was associated with greater skeletal muscle fat infiltration in both males and females, and accelerated muscle adipose accumulation rate in males. These findings support the important role of smoking cessation in preserving muscle health.

Kirigami electronics for long-term electrophysiological recording of human neural organoids and assembloids.

Organoids and assembloids have emerged as a promising platform to model aspects of nervous system development. Longterm, minimally-invasive recordings in these multi-cellular systems are essential for developing disease models. Current technologies, such as patch-clamp, penetrating microelectrodes, planar electrode arrays and substrate-attached flexible electrodes, do not, however, allow chronic recording of organoids in suspension, which is necessary to preserve their architecture. Inspired by the art of kirigami, we developed flexible electronics that transition from a 2D pattern to a 3D basketlike configuration to accommodate the long-term culture of organoids in suspension. This platform, named kirigami electronics (KiriE), integrates with and enables chronic recording of cortical organoids while preserving morphology, cytoarchitecture, and cell composition. KiriE can be integrated with optogenetic and pharmacological stimulation and model disease. Moreover, KiriE can capture activity in cortico-striatal assembloids. Moving forward, KiriE could reveal disease phenotypes and activity patterns underlying the assembly of the nervous system.

Motifs in SARS-CoV-2 evolution.

We present a novel framework enhancing the prediction of whether novel lineage poses the threat of eventually dominating the viral population. The framework is based purely on genomic sequence data, without requiring prior established biological analysis. Its building blocks are sets of coevolving sites in the alignment (motifs), identified via coevolutionary signals. The collection of such motifs forms a relational structure over the polymorphic sites. Motifs are constructed using distances quantifying the coevolutionary coupling of pairs and manifest as coevolving clusters of sites. We present an approach to genomic surveillance based on this notion of relational structure. Our system will issue an alert regarding a lineage, based on its contribution to drastic changes in the relational structure. We then conduct a comprehensive retrospective analysis of the COVID-19 pandemic based on SARS-CoV-2 genomic sequence data in GISAID from October 2020 to September 2022, across 21 lineages and 27 countries with weekly resolution. We investigate the performance of this surveillance system in terms of its accuracy, timeliness, and robustness. Lastly, we study how well each lineage is classified by such a system.

UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation.

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks. Our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively. Code, pre-trained models, and use case pipeline are available at: https://github.com/MASILab/UNesT.

Time-distance vision transformers in lung cancer diagnosis from longitudinal computed tomography.

Features learned from single radiologic images are unable to provide information about whether and how much a lesion may be changing over time. Time-dependent features computed from repeated images can capture those changes and help identify malignant lesions by their temporal behavior. However, longitudinal medical imaging presents the unique challenge of sparse, irregular time intervals in data acquisition. While self-attention has been shown to be a versatile and efficient learning mechanism for time series and natural images, its potential for interpreting temporal distance between sparse, irregularly sampled spatial features has not been explored. In this work, we propose two interpretations of a time-distance vision transformer (ViT) by using (1) vector embeddings of continuous time and (2) a temporal emphasis model to scale self-attention weights. The two algorithms are evaluated based on benign versus malignant lung cancer discrimination of synthetic pulmonary nodules and lung screening computed tomography studies from the National Lung Screening Trial (NLST). Experiments evaluating the time-distance ViTs on synthetic nodules show a fundamental improvement in classifying irregularly sampled longitudinal images when compared to standard ViTs. In cross-validation on screening chest CTs from the NLST, our methods (0.785 and 0.786 AUC respectively) significantly outperform a cross-sectional approach (0.734 AUC) and match the discriminative performance of the leading longitudinal medical imaging algorithm (0.779 AUC) on benign versus malignant classification. This work represents the first self-attention-based framework for classifying longitudinal medical images. Our code is available at https://github.com/tom1193/time-distance-transformer.

Stratification of Lung Cancer Risk with Thoracic Imaging Phenotypes.

In lung cancer screening, estimation of future lung cancer risk is usually guided by demographics and smoking status. The role of constitutional profiles of human body, a.k.a. body habitus, is increasingly understood to be important, but has not been integrated into risk models. Chest low dose computed tomography (LDCT) is the standard imaging study in lung cancer screening, with the capability to discriminate differences in body composition and organ arrangement in the thorax. We hypothesize that the primary phenotypes identified using lung screening chest LDCT can form a representation of body habitus and add predictive power for lung cancer risk stratification. In this pilot study, we evaluated the feasibility of body habitus image-based phenotyping on a large lung screening LDCT dataset. A thoracic imaging manifold was estimated based on an intensity-based pairwise (dis)similarity metric for pairs of spatial normalized chest LDCT images. We applied the hierarchical clustering method on this manifold to identify the primary phenotypes. Body habitus features of each identified phenotype were evaluated and associated with future lung cancer risk using time-to-event analysis. We evaluated the method on the baseline LDCT scans of 1,200 male subjects sampled from National Lung Screening Trial. Five primary phenotypes were identified, which were associated with highly distinguishable clinical and body habitus features. Time-to-event analysis against future lung cancer incidences showed two of the five identified phenotypes were associated with elevated future lung cancer risks (HR=1.61, 95% CI = [1.08, 2.38], p=0.019; HR=1.67, 95% CI = [0.98, 2.86], p=0.057). These results indicated that it is feasible to capture the body habitus by image-base phenotyping using lung screening LDCT and the learned body habitus representation can potentially add value for future lung cancer risk stratification.

AI Body Composition in Lung Cancer Screening: Added Value Beyond Lung Cancer Detection.

Background An artificial intelligence (AI) algorithm has been developed for fully automated body composition assessment of lung cancer screening noncontrast low-dose CT of the chest (LDCT) scans, but the utility of these measurements in disease risk prediction models has not been assessed. Purpose To evaluate the added value of CT-based AI-derived body composition measurements in risk prediction of lung cancer incidence, lung cancer death, cardiovascular disease (CVD) death, and all-cause mortality in the National Lung Screening Trial (NLST). Materials and Methods In this secondary analysis of the NLST, body composition measurements, including area and attenuation attributes of skeletal muscle and subcutaneous adipose tissue, were derived from baseline LDCT examinations by using a previously developed AI algorithm. The added value of these measurements was assessed with sex- and cause-specific Cox proportional hazards models with and without the AI-derived body composition measurements for predicting lung cancer incidence, lung cancer death, CVD death, and all-cause mortality. Models were adjusted for confounding variables including age; body mass index; quantitative emphysema; coronary artery calcification; history of diabetes, heart disease, hypertension, and stroke; and other PLCOM2012 lung cancer risk factors. Goodness-of-fit improvements were assessed with the likelihood ratio test. Results Among 20 768 included participants (median age, 61 years [IQR, 57-65 years]; 12 317 men), 865 were diagnosed with lung cancer and 4180 died during follow-up. Including the AI-derived body composition measurements improved risk prediction for lung cancer death (male participants: χ2 = 23.09, P < .001; female participants: χ2 = 15.04, P = .002), CVD death (males: χ2 = 69.94, P < .001; females: χ2 = 16.60, P < .001), and all-cause mortality (males: χ2 = 248.13, P < .001; females: χ2 = 94.54, P < .001), but not for lung cancer incidence (male participants: χ2 = 2.53, P = .11; female participants: χ2 = 1.73, P = .19). Conclusion The body composition measurements automatically derived from baseline low-dose CT examinations added predictive value for lung cancer death, CVD death, and all-cause death, but not for lung cancer incidence in the NLST. Clinical trial registration no. NCT00047385 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Fintelmann in this issue.

Quantifying emphysema in lung screening computed tomography with robust automated lobe segmentation.

Purpose: Anatomy-based quantification of emphysema in a lung screening cohort has the potential to improve lung cancer risk stratification and risk communication. Segmenting lung lobes is an essential step in this analysis, but leading lobe segmentation algorithms have not been validated for lung screening computed tomography (CT). Approach: In this work, we develop an automated approach to lobar emphysema quantification and study its association with lung cancer incidence. We combine self-supervised training with level set regularization and finetuning with radiologist annotations on three datasets to develop a lobe segmentation algorithm that is robust for lung screening CT. Using this algorithm, we extract quantitative CT measures for a cohort (n=1189) from the National Lung Screening Trial and analyze the multivariate association with lung cancer incidence. Results: Our lobe segmentation approach achieved an external validation Dice of 0.93, significantly outperforming a leading algorithm at 0.90 (p<0.01). The percentage of low attenuation volume in the right upper lobe was associated with increased lung cancer incidence (odds ratio: 1.97; 95% CI: [1.06, 3.66]) independent of PLCOm2012 risk factors and diagnosis of whole lung emphysema. Quantitative lobar emphysema improved the goodness-of-fit to lung cancer incidence (χ2=7.48, p=0.02). Conclusions: We are the first to develop and validate an automated lobe segmentation algorithm that is robust to smoking-related pathology. We discover a quantitative risk factor, lending further evidence that regional emphysema is independently associated with increased lung cancer incidence. The algorithm is provided at https://github.com/MASILab/EmphysemaSeg.

Body composition assessment with limited field-of-view computed tomography: A semantic image extension perspective.

Field-of-view (FOV) tissue truncation beyond the lungs is common in routine lung screening computed tomography (CT). This poses limitations for opportunistic CT-based body composition (BC) assessment as key anatomical structures are missing. Traditionally, extending the FOV of CT is considered as a CT reconstruction problem using limited data. However, this approach relies on the projection domain data which might not be available in application. In this work, we formulate the problem from the semantic image extension perspective which only requires image data as inputs. The proposed two-stage method identifies a new FOV border based on the estimated extent of the complete body and imputes missing tissues in the truncated region. The training samples are simulated using CT slices with complete body in FOV, making the model development self-supervised. We evaluate the validity of the proposed method in automatic BC assessment using lung screening CT with limited FOV. The proposed method effectively restores the missing tissues and reduces BC assessment error introduced by FOV tissue truncation. In the BC assessment for large-scale lung screening CT datasets, this correction improves both the intra-subject consistency and the correlation with anthropometric approximations. The developed method is available at https://github.com/MASILab/S-EFOV.

Cutaneous nerve fiber and peripheral Nav1.7 assessment in a large cohort of patients with postherpetic neuralgia.

ABSTRACT: The mechanisms of pain in postherpetic neuralgia (PHN) are still unclear, with some studies showing loss of cutaneous sensory nerve fibers that seemed to correlate with pain level. We report results of skin biopsies and correlations with baseline pain scores, mechanical hyperalgesia, and the Neuropathic Pain Symptom Inventory (NPSI) in 294 patients who participated in a clinical trial of TV-45070, a topical semiselective sodium 1.7 channel (Nav1.7) blocker. Intraepidermal nerve fibers and subepidermal Nav1.7 immunolabeled fibers were quantified in skin punch biopsies from the area of maximal PHN pain, as well as from the contralateral, homologous (mirror image) region. Across the entire study population, a 20% reduction in nerve fibers on the PHN-affected side compared with that in the contralateral side was noted; however, the reduction was much higher in older individuals, approaching 40% in those aged 70 years or older. There was a decrease in contralateral fiber counts as well, also noted in prior biopsy studies, the mechanism of which is not fully clear. Nav1.7-positive immunolabeling was present in approximately one-third of subepidermal nerve fibers and did not differ on the PHN-affected vs contralateral sides. Using cluster analysis, 2 groups could be identified, with the first cluster showing higher baseline pain, higher NPSI scores for squeezing and cold-induced pain, higher nerve fiber density, and higher Nav1.7 expression. While Nav1.7 varies from patient to patient, it does not seem to be a key pathophysiological driver of PHN pain. Individual differences in Nav1.7 expression, however, may determine the intensity and sensory aspects of pain.

Closing the Gap Between Theory and Practice During Alternating Optimization for GANs.

Synthesizing high-quality and diverse samples is the main goal of generative models. Despite recent great progress in generative adversarial networks (GANs), mode collapse is still an open problem, and mitigating it will benefit the generator to better capture the target data distribution. This article rethinks alternating optimization in GANs, which is a classic approach to training GANs in practice. We find that the theory presented in the original GANs does not accommodate this practical solution. Under the alternating optimization manner, the vanilla loss function provides an inappropriate objective for the generator. This objective forces the generator to produce the output with the highest discriminative probability of the discriminator, which leads to mode collapse in GANs. To address this problem, we introduce a novel loss function for the generator to adapt to the alternating optimization nature. When updating the generator by the proposed loss function, the reverse Kullback-Leibler divergence between the model distribution and the target distribution is theoretically optimized, which encourages the model to learn the target distribution. The results of extensive experiments demonstrate that our approach can consistently boost model performance on various datasets and network structures.

Nerve-sparing technique in RPLND for testicular cancer.

PURPOSE OF REVIEW: The management of testicular cancer has evolved over time with multimodal therapy. Retroperitoneal lymph node dissection (RPLND), which is a complex and potentially morbid treatment option, remains the mainstay in surgical treatment. This article reviews the surgical template, approach and anatomical considerations with regards to nerve spare in RPLND. RECENT FINDINGS: The standard full bilateral RPLND template has evolved over time to include the area between the renal hilum, bifurcation of the common iliac vessels, and the ureters. Morbidity with regards to ejaculatory dysfunction has led to further refinements in this procedure. Advancements in anatomical understanding of the retroperitoneal structures and their relationship to the sympathetic chain and hypogastric plexus has allowed for modification of surgical templates. Further refinements in surgical nerve sparing techniques have improved functional outcomes without sacrificing oncological outcomes. Finally, extraperitoneal access to the retroperitoneum and minimally invasive platforms have been implemented to further reduce morbidity. SUMMARY: RPLND requires strict adherence to oncological surgical principles regardless of template, approach and technique. Contemporary evidence shows that outcomes are best for advanced testis cancer patients when managed at high volume tertiary care facilities with surgical expertise and access to multidisciplinary care.

Major Postoperative Complications Limit Adjuvant Therapy Administration in Patients Undergoing Pancreatoduodenectomy for Distal Cholangiocarcinoma or Pancreatic Ductal Adenocarcinoma.

INTRODUCTION: Guidelines for perioperative systemic therapy administration in patients undergoing pancreatoduodenectomy for pancreatic adenocarcinoma (PDAC) and distal cholangiocarcinoma (dCCA) are evolving. Decisions regarding adjuvant therapy are influenced by postoperative morbidity, which is common after pancreatoduodenectomy. We evaluated whether postoperative complications are associated with receipt of adjuvant therapy after pancreatoduodenectomy. METHODS: A retrospective analysis of patients undergoing pancreatoduodenectomy for PDAC or dCCA from 2015 to 2020 was conducted. Demographic, clinicopathologic, and postoperative variables were analyzed. RESULTS: Overall, 186 patients were included-145 with PDAC and 41 with dCCA. Postoperative complication rates were similar for both pathologies (61% and 66% for PDAC and dCCA, respectively). Major postoperative complications (MPCs), defined as Clavien-Dindo >3, occurred in 15% and 24% of PDAC and dCCA patients, respectively. Patients with MPCs received lower rates of adjuvant therapy administration, irrespective of primary tumor (PDAC: 21 vs. 72%, p = 0.008; dCCA: 20 vs. 58%, p = 0.065). Recurrence-free survival (RFS) was worse for patients with PDAC who experienced an MPC [8 months (interquartile range [IQR] 1-15) vs. 23 months (IQR 19-27), p < 0.001] or who did not receive any perioperative systemic therapy [11 months (IQR 7-15) vs. 23 months (IQR 18-29), p = 0.038]. In patients with dCCA, 1-year RFS was worse for patients who did not receive adjuvant therapy (55 vs. 77%, p = 0.038). CONCLUSION: Patients who underwent pancreatoduodenectomy for either PDAC or dCCA and who experienced an MPC had lower rates of adjuvant therapy and worse RFS, suggesting that clinicians adopt a standard neoadjuvant systemic therapy strategy in patients with PDAC. Our results propose a paradigm shift towards preoperative systemic therapy in patients with dCCA.

Characterizing browser-based medical imaging AI with serverless edge computing: towards addressing clinical data security constraints.

Artificial intelligence (AI) has been widely introduced to various medical imaging applications ranging from disease visualization to medical decision support. However, data privacy has become an essential concern in clinical practice of deploying the deep learning algorithms through cloud computing. The sensitivity of patient health information (PHI) commonly limits network transfer, installation of bespoke desktop software, and access to computing resources. Serverless edge-computing shed light on privacy preserved model distribution maintaining both high flexibility (as cloud computing) and security (as local deployment). In this paper, we propose a browser-based, cross-platform, and privacy preserved medical imaging AI deployment system working on consumer-level hardware via serverless edge-computing. Briefly we implement this system by deploying a 3D medical image segmentation model for computed tomography (CT) based lung cancer screening. We further curate tradeoffs in model complexity and data size by characterizing the speed, memory usage, and limitations across various operating systems and browsers. Our implementation achieves a deployment with (1) a 3D convolutional neural network (CNN) on CT volumes (256×256×256 resolution), (2) an average runtime of 80 seconds across Firefox v.102.0.1/Chrome v.103.0.5060.114/Microsoft Edge v.103.0.1264.44 and 210 seconds on Safari v.14.1.1, and (3) an average memory usage of 1.5 GB on Microsoft Windows laptops, Linux workstation, and Apple Mac laptops. In conclusion, this work presents a privacy-preserved solution for medical imaging AI applications that minimizes the risk of PHI exposure. We characterize the tools, architectures, and parameters of our framework to facilitate the translation of modern deep learning methods into routine clinical care.