Multimodal Spatiotemporal Deep Learning Framework to Predict Response of Breast Cancer to Neoadjuvant Systemic Therapy.

Current approaches to breast cancer therapy include neoadjuvant systemic therapy (NST). The efficacy of NST is measured by pathologic complete response (pCR). A patient who attains pCR has significantly enhanced disease-free survival progress. The accurate prediction of pCR in response to a given treatment regimen could increase the likelihood of achieving pCR and prevent toxicities caused by treatments that are not effective. Th early prediction of response to NST can increase the likelihood of survival and help with decisions regarding breast-conserving surgery. An automated NST prediction framework that is able to precisely predict which patient undergoing NST will achieve a pathological complete response (pCR) at an early stage of treatment is needed. Here, we propose an end-to-end efficient multimodal spatiotemporal deep learning framework (deep-NST) framework to predict the outcome of NST prior or at an early stage of treatment. The deep-NST model incorporates imaging data captured at different timestamps of NST regimens, a tumor's molecular data, and a patient's demographic data. The efficacy of the proposed work is validated on the publicly available ISPY-1 dataset, in terms of accuracy, area under the curve (AUC), and computational complexity. In addition, seven ablation experiments were carried out to evaluate the impact of each design module in the proposed work. The experimental results show that the proposed framework performs significantly better than other recent methods.

The Development of an Artificial Intelligence Model Based Solely on Computer Tomography Successfully Predicts Which Patients Will Pass Obstructing Ureteral Calculi.

OBJECTIVE: To improve upon prior attempts to predict which patients will pass their obstructing ureteral stones, we developed a machine learning algorithm to predict the passage of obstructing ureteral stones using only the CT scan at a patient's initial presentation. METHODS: We obtained Institutional Review Board approval to conduct a retrospective study by extracting data from all patients with an obstructing 3-10 mm ureteral stone. We included patients with sufficient data to be categorized as having either passed or failed to pass an obstructing ureteral stone. We developed a 3D-convolutional neural network (CNN) model using a dynamic learning rate, the Adam optimizer, and early stopping with 10-fold cross-validation. Using this model, we calculated the area under the curve (AUC) and developed a model confusion matrix, which we compared with a model based only on the largest dimension of the stone. RESULTS: A total of 138 patients met inclusion criteria and had adequate images that could be preprocessed and included in the study. Seventy patients failed to pass their ureteral stones, and 68 patients passed their stones. For the 3D-CNN model, the mean AUC was 0.95 with an overall mean sensitivity of 95% and mean specificity of 77%, which outperformed the model based on stone-size. CONCLUSION: The 3D-CNN model predicts which patients will pass their obstructing ureteral stones based on CT scan alone and does not require any further measurements. This can provide useful clinical information which may help obviate the need for a delay in care for patients who inevitably require surgical intervention.

RegenX: an NLP recommendation engine for neuroregeneration topics over time.

Background: In this investigation, we explore the literature regarding neuroregeneration from the 1700s to the present. The regeneration of central nervous system neurons or the regeneration of axons from cell bodies and their reconnection with other neurons remains a major hurdle. Injuries relating to war and accidents attracted medical professionals throughout early history to regenerate and reconnect nerves. Early literature till 1990 lacked specific molecular details and is likely provide some clues to conditions that promoted neuron and/or axon regeneration. This is an avenue for the application of natural language processing (NLP) to gain actionable intelligence. Post 1990 period saw an explosion of all molecular details. With the advent of genomic, transcriptomics, proteomics, and other omics-there is an emergence of big data sets and is another rich area for application of NLP. How the neuron and/or axon regeneration related keywords have changed over the years is a first step towards this endeavor. Methods: Specifically, this article curates over 600 published works in the field of neuroregeneration. We then apply a dynamic topic modeling algorithm based on the Latent Dirichlet allocation (LDA) algorithm to assess how topics cluster based on topics. Results: Based on how documents are assigned to topics, we then build a recommendation engine to assist researchers to access domain-specific literature based on how their search text matches to recommended document topics. The interface further includes interactive topic visualizations for researchers to understand how topics grow closer and further apart, and how intra-topic composition changes over time. Conclusions: We present a recommendation engine and interactive interface that enables dynamic topic modeling for neuronal regeneration.

Analyses of pseudoexfoliation aqueous humor lipidome.

Pseudoexfoliation syndrome (PEX) is a systemic disorder that manifests as a fluffy, proteinaceous fibrillar material throughout the body. In the eye, such deposits result in glaucoma (PEXG), due to impeding aqueous humor outflow. Serum lipid alterations and increased lipid peroxidation have been reported in PEX. We report the first ever comprehensive lipid profiling of the aqueous humor (AH) of PEXG. Our untargeted lipidomic analysis of 23 control, 19 primary open angle glaucoma (POAG), 9 PEX, and 14 PEXG AH patients resulted in the identification of 489 lipid species within 26 lipid classes across PEX, PEXG, POAG, and control AH samples. Multiple cholesterol esters (ChEs), phosphatidylcholines (PCs), triglycerides (TGs), and ceramides (Cers) were present in higher concentrations in the PEXG AH than in all other groups. CerG2GNAc1(d34 : 1) was enriched in control samples and depleted in both the PEX and PEXG samples. Machine learning prediction with three supervised logistic regression binary classification tasks showed (1) POAG vs. control, with an 86% accuracy, (2) PEXG vs. control, with a 71% accuracy and (3) PEX vs. control, with an 86% accuracy. In conclusion, the analysis showed that the control (mean peak area 13.54 ± 6) had, on average, a higher total lipid content than the PEX, PEXG, and POAG AH samples. Elevations in Apolipoprotein A-I (APOA1) correlated with an increased abundance of PC lipid species in the AH of patients with PEXG. PC (18 : 0/18 : 2), PC (36 : 2), and PC (34 : 1e) are in low concentrations for PEX but are highly concentrated in PEXG, despite both having similar material deposits, suggesting that they are fundamentally different in composition.

The Influence of Age and Gender Information on the Diagnosis of Diabetic Retinopathy: Based on Neural Networks.

This paper proposes the importance of age and gender information in the diagnosis of diabetic retinopathy. We utilized Deep Residual Neural Networks (ResNet) and Densely Connected Convolutional Networks (DenseNet), which are proven effective on image classification problems and the diagnosis of diabetic retinopathy using the retinal fundus images. We used the ensemble of several classical networks and decentralized the training so that the network was simple and avoided overfitting. To observe whether the age and gender information could help enhance the performance, we added the information before the dense layer and compared the results with the results that did not add age and gender information. We found that the test accuracy of the network with age and gender information was 2.67% higher than that of the network without age and gender information. Meanwhile, compared with gender information, age information had a better help for the results.Clinical Relevance- The additional information in the dataset (such as age, gender, time of illness, etc.) can improve the accuracy of automatic diagnosis. Therefore, we strongly recommend that researchers add these different kinds of additional information when creating the dataset.

Proteomics and systems biology in optic nerve regeneration.

We present an overview of current state of proteomic approaches as applied to optic nerve regeneration in the historical context of nerve regeneration particularly central nervous system neuronal regeneration. We present outlook pertaining to the optic nerve regeneration proteomics that the latter can extrapolate information from multi-systems level investigations. We present an account of the current need of systems level standardization for comparison of proteome from various models and across different pharmacological or biophysical treatments that promote adult neuron regeneration. We briefly overview the need for deriving knowledge from proteomics and integrating with other omics to obtain greater biological insight into process of adult neuron regeneration in the optic nerve and its potential applicability to other central nervous system neuron regeneration.

Convolutional neural networks for breast cancer detection in mammography: A survey.

Despite its proven record as a breast cancer screening tool, mammography remains labor-intensive and has recognized limitations, including low sensitivity in women with dense breast tissue. In the last ten years, Neural Network advances have been applied to mammography to help radiologists increase their efficiency and accuracy. This survey aims to present, in an organized and structured manner, the current knowledge base of convolutional neural networks (CNNs) in mammography. The survey first discusses traditional Computer Assisted Detection (CAD) and more recently developed CNN-based models for computer vision in mammography. It then presents and discusses the literature on available mammography training datasets. The survey then presents and discusses current literature on CNNs for four distinct mammography tasks: (1) breast density classification, (2) breast asymmetry detection and classification, (3) calcification detection and classification, and (4) mass detection and classification, including presenting and comparing the reported quantitative results for each task and the pros and cons of the different CNN-based approaches. Then, it offers real-world applications of CNN CAD algorithms by discussing current Food and Drug Administration (FDA) approved models. Finally, this survey highlights the potential opportunities for future work in this field. The material presented and discussed in this survey could serve as a road map for developing CNN-based solutions to improve mammographic detection of breast cancer further.

Differentiation of soluble aqueous humor metabolites in primary open angle glaucoma and controls.

We report an analysis of the aqueous humor (AH) metabolome of primary open angle glaucoma (POAG) in comparison to normal controls. The AH samples were obtained from human donors [control (n = 35), POAG (n = 23)]. The AH samples were subjected to one-dimensional 1H nuclear magnetic resonance (NMR) analyses on a Bruker Avance 600 MHz instrument with a 1.7 mM NMR probe. The same samples were then subjected to isotopic ratio outlier analysis (IROA) using a Q Exactive orbitrap mass spectrometer after chromatography on an Accela 600 HPLC. Clusterfinder Build 3.1.10 was used for identification and quantification based on long-term metabolite matrix standards. In total, 278 metabolites were identified in control samples and 273 in POAG AH. The metabolites identified were fed into previously reported proteome and genome information and the OmicsNet interaction network generator to construct a protein-metabolite interactions network with an embedded protein-protein network. Significant differences in metabolite composition in POAG compared to controls were identified indicating potential protein/gene pathways associated with these metabolites. These results will expand our previous understanding of the impeded AH metabolite composition, provide new insight into the regulation of AH outflow, and likely aid in future AH and trabecular meshwork multi-omics network analyses.

Type 2 diabetes induced microbiome dysbiosis is associated with therapy resistance in pancreatic adenocarcinoma.

Resistance to therapy is one of the major factors that contribute to dismal survival statistics in pancreatic cancer. While there are many tumor intrinsic and tumor microenvironment driven factors that contribute to therapy resistance, whether pre-existing metabolic diseases like type 2 diabetes (T2D) contribute to this has remained understudied. It is well accepted that hyperglycemia associated with type 2 diabetes changes the gut microbiome. Further, hyperglycemia also enriches for a "stem-like" population within the tumor. In the current study, we observed that in a T2D mouse model, the microbiome changed significantly as the hyperglycemia developed in these animals. Our results further showed that, tumors implanted in the T2D mice responded poorly to gemcitabine/paclitaxel (Gem/Pac) standard of care compared to those in the control group. A metabolomic reconstruction of the WGS of the gut microbiota further revealed that an enrichment of bacterial population involved in drug metabolism in the T2D group. Additionally, we also observed an increase in the CD133+ tumor cells population in the T2D model. These observations indicated that in an animal model for T2D, microbial dysbiosis is associated with increased resistance to chemotherapeutic compounds.

Aqueous humor metabolite profile of pseudoexfoliation glaucoma is distinctive.

Pseudoexfoliation (PEX) is a known cause of secondary open angle glaucoma. PEX glaucoma is associated with structural and metabolic changes in the eye. Despite similarities, PEX and primary open angle glaucoma (POAG) may have differences in the composition of metabolites. We analyzed the metabolites of the aqueous humor (AH) of PEX subjects sequentially first using nuclear magnetic resonance (1H NMR: HSQC and TOCSY), and subsequently with liquid chromatography tandem mass spectrometry (LC-MS/MS) implementing isotopic ratio outlier analysis (IROA) quantification. The findings were compared with previous results for POAG and control subjects analyzed using identical sequential steps. We found significant differences in metabolites between the three conditions. Principle component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) indicated clear grouping based on the metabolomes of the three conditions. We used machine learning algorithms and a percentage set of the data to train, and utilized a different or larger dataset to test whether a trained model can correctly classify the test dataset as PEX, POAG or control. Three different algorithms: linear support vector machines (SVM), deep learning, and a neural network were used for prediction. They all accurately classified the test datasets based on the AH metabolome of the sample. We next compared the AH metabolome with known AH and TM proteomes and genomes in order to understand metabolic pathways that may contribute to alterations in the AH metabolome in PEX. We found potential protein/gene pathways associated with observed significant metabolite changes in PEX.