Topology preserving stratification of tissue neoplasticity using Deep Neural Maps and microRNA signatures.

BACKGROUND: Accurate cancer classification is essential for correct treatment selection and better prognostication. microRNAs (miRNAs) are small RNA molecules that negatively regulate gene expression, and their dyresgulation is a common disease mechanism in many cancers. Through a clearer understanding of miRNA dysregulation in cancer, improved mechanistic knowledge and better treatments can be sought. RESULTS: We present a topology-preserving deep learning framework to study miRNA dysregulation in cancer. Our study comprises miRNA expression profiles from 3685 cancer and non-cancer tissue samples and hierarchical annotations on organ and neoplasticity status. Using unsupervised learning, a two-dimensional topological map is trained to cluster similar tissue samples. Labelled samples are used after training to identify clustering accuracy in terms of tissue-of-origin and neoplasticity status. In addition, an approach using activation gradients is developed to determine the attention of the networks to miRNAs that drive the clustering. Using this deep learning framework, we classify the neoplasticity status of held-out test samples with an accuracy of 91.07%, the tissue-of-origin with 86.36%, and combined neoplasticity status and tissue-of-origin with an accuracy of 84.28%. The topological maps display the ability of miRNAs to recognize tissue types and neoplasticity status. Importantly, when our approach identifies samples that do not cluster well with their respective classes, activation gradients provide further insight in cancer subtypes or grades. CONCLUSIONS: An unsupervised deep learning approach is developed for cancer classification and interpretation. This work provides an intuitive approach for understanding molecular properties of cancer and has significant potential for cancer classification and treatment selection.

Towards targeted ultrasound-guided prostate biopsy by incorporating model and label uncertainty in cancer detection.

PURPOSE: Systematic prostate biopsy is widely used for cancer diagnosis. The procedure is blind to underlying prostate tissue micro-structure; hence, it can lead to a high rate of false negatives. Development of a machine-learning model that can reliably identify suspicious cancer regions is highly desirable. However, the models proposed to-date do not consider the uncertainty present in their output or the data to benefit clinical decision making for targeting biopsy. METHODS: We propose a deep network for improved detection of prostate cancer in systematic biopsy considering both the label and model uncertainty. The architecture of our model is based on U-Net, trained with temporal enhanced ultrasound (TeUS) data. We estimate cancer detection uncertainty using test-time augmentation and test-time dropout. We then use uncertainty metrics to report the cancer probability for regions with high confidence to help the clinical decision making during the biopsy procedure. RESULTS: Experiments for prostate cancer classification includes data from 183 prostate biopsy cores of 41 patients. We achieve an area under the curve, sensitivity, specificity and balanced accuracy of 0.79, 0.78, 0.71 and 0.75, respectively. CONCLUSION: Our key contribution is to automatically estimate model and label uncertainty towards enabling targeted ultrasound-guided prostate biopsy. We anticipate that such information about uncertainty can decrease the number of unnecessary biopsy with a higher rate of cancer yield.

Domain adaptation and self-supervised learning for surgical margin detection.

PURPOSE: One in five women who undergo breast conserving surgery will need a second revision surgery due to remaining tumor. The iKnife is a mass spectrometry modality that produces real-time margin information based on the metabolite signatures in surgical smoke. Using this modality and real-time tissue classification, surgeons could remove all cancerous tissue during the initial surgery, improving many facets of patient outcomes. An obstacle in developing a iKnife breast cancer recognition model is the destructive, time-consuming and sensitive nature of the data collection that limits the size of the datasets. METHODS: We address these challenges by first, building a self-supervised learning model from limited, weakly labeled data. By doing so, the model can learn to contextualize the general features of iKnife data from a more accessible cancer type. Second, the trained model can then be applied to a cancer classification task on breast data. This domain adaptation allows for the transfer of learnt weights from models of one tissue type to another. RESULTS: Our datasets contained 320 skin burns (129 tumor burns, 191 normal burns) from 51 patients and 144 breast tissue burns (41 tumor and 103 normal) from 11 patients. We investigate the effect of different hyper-parameters on the performance of the final classifier. The proposed two-step method performed statistically significantly better than a baseline model (p-value < 0.0001), by achieving an accuracy, sensitivity and specificity of 92%, 88% and 92%, respectively. CONCLUSION: This is the first application of domain transfer for iKnife REIMS data. We showed that having a limited number of breast data samples for training a classifier can be compensated by self-supervised learning and domain adaption on a set of unlabeled skin data. We plan to confirm this performance by collecting new breast samples and extending it to incorporate other cancer tissues.

Image registration: Maximum likelihood, minimum entropy and deep learning.

In this work, we propose a theoretical framework based on maximum profile likelihood for pairwise and groupwise registration. By an asymptotic analysis, we demonstrate that maximum profile likelihood registration minimizes an upper bound on the joint entropy of the distribution that generates the joint image data. Further, we derive the congealing method for groupwise registration by optimizing the profile likelihood in closed form, and using coordinate ascent, or iterative model refinement. We also describe a method for feature based registration in the same framework and demonstrate it on groupwise tractographic registration. In the second part of the article, we propose an approach to deep metric registration that implements maximum likelihood registration using deep discriminative classifiers. We show further that this approach can be used for maximum profile likelihood registration to discharge the need for well-registered training data, using iterative model refinement. We demonstrate that the method succeeds on a challenging registration problem where the standard mutual information approach does not perform well.

Attitudes and experience of urology trainees in interpreting prostate magnetic resonance imaging.

INTRODUCTION: Multiparametric magnetic resonance imaging (mpMRI) has resulted in accurate prostate cancer localization and image-guided targeted sampling for biopsy. Despite its more recent uptake, knowledge gaps in interpretation and reporting exist. Our objective was to determine the need for an educational intervention among urology residents working with mpMRIs. METHODS: We administered an anonymous, cross-sectional, self-report questionnaire to a convenience sample of urology residents in U.S. and Canadian training programs. The survey included both open- and closed-ended questions employing a five-point Likert scale. It was designed to assess familiarity, exposure, experience, and comfort with interpretation of mpMRI. RESULTS: Fifty-three surveys were completed by residents in postgraduate years (PGY) 1-5 and of these, only 12 (23%) reported any formal training in mpMRI interpretation. Most residents' responses demonstrated significant experience with prostate biopsies, as well as familiarity with reviewing mpMRI for these patients. However, mean (± standard deviation [SD]) Likert responses suggested a relatively poor understanding of the components of Prostate Imaging-Reporting and Data System (PI-RADS) v2 scoring for T2-weighted films (2.45±1.01), diffusion-weighted imaging (DWI) films (2.26±0.90), and dynamic contrast-enhanced (DCE) films (2.21±0.99). Similar disagreement scores were observed for questions around interpretation of the different functional techniques of MRI images. Residents reported strong interest (4.21±0.91) in learning opportunities to enhance their ability to interpret mpMRI. CONCLUSIONS: While mpMRI of the prostate is a tool frequently used by care teams in teaching centers to identify suspicious prostate cancer lesions, there remain knowledge gaps in the ability of trainees to interpret images and understand PI-RADS v2 scoring. Online modules were suggested to balance the needs of trainee education with the residency workflow.

Generalizable deep temporal models for predicting episodes of sudden hypotension in critically ill patients: a personalized approach.

The vast quantities of data generated and collected in the Intensive Care Unit (ICU) have given rise to large retrospective datasets that are frequently used for observational studies. The temporal nature and fine granularity of much of the data collected in the ICU enable the pursuit of predictive modeling. In particular, forecasting acute hypotensive episodes (AHE) in intensive care patients has been of interest to researchers in critical care medicine. Given an advance warning of an AHE, care providers may be prompted to search for evolving disease processes and help mitigate negative clinical outcomes. However, the conventionally adopted definition of an AHE does not account for inter-patient variability and is restrictive. To reflect the wider trend of global clinical and research efforts in precision medicine, we introduce a patient-specific definition of AHE in this study and propose deep learning based models to predict this novel definition of AHE in data from multiple independent institutions. We provide extensive evaluation of the models by studying their accuracies in detecting patient-specific AHEs with lead-times ranging from 10 min to 1 hour before the onset of the event. The resulting models achieve AUROC values ranging from 0.57-0.87 depending on the lead time of the prediction. We demonstrate the generalizability and robustness of our approach through the use of independent multi-institutional data.

Improving detection of prostate cancer foci via information fusion of MRI and temporal enhanced ultrasound.

PURPOSE: The detection of clinically significant prostate cancer (PCa) is shown to greatly benefit from MRI-ultrasound fusion biopsy, which involves overlaying pre-biopsy MRI volumes (or targets) with real-time ultrasound images. In previous literature, machine learning models trained on either MRI or ultrasound data have been proposed to improve biopsy guidance and PCa detection. However, quantitative fusion of information from MRI and ultrasound has not been explored in depth in a large study. This paper investigates information fusion approaches between MRI and ultrasound to improve targeting of PCa foci in biopsies. METHODS: We build models of fully convolutional networks (FCN) using data from a newly proposed ultrasound modality, temporal enhanced ultrasound (TeUS), and apparent diffusion coefficient (ADC) from 107 patients with 145 biopsy cores. The architecture of our models is based on U-Net and U-Net with attention gates. Models are built using joint training through intermediate and late fusion of the data. We also build models with data from each modality, separately, to use as baseline. The performance is evaluated based on the area under the curve (AUC) for predicting clinically significant PCa. RESULTS: Using our proposed deep learning framework and intermediate fusion, integration of TeUS and ADC outperforms the individual modalities for cancer detection. We achieve an AUC of 0.76 for detection of all PCa foci, and 0.89 for PCa with larger foci. Results indicate a shared representation between multiple modalities outperforms the average unimodal predictions. CONCLUSION: We demonstrate the significant potential of multimodality integration of information from MRI and TeUS to improve PCa detection, which is essential for accurate targeting of cancer foci during biopsy. By using FCNs as the architecture of choice, we are able to predict the presence of clinically significant PCa in entire imaging planes immediately, without the need for region-based analysis. This reduces the overall computational time and enables future intra-operative deployment of this technology.

Structural and Functional Reorganization of the Brain in Migraine Without Aura.

It remains unknown whether migraine headache has a progressive component in its pathophysiology. Quantitative MRI may provide valuable insight into abnormal changes in the migraine interictum and assist in identifying disrupted brain networks. We carried out a data-driven study of structural integrity and functional connectivity of the resting brain in migraine without aura. MRI scanning was performed in 36 patients suffering from episodic migraine without aura and 33 age-matched healthy subjects. Voxel-wise analysis of regional brain volume was performed by registration of the T1-weighted MRI scans into a common study brain template using the tensor-based morphometry (TBM) method. Changes in functional synchronicity of the brain networks were assessed using probabilistic independent component analysis (ICA). TBM revealed that migraine is associated with reduced volume of the medial prefrontal cortex (mPFC). Among 375 functional brain networks, resting-state connectivity was decreased between two components spanning the visual cortex, posterior insula, and parietal somatosensory cortex. Our study reveals structural and functional alterations of the brain in the migraine interictum that may stem from underlying disease risk factors and the "silent" aura phenomenon. Longitudinal studies will be needed to investigate whether interictal brain changes are progressive and associated with clinical disease trajectories.

Exploring microRNA Regulation of Cancer with Context-Aware Deep Cancer Classifier.

BACKGROUND: MicroRNAs (miRNAs) are small, non-coding RNA that regulate gene expression through post-transcriptional silencing. Differential expression observed in miRNAs, combined with advancements in deep learning (DL), have the potential to improve cancer classification by modelling non-linear miRNA-phenotype associations. We propose a novel miRNA-based deep cancer classifier (DCC) incorporating genomic and hierarchical tissue annotation, capable of accurately predicting the presence of cancer in wide range of human tissues. METHODS: miRNA expression profiles were analyzed for 1746 neoplastic and 3871 normal samples, across 26 types of cancer involving six organ sub-structures and 68 cell types. miRNAs were ranked and filtered using a specificity score representing their information content in relation to neoplasticity, incorporating 3 levels of hierarchical biological annotation. A DL architecture composed of stacked autoencoders (AE) and a multi-layer perceptron (MLP) was trained to predict neoplasticity using 497 abundant and informative miRNAs. Additional DCCs were trained using expression of miRNA cistrons and sequence families, and combined as a diagnostic ensemble. Important miRNAs were identified using backpropagation, and analyzed in Cytoscape using iCTNet and BiNGO. RESULTS: Nested four-fold cross-validation was used to assess the performance of the DL model. The model achieved an accuracy, AUC/ROC, sensitivity, and specificity of 94.73%, 98.6%, 95.1%, and 94.3%, respectively. CONCLUSION: Deep autoencoder networks are a powerful tool for modelling complex miRNA-phenotype associations in cancer. The proposed DCC improves classification accuracy by learning from the biological context of both samples and miRNAs, using anatomical and genomic annotation. Analyzing the deep structure of DCCs with backpropagation can also facilitate biological discovery, by performing gene ontology searches on the most highly significant features.

Deep neural maps for unsupervised visualization of high-grade cancer in prostate biopsies.

Prostate cancer (PCa) is the most frequent noncutaneous cancer in men. Early detection of PCa is essential for clinical decision making, and reducing metastasis and mortality rates. The current approach for PCa diagnosis is histopathologic analysis of core biopsies taken under transrectal ultrasound guidance (TRUS-guided). Both TRUS-guided systematic biopsy and MR-TRUS-guided fusion biopsy have limitations in accurately identifying PCa, intraoperatively. There is a need to augment this process by visualizing highly probable areas of PCa. Temporal enhanced ultrasound (TeUS) has emerged as a promising modality for PCa detection. Prior work focused on supervised classification of PCa verified by gold standard pathology. Pathology labels are noisy, and data from an entire core have a single label even when significantly heterogeneous. Additionally, supervised methods are limited by data from cores with known pathology, and a significant portion of prostate data is discarded without being used. We provide an end-to-end unsupervised solution to map PCa distribution from TeUS data using an innovative representation learning method, deep neural maps. TeUS data are transformed to a topologically arranged hyper-lattice, where similar samples are closer together in the lattice. Therefore, similar regions of malignant and benign tissue in the prostate are clustered together. Our proposed method increases the number of training samples by several orders of magnitude. Data from biopsy cores with known labels are used to associate the clusters with PCa. Cancer probability maps generated using the unsupervised clustering of TeUS data help intuitively visualize the distribution of abnormal tissue for augmenting TRUS-guided biopsies.

Prediction of Patient-specific Acute Hypotensive Episodes in ICU Using Deep Models.

Forecasting acute hypotensive episodes (AHE) in intensive care patients has been of recent interest to researchers in the healthcare domain. Advance warning of an impending AHE may give care providers additional information to help mitigate the negative clinical impact of a serious event such as an AHE or prompt a search for an evolving disease process. However, the currently accepted definition of AHE is restrictive does not account for inter-patient variability. In this paper, we propose a novel definition of an AHE based on patient-specific features of blood pressure recordings. Next, we utilize a deep learning-based method to predict the onset of an AHE from multiple physiological readings for different definitions of the prediction task including variable input and gap lengths. Using a cohort of 538 patients, our model was able to successfully predict the onset of an AHE with an accuracy and AUC score of 0.80 and 0.87 respectively. Compared to a baseline logistic regression model, our model outperforms the baseline in most of the definitions of the prediction task.

Predictive Modeling using Intensive Care Unit Data: Considerations for Data Pre-processing and Analysis.

The vast quantities of data generated and collected in the Intensive Care Unit (ICU) have given rise to large retrospective datasets that are frequently used for observational studies. The temporal nature and fine granularity of much of the data collected in the ICU enable the pursuit of predictive modeling, an increasingly common topic in ICU literature. Since patient conditions can rapidly change in the ICU, predicting the onset of events that are indicative of deteriorating patient state has potential clinical utility. However, the development of predictive modeling applications using ICU data requires a number of considerations to maximize prospective performance and clinical utility. In this study, we discuss the challenges encountered and considerations taken by using the prediction of acute hypotensive episodes as an example.

Using the variogram for vector outlier screening: application to feature-based image registration.

PURPOSE: Matching points that are derived from features or landmarks in image data is a key step in some medical imaging applications. Since most robust point matching algorithms claim to be able to deal with outliers, users may place high confidence in the matching result and use it without further examination. However, for tasks such as feature-based registration in image-guided neurosurgery, even a few mismatches, in the form of invalid displacement vectors, could cause serious consequences. As a result, having an effective tool by which operators can manually screen all matches for outliers could substantially benefit the outcome of those applications. METHODS: We introduce a novel variogram-based outlier screening method for vectors. The variogram is a powerful geostatistical tool for characterizing the spatial dependence of stochastic processes. Since the spatial correlation of invalid displacement vectors, which are considered as vector outliers, tends to behave differently than normal displacement vectors, they can be efficiently identified on the variogram. RESULTS: We validate the proposed method on 9 sets of clinically acquired ultrasound data. In the experiment, potential outliers are flagged on the variogram by one operator and further evaluated by 8 experienced medical imaging researchers. The matching quality of those potential outliers is approximately 1.5 lower, on a scale from 1 (bad) to 5 (good), than valid displacement vectors. CONCLUSION: The variogram is a simple yet informative tool. While being used extensively in geostatistical analysis, it has not received enough attention in the medical imaging field. We believe there is a good deal of potential for clinically applying the proposed outlier screening method. By way of this paper, we also expect researchers to find variogram useful in other medical applications that involve motion vectors analyses.

Classification of Clinical Significance of MRI Prostate Findings Using 3D Convolutional Neural Networks.

Prostate cancer (PCa) remains a leading cause of cancer mortality among American men. Multi-parametric magnetic resonance imaging (mpMRI) is widely used to assist with detection of PCa and characterization of its aggressiveness. Computer-aided diagnosis (CADx) of PCa in MRI can be used as clinical decision support system to aid radiologists in interpretation and reporting of mpMRI. We report on the development of a convolution neural network (CNN) model to support CADx in PCa based on the appearance of prostate tissue in mpMRI, conducted as part of the SPIE-AAPM-NCI PROSTATEx challenge. The performance of different combinations of mpMRI inputs to CNN was assessed and the best result was achieved using DWI and DCE-MRI modalities together with the zonal information of the finding. On the test set, the model achieved an area under the receiver operating characteristic curve of 0.80.

Model-based registration of preprocedure MR and intraprocedure US of the lumbar spine.

PURPOSE: Epidural and spinal needle insertions, as well as facet joint denervation and injections are widely performed procedures on the lumbar spine for delivering anesthesia and analgesia. Ultrasound (US)-based approaches have gained popularity for accurate needle placement, as they use a non-ionizing, inexpensive and accessible modality for guiding these procedures. However, due to the inherent difficulties in interpreting spinal US, they yet to become the clinical standard-of-care. METHODS: A novel statistical shape [Formula: see text] pose [Formula: see text] scale (s [Formula: see text] p [Formula: see text] s) model of the lumbar spine is jointly registered to preoperative magnetic resonance (MR) and US images. An instance of the model is created for each modality. The shape and scale model parameters are jointly computed, while the pose parameters are estimated separately for each modality. RESULTS: The proposed method is successfully applied to nine pairs of preoperative clinical MR volumes and their corresponding US images. The results are assessed using the target registration error (TRE) metric in both MR and US domains. The s [Formula: see text] p [Formula: see text] s model in the proposed joint registration framework results in a mean TRE of 2.62 and 4.20 mm for MR and US images, respectively, on different landmarks. CONCLUSION: The joint framework benefits from the complementary features in both modalities, leading to significantly smaller TREs compared to a model-to-US registration approach. The s [Formula: see text] p [Formula: see text] s model also outperforms our previous shape [Formula: see text] pose model of the lumbar spine, as separating scale from pose allows to better capture pose and guarantees equally-sized vertebrae in both modalities. Furthermore, the simultaneous visualization of the patient-specific models on the MR and US domains makes it possible for clinicians to better evaluate the local registration accuracy.