Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning.

Magnetic Resonance (MR) images suffer from various types of artifacts due to motion, spatial resolution, and under-sampling. Conventional deep learning methods deal with removing a specific type of artifact, leading to separately trained models for each artifact type that lack the shared knowledge generalizable across artifacts. Moreover, training a model for each type and amount of artifact is a tedious process that consumes more training time and storage of models. On the other hand, the shared knowledge learned by jointly training the model on multiple artifacts might be inadequate to generalize under deviations in the types and amounts of artifacts. Model-agnostic meta-learning (MAML), a nested bi-level optimization framework is a promising technique to learn common knowledge across artifacts in the outer level of optimization, and artifact-specific restoration in the inner level. We propose curriculum-MAML (CMAML), a learning process that integrates MAML with curriculum learning to impart the knowledge of variable artifact complexity to adaptively learn restoration of multiple artifacts during training. Comparative studies against Stochastic Gradient Descent and MAML, using two cardiac datasets reveal that CMAML exhibits (i) better generalization with improved PSNR for 83% of unseen types and amounts of artifacts and improved SSIM in all cases, and (ii) better artifact suppression in 4 out of 5 cases of composite artifacts (scans with multiple artifacts).Clinical relevance- Our results show that CMAML has the potential to minimize the number of artifact-specific models; which is essential to deploy deep learning models for clinical use. Furthermore, we have also taken another practical scenario of an image affected by multiple artifacts and show that our method performs better in 80% of cases.

Automated Knowledge Modeling for Cancer Clinical Practice Guidelines.

Clinical Practice Guidelines (CPGs) for cancer diseases evolve rapidly due to new evidence generated by active research. Currently, CPGs are primarily published in a document format that is ill-suited for managing this developing knowledge. A knowledge model of the guidelines document suitable for programmatic interaction is required. This work proposes an automated method for extraction of knowledge from National Comprehensive Cancer Network (NCCN) CPGs in Oncology and generating a structured model containing the retrieved knowledge. The proposed method was tested using two versions of NCCN Non-Small Cell Lung Cancer (NSCLC) CPG to demonstrate the effectiveness in faithful extraction and modeling of knowledge. Three enrichment strategies using Cancer staging information, Unified Medical Language System (UMLS) Metathesaurus & National Cancer Institute thesaurus (NCIt) concepts, and Node classification are also presented to enhance the model towards enabling programmatic traversal and querying of cancer care guidelines. The Node classification was performed using a Support Vector Machine (SVM) model, achieving a classification accuracy of 0.81 with 10-fold cross-validation.

Efficacy of an Automated Algorithm for Screening Diabetic Retinopathy in Gradable and Ungradable Images in Real-Time Conditions.

Background: To examine the effectiveness of a computer-assisted device (CAD) for diabetic retinopathy (DR) screening from retinal photographs at a vitreoretinal outpatient department (VR OPD), telecamps, and diabetes outpatient clinic by an ophthalmologist. In particular, the effectiveness of CAD in gradable and ungradable retinal images was examined. Methods: A total of 848 eyes of 485 patients underwent 45° retinal photographs at the VR OPD of a tertiary care hospital in southern India. A total of 939 eyes of 472 patients with diabetes were examined in the telecamps conducted in remote villages in Tamil Nadu, a state in southern India. A total of 2,526 eyes of 1,263 patients were examined in a diabetes clinic using 45° field retinal photographs. The algorithm was validated under physiological dilatation (without pharmacological dilatation) in all three arms. Results: Seventy-one percent of 848 eyes in VR OPD, 13% of 939 eyes in telecamps, and 7% of 2,526 eyes in diabetes clinic were diagnosed to have DR. The algorithm showed 78.3% sensitivity and 55.1% specificity for all images and 78.9% sensitivity and 56.8% specificity for gradable images in the VR OPD; 80.1% sensitivity and 79.2% specificity for all images and 84.8% sensitivity and 80.0% sensitivity for gradable images in telecamps; 63.0% sensitivity and 79.6% specificity for all images and 63.2% sensitivity and 78.1% specificity for gradable images in the diabetes clinic. The algorithm had an overall accuracy of 76.4%. The ungradable rate was variable. Conclusion: The algorithm performs equally well in identifying DR from gradable and ungradable photographs and may be used for DR screening in a rural setting with limited or no access to eye care.

Improving Fast MRI Reconstructions with Pretext Learning in Low-Data Regime.

Supervised deep learning methods have shown great promise for making magnetic resonance (MR) imaging scans faster. However, these supervised deep learning models need large volumes of labelled data to learn valuable representations and produce high-fidelity MR image reconstructions. The data used to train these models are often fully-sampled raw MR data, retrospectively under-sampled to simulate different MR acquisition acceleration factors. Obtaining high-quality, fully sampled raw MR data is costly and time-consuming. In this paper, we exploit the self supervision based learning by introducing a pretext method to boost feature learning using the more commonly available under-sampled MR data. Our experiments using different deep-learning-based reconstruction models in a low data regime demonstrate that self-supervision ensures stable training and improves MR image reconstruction.

Deep learning based non-contact physiological monitoring in Neonatal Intensive Care Unit.

Preterm babies in the Neonatal Intensive Care Unit (NICU) have to undergo continuous monitoring of their cardiac health. Conventional monitoring approaches are contact-based, making the neonates prone to various nosocomial infections. Video-based monitoring approaches have opened up potential avenues for contactless measurement. This work presents a pipeline for remote estimation of cardiopulmonary signals from videos in NICU setup. We have proposed an end-to-end deep learning (DL) model that integrates a non-learning-based approach to generate surrogate ground truth (SGT) labels for supervision, thus refraining from direct dependency on true ground truth labels. We have performed an extended qualitative and quantitative analysis to examine the efficacy of our proposed DL-based pipeline and achieved an overall average mean absolute error of 4.6 beats per minute (bpm) and root mean square error of 6.2 bpm in the estimated heart rate.

Antibacterial Efficacy of Hubballi Propolis against Aggregatibacter Actinomycetemcomitans One of the Major Causative Organisms of Perimplantitis: An In vitro Study.

Background: Peri-implantitis can be attributed to many underlying causes, one of the chief ones being due to infection caused by oral micro flora and particularly Aggregatibacter actinomycetemcomitans. Antibiotics are administered along with mechanical debridement to control the infection. The side effect of conventional antibiotic therapy and drug resistance has led to the necessity for alternate approaches to handle infections. Natural products are being investigated because of their multi-target activity and structurally different from the normal antibiotics. Propolis a product by Apis Mellifera bees as a wound healing and bone regenerating effect along with antimicrobial effect. One of the important features of Propolis is the chemical properties of Propolis changes with the different locations of procurement. Antimicrobial activity of Hubballi propolis against Aggregatibacter actinomycetemcomitans is not been reported in the literature. Aim: The aim of this study is to evaluate the antimicrobial effect of the Hubballi Propolis against Aggregatibacter actinomycetemcomitans. Methods: The two solvents used for the study were water and 70% Aq ethanol. Minimum inhibitory concentration (MIC), total phenolic contents (TPC), and total flavonoid content (TFC) were tested. Results: Hubballi Propolis sample showed antimicrobial effect against Aggregatibacter actinomycetemcomitans with MIC range from 0.1 mg/ml to 0.25 mg/ml. Conclusion: Hubballi Propolis is effective against Aggregatibacter actinomycetemcomitans infection thus may help in treating peri-implantitis. Propolis extracted with water as solvent showed better MIC, higher TPC and TFC than the propolis extracted using alcohol as solvent. This feature is noteworthy as the formulations produced using water extract is favorable than alcohol extract of propolis which irritates the mucosa and hence difficult for its application in dentistry.

A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction.

Deep learning networks have shown promising results in fast magnetic resonance imaging (MRI) reconstruction. In our work, we develop deep networks to further improve the quantitative and the perceptual quality of reconstruction. To begin with, we propose reconsynergynet (RSN), a network that combines the complementary benefits of independently operating on both the image and the Fourier domain. For a single-coil acquisition, we introduce deep cascade RSN (DC-RSN), a cascade of RSN blocks interleaved with data fidelity (DF) units. Secondly, we improve the structure recovery of DC-RSN for T2 weighted Imaging (T2WI) through assistance of T1 weighted imaging (T1WI), a sequence with short acquisition time. T1 assistance is provided to DC-RSN through a gradient of log feature (GOLF) fusion. Furthermore, we propose perceptual refinement network (PRN) to refine the reconstructions for better visual information fidelity (VIF), a metric highly correlated to radiologist's opinion on the image quality. Lastly, for multi-coil acquisition, we propose variable splitting RSN (VS-RSN), a deep cascade of blocks, each block containing RSN, multi-coil DF unit, and a weighted average module. We extensively validate our models DC-RSN and VS-RSN for single-coil and multi-coil acquisitions and report the state-of-the-art performance. We obtain a SSIM of 0.768, 0.923, and 0.878 for knee single-coil-4x, multi-coil-4x, and multi-coil-8x in fastMRI, respectively. We also conduct experiments to demonstrate the efficacy of GOLF based T1 assistance and PRN.

MRI Super-Resolution using Laplacian Pyramid Convolutional Neural Networks with Isotropic Undecimated Wavelet Loss.

High spatial resolution of Magnetic Resonance images (MRI) provide rich structural details to facilitate accurate diagnosis and quantitative image analysis. However the long acquisition time of MRI leads to patient discomfort and possible motion artifacts in the reconstructed image. Single Image Super-Resolution (SISR) using Convolutional Neural networks (CNN) is an emerging trend in biomedical imaging especially Magnetic Resonance (MR) image analysis for image post processing. An efficient choice of SISR architecture is required to achieve better quality reconstruction. In addition, a robust choice of loss function together with the domain in which these loss functions operate play an important role in enhancing the fine structural details as well as removing the blurring effects to form a high resolution image. In this work, we propose a novel combined loss function consisting of an L1 Charbonnier loss function in the image domain and a wavelet domain loss function called the Isotropic Undecimated Wavelet loss (IUW loss) to train the existing Laplacian Pyramid Super-Resolution CNN. The proposed loss function was evaluated on three MRI datasets - privately collected Knee MRI dataset and the publicly available Kirby21 brain and iSeg infant brain datasets and on benchmark SISR datasets for natural images. Experimental analysis shows promising results with better recovery of structure and improvements in qualitative metrics.

Artificial intelligence in detection and segmentation of internal auditory canal and its nerves using deep learning techniques.

PURPOSE: Artificial intelligence (AI) in medical imaging is a burgeoning topic that involves the interpretation of complex image structures. The recent advancements in deep learning techniques increase the computational powers to extract vital features without human intervention. The automatic detection and segmentation of subtle tissue such as the internal auditory canal (IAC) and its nerves is a challenging task, and it can be improved using deep learning techniques. METHODS: The main scope of this research is to present an automatic method to detect and segment the IAC and its nerves like the facial nerve, cochlear nerve, inferior vestibular nerve, and superior vestibular nerve. To address this issue, we propose a Mask R-CNN approach driven with U-net to detect and segment the IAC and its nerves. The Mask R-CNN with its backbone network of the RESNET50 model learns a background-based localization policy to produce an actual bounding box of the IAC. Furthermore, the U-net segments the structure related information of IAC and its nerves by learning its features. RESULTS: The proposed method was experimented on clinical datasets of 50 different patients including adults and children. The localization of IAC using Mask R-CNN was evaluated using Intersection of Union (IoU), and segmentation of IAC and its nerves was evaluated using Dice similarity coefficient. CONCLUSIONS: The localization result shows that mean IoU of RESNET50, RESNET101 are 0.79 and 0.74, respectively. The Dice similarity coefficient of IAC and its nerves using region growing, PSO and U-net method scored 92%, 94%, and 96%, respectively. The result shows that the proposed method outperform better in localization and segmentation of IAC and its nerves. Thus, AI aids the radiologists in making the right decisions as the localization and segmentation of IAC is accurate.

Semantic segmentation of microscopic neuroanatomical data by combining topological priors with encoder-decoder deep networks.

Understanding of neuronal circuitry at cellular resolution within the brain has relied on neuron tracing methods which involve careful observation and interpretation by experienced neuroscientists. With recent developments in imaging and digitization, this approach is no longer feasible with the large scale (terabyte to petabyte range) images. Machine learning based techniques, using deep networks, provide an efficient alternative to the problem. However, these methods rely on very large volumes of annotated images for training and have error rates that are too high for scientific data analysis, and thus requires a significant volume of human-in-the-loop proofreading. Here we introduce a hybrid architecture combining prior structure in the form of topological data analysis methods, based on discrete Morse theory, with the best-in-class deep-net architectures for the neuronal connectivity analysis. We show significant performance gains using our hybrid architecture on detection of topological structure (e.g. connectivity of neuronal processes and local intensity maxima on axons corresponding to synaptic swellings) with precision/recall close to 90% compared with human observers. We have adapted our architecture to a high performance pipeline capable of semantic segmentation of light microscopic whole-brain image data into a hierarchy of neuronal compartments. We expect that the hybrid architecture incorporating discrete Morse techniques into deep nets will generalize to other data domains.

Validation of a Customized Algorithm for the Detection of Diabetic Retinopathy from Single-Field Fundus Photographs in a Tertiary Eye Care Hospital.

The study was done to validate the real time efficacy of a customised algorithm in detecting diabetic retinopathy (DR) among diabetic patients being examined at the vitreo retinal outpatient department (VR OPD) of a tertiary care hospital, Diabetic Retinopathy algorithm showed sensitivity of 79% and specificity of 57% which is an acceptable methodology to diagnose diabetic retinopathy and avoid unnecessary referrals.

Fully Convolutional Networks for Monocular Retinal Depth Estimation and Optic Disc-Cup Segmentation.

Glaucoma is a serious ocular disorder for which the screening and diagnosis are carried out by the examination of the optic nerve head (ONH). The color fundus image (CFI) is the most common modality used for ocular screening. In CFI, the central region which is the optic disc and the optic cup region within the disc are examined to determine one of the important cues for glaucoma diagnosis called the optic cup-to-disc ratio (CDR). CDR calculation requires accurate segmentation of optic disc and cup. Another important cue for glaucoma progression is the variation of depth in ONH region. In this paper, we first propose a deep learning framework to estimate depth from a single fundus image. For the case of monocular retinal depth estimation, we are also plagued by the labeled data insufficiency. To overcome this problem we adopt the technique of pretraining the deep network where, instead of using a denoising autoencoder, we propose a new pretraining scheme called pseudo-depth reconstruction, which serves as a proxy task for retinal depth estimation. Empirically, we show pseudo-depth reconstruction to be a better proxy task than denoising. Our results outperform the existing techniques for depth estimation on the INSPIRE dataset. To extend the use of depth map for optic disc and cup segmentation, we propose a novel fully convolutional guided network, where, along with the color fundus image the network uses the depth map as a guide. We propose a convolutional block called multimodal feature extraction block to extract and fuse the features of the color image and the guide image. We extensively evaluate the proposed segmentation scheme on three datasets- ORIGA, RIMONEr3, and DRISHTI-GS. The performance of the method is comparable and in many cases, outperforms the most recent state of the art.

A high-throughput neurohistological pipeline for brain-wide mesoscale connectivity mapping of the common marmoset.

Understanding the connectivity architecture of entire vertebrate brains is a fundamental but difficult task. Here we present an integrated neuro-histological pipeline as well as a grid-based tracer injection strategy for systematic mesoscale connectivity mapping in the common marmoset (Callithrix jacchus). Individual brains are sectioned into ~1700 20 µm sections using the tape transfer technique, permitting high quality 3D reconstruction of a series of histochemical stains (Nissl, myelin) interleaved with tracer labeled sections. Systematic in-vivo MRI of the individual animals facilitates injection placement into reference-atlas defined anatomical compartments. Further, by combining the resulting 3D volumes, containing informative cytoarchitectonic markers, with in-vivo and ex-vivo MRI, and using an integrated computational pipeline, we are able to accurately map individual brains into a common reference atlas despite the significant individual variation. This approach will facilitate the systematic assembly of a mesoscale connectivity matrix together with unprecedented 3D reconstructions of brain-wide projection patterns in a primate brain.

Segmentation of Femoral Cartilage from Knee Ultrasound Images Using Mask R-CNN.

Segmentation of knee cartilage from Ultrasound (US) images is essential for various clinical tasks in diagnosis and treatment planning of Osteoarthritis. Moreover, the potential use of US imaging for guidance in robotic knee arthroscopy is presently being investigated. The femoral cartilage being the main organ at risk during the operation, it is paramount to be able to segment this structure, to make US guidance feasible. In this paper, we set forth a deep learning network, Mask R-CNN, based femoral cartilage segmentation in 2D US images for these types of applications. While the traditional imaging approaches showed promising results, they are mostly not real-time and involve human interaction. This being the case, in recent years, deep learning has paved its way into medical imaging showing commendable results. However, deep learning-based segmentation in US images remains unexplored. In the present study we employ Mask R-CNN on US images of the knee cartilage. The performance of the method is analyzed in various scenarios, with and without Gaussian filter preprocessing and pretraining the network with different datasets. The best results are observed when the images are preprocessed and the network is pretrained with COCO 2016 image dataset. A maximum Dice Similarity Coefficient (DSC) of 0.88 and an average DSC of 0.80 is achieved when tested on 55 images indicating that the proposed method has a potential for clinical applications.

RespNet: A deep learning model for extraction of respiration from photoplethysmogram.

Respiratory ailments afflict a wide range of people and manifests itself through conditions like asthma and sleep apnea. Continuous monitoring of chronic respiratory ailments is seldom used outside the intensive care ward due to the large size and cost of the monitoring system. While Electrocardiogram (ECG) based respiration extraction is a validated approach, its adoption is limited by access to a suitable continuous ECG monitor. Recently, due to the widespread adoption of wearable smartwatches with in-built Photoplethysmogram (PPG) sensor, it is being considered as a viable candidate for continuous and unobtrusive respiration monitoring. Research in this domain, however, has been predominantly focussed on estimating respiration rate from PPG. In this work, a novel end-to-end deep learning network called RespNet is proposed to perform the task of extracting the respiration signal from a given input PPG as opposed to extracting respiration rate. The proposed network was trained and tested on two different datasets utilizing different modalities of reference respiration signal recordings. Also, the similarity and performance of the proposed network against two conventional signal processing approaches for extracting respiration signal were studied. The proposed method was tested on two independent datasets with a Mean Squared Error of 0.262 and 0.145. The cross-correlation coefficient of the respective datasets were found to be 0.933 and 0.931. The reported errors and similarity was found to be better than conventional approaches. The proposed approach would aid clinicians to provide comprehensive evaluation of sleep-related respiratory conditions and chronic respiratory ailments while being comfortable and inexpensive for the patient.

Polyp Segmentation using Generative Adversarial Network.

Colorectal cancer is one of the highest causes of cancer-related death and the patient's survival rate depends on the stage at which polyps are detected. Polyp segmentation is a challenging research task due to variations in the size and shape of polyps leading to necessitate robust approaches for diagnosis. This paper studies the deep generative convolutional framework for the task of polyp segmentation. Here, the analysis of polyp segmentation has been explored with the pix2pix conditional generative adversarial network. On CVC- Clinic dataset, the proposed network achieves Jaccard index of 81.27% and Dice index of 88.48%.

Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation.

Image segmentation is a primary task in many medical applications. Recently, many deep networks derived from U-Net has been extensively used in various medical image segmentation tasks. However, in most of the cases, networks similar to U-net produce coarse and non-smooth segmentations with lots of discontinuities. To improve and refine the performance of U-Net like networks, we propose the use of parallel decoders which along with performing the mask predictions also perform contour prediction and distance map estimation. The contour and distance map aid in ensuring smoothness in the segmentation predictions. To facilitate joint training of three tasks, we propose a novel architecture called Psi-Net with a single encoder and three parallel decoders (thus having a shape of Ψ), one decoder to learn the segmentation mask prediction and other two decoders to learn the auxiliary tasks of contour detection and distance map estimation. The learning of these auxiliary tasks helps in capturing the shape and the boundary information. We also propose a new joint loss function for the proposed architecture. The loss function consists of a weighted combination of Negative Log Likelihood and Mean Square Error loss. We have used two publicly available datasets: 1) Origa dataset for the task of optic cup and disc segmentation and 2) Endovis segment dataset for the task of polyp segmentation to evaluate our model. We have conducted extensive experiments using our network to show our model gives better results in terms of segmentation, boundary and shape metrics.

Brain-wide Maps Reveal Stereotyped Cell-Type-Based Cortical Architecture and Subcortical Sexual Dimorphism.

The stereotyped features of neuronal circuits are those most likely to explain the remarkable capacity of the brain to process information and govern behaviors, yet it has not been possible to comprehensively quantify neuronal distributions across animals or genders due to the size and complexity of the mammalian brain. Here we apply our quantitative brain-wide (qBrain) mapping platform to document the stereotyped distributions of mainly inhibitory cell types. We discover an unexpected cortical organizing principle: sensory-motor areas are dominated by output-modulating parvalbumin-positive interneurons, whereas association, including frontal, areas are dominated by input-modulating somatostatin-positive interneurons. Furthermore, we identify local cell type distributions with more cells in the female brain in 10 out of 11 sexually dimorphic subcortical areas, in contrast to the overall larger brains in males. The qBrain resource can be further mined to link stereotyped aspects of neuronal distributions to known and unknown functions of diverse brain regions.

Local characterization of neovascularization and identification of proliferative diabetic retinopathy in retinal fundus images.

Neovascularization (NV) is a characteristic of the onset of sight-threatening stage of DR, called proliferative DR (PDR). Identification of PDR requires modeling of these unregulated ill-formed vessels, and other associated signs of PDR. We present an approach that models the micro-pattern of local variations (using texture based analysis) and quantifies structural changes in vessel patterns in localized patches, to arrive at a score of neovascularity. The distribution of patch-level confidence scores is collated into an image-level decision of presence or absence of PDR. Evaluated on a dataset of 779 images combining public data and clinical data from local hospitals, the patch-level neovascularity prediction has a sensitivity of 92.4% at 92.6% specificity. For image-level PDR identification our method is shown to achieve sensitivity of 83.3% at a high specificity operating point of 96.1% specificity, and specificity of 83% at high sensitivity operating point of 92.2% sensitivity. Our approach could have potential application in DR grading where it can localize NVE regions and identify PDR images for immediate intervention.

Assessment of Computer-Assisted Screening Technology for Diabetic Retinopathy Screening in India - Preliminary Results and Recommendations from a Pilot Study.

BACKGROUND: Diabetic retinopathy (DR) is regarded as a major cause of preventable blindness, which can be detected and treated if the cases are identified by screening. Screening for DR is therefore being practiced in developed countries, and tele screening has been a prominent model of delivery of eye care for screening DR. AIM: Our study has been designed to provide inputs on the suitability of a computer-assisted DR screening solution, for use in a larger prospective study. METHODS: Computer-assisted screening technology for grading diabetic retinopathy from fundus images by a set of machine learning algorithms. RESULTS: The preliminary recommendations from a pilot study of a system built using the public datasets and retrospective images, showed a good sensitivity and specificity. CONCLUSION: The machine learning algorithms has to be validated on a larger dataset of a population level study.