Abhijit Guha Roy

ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks

Optical coherence tomography (OCT) is used for non-invasive diagnosis of diabetic macular edema assessing the retinal layers. In this paper, we propose a new fully convolutional deep architecture, termed ReLayNet, for end-to-end segmentation of retinal layers and fluid masses in eye OCT scans. ReLayNet uses a contracting path of convolutional blocks (encoders) to learn a hierarchy of contextual features, followed by an expansive path of convolutional blocks (decoders) for semantic segmentation. ReLayNet is trained to optimize a joint loss function comprising of weighted logistic regression and Dice overlap loss. The framework is validated on a publicly available benchmark dataset with comparisons against five state-of-the-art segmentation methods including two deep learning based approaches to substantiate its effectiveness.

Magnetic ordering in Fe2-xZnxMoO4(X = 0.1-1) spinel

Abstract We have studied the diluted Fe 2− x Zn x MoO 4 spinel ferrite which shows a frozen disordered magnetic state at low temperature. Magnetic properties are examined by DC magnetisation measurements as a function of temperature, field and time and AC susceptibility experiment. Our measurements show that this disordered magnetic system at low fields, shares many common features with spin glass or cluster glass like phases. Results suggest that the interaction gradually changes as the magnetic ion concentration decreases by the substitution of non-magnetic Zn on A site and causing a perturbation to the magnetically ordered spins and magnetic order decreases.

Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data

Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with existing tools and to use them for pre-training. For the subsequent fine-tuning of the network with manually labeled data, we introduce error corrective boosting (ECB), which emphasizes parameter updates on classes with lower accuracy. Furthermore, we introduce SkipDeconv-Net (SD-Net), a new F-CNN architecture for brain segmentation that combines skip connections with the unpooling strategy for upsampling. The SD-Net addresses challenges of severe class imbalance and errors along boundaries. With application to whole-brain MRI T1 scan segmentation, we generate auxiliary labels on a large dataset with FreeSurfer and fine-tune on two datasets with manual annotations. Our results show that the inclusion of auxiliary labels and ECB yields significant improvements. SD-Net segments a 3D scan in 7 secs in comparison to 30 hours for the closest multi-atlas segmentation method, while reaching similar performance. It also outperforms the latest state-of-the-art F-CNN models.

Magnetic properties of Fe2Mo1−xTixO4

Abstract We report the synthesis and characterisation of the spinel oxide Fe2Mo1−xTixO4 (x = 0 to 1). The substitution of Ti in Fe2MoO4 shows interesting features in the Field Cooled and Zero Field Cooled magnetisation data. We observed a strong negative remanence and spin compensation temperature below Curie temperature. The results suggest the role of Mo in the double exchange interaction with systematic variation of TC with increasing Ti concentration. Field Cooled and Zero Field Cooled data measured under same field shows different compensation temperatures where the magnetic moment is minimum. Also applying a negative field resulted in the negative image of the same magnetisation.

Supervised domain adaptation of decision forests: Transfer of models trained in vitro for in vivo intravascular ultrasound tissue characterization

In this paper, we propose a supervised domain adaptation (DA) framework for adapting decision forests in the presence of distribution shift between training (source) and testing (target) domains, given few labeled examples. We introduce a novel method for DA through an error-correcting hierarchical transfer relaxation scheme with domain alignment, feature normalization, and leaf posterior reweighting to correct for the distribution shift between the domains. For the first time we apply DA to the challenging problem of extending in vitro trained forests (source domain) for in vivo applications (target domain). The proof-of-concept is provided for in vivo characterization of atherosclerotic tissues using intravascular ultrasound signals, where presence of flowing blood is a source of distribution shift between the two domains. This potentially leads to misclassification upon direct deployment of in vitro trained classifier, thus motivating the need for DA as obtaining reliable in vivo training labels is often challenging if not infeasible. Exhaustive validations and parameter sensitivity analysis substantiate the reliability of the proposed DA framework and demonstrates improved tissue characterization performance for scenarios where adaptation is conducted in presence of only a few examples. The proposed method can thus be leveraged to reduce annotation costs and improve computational efficiency over conventional retraining approaches.

Lumen Segmentation in Intravascular Optical Coherence Tomography Using Backscattering Tracked and Initialized Random Walks

Intravascular imaging using ultrasound or optical coherence tomography (OCT) is predominantly used to adjunct clinical information in interventional cardiology. OCT provides high-resolution images for detailed investigation of atherosclerosis induced thickening of the lumen wall resulting in arterial blockage and triggering acute coronary events. However, the stochastic uncertainty of speckles limits effective visual investigation over large volume of pullback data, and clinicians are challenged by their inability to investigate subtle variations in the lumen topology associated with plaque vulnerability and onset of necrosis. This paper presents a lumen segmentation method using OCT imaging physics-based graph representation of signals and random walks image segmentation approaches. The edge weights in the graph are assigned incorporating OCT signal attenuation physics models. Optical backscattering maxima is tracked along each Ascan of OCT and is subsequently refined using global graylevel statistics and used for initializing seeds for the random walks image segmentation. Accuracy of lumen versus tunica segmentation has been measured on 15 in vitro and 6 in vivo pullbacks, each with 150-200 frames using 1) Cohens kappa coefficient (0.9786 ± 0.0061) measured with respect to cardiologists annotation and 2) divergence of histogram of the segments computed with Kullback-Leibler (5.17 ± 2.39) and Bhattacharya measures (0.56 ± 0.28). High segmentation accuracy and consistency substantiates the characteristics of this method to reliably segment lumen across pullbacks in the presence of vulnerability cues and necrotic pool and has a deterministic finite time-complexity. This paper in general also illustrates the development of methods and framework for tissue classification and segmentation incorporating cues of tissue-energy interaction physics in imaging.

Deep neural ensemble for retinal vessel segmentation in fundus images towards achieving label-free angiography

Automated segmentation of retinal blood vessels in label-free fundus images entails a pivotal role in computed aided diagnosis of ophthalmic pathologies, viz., diabetic retinopathy, hypertensive disorders and cardiovascular diseases. The challenge remains active in medical image analysis research due to varied distribution of blood vessels, which manifest variations in their dimensions of physical appearance against a noisy background. In this paper we formulate the segmentation challenge as a classification task. Specifically, we employ unsupervised hierarchical feature learning using ensemble of two level of sparsely trained denoised stacked autoencoder. First level training with bootstrap samples ensures decoupling and second level ensemble formed by different network architectures ensures architectural revision. We show that ensemble training of auto-encoders fosters diversity in learning dictionary of visual kernels for vessel segmentation. SoftMax classifier is used for fine tuning each member autoencoder and multiple strategies are explored for 2-level fusion of ensemble members. On DRIVE dataset, we achieve maximum average accuracy of 95.33% with an impressively low standard deviation of 0.003 and Kappa agreement coefficient of 0.708. Comparison with other major algorithms substantiates the high efficacy of our model.Automated segmentation of retinal blood vessels in label-free fundus images entails a pivotal role in computed aided diagnosis of ophthalmic pathologies, viz., diabetic retinopathy, hypertensive disorders and cardiovascular diseases. The challenge remains active in medical image analysis research due to varied distribution of blood vessels, which manifest variations in their dimensions of physical appearance against a noisy background. In this paper we formulate the segmentation challenge as a classification task. Specifically, we employ unsupervised hierarchical feature learning using ensemble of two level of sparsely trained denoised stacked autoencoder. First level training with bootstrap samples ensures decoupling and second level ensemble formed by different network architectures ensures architectural revision. We show that ensemble training of auto-encoders fosters diversity in learning dictionary of visual kernels for vessel segmentation. SoftMax classifier is used for fine tuning each member autoencoder and multiple strategies are explored for 2-level fusion of ensemble members. On DRIVE dataset, we achieve maximum average accuracy of 95.33% with an impressively low standard deviation of 0.003 and Kappa agreement coefficient of 0.708. Comparison with other major algorithms substantiates the high efficacy of our model.

Analysis of polarization speckle for imaging through random birefringent scatterer

Propagation of a coherent light through an anisotropic random medium generates randomly polarized field, known as polarization speckle. In this paper, an experimental technique is proposed and demonstrated to recover the transmittance of a polarized object from polarization speckle. Recovery of the polarized object from polarization speckle is made possible by combining the far-field intensity correlation of the object speckle with off-axis holography to determine the complex coherence function of the speckle. The desired object speckle which is uniformly polarized is filtered from the polarization speckle using a polarizer. The results are compared with the case where the complex coherence function is determined in the absence of the polarizer.

Classifying histopathology whole-slides using fusion of decisions from deep convolutional network on a collection of random multi-views at multi-magnification

Histopathology forms the gold standard for confirmed diagnosis of a suspicious hyperplasia being benign or malignant and for its sub-typing. While techniques like whole-slide imaging have enabled computer assisted analysis for exhaustive reporting of the tissue section, it has also given rise to the big-data deluge and the time complexity associated with processing GBs of image data acquired over multiple magnifications. Since preliminary screening of a slide into benign or malignant carried out on the fly during the digitization process can reduce a Pathologists work load, to devote more time for detailed analysis, slide screening has to be performed on the fly with high sensitivity. We propose a deep convolutional neural network (CNN) based solution, where we analyse images from random number of regions of the tissue section at multiple magnifications without any necessity of view correspondence across magnifications. Further a majority voting based approach is used for slide level diagnosis, i.e., the class posteriori estimate of each views at a particular magnification is obtained from the magnification specific CNN, and subsequently posteriori estimate across random multi-views at multi-magnification are voting filtered to provide a slide level diagnosis. We have experimentally evaluated performance using a patient level 5-folded cross-validation with 58 malignant and 24 benign cases of breast tumors to obtain average accuracy of 94.67 ± 14.60%, sensitivity of 96.00 ± 8.94%, specificity of 92.00 ± 17.85% and F-score of 96.24 ± 5.29% while processing each view in ≈ 10 ms.

Hashing with Residual Networks for Image Retrieval

We propose a novel deeply learnt convolutional neural network architecture for supervised hashing of medical images through residual learning, coined as Deep Residual Hashing (DRH). It offers maximal separability of classes in hashing space while preserving semantic similarities in local embedding neighborhoods. We also introduce a new optimization formulation comprising of complementary loss terms and regularizations that suit hashing objectives the best by controlling over quantization errors. We conduct extensive validations on 2,599 Chest X-ray images with co-morbidities against eight state-of-the-art hashing techniques and demonstrate improved performance and computational benefits of the proposed algorithm for fast and scalable retrieval.