Debdoot Sheet

Brightness preserving dynamic fuzzy histogram equalization

This paper proposes a novel modification of the brightness preserving dynamic histogram equalization technique to improve its brightness preserving and contrast enhancement abilities while reducing its computational complexity. The modified technique, called Brightness Preserving Dynamic Fuzzy Histogram Equalization (BPDFHE), uses fuzzy statistics of digital images for their representation and processing. Representation and processing of images in the fuzzy domain enables the technique to handle the inexactness of gray level values in a better way, resulting in improved performance. Execution time is dependent on image size and nature of the histogram, however experimental results show it to be faster as compared to the techniques compared here. The performance analysis of the BPDFHE along with that for BPDHE has been given for comparative evaluation.

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.

Characterization and scanning electron microscopic investigation of crosslinked freeze dried gelatin matrices for study of drug diffusivity and release kinetics

Drug delivery is a promising technique to enhance the therapeutic efficacy of the drug. However, properties of carrier materials require intense improvement for effective transport of drug molecules. In the current study, attempts have been made to develop freeze dried gelatin matrices cross linked with genipin at various temperatures (5°C, 15°C and 25°C) prior to freeze-drying (-80°C). The freeze dried matrices thus obtained at the said temperatures are characterized for crosslinking density, compression strength, swelling behaviors. The matrix crosslinked at 25°C showed highest Flory-Rehner crosslinking density (467 ± 46) (p<0.05), highest compressive strength (12.36 ± 0.12) (p<0.05) and lowest equilibrium water content. In this context, scanning electron microscopy (SEM) was performed to study the surface morphology (size and shape of pores) of the crosslinked matrices. These images were further processed for quantitative analysis of morphological features, viz., areas, radius, ferret diameter, length of major and minor axis and eccentricity using MATLAB toolboxes. These quantitative analyses correlate transport and the release kinetics of model anti-inflammatory drug (indomethacin) from crosslinked matrices in vitro to tune as a controllable delivery system. The diffusional exponent (n) for all constructs ranging from 0.61 to 0.69 (p<0.05) (0.45

Iterative Self-Organizing Atherosclerotic Tissue Labeling in Intravascular Ultrasound Images and Comparison With Virtual Histology

Intravascular ultrasound (IVUS) is the predominant imaging modality in the field of interventional cardiology that provides real-time cross-sectional images of coronary arteries and the extent of atherosclerosis. Due to heterogeneity of lesions and stringent spatial/spectral behavior of tissues, atherosclerotic plaque characterization has always been a challenge and still is an open problem. In this paper, we present a systematic framework from in vitro data collection, histology preparation, IVUS-histology registration along with matching procedure, and finally a robust texture-derived unsupervised atherosclerotic plaque labeling. We have performed our algorithm on in vitro and in vivo images acquired with single-element 40 MHz and 64-elements phased array 20 MHz transducers, respectively. In former case, we have quantified results by local contrasting of constructed tissue colormaps with corresponding histology images employing an independent expert and in the latter case, virtual histology images have been utilized for comparison. We tackle one of the main challenges in the field that is the reliability of tissues behind arc of calcified plaques and validate the results through a novel random walks framework by incorporating underlying physics of ultrasound imaging. We conclude that proposed framework is a formidable approach for retrieving imperative information regarding tissues and building a reliable training dataset for supervised classification and its extension for in vivo applications.

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.

Deep neural network and random forest hybrid architecture for learning to detect retinal vessels in fundus images

Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large-scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational imaging framework using deep and ensemble learning based hybrid architecture for reliable detection of blood vessels in fundus color images. A deep neural network (DNN) is used for unsupervised learning of vesselness dictionaries using sparse trained denoising auto-encoders (DAE), followed by supervised learning of the DNN response using a random forest for detecting vessels in color fundus images. In experimental evaluation with the DRIVE database, we achieve the objective of vessel detection with max. avg. accuracy of 0.9327 and area under ROC curve of 0.9195.

Joint learning of ultrasonic backscattering statistical physics and signal confidence primal for characterizing atherosclerotic plaques using intravascular ultrasound.

Intravascular Ultrasound (IVUS) is a predominant imaging modality in interventional cardiology. It provides real-time cross-sectional images of arteries and assists clinicians to infer about atherosclerotic plaques composition. These plaques are heterogeneous in nature and constitute fibrous tissue, lipid deposits and calcifications. Each of these tissues backscatter ultrasonic pulses and are associated with a characteristic intensity in B-mode IVUS image. However, clinicians are challenged when colocated heterogeneous tissue backscatter mixed signals appearing as non-unique intensity patterns in B-mode IVUS image. Tissue characterization algorithms have been developed to assist clinicians to identify such heterogeneous tissues and assess plaque vulnerability. In this paper, we propose a novel technique coined as Stochastic Driven Histology (SDH) that is able to provide information about co-located heterogeneous tissues. It employs learning of tissue specific ultrasonic backscattering statistical physics and signal confidence primal from labeled data for predicting heterogeneous tissue composition in plaques. We employ a random forest for the purpose of learning such a primal using sparsely labeled and noisy samples. In clinical deployment, the posterior prediction of different lesions constituting the plaque is estimated. Folded cross-validation experiments have been performed with 53 plaques indicating high concurrence with traditional tissue histology. On the wider horizon, this framework enables learning of tissue-energy interaction statistical physics and can be leveraged for promising clinical applications requiring tissue characterization beyond the application demonstrated in this paper.

Brightness preserving contrast enhancement in digital pathology

Majority of images in digital pathology require post acquisition adjustments to optimize brightness, contrast, and image visibility. Despite this fact much research effort has not been put in development of customized contrast enhancement techniques for this application. In this respect various contrast enhancement techniques developed for other application areas can be customized for the digital pathology. This paper proposes use of a brightness preserving contrast enhancement technique for image enhancement in digital pathology applications and compares its functional superiority over other contemporary techniques.

Hunting for necrosis in the shadows of intravascular ultrasound.

Coronary artery disease leads to failure of coronary circulation secondary to accumulation of atherosclerotic plaques. In adjunction to primary imaging of such vascular plaques using coronary angiography or alternatively magnetic resonance imaging, intravascular ultrasound (IVUS) is used predominantly for diagnosis and reporting of their vulnerability. In addition to plaque burden estimation, necrosis detection is an important aspect in reporting of IVUS. Since necrotic regions generally appear as hypoechic, with speckle appearance in these regions resembling true shadows or severe signal dropout regions, it contributes to variability in diagnosis. This dilemma in clinical assessment of necrosis imaged with IVUS is addressed in this work. In our approach, fidelity of the backscattered ultrasonic signal received by the imaging transducer is initially estimated. This is followed by identification of true necrosis using statistical physics of ultrasonic backscattering. A random forest machine learning framework is used for the purpose of learning the parameter space defining ultrasonic backscattering distributions related to necrotic regions and discriminating it from non-necrotic shadows. Evidence of hunting down true necrosis in shadows of intravascular ultrasound is presented with ex vivo experiments along with cross-validation using ground truth obtained from histology. Nevertheless, in some rare cases necrosis is marginally over-estimated, primarily on account of non-reliable statistics estimation. This limitation is due to sparse spatial sampling between neighboring scan-lines at location far from the transducer. We suggest considering the geometrical location of detected necrosis together with estimated signal confidence during clinical decision making in view of such limitation.

Detection of retinal vessels in fundus images through transfer learning of tissue specific photon interaction statistical physics

Loss of visual acuity on account of retina-related vision impairment can be partly prevented through periodic screening with fundus color imaging. Largescale screening is currently challenged by inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a framework for reliable blood vessel detection in fundus color imaging through inductive transfer learning of photon-tissue interaction statistical physics. The source task estimates photon-tissue interaction as a spatially localized Poisson process of photons sensed by the RGB sensor. The target task identifies vascular and non-vascular tissues using knowledge transferred from source task. The source and target domains are retinal images obtained using a color fundus camera with white-light illumination. In experimental evaluation with the DRIVE database, we achieve the objective of vessel detection with max. avg. accuracy of 0.9766 and kappa of 0.8213.