arXiv subjects

Kumar Abhishek

Publications and source records attributed to Kumar Abhishek.

32 records · Page 2Linked to original sources

arXiv2021

D-LEMA: Deep Learning Ensembles from Multiple Annotations -- Application to Skin Lesion Segmentation

Medical image segmentation annotations suffer from inter- and intra-observer variations even among experts due to intrinsic differences in human annotators and ambiguous boundaries. Leveraging a collection of annotators' opinions for an image is an interesting way of estimating a gold standard. Although training deep models in a supervised setting with a single annotation per image has been extensively studied, generalizing their training to work with datasets containing multiple annotations per image remains a fairly unexplored problem. In this paper, we propose an approach to handle annotators' disagreements when training a deep model. To this end, we propose an ensemble of Bayesian fully convolutional networks (FCNs) for the segmentation task by considering two major factors in the aggregation of multiple ground truth annotations: (1) handling contradictory annotations in the training data originating from inter-annotator disagreements and (2) improving confidence calibration through the fusion of base models' predictions. We demonstrate the superior performance of our approach on the ISIC Archive and explore the generalization performance of our proposed method by cross-dataset evaluation on the PH2 and DermoFit datasets.

eess.IV↗

arXiv2021

Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation

The segmentation of skin lesions is a crucial task in clinical decision support systems for the computer aided diagnosis of skin lesions. Although deep learning-based approaches have improved segmentation performance, these models are often susceptible to class imbalance in the data, particularly, the fraction of the image occupied by the background healthy skin. Despite variations of the popular Dice loss function being proposed to tackle the class imbalance problem, the Dice loss formulation does not penalize misclassifications of the background pixels. We propose a novel metric-based loss function using the Matthews correlation coefficient, a metric that has been shown to be efficient in scenarios with skewed class distributions, and use it to optimize deep segmentation models. Evaluations on three skin lesion image datasets: the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset, the DermoFit Image Library, and the PH2 dataset, show that models trained using the proposed loss function outperform those trained using Dice loss by 11.25%, 4.87%, and 0.76% respectively in the mean Jaccard index. The code is available at https://github.com/kakumarabhishek/MCC-Loss.

eess.IV↗

arXiv2021

A Multi-Arm Bandit Approach To Subset Selection Under Constraints

We explore the class of problems where a central planner needs to select a subset of agents, each with different quality and cost. The planner wants to maximize its utility while ensuring that the average quality of the selected agents is above a certain threshold. When the agents' quality is known, we formulate our problem as an integer linear program (ILP) and propose a deterministic algorithm, namely \dpss\ that provides an exact solution to our ILP. We then consider the setting when the qualities of the agents are unknown. We model this as a Multi-Arm Bandit (MAB) problem and propose \newalgo\ to learn the qualities over multiple rounds. We show that after a certain number of rounds, $τ$, \newalgo\ outputs a subset of agents that satisfy the average quality constraint with a high probability. Next, we provide bounds on $τ$ and prove that after $τ$ rounds, the algorithm incurs a regret of $O(\ln T)$, where $T$ is the total number of rounds. We further illustrate the efficacy of \newalgo\ through simulations. To overcome the computational limitations of \dpss, we propose a polynomial-time greedy algorithm, namely \greedy, that provides an approximate solution to our ILP. We also compare the performance of \dpss\ and \greedy\ through experiments.

cs.LG↗

arXiv2020

Artificial Intelligence in Glioma Imaging: Challenges and Advances

Primary brain tumors including gliomas continue to pose significant management challenges to clinicians. While the presentation, the pathology, and the clinical course of these lesions are variable, the initial investigations are usually similar. Patients who are suspected to have a brain tumor will be assessed with computed tomography (CT) and magnetic resonance imaging (MRI). The imaging findings are used by neurosurgeons to determine the feasibility of surgical resection and plan such an undertaking. Imaging studies are also an indispensable tool in tracking tumor progression or its response to treatment. As these imaging studies are non-invasive, relatively cheap and accessible to patients, there have been many efforts over the past two decades to increase the amount of clinically-relevant information that can be extracted from brain imaging. Most recently, artificial intelligence (AI) techniques have been employed to segment and characterize brain tumors, as well as to detect progression or treatment-response. However, the clinical utility of such endeavours remains limited due to challenges in data collection and annotation, model training, and the reliability of AI-generated information. We provide a review of recent advances in addressing the above challenges. First, to overcome the challenge of data paucity, different image imputation and synthesis techniques along with annotation collection efforts are summarized. Next, various training strategies are presented to meet multiple desiderata, such as model performance, generalization ability, data privacy protection, and learning with sparse annotations. Finally, standardized performance evaluation and model interpretability methods have been reviewed. We believe that these technical approaches will facilitate the development of a fully-functional AI tool in the clinical care of patients with gliomas.

eess.IV↗

arXiv2020

Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images

The semantic segmentation of skin lesions is an important and common initial task in the computer aided diagnosis of dermoscopic images. Although deep learning-based approaches have considerably improved the segmentation accuracy, there is still room for improvement by addressing the major challenges, such as variations in lesion shape, size, color and varying levels of contrast. In this work, we propose the first deep semantic segmentation framework for dermoscopic images which incorporates, along with the original RGB images, information extracted using the physics of skin illumination and imaging. In particular, we incorporate information from specific color bands, illumination invariant grayscale images, and shading-attenuated images. We evaluate our method on three datasets: the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset, the DermoFit Image Library, and the PH2 dataset and observe improvements of 12.02%, 4.30%, and 8.86% respectively in the mean Jaccard index over a baseline model trained only with RGB images.

cs.CV↗

arXiv2020

Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions

For sponsored search auctions, we consider contextual multi-armed bandit problem in the presence of strategic agents. In this setting, at each round, an advertising platform (center) runs an auction to select the best-suited ads relevant to the query posted by the user. It is in the best interest of the center to select an ad that has a high expected value (i.e., probability of getting a click $\times$ value it derives from a click of the ad). The probability of getting a click (CTR) is unknown to the center and depends on the user's profile (context) posting the query. Further, the value derived for a click is the private information to the advertiser and thus needs to be elicited truthfully. The existing solution in this setting is not practical as it suffers from very high regret ($O(T^{\frac{2}{3}})$).

cs.GT↗

arXiv2019

Signed Input Regularization

Over-parameterized deep models usually over-fit to a given training distribution, which makes them sensitive to small changes and out-of-distribution samples at inference time, leading to low generalization performance. To this end, several model-based and randomized data-dependent regularization methods are applied, such as data augmentation, which prevents a model from memorizing the training distribution. Instead of the random transformation of the input images, we propose SIGN, a new regularization method, which modifies the input variables using a linear transformation by estimating each variable's contribution to the final prediction. Our proposed technique maps the input data to a new manifold where the less important variables are de-emphasized. To test the effectiveness of the proposed idea and compare it with other competing methods, we design several test scenarios, such as classification performance, uncertainty, out-of-distribution, and robustness analyses. We compare the methods using three different datasets and four models. We find that SIGN encourages more compact class representations, which results in the model's robustness to random corruptions and out-of-distribution samples while also simultaneously achieving superior performance on normal data compared to other competing methods. Our experiments also demonstrate the successful transferability of the SIGN samples from one model to another.

cs.CV↗

arXiv2019

EvoZip: Efficient Compression of Large Collections of Evolutionary Trees

Phylogenetic trees represent evolutionary relationships among sets of organisms. Popular phylogenetic reconstruction approaches typically yield hundreds to thousands of trees on a common leafset. Storing and sharing such large collection of trees requires considerable amount of space and bandwidth. Furthermore, the huge size of phylogenetic tree databases can make search and retrieval operations time-consuming. Phylogenetic compression techniques are specialized compression techniques that exploit redundant topological information to achieve better compression of phylogenetic trees. Here, we present EvoZip, a new approach for phylogenetic tree compression. On average, EvoZip achieves 71.6% better compression and takes 80.71% less compression time and 60.47% less decompression time than TreeZip, the current state-of-the-art algorithm for phylogenetic tree compression. While EvoZip is based on TreeZip, it betters TreeZip due to (a) an improved bipartition and support list encoding scheme, (b) use of Deflate compression algorithm, and (c) use of an efficient tree reconstruction algorithm. EvoZip is freely available online for use by the scientific community.

q-bio.PE↗

arXiv2019

Introduction to Concentration Inequalities

In this report, we aim to exemplify concentration inequalities and provide easy to understand proofs for it. Our focus is on the inequalities which are helpful in the design and analysis of machine learning algorithms.

math.PR↗

arXiv2019

Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis

Skin lesion segmentation is a vital task in skin cancer diagnosis and further treatment. Although deep learning based approaches have significantly improved the segmentation accuracy, these algorithms are still reliant on having a large enough dataset in order to achieve adequate results. Inspired by the immense success of generative adversarial networks (GANs), we propose a GAN-based augmentation of the original dataset in order to improve the segmentation performance. In particular, we use the segmentation masks available in the training dataset to train the Mask2Lesion model, and use the model to generate new lesion images given any arbitrary mask, which are then used to augment the original training dataset. We test Mask2Lesion augmentation on the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset and achieve an improvement of 5.17% in the mean Dice score as compared to a model trained with only classical data augmentation techniques.

eess.IV↗

arXiv2019

Improved Inference via Deep Input Transfer

Although numerous improvements have been made in the field of image segmentation using convolutional neural networks, the majority of these improvements rely on training with larger datasets, model architecture modifications, novel loss functions, and better optimizers. In this paper, we propose a new segmentation performance boosting paradigm that relies on optimally modifying the network's input instead of the network itself. In particular, we leverage the gradients of a trained segmentation network with respect to the input to transfer it to a space where the segmentation accuracy improves. We test the proposed method on three publicly available medical image segmentation datasets: the ISIC 2017 Skin Lesion Segmentation dataset, the Shenzhen Chest X-Ray dataset, and the CVC-ColonDB dataset, for which our method achieves improvements of 5.8%, 0.5%, and 4.8% in the average Dice scores, respectively.

cs.CV↗

arXiv2019

A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations

The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations. To tackle this problem, we propose a non-linear radial basis convolutional feature mapping by learning a Mahalanobis-like distance function. Our method then maps the convolutional features onto a linearly well-separated manifold, which prevents small adversarial perturbations from forcing a sample to cross the decision boundary. We test the proposed method on three publicly available image classification and segmentation datasets namely, MNIST, ISBI ISIC 2017 skin lesion segmentation, and NIH Chest X-Ray-14. We evaluate the robustness of our method to different gradient (targeted and untargeted) and non-gradient based attacks and compare it to several non-gradient masking defense strategies. Our results demonstrate that the proposed method can increase the resilience of deep convolutional neural networks to adversarial perturbations without accuracy drop on clean data.

cs.CV↗

arXiv2019

Summarization and Visualization of Large Volumes of Broadcast Video Data

Over the past few years, there has been an astounding growth in the number of news channels as well as the amount of broadcast news video data. As a result, it is imperative that automated methods need to be developed in order to effectively summarize and store this voluminous data. Format detection of news videos plays an important role in news video analysis. Our problem involves building a robust and versatile news format detector, which identifies the different band elements in a news frame. Probabilistic progressive Hough transform has been used for the detection of band edges. The detected bands are classified as natural images, computer generated graphics (non-text) and text bands. A contrast based text detector has been used to identify the text regions from news frames. Two classifers have been trained and evaluated for the labeling of the detected bands as natural or artificial - Support Vector Machine (SVM) Classifer with RBF kernel, and Extreme Learning Machine (ELM) classifier. The classifiers have been trained on a dataset of 6000 images (3000 images of each class). The ELM classifier reports a balanced accuracy of 77.38%, while the SVM classifier outperforms it with a balanced accuracy of 96.5% using 10-fold cross-validation. The detected bands which have been fragmented due to the presence of gradients in the image have been merged using a three-tier hierarchical reasoning model. The bands were detected with a Jaccard Index of 0.8138, when compared to manually marked ground truth data. We have also presented an extensive literature review of previous work done towards news videos format detection, element band classification, and associative reasoning.

cs.CV↗

arXiv2010

Point- and arc-reaching sets of vertices in a digraph

In a digraph $D = (X, \mathcal{U})$, not necessarily finite, an arc $(x, y) \in \mathcal{U}$ is reachable from a vertex $u$ if there exists a directed walk $W$ that originates from $u$ and contains $(x, y)$. A subset $S \subseteq X$ is an arc-reaching set of $D$ if for every arc $(x, y)$ there exists a diwalk $W$ originating at a vertex $u \in S$ and containing $(x, y)$. A minimal arc-reaching set is an arc-basis. $S$ is a point-reaching set if for every vertex $v$ there exists a diwalk $W$ to $v$ originating at a vertex $u \in S$. A minimal point-reaching set is a point-basis. We extend the results of Harary, Norman, and Cartwright on point-bases in finite digraphs to point- and arc-bases in infinite digraphs.

math.CO↗