Santanu Chaudhury

Aiman Farooq, Deepak Mishra, Santanu Chaudhury

Survival prediction is a crucial task associated with cancer diagnosis and treatment planning. This paper presents a novel approach to survival prediction by harnessing comprehensive information from CT and PET scans, along with associated Genomic data. Current methods rely on either a single modality or the integration of multiple modalities for prediction without adequately addressing associations across patients or modalities. We aim to develop a robust predictive model for survival outcomes by integrating multi-modal imaging data with genetic information while accounting for associations across patients and modalities. We learn representations for each modality via a self-supervised module and harness the semantic similarities across the patients to ensure the embeddings are aligned closely. However, optimizing solely for global relevance is inadequate, as many pairs sharing similar high-level semantics, such as tumor type, are inadvertently pushed apart in the embedding space. To address this issue, we use a cross-patient module (CPM) designed to harness inter-subject correspondences. The CPM module aims to bring together embeddings from patients with similar disease characteristics. Our experimental evaluation of the dataset of Non-Small Cell Lung Cancer (NSCLC) patients demonstrates the effectiveness of our approach in predicting survival outcomes, outperforming state-of-the-art methods.

Aiman Farooq, Deepak Mishra, Santanu Chaudhury

In this study, we present a novel approach for predicting genomic information from medical imaging modalities using a transformer-based model. We aim to bridge the gap between imaging and genomics data by leveraging transformer networks, allowing for accurate genomic profile predictions from CT/MRI images. Presently most studies rely on the use of whole slide images (WSI) for the association, which are obtained via invasive methodologies. We propose using only available CT/MRI images to predict genomic sequences. Our transformer based approach is able to efficiently generate associations between multiple sequences based on CT/MRI images alone. This work paves the way for the use of non-invasive imaging modalities for precise and personalized healthcare, allowing for a better understanding of diseases and treatment.

Aiman Farooq, Azad Singh, Deepak Mishra et al.

Cancer survival prediction using multi-modal medical imaging presents a critical challenge in oncology, mainly due to the vulnerability of deep learning models to noise and protocol variations across imaging centers. Current approaches struggle to extract consistent features from heterogeneous CT and PET images, limiting their clinical applicability. We address these challenges by introducing RobSurv, a robust deep-learning framework that leverages vector quantization for resilient multi-modal feature learning. The key innovation of our approach lies in its dual-path architecture: one path maps continuous imaging features to learned discrete codebooks for noise-resistant representation, while the parallel path preserves fine-grained details through continuous feature processing. This dual representation is integrated through a novel patch-wise fusion mechanism that maintains local spatial relationships while capturing global context via Transformer-based processing. In extensive evaluations across three diverse datasets (HECKTOR, H\&N1, and NSCLC Radiogenomics), RobSurv demonstrates superior performance, achieving concordance index of 0.771, 0.742, and 0.734 respectively - significantly outperforming existing methods. Most notably, our model maintains robust performance even under severe noise conditions, with performance degradation of only 3.8-4.5\% compared to 8-12\% in baseline methods. These results, combined with strong generalization across different cancer types and imaging protocols, establish RobSurv as a promising solution for reliable clinical prognosis that can enhance treatment planning and patient care.

Atharva Pandey, Vishal Yadav, Rajendra Nagar et al.

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed, differing in memory efficiency and shape retrieval effectiveness, such as volumetric, parametric, and implicit surfaces. Radial basis functions provide memory-efficient parameterization of the implicit surface. However, we show that training a neural network using the mean squared error between the ground-truth implicit surface and the linear basis-based implicit surfaces does not converge to the global solution. In this work, we propose locally supported compact radial basis functions for a linear representation of the implicit surface. This representation enables us to generate 3D shapes with arbitrary topologies at any resolution due to their continuous nature. We then propose a neural network architecture for learning the linear implicit shape representation of the 3D surface of an object. We learn linear implicit shapes within a supervised learning framework using ground truth Signed-Distance Field (SDF) data for guidance. The classical strategies face difficulties in finding linear implicit shapes from a given 3D point cloud due to numerical issues (requires solving inverse of a large matrix) in basis and query point selection. The proposed approach achieves better Chamfer distance and comparable F-score than the state-of-the-art approach on the benchmark dataset. We also show the effectiveness of the proposed approach by using it for the 3D shape completion task.

Sai Phani Kumar Malladi, Jayanta Mukhopadhyay, Chaker Larabi et al.

Deep neural networks have shown their profound impact on achieving human level performance in visual saliency prediction. However, it is still unclear how they learn the task and what it means in terms of understanding human visual system. In this work, we develop a technique to derive explainable saliency models from their corresponding deep neural architecture based saliency models by applying human perception theories and the conventional concepts of saliency. This technique helps us understand the learning pattern of the deep network at its intermediate layers through their activation maps. Initially, we consider two state-of-the-art deep saliency models, namely UNISAL and MSI-Net for our interpretation. We use a set of biologically plausible log-gabor filters for identifying and reconstructing the activation maps of them using our explainable saliency model. The final saliency map is generated using these reconstructed activation maps. We also build our own deep saliency model named cross-concatenated multi-scale residual block based network (CMRNet) for saliency prediction. Then, we evaluate and compare the performance of the explainable models derived from UNISAL, MSI-Net and CMRNet on three benchmark datasets with other state-of-the-art methods. Hence, we propose that this approach of explainability can be applied to any deep visual saliency model for interpretation which makes it a generic one.

Chetan Ralekar, Shubham Choudhary, Tapan Kumar Gandhi et al.

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the congruence, or lack thereof, in the information-gathering strategies of the two systems. We have operationalized our investigation as a character recognition task. We have used eye-tracking to assay the spatial distribution of information hotspots for humans via fixation maps and an activation mapping technique for obtaining analogous distributions for deep networks through visualization maps. Qualitative comparison between visualization maps and fixation maps reveals an interesting correlate of congruence. The deep learning model considered similar regions in character, which humans have fixated in the case of correctly classified characters. On the other hand, when the focused regions are different for humans and deep nets, the characters are typically misclassified by the latter. Hence, we propose to use the visual fixation maps obtained from the eye-tracking experiment as a supervisory input to align the model's focus on relevant character regions. We find that such supervision improves the model's performance significantly and does not require any additional parameters. This approach has the potential to find applications in diverse domains such as medical analysis and surveillance in which explainability helps to determine system fidelity.

Aakarsh Malhotra, Surbhi Mittal, Puspita Majumdar et al.

With increasing number of COVID-19 cases globally, all the countries are ramping up the testing numbers. While the RT-PCR kits are available in sufficient quantity in several countries, others are facing challenges with limited availability of testing kits and processing centers in remote areas. This has motivated researchers to find alternate methods of testing which are reliable, easily accessible and faster. Chest X-Ray is one of the modalities that is gaining acceptance as a screening modality. Towards this direction, the paper has two primary contributions. Firstly, we present the COVID-19 Multi-Task Network which is an automated end-to-end network for COVID-19 screening. The proposed network not only predicts whether the CXR has COVID-19 features present or not, it also performs semantic segmentation of the regions of interest to make the model explainable. Secondly, with the help of medical professionals, we manually annotate the lung regions of 9000 frontal chest radiographs taken from ChestXray-14, CheXpert and a consolidated COVID-19 dataset. Further, 200 chest radiographs pertaining to COVID-19 patients are also annotated for semantic segmentation. This database will be released to the research community.

Ronak Gupta, Prashant Anand, Santanu Chaudhury et al.

Fall detection holds immense importance in the field of healthcare, where timely detection allows for instant medical assistance. In this context, we propose a 3D ConvNet architecture which consists of 3D Inception modules for fall detection. The proposed architecture is a custom version of Inflated 3D (I3D) architecture, that takes compressed measurements of video sequence as spatio-temporal input, obtained from compressive sensing framework, rather than video sequence as input, as in the case of I3D convolutional neural network. This is adopted since privacy raises a huge concern for patients being monitored through these RGB cameras. The proposed framework for fall detection is flexible enough with respect to a wide variety of measurement matrices. Ten action classes randomly selected from Kinetics-400 with no fall examples, are employed to train our 3D ConvNet post compressive sensing with different types of sensing matrices on the original video clips. Our results show that 3D ConvNet performance remains unchanged with different sensing matrices. Also, the performance obtained with Kinetics pre-trained 3D ConvNet on compressively sensed fall videos from benchmark datasets is better than the state-of-the-art techniques.

Prerana Mukherjee, Manoj Sharma, Megh Makwana et al.

Synthesizing high quality saliency maps from noisy images is a challenging problem in computer vision and has many practical applications. Samples generated by existing techniques for saliency detection cannot handle the noise perturbations smoothly and fail to delineate the salient objects present in the given scene. In this paper, we present a novel end-to-end coupled Denoising based Saliency Prediction with Generative Adversarial Network (DSAL-GAN) framework to address the problem of salient object detection in noisy images. DSAL-GAN consists of two generative adversarial-networks (GAN) trained end-to-end to perform denoising and saliency prediction altogether in a holistic manner. The first GAN consists of a generator which denoises the noisy input image, and in the discriminator counterpart we check whether the output is a denoised image or ground truth original image. The second GAN predicts the saliency maps from raw pixels of the input denoised image using a data-driven metric based on saliency prediction method with adversarial loss. Cycle consistency loss is also incorporated to further improve salient region prediction. We demonstrate with comprehensive evaluation that the proposed framework outperforms several baseline saliency models on various performance benchmarks.

Deepak Mishra, Prathosh A. P., Aravind Jayendran et al.

Generative adversarial networks (GANs) have shown remarkable success in generation of unstructured data, such as, natural images. However, discovery and separation of modes in the generated space, essential for several tasks beyond naive data generation, is still a challenge. In this paper, we address the problem of imposing desired modal properties on the generated space using a latent distribution, engineered in accordance with the modal properties of the true data distribution. This is achieved by training a latent space inversion network in tandem with the generative network using a divergence loss. The latent space is made to follow a continuous multimodal distribution generated by reparameterization of a pair of continuous and discrete random variables. In addition, the modal priors of the latent distribution are learned to match with the true data distribution using minimal-supervision with negligible increment in number of learnable parameters. We validate our method on multiple tasks such as mode separation, conditional generation, and attribute discovery on multiple real world image datasets and demonstrate its efficacy over other state-of-the-art methods.

Deepak Mishra, Rajeev Ranjan, Santanu Chaudhury et al.

Image registration is a process of aligning two or more images of same objects using geometric transformation. Most of the existing approaches work on the assumption of location invariance. These approaches require object-centric images to perform matching. Further, in absence of intensity level symmetry between the corresponding points in two images, the learning based registration approaches rely on synthetic deformations, which often fail in real scenarios. To address these issues, a combination of convolutional neural networks (CNNs) to perform the desired registration is developed in this work. The complete objective is divided into three sub-objectives: object localization, segmentation and matching transformation. Object localization step establishes an initial correspondence between the images. A modified version of single shot multi-box detector is used for this purpose. The detected region is cropped to make the images object-centric. Subsequently, the objects are segmented and matched using a spatial transformer network employing thin plate spline deformation. Initial experiments on MNIST and Caltech-101 datasets show that the proposed model is able to produce accurate matching. Quantitative evaluation performed using dice coefficient (DC) and mean intersection over union (mIoU) show that proposed method results in the values of 79% and 66%, respectively for MNIST dataset and the values of 94% and 90%, respectively for Caltech-101 dataset. The proposed framework is extended to the registration of CT and US images, which is free from any data specific assumptions and has better generalization capability as compared to the existing rule-based/classical approaches.

Deepak Mishra, Santanu Chaudhury, Mukul Sarkar et al.

Contrast and quality of ultrasound images are adversely affected by the excessive presence of speckle. However, being an inherent imaging property, speckle helps in tissue characterization and tracking. Thus, despeckling of the ultrasound images requires the reduction of speckle extent without any oversmoothing. In this letter, we aim to address the despeckling problem using an unsupervised deep adversarial approach. A despeckling residual neural network (DRNN) is trained with an adversarial loss imposed by a discriminator. The discriminator tries to differentiate between the despeckled images generated by the DRNN and the set of high-quality images. Further to prevent the developed DRNN from oversmoothing, a structural loss term is used along with the adversarial loss. Experimental evaluations show that the proposed DRNN is able to outperform the state-of-the-art despeckling approaches.

Siddharth Srivastava, Swati Bhugra, Brejesh Lall et al.

Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner. In this context, an accurate 3D model of plant canopy provides a reliable representation for drought stress characterization in contrast to using 2D images. In this paper, we propose a novel end-to-end pipeline including 3D reconstruction, segmentation and feature extraction, leveraging deep neural networks at various stages, for drought stress study. To overcome the high degree of self-similarities and self-occlusions in plant canopy, prior knowledge of leaf shape based on features from deep siamese network are used to construct an accurate 3D model using structure from motion on wheat plants. The drought stress is characterized with a deep network based feature aggregation. We compare the proposed methodology on several descriptors, and show that the network outperforms conventional methods.

Disha Shrivastava, Santanu Chaudhury, Dr. Jayadeva

Training deep networks is expensive and time-consuming with the training period increasing with data size and growth in model parameters. In this paper, we provide a framework for distributed training of deep networks over a cluster of CPUs in Apache Spark. The framework implements both Data Parallelism and Model Parallelism making it suitable to use for deep networks which require huge training data and model parameters which are too big to fit into the memory of a single machine. It can be scaled easily over a cluster of cheap commodity hardware to attain significant speedup and obtain better results making it quite economical as compared to farm of GPUs and supercomputers. We have proposed a new algorithm for training of deep networks for the case when the network is partitioned across the machines (Model Parallelism) along with detailed cost analysis and proof of convergence of the same. We have developed implementations for Fully-Connected Feedforward Networks, Convolutional Neural Networks, Recurrent Neural Networks and Long Short-Term Memory architectures. We present the results of extensive simulations demonstrating the speedup and accuracy obtained by our framework for different sizes of the data and model parameters with variation in the number of worker cores/partitions; thereby showing that our proposed framework can achieve significant speedup (upto 11X for CNN) and is also quite scalable.

Jobin Wilson, Ram Mohan, Muhammad Arif et al.

The crux of the problem in KDD Cup 2016 involves developing data mining techniques to rank research institutions based on publications. Rank importance of research institutions are derived from predictions on the number of full research papers that would potentially get accepted in upcoming top-tier conferences, utilizing public information on the web. This paper describes our solution to KDD Cup 2016. We used a two step approach in which we first identify full research papers corresponding to each conference of interest and then train two variants of exponential smoothing models to make predictions. Our solution achieves an overall score of 0.7508, while the winning submission scored 0.7656 in the overall results.

Vandna Bhalla, Santanu Chaudhury, Arihant Jain

Machine learning methods are used today for most recognition problems. Convolutional Neural Networks (CNN) have time and again proved successful for many image processing tasks primarily for their architecture. In this paper we propose to apply CNN to small data sets like for example, personal albums or other similar environs where the size of training dataset is a limitation, within the framework of a proposed hybrid CNN-AIS model. We use Artificial Immune System Principles to enhance small size of training data set. A layer of Clonal Selection is added to the local filtering and max pooling of CNN Architecture. The proposed Architecture is evaluated using the standard MNIST dataset by limiting the data size and also with a small personal data sample belonging to two different classes. Experimental results show that the proposed hybrid CNN-AIS based recognition engine works well when the size of training data is limited in size

Anupama Ray, Sai Rajeswar, Santanu Chaudhury

Deep LSTM is an ideal candidate for text recognition. However text recognition involves some initial image processing steps like segmentation of lines and words which can induce error to the recognition system. Without segmentation, learning very long range context is difficult and becomes computationally intractable. Therefore, alternative soft decisions are needed at the pre-processing level. This paper proposes a hybrid text recognizer using a deep recurrent neural network with multiple layers of abstraction and long range context along with a language model to verify the performance of the deep neural network. In this paper we construct a multi-hypotheses tree architecture with candidate segments of line sequences from different segmentation algorithms at its different branches. The deep neural network is trained on perfectly segmented data and tests each of the candidate segments, generating unicode sequences. In the verification step, these unicode sequences are validated using a sub-string match with the language model and best first search is used to find the best possible combination of alternative hypothesis from the tree structure. Thus the verification framework using language models eliminates wrong segmentation outputs and filters recognition errors.

Jobin Wilson, Chitharanj Kachappilly, Rakesh Mohan et al.

Communication Service Providers (CSPs) are in a unique position to utilize their vast transactional data assets generated from interactions of subscribers with network elements as well as with other subscribers. CSPs could leverage its data assets for a gamut of applications such as service personalization, predictive offer management, loyalty management, revenue forecasting, network capacity planning, product bundle optimization and churn management to gain significant competitive advantage. However, due to the sheer data volume, variety, velocity and veracity of mobile subscriber datasets, sophisticated data analytics techniques and frameworks are necessary to derive actionable insights in a useable timeframe. In this paper, we describe our journey from a relational database management system (RDBMS) based campaign management solution which allowed data scientists and marketers to use hand-written rules for service personalization and targeted promotions to a distributed Big Data Analytics platform, capable of performing large scale machine learning and data mining to deliver real time service personalization, predictive modelling and product optimization. Our work involves a careful blend of technology, processes and best practices, which facilitate man-machine collaboration and continuous experimentation to derive measurable economic value from data. Our platform has a reach of more than 500 million mobile subscribers worldwide, delivering over 1 billion personalized recommendations annually, processing a total data volume of 64 Petabytes, corresponding to 8.5 trillion events.

Jobin Wilson, Santanu Chaudhury, Brejesh Lall et al.

Standard Collaborative Filtering (CF) algorithms make use of interactions between users and items in the form of implicit or explicit ratings alone for generating recommendations. Similarity among users or items is calculated purely based on rating overlap in this case,without considering explicit properties of users or items involved, limiting their applicability in domains with very sparse rating spaces. In many domains such as movies, news or electronic commerce recommenders, considerable contextual data in text form describing item properties is available along with the rating data, which could be utilized to improve recommendation quality.In this paper, we propose a novel approach to improve standard CF based recommenders by utilizing latent Dirichlet allocation (LDA) to learn latent properties of items, expressed in terms of topic proportions, derived from their textual description. We infer user's topic preferences or persona in the same latent space,based on her historical ratings. While computing similarity between users, we make use of a combined similarity measure involving rating overlap as well as similarity in the latent topic space. This approach alleviates sparsity problem as it allows calculation of similarity between users even if they have not rated any items in common. Our experiments on multiple public datasets indicate that the proposed hybrid approach significantly outperforms standard user Based and item Based CF recommenders in terms of classification accuracy metrics such as precision, recall and f-measure.