Subhashis Banerjee

Britty Baby, Daksh Thapar, Mustafa Chasmai et al.

Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level. Surgical tools are similar in appearance and are long, thin, and handled at an angle. The fine-tuning of state-of-the-art (SOTA) instance segmentation models trained on natural images for instrument segmentation has difficulty discriminating instrument classes. Our research demonstrates that while the bounding box and segmentation mask are often accurate, the classification head mis-classifies the class label of the surgical instrument. We present a new neural network framework that adds a classification module as a new stage to existing instance segmentation models. This module specializes in improving the classification of instrument masks generated by the existing model. The module comprises multi-scale mask attention, which attends to the instrument region and masks the distracting background features. We propose training our classifier module using metric learning with arc loss to handle low inter-class variance of surgical instruments. We conduct exhaustive experiments on the benchmark datasets EndoVis2017 and EndoVis2018. We demonstrate that our method outperforms all (more than 18) SOTA methods compared with, and improves the SOTA performance by at least 12 points (20%) on the EndoVis2017 benchmark challenge and generalizes effectively across the datasets.

Divij Khaitan, Subhashis Banerjee

Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and quantify the distributional robustness of neural networks by studying the interactions between layer weights and activations. We model these interactions using Bernoulli distributions, using the separation between classes as a diagnostic proxy for robustness. We demonstrate the usefulness of this framework through models trained on CIFAR-10 and ImageNet. We show that our proposed metrics can distinguish between networks that have memorised their training data and those that have not. We also perform analogous experiments in the activation space and find that the same properties do not hold up. Additionally, we investigate the behaviour of our metrics under various distribution shifts and show that these shifts reduce separation under our path-based diagnostics. Our results suggest that this framework provides useful model-level diagnostics of representation structure and robustness.

Raghav Mehta, Angelos Filos, Ujjwal Baid et al.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at: https://github.com/RagMeh11/QU-BraTS.

Subhashis Banerjee, Sushmita Mitra, Lawrence O. Hall

Prediction of Overall Survival (OS) of brain cancer patients from multi-modal MRI is a challenging field of research. Most of the existing literature on survival prediction is based on Radiomic features, which does not consider either non-biological factors or the functional neurological status of the patient(s). Besides, the selection of an appropriate cut-off for survival and the presence of censored data create further problems. Application of deep learning models for OS prediction is also limited due to the lack of large annotated publicly available datasets. In this scenario we analyse the potential of two novel neuroimaging feature families, extracted from brain parcellation atlases and spatial habitats, along with classical radiomic and geometric features; to study their combined predictive power for analysing overall survival. A cross validation strategy with grid search is proposed to simultaneously select and evaluate the most predictive feature subset based on its predictive power. A Cox Proportional Hazard (CoxPH) model is employed for univariate feature selection, followed by the prediction of patient-specific survival functions by three multivariate parsimonious models viz. Coxnet, Random survival forests (RSF) and Survival SVM (SSVM). The brain cancer MRI data used for this research was taken from two open-access collections TCGA-GBM and TCGA-LGG available from The Cancer Imaging Archive (TCIA). Corresponding survival data for each patient was downloaded from The Cancer Genome Atlas (TCGA). A high cross validation $C-index$ score of $0.82\pm.10$ was achieved using RSF with the best $24$ selected features. Age was found to be the most important biological predictor. There were $9$, $6$, $6$ and $2$ features selected from the parcellation, habitat, radiomic and region-based feature groups respectively.

Lokender Tiwari, Anish Madan, Saket Anand et al.

Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transformations that typically require retraining or fine-tuning the model to achieve reasonable performance. In this work, our investigations of intermediate representations of a pre-trained DNN lead to an interesting discovery pointing to intrinsic robustness to adversarial attacks. We find that we can learn a generative classifier by statistically characterizing the neural response of an intermediate layer to clean training samples. The predictions of multiple such intermediate-layer based classifiers, when aggregated, show unexpected robustness to adversarial attacks. Specifically, we devise an ensemble of these generative classifiers that rank-aggregates their predictions via a Borda count-based consensus. Our proposed approach uses a subset of the clean training data and a pre-trained model, and yet is agnostic to network architectures or the adversarial attack generation method. We show extensive experiments to establish that our defense strategy achieves state-of-the-art performance on the ImageNet validation set.

Prashant Agrawal, Anubhutie Singh, Malavika Raghavan et al.

Governments around the world are trying to build large data registries for effective delivery of a variety of public services. However, these efforts are often undermined due to serious concerns over privacy risks associated with collection and processing of personally identifiable information. While a rich set of special-purpose privacy-preserving techniques exist in computer science, they are unable to provide end-to-end protection in alignment with legal principles in the absence of an overarching operational architecture to ensure purpose limitation and protection against insider attacks. This either leads to weak privacy protection in large designs, or adoption of overly defensive strategies to protect privacy by compromising on utility. In this paper, we present an operational architecture for privacy-by-design based on independent regulatory oversight stipulated by most data protection regimes, regulated access control, purpose limitation and data minimisation. We briefly discuss the feasibility of implementing our architecture based on existing techniques. We also present some sample case studies of privacy-preserving design sketches of challenging public service applications.

Arpan Mangal, Surya Kalia, Harish Rajgopal et al.

The exponential increase in COVID-19 patients is overwhelming healthcare systems across the world. With limited testing kits, it is impossible for every patient with respiratory illness to be tested using conventional techniques (RT-PCR). The tests also have long turn-around time, and limited sensitivity. Detecting possible COVID-19 infections on Chest X-Ray may help quarantine high risk patients while test results are awaited. X-Ray machines are already available in most healthcare systems, and with most modern X-Ray systems already digitized, there is no transportation time involved for the samples either. In this work we propose the use of chest X-Ray to prioritize the selection of patients for further RT-PCR testing. This may be useful in an inpatient setting where the present systems are struggling to decide whether to keep the patient in the ward along with other patients or isolate them in COVID-19 areas. It would also help in identifying patients with high likelihood of COVID with a false negative RT-PCR who would need repeat testing. Further, we propose the use of modern AI techniques to detect the COVID-19 patients using X-Ray images in an automated manner, particularly in settings where radiologists are not available, and help make the proposed testing technology scalable. We present CovidAID: COVID-19 AI Detector, a novel deep neural network based model to triage patients for appropriate testing. On the publicly available covid-chestxray-dataset [2], our model gives 90.5% accuracy with 100% sensitivity (recall) for the COVID-19 infection. We significantly improve upon the results of Covid-Net [10] on the same dataset.

Prashant Agrawal, Kabir Tomer, Abhinav Nakarmi et al.

In this paper we address the problem of recovery from failures without re-running entire elections when elections fail to verify. We consider the setting of \emph{dual voting} protocols, where the cryptographic guarantees of end-to-end verifiable voting (E2E-V) are combined with the simplicity of audit using voter-verified paper records (VVPR). We first consider the design requirements of such a system and then suggest a protocol called \emph{OpenVoting}, which identifies a verifiable subset of error-free votes consistent with the VVPRs, and the polling booths corresponding to the votes that fail to verify with possible reasons for the failures. To an ordinary voter \emph{OpenVoting} looks just like an old fashioned paper based voting system, with minimal additional cognitive overload.

Subhashis Banerjee, Sushmita Mitra, Francesco Masulli et al.

Glioma constitutes 80% of malignant primary brain tumors and is usually classified as HGG and LGG. The LGG tumors are less aggressive, with slower growth rate as compared to HGG, and are responsive to therapy. Tumor biopsy being challenging for brain tumor patients, noninvasive imaging techniques like Magnetic Resonance Imaging (MRI) have been extensively employed in diagnosing brain tumors. Therefore automated systems for the detection and prediction of the grade of tumors based on MRI data becomes necessary for assisting doctors in the framework of augmented intelligence. In this paper, we thoroughly investigate the power of Deep ConvNets for classification of brain tumors using multi-sequence MR images. We propose novel ConvNet models, which are trained from scratch, on MRI patches, slices, and multi-planar volumetric slices. The suitability of transfer learning for the task is next studied by applying two existing ConvNets models (VGGNet and ResNet) trained on ImageNet dataset, through fine-tuning of the last few layers. LOPO testing, and testing on the holdout dataset are used to evaluate the performance of the ConvNets. Results demonstrate that the proposed ConvNets achieve better accuracy in all cases where the model is trained on the multi-planar volumetric dataset. Unlike conventional models, it obtains a testing accuracy of 95% for the low/high grade glioma classification problem. A score of 97% is generated for classification of LGG with/without 1p/19q codeletion, without any additional effort towards extraction and selection of features. We study the properties of self-learned kernels/ filters in different layers, through visualization of the intermediate layer outputs. We also compare the results with that of state-of-the-art methods, demonstrating a maximum improvement of 7% on the grading performance of ConvNets and 9% on the prediction of 1p/19q codeletion status.

Spyridon Bakas, Mauricio Reyes, Andras Jakab et al.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Suvam Patra, Pranjal Maheshwari, Shashank Yadav et al.

In this paper, we address the problem of road segmentation and free space detection in the context of autonomous driving. Traditional methods either use 3-dimensional (3D) cues such as point clouds obtained from LIDAR, RADAR or stereo cameras or 2-dimensional (2D) cues such as lane markings, road boundaries and object detection. Typical 3D point clouds do not have enough resolution to detect fine differences in heights such as between road and pavement. Image based 2D cues fail when encountering uneven road textures such as due to shadows, potholes, lane markings or road restoration. We propose a novel free road space detection technique combining both 2D and 3D cues. In particular, we use CNN based road segmentation from 2D images and plane/box fitting on sparse depth data obtained from SLAM as priors to formulate an energy minimization using conditional random field (CRF), for road pixels classification. While the CNN learns the road texture and is unaffected by depth boundaries, the 3D information helps in overcoming texture based classification failures. Finally, we use the obtained road segmentation with the 3D depth data from monocular SLAM to detect the free space for the navigation purposes. Our experiments on KITTI odometry dataset, Camvid dataset, as well as videos captured by us, validate the superiority of the proposed approach over the state of the art.

Suvam Patra, Kartikeya Gupta, Faran Ahmad et al.

Regardless of the tremendous progress, a truly general purpose pipeline for Simultaneous Localization and Mapping (SLAM) remains a challenge. We investigate the reported failure of state of the art (SOTA) SLAM techniques on egocentric videos. We find that the dominant 3D rotations, low parallax between successive frames, and primarily forward motion in egocentric videos are the most common causes of failures. The incremental nature of SOTA SLAM, in the presence of unreliable pose and 3D estimates in egocentric videos, with no opportunities for global loop closures, generates drifts and leads to the eventual failures of such techniques. Taking inspiration from batch mode Structure from Motion (SFM) techniques, we propose to solve SLAM as an SFM problem over the sliding temporal windows. This makes the problem well constrained. Further, we propose to initialize the camera poses using 2D rotation averaging, followed by translation averaging before structure estimation using bundle adjustment. This helps in stabilizing the camera poses when 3D estimates are not reliable. We show that the proposed SLAM technique, incorporating the two key ideas works successfully for long, shaky egocentric videos where other SOTA techniques have been reported to fail. Qualitative and quantitative comparisons on publicly available egocentric video datasets validate our results.

Suvam Patra, Himanshu Aggarwal, Himani Arora et al.

Finding the camera pose is an important step in many egocentric video applications. It has been widely reported that, state of the art SLAM algorithms fail on egocentric videos. In this paper, we propose a robust method for camera pose estimation, designed specifically for egocentric videos. In an egocentric video, the camera views the same scene point multiple times as the wearer's head sweeps back and forth. We use this specific motion profile to perform short loop closures aligned with wearer's footsteps. For egocentric videos, depth estimation is usually noisy. In an important departure, we use 2D computations for rotation averaging which do not rely upon depth estimates. The two modification results in much more stable algorithm as is evident from our experiments on various egocentric video datasets for different egocentric applications. The proposed algorithm resolves a long standing problem in egocentric vision and unlocks new usage scenarios for future applications.