Pranav Kumar Singh

Pranav Singh, Jacopo Cirrone

Existing self-supervised techniques have extreme computational requirements and suffer a substantial drop in performance with a reduction in batch size or pretraining epochs. This paper presents Cross Architectural - Self Supervision (CASS), a novel self-supervised learning approach that leverages Transformer and CNN simultaneously. Compared to the existing state-of-the-art self-supervised learning approaches, we empirically show that CASS-trained CNNs and Transformers across four diverse datasets gained an average of 3.8% with 1% labeled data, 5.9% with 10% labeled data, and 10.13% with 100% labeled data while taking 69% less time. We also show that CASS is much more robust to changes in batch size and training epochs than existing state-of-the-art self-supervised learning approaches. We have open-sourced our code at https://github.com/pranavsinghps1/CASS.

Pranav Singh, Jacopo Cirrone

The current study of cell architecture of inflammation in histopathology images commonly performed for diagnosis and research purposes excludes a lot of information available on the biopsy slide. In autoimmune diseases, major outstanding research questions remain regarding which cell types participate in inflammation at the tissue level, and how they interact with each other. While these questions can be partially answered using traditional methods, artificial intelligence approaches for segmentation and classification provide a much more efficient method to understand the architecture of inflammation in autoimmune disease, holding great promise for novel insights. In this paper, we empirically develop deep learning approaches that use dermatomyositis biopsies of human tissue to detect and identify inflammatory cells. Our approach improves classification performance by 26% and segmentation performance by 5%. We also propose a novel post-processing autoencoder architecture that improves segmentation performance by an additional 3%.

Pranav Singh, Jacopo Cirrone

In healthcare and biomedical applications, extreme computational requirements pose a significant barrier to adopting representation learning. Representation learning can enhance the performance of deep learning architectures by learning useful priors from limited medical data. However, state-of-the-art self-supervised techniques suffer from reduced performance when using smaller batch sizes or shorter pretraining epochs, which are more practical in clinical settings. We present Cross Architectural - Self Supervision (CASS) in response to this challenge. This novel siamese self-supervised learning approach synergistically leverages Transformer and Convolutional Neural Networks (CNN) for efficient learning. Our empirical evaluation demonstrates that CASS-trained CNNs and Transformers outperform existing self-supervised learning methods across four diverse healthcare datasets. With only 1% labeled data for finetuning, CASS achieves a 3.8% average improvement; with 10% labeled data, it gains 5.9%; and with 100% labeled data, it reaches a remarkable 10.13% enhancement. Notably, CASS reduces pretraining time by 69% compared to state-of-the-art methods, making it more amenable to clinical implementation. We also demonstrate that CASS is considerably more robust to variations in batch size and pretraining epochs, making it a suitable candidate for machine learning in healthcare applications.

Abhishek Narayanan, Rushabh Musthyala, Rahul Sankar et al.

Visual Question Answering (VQA) in the medical domain presents a unique, interdisciplinary challenge, combining fields such as Computer Vision, Natural Language Processing, and Knowledge Representation. Despite its importance, research in medical VQA has been scant, only gaining momentum since 2018. Addressing this gap, our research delves into the effective representation of radiology images and the joint learning of multimodal representations, surpassing existing methods. We innovatively augment the SLAKE dataset, enabling our model to respond to a more diverse array of questions, not limited to the immediate content of radiology or pathology images. Our model achieves a top-1 accuracy of 79.55\% with a less complex architecture, demonstrating comparable performance to current state-of-the-art models. This research not only advances medical VQA but also opens avenues for practical applications in diagnostic settings.

Pranav Singh, Pravendra Singh

IRSTD (InfraRed Small Target Detection) detects small targets in infrared blurry backgrounds and is essential for various applications. The detection task is challenging due to the small size of the targets and their sparse distribution in infrared small target datasets. Although existing IRSTD methods and datasets have led to significant advancements, they are limited by their reliance solely on the image modality. Recent advances in deep learning and large vision-language models have shown remarkable performance in various visual recognition tasks. In this work, we propose a novel multimodal IRSTD framework that incorporates language priors to guide small target detection. We leverage language-guided attention weights derived from the language prior to enhance the model's ability for IRSTD, presenting a novel approach that combines textual information with image data to improve IRSTD capabilities. Utilizing the state-of-the-art GPT-4 vision model, we generate text descriptions that provide the locations of small targets in infrared images, employing careful prompt engineering to ensure improved accuracy. Due to the absence of multimodal IR datasets, existing IRSTD methods rely solely on image data. To address this shortcoming, we have curated a multimodal infrared dataset that includes both image and text modalities for small target detection, expanding upon the popular IRSTD-1k and NUDT-SIRST datasets. We validate the effectiveness of our approach through extensive experiments and comprehensive ablation studies. The results demonstrate significant improvements over the state-of-the-art method, with relative percentage differences of 9.74%, 13.02%, 1.25%, and 67.87% in IoU, nIoU, Pd, and Fa on the NUAA-SIRST subset, and 4.41%, 2.04%, 2.01%, and 113.43% on the IRSTD-1k subset of the LangIR dataset, respectively.

Pranav Singh, Jacopo Cirrone

Recent advancements in self-supervised learning have unlocked the potential to harness unlabeled data for auxiliary tasks, facilitating the learning of beneficial priors. This has been particularly advantageous in fields like medical image analysis, where labeled data are scarce. Although effective for classification tasks, this methodology has shown limitations in more complex applications, such as medical image segmentation. In this paper, we introduce Medical imaging Enhanced with Dynamic Self-Adaptive Semantic Segmentation (MedSASS), a dedicated self-supervised framework tailored for medical image segmentation. We evaluate MedSASS against existing state-of-the-art methods across four diverse medical datasets, showcasing its superiority. MedSASS outperforms existing CNN-based self-supervised methods by 3.83% and matches the performance of ViT-based methods. Furthermore, when MedSASS is trained end-to-end, covering both encoder and decoder, it demonstrates significant improvements of 14.4% for CNNs and 6% for ViT-based architectures compared to existing state-of-the-art self-supervised strategies.

Pranav Kumar Singh, Sukumar Nandi, Sunit K. Nandi et al.

The Internet of Vehicles (IoV) is flourishing and offers various applications relating to road safety, traffic and fuel efficiency, and infotainment. Dealing with security and privacy threats and managing the trust (detecting malicious and misbehaving peers) in IoV remains the most significant concern. Artificial Intelligence is one of the most revolutionizing technologies, and the predictive power of its machine learning models can help detect intrusions and misbehaviors. Similarly, empowering the state-of-the-art IoV security framework with blockchain can make it secure and resilient. This article discusses joint AI and blockchain for security, privacy and trust-related risks in IoV. This paper also presents problems, challenges, requirements and solutions using ML and blockchain to address aforementioned issues in IoV.

Pranav Kumar Singh, Roshan Singh, Sukumar Nandi

One of the biggest challenges associated with connected and autonomous vehicles (CAVs) is to maintain and make use of vehicles health records (VHR). VHR can facilitate different entities to offer various services in a proactive, transparent, secure, reliable and in an efficient manner. The state-of-the-art solutions for maintaining the VHR are centralized in nature, mainly owned by manufacturer and authorized in-vehicle device developers. Owners, drivers, and other key service providers have limited accessibility and control to the VHR. We need to change the strategy from single or limited party access to multi-party access to VHR in an secured manner so that all stakeholders of intelligent transportation system (ITS) can be benefited from this. Any unauthorized attempt to alter the data should also be prevented. Blockchain is one such potential candidate, which can facilitate the sharing of such data among different participating organizations and individuals. For example, owners, manufacturers, trusted third parties, road authorities, insurance companies, charging stations, and car selling ventures can access VHR stored on the blockchain in a permissioned, secured, and with a higher level of confidence. In this paper, a blockchain-based decentralized secure system for V-CARE is proposed to manage records in an interoperable framework that leads to improved ITS services in terms of safety, availability, reliability, efficiency, and maintenance. Insurance based on pay-how-you-drive (PHYD), and sale and purchase of used vehicles can also be made more transparent and reliable without compromising the confidentiality and security of sensitive data.