Search

Cone Beam Computed Tomography (CBCT) and Panoramic X-rays are the most commonly used imaging modalities in dental health care. CBCT can produce three-dimensional views of a patient's head, providing clinicians with better diagnostic capability, whereas Panoramic X-ray can capture the entire maxillofacial region in a single image. If the CBCT is already available, it can be beneficial to synthesize a Panoramic X-ray, thereby avoiding an immediate additional scan and extra radiation exposure. Existing methods focus on delineating an approximate dental arch and creating orthogonal projections along this arch. However, no golden standard is available for such dental arch extractions, and this choice can affect the quality of synthesized X-rays. To avoid such issues, we propose a novel method for synthesizing Panoramic X-rays from diverse head CBCTs, employing a simulated projection geometry and dynamic rotation centers. Our method effectively synthesized panoramic views from CBCT, even for patients with missing or nonexistent teeth and in the presence of severe metal implants. Our results demonstrate that this method can generate high-quality panoramic images irrespective of the CBCT scanner geometry., Comment: 12 pages, 6 figures, 1 table, Journal submission planned

Physics-informed neural networks have proven to be a powerful tool for solving differential equations, leveraging the principles of physics to inform the learning process. However, traditional deep neural networks often face challenges in achieving high accuracy without incurring significant computational costs. In this work, we implement the Physics-Informed Kolmogorov-Arnold Neural Networks (PIKAN) through efficient-KAN and WAV-KAN, which utilize the Kolmogorov-Arnold representation theorem. PIKAN demonstrates superior performance compared to conventional deep neural networks, achieving the same level of accuracy with fewer layers and reduced computational overhead. We explore both B-spline and wavelet-based implementations of PIKAN and benchmark their performance across various ordinary and partial differential equations using unsupervised (data-free) and supervised (data-driven) techniques. For certain differential equations, the data-free approach suffices to find accurate solutions, while in more complex scenarios, the data-driven method enhances the PIKAN's ability to converge to the correct solution. We validate our results against numerical solutions and achieve $99 \%$ accuracy in most scenarios.

Event-by-event fluctuations in the initial stages of ultrarelativistic nucleus-nucleus collisions depend little on rapidity. The hydrodynamic expansion which occurs in later stages then gives rise to correlations among outgoing particles which depend weakly on their relative rapidity. Azimuthal correlations, through which anisotropic flow ($v_n(p_T)$) is defined, have been the most studied. Here we study a new observable introduced in 2020 by Schenke, Shen and Teaney and dubbed $v_0(p_T)$, which quantifies the relative change in the $p_T$ spectrum induced by a fluctuation. We describe how it can be measured. Using hydrodynamic simulations, we make quantitative predictions for $v_0(p_T)$ of charged and identified hadrons. We then discuss how $v_0(p_T)$ relates to two phenomena which have been measured: The increase of the mean transverse momentum in ultracentral collisions, and the event-by-event fluctuations of the transverse momentum per particle $[ p_T]$. We show that $v_0(p_T)$ determines the dependence of these quantities on the $p_T$ cuts implemented in the analysis. We quantitatively explain the rise of $\sigma_{p_T}$ observed by ATLAS as the upper $p_T$-cut is increased from $2$ to $5$~GeV/$c$., Comment: 5 figures

Deploying deep learning-based imaging tools across various clinical sites poses significant challenges due to inherent domain shifts and regulatory hurdles associated with site-specific fine-tuning. For histopathology, stain normalization techniques can mitigate discrepancies, but they often fall short of eliminating inter-site variations. Therefore, we present Data Alchemy, an explainable stain normalization method combined with test time data calibration via a template learning framework to overcome barriers in cross-site analysis. Data Alchemy handles shifts inherent to multi-site data and minimizes them without needing to change the weights of the normalization or classifier networks. Our approach extends to unseen sites in various clinical settings where data domain discrepancies are unknown. Extensive experiments highlight the efficacy of our framework in tumor classification in hematoxylin and eosin-stained patches. Our explainable normalization method boosts classification tasks' area under the precision-recall curve(AUPR) by 0.165, 0.545 to 0.710. Additionally, Data Alchemy further reduces the multisite classification domain gap, by improving the 0.710 AUPR an additional 0.142, elevating classification performance further to 0.852, from 0.545. Our Data Alchemy framework can popularize precision medicine with minimal operational overhead by allowing for the seamless integration of pre-trained deep learning-based clinical tools across multiple sites., Comment: accepted to Machine Learning in Medical Imaging (MLMI 2024)

Federated learning (FL) allows a set of clients to collaboratively train a machine-learning model without exposing local training samples. In this context, it is considered to be privacy-preserving and hence has been adopted by medical centers to train machine-learning models over private data. However, in this paper, we propose a novel attack named MediLeak that enables a malicious parameter server to recover high-fidelity patient images from the model updates uploaded by the clients. MediLeak requires the server to generate an adversarial model by adding a crafted module in front of the original model architecture. It is published to the clients in the regular FL training process and each client conducts local training on it to generate corresponding model updates. Then, based on the FL protocol, the model updates are sent back to the server and our proposed analytical method recovers private data from the parameter updates of the crafted module. We provide a comprehensive analysis for MediLeak and show that it can successfully break the state-of-the-art cryptographic secure aggregation protocols, designed to protect the FL systems from privacy inference attacks. We implement MediLeak on the MedMNIST and COVIDx CXR-4 datasets. The results show that MediLeak can nearly perfectly recover private images with high recovery rates and quantitative scores. We further perform downstream tasks such as disease classification with the recovered data, where our results show no significant performance degradation compared to using the original training samples.

Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic languages, is the availability of high-quality data for building foundation LLMs. In this paper, we are proposing a large pre-train dataset in Hindi useful for the Indic language Hindi. We have collected the data span across several domains including major dialects in Hindi. The dataset contains 1.28 billion Hindi tokens. We have explained our pipeline including data collection, pre-processing, and availability for LLM pre-training. The proposed approach can be easily extended to other Indic and low-resource languages and will be available freely for LLM pre-training and LLM research purposes., Comment: Accepted as a book chapter in the book Title "APPLIED SPEECH AND TEXT PROCESSING FOR LOW RESOURCE LANGUAGES"

Lung cancer has been one of the major threats to human life for decades. Computer-aided diagnosis can help with early lung nodul detection and facilitate subsequent nodule characterization. Large Visual Language models (VLMs) have been found effective for multiple downstream medical tasks that rely on both imaging and text data. However, lesion level detection and subsequent diagnosis using VLMs have not been explored yet. We propose CADe, for segmenting lung nodules in a zero-shot manner using a variant of the Segment Anything Model called MedSAM. CADe trains on a prompt suite on input computed tomography (CT) scans by using the CLIP text encoder through prefix tuning. We also propose, CADx, a method for the nodule characterization as benign/malignant by making a gallery of radiomic features and aligning image-feature pairs through contrastive learning. Training and validation of CADe and CADx have been done using one of the largest publicly available datasets, called LIDC. To check the generalization ability of the model, it is also evaluated on a challenging dataset, LUNGx. Our experimental results show that the proposed methods achieve a sensitivity of 0.86 compared to 0.76 that of other fully supervised methods.The source code, datasets and pre-processed data can be accessed using the link

Large vision language models (VLMs) have progressed incredibly from research to applicability for general-purpose use cases. LLaVA-Med, a pioneering large language and vision assistant for biomedicine, can perform multi-modal biomedical image and data analysis to provide a natural language interface for radiologists. While it is highly generalizable and works with multi-modal data, it is currently limited by well-known challenges that exist in the large language model space. Hallucinations and imprecision in responses can lead to misdiagnosis which currently hinder the clinical adaptability of VLMs. To create precise, user-friendly models in healthcare, we propose D-Rax -- a domain-specific, conversational, radiologic assistance tool that can be used to gain insights about a particular radiologic image. In this study, we enhance the conversational analysis of chest X-ray (CXR) images to support radiological reporting, offering comprehensive insights from medical imaging and aiding in the formulation of accurate diagnosis. D-Rax is achieved by fine-tuning the LLaVA-Med architecture on our curated enhanced instruction-following data, comprising of images, instructions, as well as disease diagnosis and demographic predictions derived from MIMIC-CXR imaging data, CXR-related visual question answer (VQA) pairs, and predictive outcomes from multiple expert AI models. We observe statistically significant improvement in responses when evaluated for both open and close-ended conversations. Leveraging the power of state-of-the-art diagnostic models combined with VLMs, D-Rax empowers clinicians to interact with medical images using natural language, which could potentially streamline their decision-making process, enhance diagnostic accuracy, and conserve their time., Comment: accepted to the MICCAI 2024 Second International Workshop on Foundation Models for General Medical AI

In this work, we prescribe a theoretical framework aiming at predicting the position of monovacancy defects at the edges of zigzag graphene nanoribbons (ZGNRs) using Floquet-Bloch formalism, which can be experimentally observed through time- and angle-resolved photoemission spectroscopy (tr-ARPES). Our methodology involves an in-depth investigation of the Floquet quasienergy band spectrum influenced by light with varying polarization across a range of frequencies. Particularly under the influence of circularly polarized light with a frequency comparable to the bandwidth of the system, our findings suggest a promising approach for locating monovacancy defects at either edge, a challenge that proves intricate to predict from the ARPES spectrum of ZGNRs with monovacancy defects. This has been achieved by analyzing the orientation of the Floquet edge state and the appearance of new Dirac points in the vicinity of the Fermi level. The real-world applications of these captivating characteristics underscore the importance and pertinence of our theoretical framework, paving the way for additional exploration and practical use. Our approach, employing the Floquet formalism, is not limited to monovacancy-type defects; rather, it can be expanded to encompass various types of vacancy defects., Comment: Total number of 10 pages and 12 figures

Fitch Cheney's 5-card trick was introduced in 1950. In 2013, Mulcahy invented a 4-card trick in which the cards are allowed to be displayed face down. We suggest our own invention: a 3-card trick in which the cards can be face down and also allowed to be placed both vertically and horizontally. We discuss the theory behind all the tricks and estimate the maximum deck size given the number of chosen cards. We also discuss the cases of hiding several cards and the deck that has duplicates., Comment: 24 pages, 13 tables

S\'ami, an indigenous language group comprising multiple languages, faces digital marginalization due to the limited availability of data and sophisticated language models designed for its linguistic intricacies. This work focuses on increasing technological participation for the S\'ami language. We draw the attention of the ML community towards the language modeling problem of Ultra Low Resource (ULR) languages. ULR languages are those for which the amount of available textual resources is very low, and the speaker count for them is also very low. ULRLs are also not supported by mainstream Large Language Models (LLMs) like ChatGPT, due to which gathering artificial training data for them becomes even more challenging. Mainstream AI foundational model development has given less attention to this category of languages. Generally, these languages have very few speakers, making it hard to find them. However, it is important to develop foundational models for these ULR languages to promote inclusion and the tangible abilities and impact of LLMs. To this end, we have compiled the available S\'ami language resources from the web to create a clean dataset for training language models. In order to study the behavior of modern LLM models with ULR languages (S\'ami), we have experimented with different kinds of LLMs, mainly at the order of $\sim$ seven billion parameters. We have also explored the effect of multilingual LLM training for ULRLs. We found that the decoder-only models under a sequential multilingual training scenario perform better than joint multilingual training, whereas multilingual training with high semantic overlap, in general, performs better than training from scratch.This is the first study on the S\'ami language for adapting non-statistical language models that use the latest developments in the field of natural language processing (NLP).

We investigate the topological properties of hardcore bosons possessing nearest-neighbor repulsive interactions on a two-leg ladder. We show that by allowing nearest neighbour dimerized interactions instead of hopping dimerization, the system exhibits topological phases and phase transitions under proper conditions. First, by assuming uniform hopping throughout the ladder, we show that when interaction along the legs are dimerized and the dimerization pattern is different in the legs, a trivial rung-Mott insulator to a topological bond order phase transition occurs as a function of the dimerization strength. However, for a fixed dimerization strength, the system exhibits a topological to trivial phase transition with increase in the rung hopping. A completely different scenario appears when the rung interaction is turned on. We obtain that for a ladder with uniform hopping, the repulsive interaction either turns the topological phase into a trivial rung-Mott insulator or a charge density wave phase. Such topological features are absent when the dimerization pattern in the nearest neighbour interaction is considered to be identical in both the legs of the ladder. We numerically obtain the ground state properties and also show the signatures of topological phase transitions through Thouless charge pumping., Comment: 15 pages, 18 figures

Clinical trials are pivotal in the drug discovery process to determine the safety and efficacy of a drug candidate. The high failure rates of these trials are attributed to deficiencies in clinical model development and protocol design. Improvements in the clinical drug design process could therefore yield significant benefits for all stakeholders involved. This paper examines the current challenges faced in clinical trial design and optimization, reviews established classical computational approaches, and introduces quantum algorithms aimed at enhancing these processes. Specifically, the focus is on three critical aspects: clinical trial simulations, site selection, and cohort identification. This study aims to provide a comprehensive framework that leverages quantum computing to innovate and refine the efficiency and effectiveness of clinical trials.

In this paper, with a set of high-resolution He I 10830 \AA\ filtergrams, we select an area in a plage, very likely an EUV moss area, as an interface layer to follow the clues of coronal heating channels down to the photosphere. The filtergrams are obtained from the 1-meter aperture New Vacuum Solar Telescope (NVST). We make a distinction between the darker and the brighter regions in the selected area and name the two regions enhanced absorption patches (EAPs) and low absorption patches (LAPs). With well-aligned, nearly simultaneous data from multiple channels of the AIA and the continuum of the HMI on board SDO, we compare the EUV/UV emissions, emission measure, mean temperature, and continuum intensity in the two kinds of regions. The following progress is made: 1) The mean EUV emissions over EAPs are mostly stronger than the corresponding emissions over LAPs except for the emission at 335 \AA. The UV emissions at 1600 and 1700 \AA\ fail to capture the difference between the two regions. 2) In the logarithmic temperature range of 5.6-6.2, EAPs have higher EUV emission measure than LAPs, but they have lower mean coronal temperature. 3) The mean continuum intensity over EAPs is lower. Based on the above progress, we suggest that the energy for coronal heating in the moss region can be traced down to some areas in intergranular lanes with enhanced density of both cool and hot material. The lower temperature over the EAPs is due to the greater fraction of cool material over there., Comment: ApJ accepted for publication. 11 pages, 7 figures

Chest X-Ray (CXR) is a widely used clinical imaging modality and has a pivotal role in the diagnosis and prognosis of various lung and heart related conditions. Conventional automated clinical diagnostic tool design strategies relying on radiology reads and supervised learning, entail the cumbersome requirement of high quality annotated training data. To address this challenge, self-supervised pre-training has proven to outperform supervised pre-training in numerous downstream vision tasks, representing a significant breakthrough in the field. However, medical imaging pre-training significantly differs from pre-training with natural images (e.g., ImageNet) due to unique attributes of clinical images. In this context, we introduce Diverse Concept Modeling (DiCoM), a novel self-supervised training paradigm that leverages a student teacher framework for learning diverse concepts and hence effective representation of the CXR data. Hence, expanding beyond merely modeling a single primary label within an image, instead, effectively harnessing the information from all the concepts inherent in the CXR. The pre-trained model is subsequently fine-tuned to address diverse domain-specific tasks. Our proposed paradigm consistently demonstrates robust performance across multiple downstream tasks on multiple datasets, highlighting the success and generalizability of the pre-training strategy. To establish the efficacy of our methods we analyze both the power of learned representations and the speed of convergence (SoC) of our models. For diverse data and tasks, DiCoM is able to achieve in most cases better results compared to other state-of-the-art pre-training strategies. This when combined with the higher SoC and generalization capabilities positions DiCoM to be established as a foundation model for CXRs, a widely used imaging modality.

Tuberculosis (TB) remains a significant global health challenge, with pediatric cases posing a major concern. The World Health Organization (WHO) advocates for chest X-rays (CXRs) for TB screening. However, visual interpretation by radiologists can be subjective, time-consuming and prone to error, especially in pediatric TB. Artificial intelligence (AI)-driven computer-aided detection (CAD) tools, especially those utilizing deep learning, show promise in enhancing lung disease detection. However, challenges include data scarcity and lack of generalizability. In this context, we propose a novel self-supervised paradigm leveraging Vision Transformers (ViT) for improved TB detection in CXR, enabling zero-shot pediatric TB detection. We demonstrate improvements in TB detection performance ($\sim$12.7% and $\sim$13.4% top AUC/AUPR gains in adults and children, respectively) when conducting self-supervised pre-training when compared to fully-supervised (i.e., non pre-trained) ViT models, achieving top performances of 0.959 AUC and 0.962 AUPR in adult TB detection, and 0.697 AUC and 0.607 AUPR in zero-shot pediatric TB detection. As a result, this work demonstrates that self-supervised learning on adult CXRs effectively extends to challenging downstream tasks such as pediatric TB detection, where data are scarce., Comment: 5 pages, 3 figures, 2 tables. This paper has been accepted at IEEE ISBI 2024

Image harmonization is an important preprocessing strategy to address domain shifts arising from data acquired using different machines and scanning protocols in medical imaging. However, benchmarking the effectiveness of harmonization techniques has been a challenge due to the lack of widely available standardized datasets with ground truths. In this context, we propose three metrics: two intensity harmonization metrics and one anatomy preservation metric for medical images during harmonization, where no ground truths are required. Through extensive studies on a dataset with available harmonization ground truth, we demonstrate that our metrics are correlated with established image quality assessment metrics. We show how these novel metrics may be applied to real-world scenarios where no harmonization ground truth exists. Additionally, we provide insights into different interpretations of the metric values, shedding light on their significance in the context of the harmonization process. As a result of our findings, we advocate for the adoption of these quantitative harmonization metrics as a standard for benchmarking the performance of image harmonization techniques., Comment: Accepted for presentation at the ISBI 2024

In this paper, we report a study of $Z$ boson kinematic distributions in the $Z$+ 1-jet events from proton-proton ($pp$) collisions at $\sqrt{s}$ = 13.6 TeV at the Large Hadron Collider (LHC) using Leading-Order (LO) event generators. Three LO event generators, namely Pythia8, Herwig7 and Sherpa2, are explored with the implementation of appropriate Parton Shower (PS) and Matrix Element (ME) corrections. The $Z$ boson is reconstructed from oppositely charged di-lepton pairs ($\mu^+\mu^-$ and $e^+e^-$), and the associate leading jet is reconstructed with the anti-$k_T$ algorithm with radius $r$=0.4. The di-lepton invariant mass, $M_{\ell^+\ell^-}$, and the transverse momentum of the reconstructed $Z$ boson, $p_{T}^Z$, distributions are extensively studied by comparing three of the Monte Carlo (MC) predictions. In addition to this, we also explore several other kinematic distributions associated with the candidate lepton and the jet to distinguish the modelling of the LO event generators in depth. Furthermore, various showering modules within these event generators are explored for $Z$ + 1-jet production. While the three of these MC frameworks reproduce the $Z$ + 1-jet kinematics similarly, certain discrepancies in their predictions are identified in some variables. We analyzed them using different statistical tests. The best match of the $p_{T}^Z$ spectra was found between the Pythia8 and Sherpa2 results., Comment: 29 pages

This study ventures into the dynamic realm of ecosystem orchestration for industrial firms, emphasizing its significance in maintaining competitive advantage in the digital era. The fragmented research on this important subject poses challenges for firms aiming to navigate and capitalize on ecosystem orchestration. To bridge this knowledge gap, we conducted a comprehensive qualitative meta-analysis of 31 case studies and identified multifaceted orchestration practices employed by industrial firms. The core contribution of this research is the illumination of five interdependent but interrelated orchestration practices: strategic design, relational, resource integration, technological, and innovation. Together, these practices are synthesized into an integrative framework termed the "Stirring Model," which serves as a practical guide to the orchestration practices. Furthermore, the conceptual framework clarifies the synergy between the identified practices and highlights their collective impact. This study proposes theoretical and practical implications for ecosystem orchestration literature and suggests avenues for further research.