Search

Osteochondrodysplasia, affecting 2-3% of newborns globally, is a group of bone and cartilage disorders that often result in head malformations, contributing to childhood morbidity and reduced quality of life. Current research on this disease using mouse models faces challenges since it involves accurately segmenting the developing cartilage in 3D micro-CT images of embryonic mice. Tackling this segmentation task with deep learning (DL) methods is laborious due to the big burden of manual image annotation, expensive due to the high acquisition costs of 3D micro-CT images, and difficult due to embryonic cartilage's complex and rapidly changing shapes. While DL approaches have been proposed to automate cartilage segmentation, most such models have limited accuracy and generalizability, especially across data from different embryonic age groups. To address these limitations, we propose novel DL methods that can be adopted by any DL architectures -- including CNNs, Transformers, or hybrid models -- which effectively leverage age and spatial information to enhance model performance. Specifically, we propose two new mechanisms, one conditioned on discrete age categories and the other on continuous image crop locations, to enable an accurate representation of cartilage shape changes across ages and local shape details throughout the cranial region. Extensive experiments on multi-age cartilage segmentation datasets show significant and consistent performance improvements when integrating our conditional modules into popular DL segmentation architectures. On average, we achieve a 1.7% Dice score increase with minimal computational overhead and a 7.5% improvement on unseen data. These results highlight the potential of our approach for developing robust, universal models capable of handling diverse datasets with limited annotated data, a key challenge in DL-based medical image analysis.

Today, we are open-sourcing our core speech recognition and diarization models for non-commercial use. We are releasing both a full production pipeline for developers as well as pared-down research models for experimentation. Rev hopes that these releases will spur research and innovation in the fast-moving domain of voice technology. The speech recognition models released today outperform all existing open source speech recognition models across a variety of long-form speech recognition domains.

Common measures of accuracy used to assess the performance of automatic speech recognition (ASR) systems, as well as human transcribers, conflate multiple sources of error. Stylistic differences, such as verbatim vs non-verbatim, can play a significant role in ASR performance evaluation when differences exist between training and test datasets. The problem is compounded for speech from underrepresented varieties, where the speech to orthography mapping is not as standardized. We categorize the kinds of stylistic differences between 6 transcription versions, 4 human- and 2 ASR-produced, of 10 hours of African American English (AAE) speech. Focusing on verbatim features and AAE morphosyntactic features, we investigate the interactions of these categories with how well transcripts can be compared via word error rate (WER). The results, and overall analysis, help clarify how ASR outputs are a function of the decisions made by the training data's human transcribers., Comment: Published in Interspeech 2024 Proceedings, 5 pages excluding references, 5 figures

The Segment Anything Model (SAM) exhibits impressive capabilities in zero-shot segmentation for natural images. Recently, SAM has gained a great deal of attention for its applications in medical image segmentation. However, to our best knowledge, no studies have shown how to harness the power of SAM for medical image classification. To fill this gap and make SAM a true ``foundation model'' for medical image analysis, it is highly desirable to customize SAM specifically for medical image classification. In this paper, we introduce SAMAug-C, an innovative augmentation method based on SAM for augmenting classification datasets by generating variants of the original images. The augmented datasets can be used to train a deep learning classification model, thereby boosting the classification performance. Furthermore, we propose a novel framework that simultaneously processes raw and SAMAug-C augmented image input, capitalizing on the complementary information that is offered by both. Experiments on three public datasets validate the effectiveness of our new approach.

For predicting cancer survival outcomes, standard approaches in clinical research are often based on two main modalities: pathology images for observing cell morphology features, and genomic (e.g., bulk RNA-seq) for quantifying gene expressions. However, existing pathology-genomic multi-modal algorithms face significant challenges: (1) Valuable biological insights regarding genes and gene-gene interactions are frequently overlooked; (2) one modality often dominates the optimization process, causing inadequate training for the other modality. In this paper, we introduce a new multi-modal ``Path-GPTOmic" framework for cancer survival outcome prediction. First, to extract valuable biological insights, we regulate the embedding space of a foundation model, scGPT, initially trained on single-cell RNA-seq data, making it adaptable for bulk RNA-seq data. Second, to address the imbalance-between-modalities problem, we propose a gradient modulation mechanism tailored to the Cox partial likelihood loss for survival prediction. The contributions of the modalities are dynamically monitored and adjusted during the training process, encouraging that both modalities are sufficiently trained. Evaluated on two TCGA(The Cancer Genome Atlas) datasets, our model achieves substantially improved survival prediction accuracy., Comment: Accepted by IEEE International Symposium on Biomedical Imaging (ISBI 2024)

Legal judgment prediction suffers from the problem of long case documents exceeding tens of thousands of words, in general, and having a non-uniform structure. Predicting judgments from such documents becomes a challenging task, more so on documents with no structural annotation. We explore the classification of these large legal documents and their lack of structural information with a deep-learning-based hierarchical framework which we call MESc; "Multi-stage Encoder-based Supervised with-clustering"; for judgment prediction. Specifically, we divide a document into parts to extract their embeddings from the last four layers of a custom fine-tuned Large Language Model, and try to approximate their structure through unsupervised clustering. Which we use in another set of transformer encoder layers to learn the inter-chunk representations. We analyze the adaptability of Large Language Models (LLMs) with multi-billion parameters (GPT-Neo, and GPT-J) with the hierarchical framework of MESc and compare them with their standalone performance on legal texts. We also study their intra-domain(legal) transfer learning capability and the impact of combining embeddings from their last layers in MESc. We test these methods and their effectiveness with extensive experiments and ablation studies on legal documents from India, the European Union, and the United States with the ILDC dataset and a subset of the LexGLUE dataset. Our approach achieves a minimum total performance gain of approximately 2 points over previous state-of-the-art methods., Comment: This paper was accepted as a long paper at ECIR 2024. arXiv admin note: substantial text overlap with arXiv:2309.10563

Various methods for designing input features have been proposed for fault recognition in rotating machines using one-dimensional raw sensor data. The available methods are complex, rely on empirical approaches, and may differ depending on the condition monitoring data used. Therefore, this article proposes a novel algorithm to design input features that unifies the feature extraction process for different time-series sensor data. This new insight for designing/extracting input features is obtained through the lens of histogram theory. The proposed algorithm extracts discriminative input features, which are suitable for a simple classifier to deep neural network-based classifiers. The designed input features are given as input to the classifier with end-to-end training in a single framework for machine conditions recognition. The proposed scheme has been validated through three real-time datasets: a) acoustic dataset, b) CWRU vibration dataset, and c) IMS vibration dataset. The real-time results and comparative study show the effectiveness of the proposed scheme for the prediction of the machine's health states.

Male infertility accounts for about one-third of global infertility cases. Manual assessment of sperm abnormalities through head morphology analysis encounters issues of observer variability and diagnostic discrepancies among experts. Its alternative, Computer-Assisted Semen Analysis (CASA), suffers from low-quality sperm images, small datasets, and noisy class labels. We propose a new approach for sperm head morphology classification, called SHMC-Net, which uses segmentation masks of sperm heads to guide the morphology classification of sperm images. SHMC-Net generates reliable segmentation masks using image priors, refines object boundaries with an efficient graph-based method, and trains an image network with sperm head crops and a mask network with the corresponding masks. In the intermediate stages of the networks, image and mask features are fused with a fusion scheme to better learn morphological features. To handle noisy class labels and regularize training on small datasets, SHMC-Net applies Soft Mixup to combine mixup augmentation and a loss function. We achieve state-of-the-art results on SCIAN and HuSHeM datasets, outperforming methods that use additional pre-training or costly ensembling techniques., Comment: Published on ISBI 2024

Studying the morphological development of cartilaginous and osseous structures is critical to the early detection of life-threatening skeletal dysmorphology. Embryonic cartilage undergoes rapid structural changes within hours, introducing biological variations and morphological shifts that limit the generalization of deep learning-based segmentation models that infer across multiple embryonic age groups. Obtaining individual models for each age group is expensive and less effective, while direct transfer (predicting an age unseen during training) suffers a potential performance drop due to morphological shifts. We propose a novel Transformer-based segmentation model with improved biological priors that better distills morphologically diverse information through conditional mechanisms. This enables a single model to accurately predict cartilage across multiple age groups. Experiments on the mice cartilage dataset show the superiority of our new model compared to other competitive segmentation models. Additional studies on a separate mice cartilage dataset with a distinct mutation show that our model generalizes well and effectively captures age-based cartilage morphology patterns., Comment: Published in ISBI 2024

Novae, explosive events in binary star systems involving a white dwarf and a companion star, offer profound insights into extreme astrophysical conditions. During the eruption of a nova, material accreted onto the white dwarf's surface undergoes a thermonuclear runaway reaction resulting in the ejection of matter into space and the formation of a luminous shell. The classical V5668 Sgr (Nova Sagittarii) was the second and brighter of the two novae in the southern constellation of Sagittarius. It was discovered by John Seach of Chatsworth Island, Australia, on March 15, 2015. In this paper, drawing on data from Karl G. Jansky Very Large Array, the US-based radio astronomy observatory, on V5668 Sgr as well as from research that aggregates data from a range of sources including telescope archives, this study used the Uniform Slab Model and statistical techniques to plot the nova's light and frequency curves and estimate its ejected shell mass and the brightness temperature. These characteristics help us better understand the nova's formation and eruption. The paper presents the light curves in a machine-readable format and provides insight into the behaviour of ionised gas clouds., Comment: 3 Figures

Predicting the judgment of a legal case from its unannotated case facts is a challenging task. The lengthy and non-uniform document structure poses an even greater challenge in extracting information for decision prediction. In this work, we explore and propose a two-level classification mechanism; both supervised and unsupervised; by using domain-specific pre-trained BERT to extract information from long documents in terms of sentence embeddings further processing with transformer encoder layer and use unsupervised clustering to extract hidden labels from these embeddings to better predict a judgment of a legal case. We conduct several experiments with this mechanism and see higher performance gains than the previously proposed methods on the ILDC dataset. Our experimental results also show the importance of domain-specific pre-training of Transformer Encoders in legal information processing., Comment: Published in the 1st International Workshop on Legal Information Retrieval at ECIR 2023, April 2nd 2023, Dublin, Ireland. (https://tmr.liacs.nl/legalIR/)

Studying water droplets is a rich lesson in fields of fluid dynamics, nonlinear systems, and differential equations. Understanding various physical aspects of raindrops can help us in understanding drop dynamics, rainfall density estimation, size distributions which can be grant insights in the fields of meteorology, hydrology, and climate science. This work identifies the real world significance in developing more accurate atmospheric attenuation correction algorithms that could potentially overcome the scattering effect of rain on radio and micro wave communication. This works presents and aims to compile some historical work which focuses on the influence of surface tension in the droplet nucleation and formation, raindrop oscillation, burst cycles, and transformation into parachute-like shapes before fragmentation. The interplay between surface tension and air resistance in raindrop dynamics is also explored., Comment: 15 pages, 2 figures

This work focuses on the analysis of Chess 960, also known as Fischer Random Chess, a variant of traditional chess where the starting positions of the pieces are randomized. The study aims to predict the game outcome using machine learning techniques and develop an opening theme for each starting position. The first part of the analysis utilizes machine learning models to predict the game result based on certain moves in each position. The methodology involves segregating raw data from .pgn files into usable formats and creating datasets comprising approximately 500 games for each starting position. Three machine learning algorithms -- KNN Clustering, Random Forest, and Gradient Boosted Trees -- have been used to predict the game outcome. To establish an opening theme, the board is divided into five regions: center, white kingside, white queenside, black kingside, and black queenside. The data from games played by top engines in all 960 positions is used to track the movement of pieces in the opening. By analysing the change in the number of pieces in each region at specific moves, the report predicts the region towards which the game is developing. These models provide valuable insights into predicting game outcomes and understanding the opening theme in Chess 960., Comment: 16 pages, 6 figures and 3 tables

For over 165 million years, dinosaurs reigned on this planet. Their entire existence saw variations in their body size and mass . Understanding the relationship between various attributes such as femur length, breadth; humerus length, breadth; tibia length, breadth and body mass of dinosaurs contributes to our understanding of the Jurassic era and further provides reasoning for bone and body size evolution of modern day descendants of those from the Dinosauria clade. The following work consists of statistical evidence derived from an encyclopedic data set consisting of a wide variety of measurements pertaining to discovered fossils of a particular taxa of dinosaur. Our study establishes linearly regressive correspondence between femur and humerus length and radii. Furthermore, there is also a comparison with terrestrial bird bone lengths, to verify the claim of birds being closest alive species to dinosaurs. An analysis into bone ratios of early humans shows that terrestrial birds are closer to humans than that of dinosaurs. Not only on one hand it challenges the closeness of birds with dinosaurs, but on the other hand it makes a case of convergent evolution between birds and humans, due to their closeness in regressive fits. A correlation between bone ratios of dinosaurs and early humans also advances understanding in the structural and physical distinctions between the two species. Overall, the work contains evaluation of dinosaur skeletons and promotes further exploration and research in the paleontological field to strengthen the conclusions drawn thus far., Comment: 13 pages, 14 figures, 7 tables

The present work investigates the effect of an external rotating magnetic field on a magnetic needle, and aims to study chaotic behaviour. The equation of motion is modified to include damping and gravity. The bifurcation behaviour of such evolving systems is also studied. Furthermore, the coupling in pairs of magnetic needles is also analyzed. In addition, a 2-dimensional array of coupled needles is set up, and the synchronization properties of the population is studied. The study is completed by carrying out an investigation of the effects of noise on the synchronization of such a system., Comment: 7 pages, 11 Figures

Automatic legal judgment prediction and its explanation suffer from the problem of long case documents exceeding tens of thousands of words, in general, and having a non-uniform structure. Predicting judgments from such documents and extracting their explanation becomes a challenging task, more so on documents with no structural annotation. We define this problem as "scarce annotated legal documents" and explore their lack of structural information and their long lengths with a deep-learning-based classification framework which we call MESc; "Multi-stage Encoder-based Supervised with-clustering"; for judgment prediction. We explore the adaptability of LLMs with multi-billion parameters (GPT-Neo, and GPT-J) to legal texts and their intra-domain(legal) transfer learning capacity. Alongside this, we compare their performance and adaptability with MESc and the impact of combining embeddings from their last layers. For such hierarchical models, we also propose an explanation extraction algorithm named ORSE; Occlusion sensitivity-based Relevant Sentence Extractor; based on the input-occlusion sensitivity of the model, to explain the predictions with the most relevant sentences from the document. We explore these methods and test their effectiveness with extensive experiments and ablation studies on legal documents from India, the European Union, and the United States with the ILDC dataset and a subset of the LexGLUE dataset. MESc achieves a minimum total performance gain of approximately 2 points over previous state-of-the-art proposed methods, while ORSE applied on MESc achieves a total average gain of 50% over the baseline explainability scores., Comment: Published as non archival paper in the The 3rd International Workshop on Mining and Learning in the Legal Domain (MLLD-2023) at CIKM 2023, Birmingham, United Kingdom. (https://sites.google.com/view/mlld2023/)

Modern medical image segmentation methods primarily use discrete representations in the form of rasterized masks to learn features and generate predictions. Although effective, this paradigm is spatially inflexible, scales poorly to higher-resolution images, and lacks direct understanding of object shapes. To address these limitations, some recent works utilized implicit neural representations (INRs) to learn continuous representations for segmentation. However, these methods often directly adopted components designed for 3D shape reconstruction. More importantly, these formulations were also constrained to either point-based or global contexts, lacking contextual understanding or local fine-grained details, respectively--both critical for accurate segmentation. To remedy this, we propose a novel approach, SwIPE (Segmentation with Implicit Patch Embeddings), that leverages the advantages of INRs and predicts shapes at the patch level--rather than at the point level or image level--to enable both accurate local boundary delineation and global shape coherence. Extensive evaluations on two tasks (2D polyp segmentation and 3D abdominal organ segmentation) show that SwIPE significantly improves over recent implicit approaches and outperforms state-of-the-art discrete methods with over 10x fewer parameters. Our method also demonstrates superior data efficiency and improved robustness to data shifts across image resolutions and datasets. Code is available on Github (https://github.com/charzharr/miccai23-swipe-implicit-segmentation)., Comment: Accepted to the 2023 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'23)

This work delves into the realm of logic puzzles by focusing on the Knight and Knave problems popularized by Raymond Smullyan in his book series "What is the Name of This Book?". The puzzles revolve around characters known as Knights (truth-tellers) and Knaves (liars), challenging solvers to determine the true identity of each person based on their statements. This paper explores the utilization of Python algorithms to automate the process of solving these puzzles, offering a computational approach that enhances efficiency and accessibility. In this work, we aim to develop a Python algorithm capable of parsing and analyzing the statements provided in the Knight and Knave puzzles. A logical reasoning framework is integrated within the algorithm to deduce the identities of the characters based on their statements. The algorithm processes the input statements, create a knowledge base, and make deductions following the rules of Knight and Knave logic. The developed algorithm is thoroughly tested on various instances of Knight and Knave puzzles, comparing its results to known solutions and manual approaches. We further expand the scope of the problem by introducing a Normal (who can sometimes lie and sometimes say the truth)., Comment: 8 pages

This research paper focuses on the implementation of radial Basis Function (RBF) Support Vector Machines (SVM) for classifying asteroid orbits. Asteroids are important astronomical objects, and their orbits play a crucial role in understanding the dynamics of the solar system. The International Astronomical Union maintains data archives that provide a playground to experiment with various machine-learning techniques. In this study, we explore the application of RBF SVM algorithm to classify asteroids. The results show that the RBF SVM algorithm provides a good efficiency and accuracy to the dataset. We also analyze the impact of various parameters on the performance of the RBF SVM algorithm and present the optimal parameter settings. Our study highlights the importance of using machine learning techniques for classifying asteroid orbits and the effectiveness of the RBF SVM algorithm in this regard., Comment: 15 pages, 8 figures, 3 tables

Statistical physics is important in understanding the physics of interacting many bodies. This has been historically developed by attempts to understand colliding gases and quantifying quantities like entropy, free energy, and other thermodynamic quantities. An important contribution in statistical physics was by Boltzmann in the form of the H-theorem, which considered collisions between particles and used the assumption of molecular chaos or Stosszahlansatz to understand macroscopic irreversibility. To elucidate these ideas, Mark Kac introduced a classical analog called Kac rings. In this work, we attempt to introduce quantum-ness in a Kac ring and study its entropy and recurrence, comparing and contrasting to corresponding trends in a classical Kac ring. We look at the trends of recurrence time for a system with a qubit as a pointer. We further study the time distribution of entropy for these systems., Comment: 13 Pages, 9 Figures

Biomedical image classification requires capturing of bio-informatics based on specific feature distribution. In most of such applications, there are mainly challenges due to limited availability of samples for diseased cases and imbalanced nature of dataset. This article presents the novel framework of multi-head self-attention for vision transformer (ViT) which makes capable of capturing the specific image features for classification and analysis. The proposed method uses the concept of residual connection for accumulating the best attention output in each block of multi-head attention. The proposed framework has been evaluated on two small datasets: (i) blood cell classification dataset and (ii) brain tumor detection using brain MRI images. The results show the significant improvement over traditional ViT and other convolution based state-of-the-art classification models.

We consider the problem of optimal unsignalized intersection management, wherein we seek to obtain safe and optimal trajectories, for a set of robots that arrive randomly and continually. This problem involves repeatedly solving a mixed integer program (with robot acceleration trajectories as decision variables) with different parameters, for which the computation time using a naive optimization algorithm scales exponentially with the number of robots and lanes. Hence, such an approach is not suitable for real-time implementation. In this paper, we propose a solution framework that combines learning and sequential optimization. In particular, we propose an algorithm for learning a shared policy that given the traffic state information, determines the crossing order of the robots. Then, we optimize the trajectories of the robots sequentially according to that crossing order. This approach inherently guarantees safety at all times. We validate the performance of this approach using extensive simulations and compare our approach against $5$ different heuristics from the literature in $9$ different simulation settings. Our approach, on average, significantly outperforms the heuristics from the literature in various metrics like objective function, weighted average of crossing times and computation time. For example, in some scenarios, we have observed that our approach offers up to $150\%$ improvement in objective value over the first come first serve heuristic. Even on untrained scenarios, our approach shows a consistent improvement (in objective value) of more than $30\%$ over all heuristics under consideration. We also show through simulations that the computation time for our approach scales linearly with the number of robots (assuming all other factors are constant). Learnt policies are implemented on physical robots with slightly modified framework to address real-world challenges., Comment: 19 pages, 35 figures

Understanding of spatial attributes is central to effective 3D radiology image analysis where crop-based learning is the de facto standard. Given an image patch, its core spatial properties (e.g., position & orientation) provide helpful priors on expected object sizes, appearances, and structures through inherent anatomical consistencies. Spatial correspondences, in particular, can effectively gauge semantic similarities between inter-image regions, while their approximate extraction requires no annotations or overbearing computational costs. However, recent 3D contrastive learning approaches either neglect correspondences or fail to maximally capitalize on them. To this end, we propose an extensible 3D contrastive framework (Spade, for Spatial Debiasing) that leverages extracted correspondences to select more effective positive & negative samples for representation learning. Our method learns both globally invariant and locally equivariant representations with downstream segmentation in mind. We also propose separate selection strategies for global & local scopes that tailor to their respective representational requirements. Compared to recent state-of-the-art approaches, Spade shows notable improvements on three downstream segmentation tasks (CT Abdominal Organ, CT Heart, MR Heart)., Comment: Accepted to 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM'22)