Search

Weakly-supervised medical image segmentation is a challenging task that aims to reduce the annotation cost while keep the segmentation performance. In this paper, we present a novel framework, SimTxtSeg, that leverages simple text cues to generate high-quality pseudo-labels and study the cross-modal fusion in training segmentation models, simultaneously. Our contribution consists of two key components: an effective Textual-to-Visual Cue Converter that produces visual prompts from text prompts on medical images, and a text-guided segmentation model with Text-Vision Hybrid Attention that fuses text and image features. We evaluate our framework on two medical image segmentation tasks: colonic polyp segmentation and MRI brain tumor segmentation, and achieve consistent state-of-the-art performance., Comment: accepted by MICCAI 2024

Hill function is one of the widely used gene transcription regulation models. Its attribute of fitting may result in a lack of an underlying physical picture, yet the fitting parameters can provide information about biochemical reactions, such as the number of transcription factors (TFs) and the binding energy between regulatory elements. However, it remains unclear when and how much biochemical information can Hill function provide in addition to fitting. Here, started from the interactions between TFs and RNA polymerase during transcription regulation and both of their association-dissociation reactions at specific/nonspecific sites on DNA, the regulatory effect of TFs was deduced as fold change. We found that, for weak promoter, fold change can degrade into the regulatory factor (Freg) which is closely correlated with Hill function. By directly comparing and fitting with Hill function, the fitting parameters and corresponding biochemical reaction parameters in Freg were analyzed and discussed, where the single TF and multiple TFs that with cooperativity and basic logic effects were considered. We concluded the strength of promoter and interactions between TFs determine whether Hill function can reflect the corresponding biochemical information. Our findings highlight the role of Hill function in modeling/fitting for transcriptional regulation, which also benefits the preparation of synthetic regulatory elements.

Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise. As noise cannot easily be discerned from image details, such as high-frequency signals, its presence leads to extra bits needed for compression. Since the emerging learned image compression paradigm enables end-to-end optimization of codecs, recent efforts were made to integrate denoising into the compression model, relying on clean image features to guide denoising. However, these methods exhibit suboptimal performance under high noise levels, lacking the capability to generalize across diverse noise types. In this paper, we propose a novel method integrating a multi-scale denoiser comprising of Self Organizing Operational Neural Networks, for joint image compression and denoising. We employ contrastive learning to boost the network ability to differentiate noise from high frequency signal components, by emphasizing the correlation between noisy and clean counterparts. Experimental results demonstrate the effectiveness of the proposed method both in rate-distortion performance, and codec speed, outperforming the current state-of-the-art., Comment: Copyright 2024 IEEE - Submitted to IEEE ICIP 2024

Via evaluation of the Lyapunov exponent, we report the discovery of three prominent sets of phase space regimes of quasi-periodic orbits of charged particles trapped in a dipole magnetic field. Besides the low energy regime that has been studied extensively and covers more than 10% in each dimension of the phase space of trapped orbits, there are two sets of high energy regimes, the largest of which covers more than 4% in each dimension of the phase space of trapped orbits. Particles in these high energy orbits may be observed in space and be realized in plasma experiments on the Earth. It is well-known that there are quasi-periodic orbits around stable periodic orbits in Hamiltonian systems with 2 degrees of freedom and these quasi-periodic orbits are stable as well. Since periodic orbits appear to have a negligible measure in the phase space, they are difficult to realize in nature. Quasi-periodic orbits, on the other hand, may occupy a finite volume in the 4 dimensional (4D) phase space and be readily detectable. A chaotic orbit has at least one positive Lyapunov exponent. The Lyapunov exponents of quasi-periodic orbits, on the other hand, should be zero. Via calculation of the Lyapunov exponent of orbits of trapped charged particles in a dipole magnetic field, we scanned the corresponding phase space and found several prominent regimes of quasi-periodic orbits associated with stable periodic orbits in the equatorial plane. These regimes appear to be connected to some small regimes of quasi-periodic orbits associated with stable periodic orbits in the Meridian plane. Our numerical results also show a continuous spectrum of these orbits from stable periodic, to quasi-periodic with vanishing Lyapunov exponents, and eventually to chaotic ones with at least one positive Lyapunov exponent and there are unstable periodic orbits with a positive maximum Lyapunov exponent.