GenSelfDiff-HIS: Generative Self-Supervision Using Diffusion for Histopathological Image Segmentation

Histopathological image segmentation is a laborious and time-intensive task, often requiring analysis from experienced pathologists for accurate examinations. To reduce this burden, supervised machine-learning approaches have been adopted using large-scale annotated datasets for histopathological image analysis. However, in several scenarios, the availability of large-scale annotated data is a bottleneck while training such models. Self-supervised learning (SSL) is an alternative paradigm that provides some respite by constructing models utilizing only the unannotated data which is often abundant. The basic idea of SSL is to train a network to perform one or many pseudo or pretext tasks on unannotated data and use it subsequently as the basis for a variety of downstream tasks. It is seen that the success of SSL depends critically on the considered pretext task. While there have been many efforts in designing pretext tasks for classification problems, there haven't been many attempts on SSL for histopathological segmentation. Motivated by this, we propose an SSL approach for segmenting histopathological images via generative diffusion models in this paper. Our method is based on the observation that diffusion models effectively solve an image-to-image translation task akin to a segmentation task. Hence, we propose generative diffusion as the pretext task for histopathological image segmentation. We also propose a multi-loss function-based fine-tuning for the downstream task. We validate our method using several metrics on two publically available datasets along with a newly proposed head and neck (HN) cancer dataset containing hematoxylin and eosin (H\&E) stained images along with annotations. Codes will be made public at https://github.com/PurmaVishnuVardhanReddy/GenSelfDiff-HIS.git.

VAFER: Signal Decomposition based Mutual Interference Suppression in FMCW Radars

With increasing application of frequency-modulated continuous wave (FMCW) radars in autonomous vehicles, mutual interference among FMCW radars poses a serious threat. Through this paper, we present a novel approach to effectively and elegantly suppress mutual interference in FMCW radars. We first decompose the received signal into modes using variational mode decomposition (VMD) and perform time-frequency analysis using Fourier synchrosqueezed transform (FSST). The interference-suppressed signal is then reconstructed by applying a proposed energy-entropy-based thresholding operation on the time-frequency spectra of VMD modes. The effectiveness of proposed method is measured in terms of signal-to-interference plus noise ratio (SINR) and correlation coefficient for both simulated and experimental automotive radar data in the presence of FMCW interference. Compared to other existing literature, our proposed method demonstrates significant improvement in the output SINR by at least 14.07 dB for simulated data and 9.87 dB for experimental data.