Kashish Verma

Mrs. Kashish Verma

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2022
Verified
Conference Paper
Open access
DRDeepak Raina
Deepak Raina
KVKashish Verma
Kashish Verma
SCSheragaru Hanumanthappa Chandrashekhara
Sheragaru Hanumanthappa Chandrashekhara
SSSubir Kumar Saha
Subir Kumar Saha
We investigate the applicability of U-Net based models for segmenting Urinary Bladder (UB) in male pelvic view UltraSound (US) images. The segmentation of UB in the US image aids radiologists in diagnosing the UB. However, UB in US images has arbitrary shapes, indistinct boundaries and considerably large inter- and intra-subject variability, making segmentation a quite challenging task. Our study of the state-of-the-art (SOTA) segmentation network, U-Net, for the problem reveals that it often fails to capture the salient characteristics of UB due to the varying shape and scales of anatomy in the noisy US image. Also, U-net has an excessive number of trainable parameters, reporting poor computational efficiency during training. We propose a Slim U-Net to address the challenges of UB segmentation. Slim U-Net proposes to efficiently preserve the salient features of UB by reshaping the structure of U-Net using a less number of 2D convolution layers in the contracting path, in order to preserve and impose them on expanding path. To effectively distinguish the blurred boundaries, we propose a novel annotation methodology, which includes the background area of the image at the boundary of a marked region of interest (RoI), thereby steering the model’s attention towards boundaries. In addition, we suggested a combination of loss functions for network training in the complex segmentation of UB. The experimental results demonstrate that Slim U-net is statistically superior to U-net for UB segmentation. The Slim U-net further decreases the number of trainable parameters and training time by and , respectively, compared to the standard U-Net, without compromising the segmentation accuracy. The project page with source code is available at https://sites.google.com/view/slimunet.

24 January 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
VPVictor Vigara Puche
Victor Vigara Puche
KVKashish Verma
Kashish Verma
MFMatteo Fumagalli
Matteo Fumagalli
The growing global demand for critical raw materials has highlighted the need for autonomous systems in abandoned underground mines. We propose a multi-robot coordination architecture using Hierarchical Finite State Machines (HFSMs) for sequential task execution in GPS-denied, infrastructure-less environments. Unlike existing centralized approaches, our system enables each robot to execute its own HFSM behavior triggered through inter-robot communication, eliminating dependency on persistent connectivity. We implemented and validated this architecture using a Deployer robot and a Stinger robot within the EU Horizon PERSEPHONE project. Experimental validation demonstrated successful coordination both with persistent connectivity and during network interruptions, proving the system’s fault tolerance capabilities. The system successfully executed sequential deployment and anchoring tasks, demonstrating that this coordination approach enables multi-robot coordination without requiring persistent connectivity, thereby addressing critical limitations for autonomous operations in underground environments.

23 February 2023 in Research Square
Verified
Preprint
Open access
PDF file
DRDeepak Raina
Deepak Raina
KVKashish Verma
Kashish Verma
SCSheragaru Hanumanthappa Chandrashekhara
Sheragaru Hanumanthappa Chandrashekhara
SSSubir Kumar Saha
Subir Kumar Saha
We investigate the applicability of U-Net based models for segmenting Urinary Bladder (UB) in male pelvic view UltraSound (US) images. The segmentation of UB in the US image aids radiologists in diagnosing the UB. However, UB in US images has arbitrary shapes, indistinct boundaries and considerably large inter- and intra-subject variability, making segmentation a quite challenging task. Our study of the state-of-the-art (SOTA) segmentation network, U-Net, for the problem reveals that it often fails to capture the salient characteristics of UB due to the varying shape and scales of anatomy in the noisy US image. Also, U-net has an excessive number of trainable parameters, reporting poor computational efficiency during training. We propose a Slim U-Net to address the challenges of UB segmentation. Slim U-Net proposes to efficiently preserve the salient features of UB by reshaping the structure of U-Net using a less number of 2D convolution layers in the contracting path, in order to preserve and impose them on expanding path. To effectively distinguish the blurred boundaries, we propose a novel annotation methodology, which includes the background area of the image at the boundary of a marked region of interest (RoI), thereby steering the model's attention towards boundaries. In addition, we suggested a combination of loss functions for network training in the complex segmentation of UB. The experimental results demonstrate that Slim U-net is statistically superior to U-net for UB segmentation. The Slim U-net further decreases the number of trainable parameters and training time by 54% and 57.7%, respectively, compared to the standard U-Net, without compromising the segmentation accuracy.