Yogish Mallya - Academia.edu (original) (raw)

Papers by Yogish Mallya

BMJ Open, Dec 1, 2022

Objective Patient monitoring in general wards primarily involves intermittent observation of temp... more Objective Patient monitoring in general wards primarily involves intermittent observation of temperature, heart rate (HR), respiratory rate (RR) and blood pressure performed by the nursing staff. Several hours can lapse between such measurements, and the patient may go unobserved. Despite the growing widespread use of sensors to monitor vital signs and physical activities of healthy individuals, most acutely ill hospitalised patients remain unmonitored, leaving them at an increased risk. We investigated whether a contactless monitoring system could measure vital parameters, such as HR and RR, in a real-world hospital setting. Design A cross-sectional prospective study. Setting and participants We examined the suitability of employing a non-contact monitoring system in a low-acuity setup at a tertiary care hospital in India. Measurements were performed on 158 subjects, with data acquired through contactless monitoring from the general ward and dialysis unit. Outcome measures Vital parameters (RR and HR) were measured using a video camera in a non-acuity setting. Results Three distinct combinations of contactless monitoring afforded excellent accuracy. Contactless RR monitoring was linearly correlated with Alice NightOne and manual counts, presenting coefficients of determination of 0.88 and 0.90, respectively. Contactless HR monitoring presented a coefficient of determination of 0.91. The mean absolute errors were 0.84 and 2.15 beats per minute for RR and HR, respectively. Conclusions Compared with existing Food and Drug Administration-approved monitors, the findings of the present study revealed that contactless monitoring of RR and HR accurately represented study populations in non-acuity settings. Contactless video monitoring is an unobtrusive and dependable method for monitoring and recording RR and HR. Further research is needed to validate its dependability and utility in other settings, including acute care. Trial registration number CTRI/2018/11/016246.

Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging

Quantitative evaluation of bones and ligaments around knee joint from magnetic resonance imaging ... more Quantitative evaluation of bones and ligaments around knee joint from magnetic resonance imaging (MRI) often requires the boundaries of selected structures to be manually traced using computer software. It may take several hours to delineate all structures of interest in a three-dimensional (3D) dataset used for the evaluation. Thus, providing automated tools, which can delineate knee anatomical structures can improve productivity and efficiency in radiology departments. In recent years, 3D deep convolutional neural networks (3D CNN) have been successfully used for segmentation of knee bones and cartilage. However, the key challenge is segmentation of the anterior cruciate ligament (ACL) and the posterior cruciate ligament (PCL), due to high variability of intensities in the areas of pathologies such as ligament tear. In this approach, an open source 3D CNN is adapted for segmentation of knee bones and ligaments in the knee MRI. The segmentation accuracy of ACL and PCL is improved further by atlas based segmentation technique. The atlas mask is non-rigidly aligned with the patient image based on composite of rigid and deformable vector field derived between the bone masks in the atlas and corresponding segmented bone masks in the patient image. The level set functions corresponding to particular objects of interest of the deformed atlas are used to refine segmentation of the corresponding objects in the patient image. The accuracy of the proposed method is assessed using Dice coefficient score for 50 manual segmentations of bone, cartilage and ligaments comprising of both normal and knee injury cases. Our results show that the proposed approach offers a viable alternative to manual contouring of knee MRI volume by a human reader with improved accuracy compared to the 3D CNN.

A multi-institution evaluation of deformable image registration algorithms for automatic organ de... more A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy

Advances in Computational Techniques for Biomedical Image Analysis, 2020

Abstract Intracranial hemorrhages (ICHs) represent a critical medical event associated with poor ... more Abstract Intracranial hemorrhages (ICHs) represent a critical medical event associated with poor outcome despite the best of care. Since early recognition and management of ICH can improve the patient outcomes, there is a need for a triaging system to rapidly detect such conditions and expedite the treatment process. This chapter examines the state-of-the-art traditional and deep learning models for automated detection tasks with a focus on ICH. The prior works are summarized to display their respective strengths and weaknesses. This is followed by depicting how the advantages of different types of models can be combined to achieve improved results. The chapter concludes with the proposed roles of such a detection framework in clinical workflow.

Lecture Notes in Computer Science, 2019

Non-contrast head/brain CT (NCHCT) is the initial imaging study of choice in patients visiting an... more Non-contrast head/brain CT (NCHCT) is the initial imaging study of choice in patients visiting any emergency services and could be the only investigation to guide management in patients with head trauma or stroke symptoms. Immediate preliminary radiology reports to trigger appropriate level of care is paramount in the emergency department. Our proposed solution comprises of an efficient method for the detection of intracranial hemorrhage, by creating multiple 2-dimensional (2D) composite images of sub-volumes from the original scan. We also propose a recurrent neural network which combines the sub-volume features and takes into consideration the contextual information across sub-volumes to give a scan level prediction. We achieve an overall AUROC of 0.914.

SPIE Proceedings, 2006

3-D analysis of blood vessels from volumetric CT and MR datasets has many applications ranging fr... more 3-D analysis of blood vessels from volumetric CT and MR datasets has many applications ranging from examination of pathologies such as aneurysm and calcification to measurement of cross-sections for therapy planning. Segmentation of the vascular structures followed by tracking is an important processing step towards automating the 3-D vessel analysis workflow. This paper demonstrates a fast and automated algorithm for

2006 International Conference of the IEEE Engineering in Medicine and Biology Society, 2006

This paper proposes 2D active contour approach for segmenting thrombus volume from 3D CT images o... more This paper proposes 2D active contour approach for segmenting thrombus volume from 3D CT images of abdominal aortic aneurysm (AAA). The major challenges in segmenting thrombus are in part because of lack of delineating contrast at anatomical boundaries due to overlap of other soft tissues and artifacts arising from stents and calcium deposits. In the present approach first the bone structures are removed from the image so that these nearby high intensity regions do not interfere in the segmentation process. Next morphological operation is done on the bone-removed image to reduce the effect of streak artifacts. The order of these two operations can be inter-changed. Then, a manual contour is initialized on an axial slice of the pre-processed image and deformed and subsequently propagated to the consecutive slices for deformation. The snake process is governed by force field defined by intensity-based object-ness measure within a band defined by local image properties. The proposed algorithm has been tested on 7 CT images and compared with the ground truth obtained from manual segmentation by radiologist and accuracy between the range 93.16% to 85.08% is observed.

2010 6th International Colloquium on Signal Processing & its Applications, 2010

Abstract Organ delineation from volumetric images is an integral part of radiation oncology plan... more Abstract Organ delineation from volumetric images is an integral part of radiation oncology planning. Model based segmentation techniques have been successfully applied for automatic segmentation of region of interest (ROI) in volumetric medical images. The ROI is ...

Medical Imaging 2009: Image Processing, 2009

ABSTRACT Angiogenesis is the process of formation of new blood vessels as outgrowths of pre-exist... more ABSTRACT Angiogenesis is the process of formation of new blood vessels as outgrowths of pre-existing ones. It occurs naturally during development, tissue repair, and abnormally in pathologic diseases such as cancer. It is associated with proliferation of blood vessels/tubular sprouts that penetrate deep into tissues to supply nutrients and remove waste products. The process starts with migration of endothelial cells. As the cells move towards the target area they form small tubular sprouts recruited from the parent vessel. The sprouts grow in length due to migration, proliferation, and recruitment of new endothelial cells and the process continues until the target area becomes fully vascular. Accurate quantification of sprout formation is very important for evaluation of treatments for ischemia as well as angiogenesis inhibitors and plays a key role in the battle against cancer. This paper presents a technique for automatic quantification of newly formed blood vessels from Micro-CT volumes of tumor samples. A semiautomatic technique based on interpolation of Bezier curves was used to segment out the cancerous growths. Small vessels as determined by their diameter within the segmented tumors were enhanced and quantified with a multi-scale 3-D line detection filter. The same technique can be easily extended for quantification of tubular structures in other 3-D medical imaging modalities. Experimental results are presented and discussed.

SPIE Proceedings, 2004

Radiologists perform a CT Angiography procedure to examine vascular structures and associated pat... more Radiologists perform a CT Angiography procedure to examine vascular structures and associated pathologies such as aneurysms. Volume rendering is used to exploit volumetric capabilities of CT that provides complete interactive 3-D visualization. However, bone forms an occluding structure and must be segmented out. The anatomical complexity of the head creates a major challenge in the segmentation of bone and vessel. An analysis of the head volume reveals varying spatial relationships between vessel and bone that can be separated into three sub-volumes: "proximal", "middle", and "distal". The "proximal" and "distal" sub-volumes contain good spatial separation between bone and vessel (carotid referenced here). Bone and vessel appear contiguous in the "middle" partition that remains the most challenging region for segmentation. The partition algorithm is used to automatically identify these partition locations so that different segmentation methods can be developed for each sub-volume. The partition locations are computed using bone, image entropy, and sinus profiles along with a rule-based method. The algorithm is validated on 21 cases (varying volume sizes, resolution, clinical sites, pathologies) using ground truth identified visually. The algorithm is also computationally efficient, processing a 500+ slice volume in 6 seconds (an impressive 0.01 seconds / slice) that makes it an attractive algorithm for pre-processing large volumes. The partition algorithm is integrated into the segmentation workflow. Fast and simple algorithms are implemented for processing the "proximal" and "distal" partitions. Complex methods are restricted to only the "middle" partition. The partitionenabled segmentation has been successfully tested and results are shown from multiple cases.

SPIE Proceedings, 2005

Recent trends in medical image processing involve computationally intensive processing techniques... more Recent trends in medical image processing involve computationally intensive processing techniques on large data sets, especially for 3D applications such as segmentation, registration, volume rendering etc. Multi-resolution image processing techniques have been used in order to speed-up these methods. However, all well-known techniques currently used in multi-resolution medical image processing rely on using Gaussain-based or other equivalent floating point representations that are lossy and irreversible. In this paper, we study the use of Integer Wavelet Transforms (IWT) to address the issue of lossless representation and reversible reconstruction for such medical image processing applications while still retaining all the benefits which floating-point transforms offer such as high speed and efficient memory usage. In particular, we consider three low-complexity reversible wavelet transforms namely the - Lazy-wavelet, the Haar wavelet or (1,1) and the S+P transform as against the Gaussian filter for multi-resolution speed-up of an automatic bone removal algorithm for abdomen CT Angiography. Perfect-reconstruction integer wavelet filters have the ability to perfectly recover the original data set at any step in the application. An additional advantage with the reversible wavelet representation is that it is suitable for lossless compression for purposes of storage, archiving and fast retrieval. Given the fact that even a slight loss of information in medical image processing can be detrimental to diagnostic accuracy, IWTs seem to be the ideal choice for multi-resolution based medical image segmentation algorithms. These could also be useful for other medical image processing methods.

Radiation Oncology, 2012

Background: Adaptive Radiotherapy aims to identify anatomical deviations during a radiotherapy co... more Background: Adaptive Radiotherapy aims to identify anatomical deviations during a radiotherapy course and modify the treatment plan to maintain treatment objectives. This requires regions of interest (ROIs) to be defined using the most recent imaging data. This study investigates the clinical utility of using deformable image registration (DIR) to automatically propagate ROIs. Methods: Target (GTV) and organ-at-risk (OAR) ROIs were non-rigidly propagated from a planning CT scan to a per-treatment CT scan for 22 patients. Propagated ROIs were quantitatively compared with expert physician-drawn ROIs on the per-treatment scan using Dice scores and mean slicewise Hausdorff distances, and center of mass distances for GTVs. The propagated ROIs were qualitatively examined by experts and scored based on their clinical utility. Results: Good agreement between the DIR-propagated ROIs and expert-drawn ROIs was observed based on the metrics used. 94% of all ROIs generated using DIR were scored as being clinically useful, requiring minimal or no edits. However, 27% (12/44) of the GTVs required major edits. Conclusion: DIR was successfully used on 22 patients to propagate target and OAR structures for ART with good anatomical agreement for OARs. It is recommended that propagated target structures be thoroughly reviewed by the treating physician.

Physics in Medicine and Biology, 2013

Medical Physics, 2013

ABSTRACT Purpose: To evaluate a correction algorithm for enhancing the accuracy of deformation ve... more ABSTRACT Purpose: To evaluate a correction algorithm for enhancing the accuracy of deformation vector field generated by deformable image registration (DIR) techniques. Methods: Delineated contours of targets and organ at risk structures (OARs) in a pre‐treatment prostate CT image volume were automatically propagated to the treatment CT image volume using an intensity based deformable image registration. All of the datasets used in this study were associated with expert‐drawn contours for the structures in the treatment CT. The contours of the automatically propagated structures were corrected to match the corresponding expert‐drawn contours of the structures in the treatment CT image. A modified Demons DIR algorithm was used to compute the incremental displacement vector field(DVF) that represented the corrections made to the automatically propagated contours. The initial DVF that was used for contour propagation was synchronized to the corrected contours by creating a composite vector field from the initial and the incremental DVF. The composite DVF was then used to propagate contours of targets and organ at risk structures from the planning CT to the treatment CT. Resulting deformed contours for each structure were compared to its corresponding expert‐drawn contours using the Dice similarity coefficient(DSC) and Hausdorff distance(HD). Results: Visually the deformed contours using the corrected DVF were similar to the corrected and the expert‐drawn contours. The Hausdorff distance improved up to 0.24mm from 1.33mm(82% improvement) and the DSC improved from up to 0.96 from 0.78(24% improvement). Conclusion: The accuracy of the automatically propagated contours of targets and OARs using a corrected DVF were significantly higher than that obtained using the pre‐corrected DVF. Therefore the technique can be used as an independent post processing step to correct the DVF generated by a DIR technique. The method could potentially be used to improve accuracy of subsequent dose deformation and accumulation steps of adaptive therapy.

2010 IEEE 2nd International Advance Computing Conference (IACC), 2010

AbstractOrgan delineation from volumetric dataset is often encountered problem in medical imagin... more AbstractOrgan delineation from volumetric dataset is often encountered problem in medical imaging. Numerous 3D polygonal surface mesh model based segmentation algorithms have been reported in this area. These algorithms aim for a fully automated solution for ...

PURPOSE To study the clinical utility of bone-free 3-D volume rendering of CTA Neuro vasculature.... more PURPOSE To study the clinical utility of bone-free 3-D volume rendering of CTA Neuro vasculature. Evaluate presentation of individual vessel segments and assessment of pathologies such as aneurysms and AVMs. METHOD AND MATERIALS Study included 20 anonymized CTA head (circle of Willis) data sets from various MDCT scanners (GE Healthcare). The radiologists used Volume Viewer of Advantage Windows (AW) Workstation (GE Healthcare) to launch a prototype automatic bone segmentation algorithm that took 30 s per case for a COW data set of size 512 x 512 x 200 to remove bone. Radiologists evaluated each case using the Volume Rendering and Maximum Intensity Projection (MIP) modes. The opacity map (for VR) and the Window/Level (for MIP) settings were adjusted for optimal rendering of each case. The head volume was broken up into several components based on anatomy and the prevalence of corresponding pathology. Each component was rated for clarity of anatomy, residual bone interference, and conf...