Deval Mehta

Dr. Deval Mehta

Monash eResearch Center, Monash University, Clayton, VIC 3800, Australia

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
7 June 2018 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
DMDeval Mehta
Deval Mehta
SCShoushun Chen
Shoushun Chen
KLKay Soon Low
Kay Soon Low
This paper presents a novel star identification algorithm for a "Lost-In-Space" mode star tracker. The spearman correlation approach provides reliable recognition even when the captured images are swayed and biased from the onboard star pattern database. The hamming distance approach provides a shortlisted list of star IDs. Thus, the proposed combination of hamming distance and spearman correlation provides a reliable and fast recognition. The achievable performance is evaluated by testing on simulated and real images.

9 August 2018 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
DMDeval Mehta
Deval Mehta
SCShoushun Chen
Shoushun Chen
KLKay-Soon Low
Kay-Soon Low
A novel star pattern recognition technique for a “Lost-in-space” mode star tracker is presented in this paper. Firstly, the two-dimensional (2D) vectors connecting the stars are constructed in a rotation-invariant frame. Later, the additive property of 2D vectors is integrated with the rotation-invariant frame to build a vector sequence for star identification. The proposed technique achieves an identification accuracy of 98.7% and has a run-time of only 12ms for real-time testing on star images.

15 September 2022
Verified
Book Chapter
Closed access
PDF file
DMDeval Mehta
Deval Mehta
YGYaniv Gal
Yaniv Gal
ABAdrian Bowling
Adrian Bowling
PBPaul Bonnington
Paul Bonnington
ZGZongyuan Ge
Zongyuan Ge

1 October 2023
Verified
Book Chapter
Closed access
PDF file
DMDeval Mehta
Deval Mehta
SSShobi Sivathamboo
Shobi Sivathamboo
HSHugh Simpson
Hugh Simpson
PKPatrick Kwan
Patrick Kwan
TOTerence O’bRien
Terence O’bRien
ZGZongyuan Ge
Zongyuan Ge

7 August 2025
Verified
Book Chapter
Closed access
PDF file
DMDeval Mehta
Deval Mehta
YJYiwen Jiang
Yiwen Jiang
CJCatherine Jan
Catherine Jan
MHMingguang He
Mingguang He
KJKshitij Jadhav
Kshitij Jadhav
ZGZongyuan Ge
Zongyuan Ge

7 February 2025 in Journal of the European Academy of Dermatology and Venereology
Verified
Journal Article
Open access
DMDeval Mehta
Deval Mehta
CPClare Primiero
Clare Primiero
BBBrigid Betz-Stablein
Brigid Betz-Stablein
TNToan D. Nguyen
Toan D. Nguyen
YGYaniv Gal
Yaniv Gal
ZGZongyuan Ge
Zongyuan Ge
Background: The surge in AI models for diagnosing skin lesions through image analysis is notable, yet their clinical implementation faces challenges. Common limitations include an over reliance on dermoscopy, lack of real‐world applicability when only binary output (e.g. benign/malignant) is offered and low accuracy when faced with rare skin conditions. Objectives: To address these common constraints associated with limited diagnostic output, and applicability to real‐world settings. Methods: We developed an All‐In‐One H ierarchical‐ O ut of Distribution‐Clinical T riage ( HOT ) AI model for skin lesion analysis. Trained on a large dataset of ~208,000 lesion images, our HOT AI model generates three outputs: a hierarchical three‐level prediction, an alert for out‐of‐distribution (OOD) images and a recommendation for dermoscopy to improve diagnostic prediction. Results: Our hierarchical prediction output provides a binary level 1 prediction (benign/malignant), Level 2 prediction of eight possible categories (e.g. melanocytic and keratinocytic) and a more definitive Level 3 prediction from 44 lesion categories. The model produced high sensitivity for Level 1 prediction (88.14% CI: 87.42–88.51); however, significantly lower for Level 3 prediction (63.90%, CI: 62.27–65.61). By relying on all three prediction levels for consensus, Level 1 false‐positives were reduced by 20–25%, and false‐negatives were decreased by 11–13% of cases. OOD detection was benchmarked against previous landmark models and outperformed comparative models. Lastly, 44% of images were recommended for dermoscopy, and with additional image input, Level 3 sensitivity increased from 48.13% (CI:45.08–49.57) to 52.54% (CI:50.25–55.04). Conclusions: Our HOT‐AI model attempts to address common challenges in existing models by combining three tasks in one model to increase accuracy and clinical utility. By providing a more nuanced prediction, and alert for OOD, the model output provides greater explainability of the AI decision process. Prospective clinical testing is required to measure how this additional output impacts user trust, and how the model performs in a real‐world setting.