Nachiket Dilip Makwana

Mr. Nachiket Dilip Makwana

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 March 2021 in Clinical Ophthalmology
Verified
Journal Article
Open access
PDF file
AMArvind Kumar Morya
Arvind Kumar Morya
JGJaitra Gowdar
Jaitra Gowdar
AKAbhishek Kaushal
Abhishek Kaushal
NMNachiket Dilip Makwana
Nachiket Dilip Makwana
SBSaurav Biswas
Saurav Biswas
PRPankaja Raghav
Pankaja Raghav
Introduction: Deep Learning (DL) and Artificial Intelligence (AI) have become widespread due to the advanced technologies and availability of digital data. Supervised learning algorithms have shown human-level performance or even better and are better feature extractor-quantifier than unsupervised learning algorithms. To get huge dataset with good quality control, there is a need of an annotation tool with a customizable feature set. This paper evaluates the viability of having an in house annotation tool which works on a smartphone and can be used in a healthcare setting. Methods: We developed a smartphone-based grading system to help researchers in grading multiple retinal fundi. The process consisted of designing the flow of user interface (UI) keeping in view feedback from experts. Quantitative and qualitative analysis of change in speed of a grader over time and feature usage statistics was done. The dataset size was approximately 16,000 images with adjudicated labels by a minimum of 2 doctors. Results for an AI model trained on the images graded using this tool and its validation over some public datasets were prepared. Results: We created a DL model and analysed its performance for a binary referrable DR Classification task, whether a retinal image has Referrable DR or not. A total of 32 doctors used the tool for minimum of 20 images each. Data analytics suggested significant portability and flexibility of the tool. Grader variability for images was in favour of agreement on images annotated. Number of images used to assess agreement is 550. Mean of 75.9% was seen in agreement. Conclusion: Our aim was to make Annotation of Medical imaging easier and to minimize time taken for annotations without quality degradation. The user feedback and feature usage statistics confirm our hypotheses of incorporation of brightness and contrast variations, green channels and zooming add-ons in correlation to certain disease types. Simulation of multiple review cycles and establishing quality control can boost the accuracy of AI models even further. Although our study aims at developing an annotation tool for diagnosing and classifying diabetic retinopathy fundus images but same concept can be used for fundus images of other ocular diseases as well as other streams of medical science such as radiology where image-based diagnostic applications are utilised.

1 January 2021 in Clinical Ophthalmology
Verified
Journal Article
Open access
PDF file
AMArvind Kumar Morya
Arvind Kumar Morya
JGJaitra Gowdar
Jaitra Gowdar
AKAbhishek Kaushal
Abhishek Kaushal
NMNachiket Dilip Makwana
Nachiket Dilip Makwana
SBSaurav Biswas
Saurav Biswas
USUmang P Salodia
Umang P Salodia
Erratum for the article Evaluating the Viability of a Smartphone-Based Annotation Tool for Faster and Accurate Image Labelling for Artificial Intelligence in Diabetic Retinopathy

20 November 2025 in medRxiv
Verified
Preprint
Open access
PDF file
NMNachiket Dilip Makwana
Nachiket Dilip Makwana
FMFarhan Adam Mukadam
Farhan Adam Mukadam
HMHarshit Mishra
Harshit Mishra
PTPradyot Tiwari
Pradyot Tiwari
KSKandasamy Subramani
Kandasamy Subramani
KHK.V.S. Hari
K.V.S. Hari
Electrocardiogram (ECG) today largely remains paper-based making them inaccessible for research and innovation. To address this unmet need, we describe an end-to-end framework for ECG signal extraction from images using a four-stage pipeline and lay down the associated data generation requirements. The signal extraction stages include perspective correction, reorientation of paper, lead isolation and signal segmentation that converts signals to voltage units enabling precise digital reconstruction of the original waveforms. Our data generation methodology generates 72,080 simulated ECG images from open source digital signal datasets. We apply novel, realistic augmentations such as coffee stains, imaging shadows and introduce 3D deformation using Blender3D. Furthermore, we employ text-to-image and image-to-image workflows by synthesizing backgrounds around ECG images using the SDXL model with IP Adapter. Our pipeline achieves acceptable signal extraction with a Pearson correlation coefficient of 0.78 and processing speeds of ≈ 1.03 seconds, which is four times faster than existing methods on a related benchmark dataset. This advancement enables practical use of ECG digitization in fast-paced clinical environments, reducing cardiology consultation turnaround times and facilitating digital storage for population health analysis.

15 November 2025 in medRxiv
Verified
Preprint
Open access
PDF file
HMHarshit Mishra
Harshit Mishra
FMFarhan Adam Mukadam
Farhan Adam Mukadam
NMNachiket Dilip Makwana
Nachiket Dilip Makwana
PTPradyot Tiwari
Pradyot Tiwari
KSKandasamy Subramani
Kandasamy Subramani
KHK.V.S. Hari
K.V.S. Hari
Atrial fibrillation (AFib) represents a critical diagnostic challenge in clinical cardiology, calling for automated detection systems capable of robust performance across diverse clinical environments. We present a computationally efficient deep neural network architecture for AFib detection that demonstrates exceptional generalizability despite training on a modest dataset. Our convolutional neural network, comprising 17 million parameters, was trained on 67,432 12-lead electrocardiograms and subsequently validated on over 1.1 million ECG recordings spanning six independent public datasets. On CPU, the model processes a 10-second ECG in 200 ms, enabling real-time inference capabilities. Our model achieves state-of-the-art performance, with an average area under the receiver operating characteristic curve (AUROC) of 0.97, an average sensitivity of 0.83, and an average specificity of 0.96 across six external validation cohorts. These metrics rank among the highest reported in the literature, while preserving computational efficiency suitable for resource-constrained environments. A key innovation of our approach is the implementation of channel-masking methodology, enabling seamless operation across variable lead configurations without model retraining. This flexibility allows deployment from single-lead ambulatory monitors to comprehensive 12-lead clinical systems using identical network weights. Gradient-based saliency analysis confirms the model’s attention to physiologically relevant features, particularly P-wave morphology and lead II characteristics, thereby enhancing clinical interpretability and trustworthiness. Our findings also establish that a single, well-curated small training dataset can yield a compact yet highly generalizable AFib detection system suitable for deployment across diverse clinical settings, from critical care monitoring to ambulatory screening applications. The combination of robust cross-dataset performance, computational efficiency, and clinical interpretability positions this approach as a viable solution for largescale AFib diagnosis and monitoring programs.

8 October 2026 in Bioengineering
Verified
Journal Article
Open access
PDF file
HMHarshit Mishra
Harshit Mishra
FMFarhan Adam Mukadam
Farhan Adam Mukadam
NMNachiket Dilip Makwana
Nachiket Dilip Makwana
PTPradyot Tiwari
Pradyot Tiwari
SKSubramani Kandasamy
Subramani Kandasamy
KHK.V.S. Hari
K.V.S. Hari
Atrial fibrillation (AFib) is the most prevalent sustained cardiac arrhythmia, yet most deep learning detectors are validated on a single cohort and few report uncertainty. We developed a compact 14M-parameter convolutional neural network for binary AFib classification from 10 s, 12-lead ECG at 500 Hz, trained exclusively on the HDXML dataset (67,432 ECGs; 9628 AFib) with on-the-fly augmentation for noise, drift and missing channels. Using one unchanged checkpoint, we evaluated six independently sourced public cohorts totaling over 1.25 million recordings, including MIMIC-IV critical care and two ambulatory Holter cohorts. All metrics are reported with 95% confidence intervals from a cluster bootstrap at the patient, recording or subject levels. ROC–AUC exceeded 0.95 in every cohort, from 0.960 (95% CI 0.956–0.963) on CODE-15 to 0.999 (0.998–0.999) on SPH, including 0.966 (0.965–0.967) on MIMIC-IV with 75.3% sensitivity and 97.7% specificity, 0.963 (0.929–0.987) on CPSC 2021 and 0.995 (0.988–0.999) on MIT-BIH. Performance was stable under progressive lead masking without retraining, and median inference took 110 ms per segment on a server-class CPU without a GPU. A compact network trained on one curated source can therefore generalize across hospitals, countries and recording hardware. This study is retrospective; prospective validation is required before clinical use.