Point-of-care thermal imaging tool assisting in the development of imaging biomarker as pre-diagnostics of graves' disease
Goswami, M.; Dhingra, V. K.; Kumar, A.; Sharma, V.
Show abstract
This article presents the development of a tool to address the scarcity of clinically validated datasets for Thyroid related abnormalities. Infrared thermography Images are taken from each of the sixty persons of different age groups and gender. Scintigraphy and standard thyroid blood test results are used to categorize these persons into thirty-three females and thirteen males suffering from graves disease. Eleven females and three males are found to be in healthy conditions and used as control. An Artificial Intelligence algorithm is used to automatically segment and extract the histogram-associated information within the thyroid and cheek region from the collected images. A very simple and novel imaging biomarker is found to be moderately correlated w.r.t age and gender. A smartphone app integrated with a dedicated smartphone-based compact IR camera add-on is developed and deployed in a clinical environment to enrich the analysis. This point-of-care tool is expected to categorize healthy cases from patients automatically. It is to reduce the ethical burden on clinicians shoulders before recommending radioactive contamination-prone Scintigraphy and/or expensive and relatively slower thyroid blood tests. If adopted, such preliminary tests will save costs on patients end and burden at pathology labs, especially in densely populated countries such as India.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Artificial intelligence tool for the study of COVID-19 microdroplet spread across the human diameter and airborne space 96%
- A Stomata Classification and Detection System in Microscope Images of Maize Cultivars 96%
- Fibre tracing in biomedical images: An objective comparison between seven algorithms 96%
Similar papers in this journal
- A computational study on the role of parameters for identification of thyroid nodules by infrared images (and its comparison with real data) 95%
- High-Throughput and Accurate 3D Scanning of Cattle Using Time-of-Flight Sensors and Deep Learning 94%
- Classification and Visualisation of Normal and Abnormal Radiographs; a comparison between Eleven Convolutional Neural Network Architectures 94%
Similar papers in this journal
- Model uncertainty estimates for deep learning mammographic density prediction using ordinal and classification approaches 90%
- SimBSI: An open-source Simulink library for developingclosed-loop brain signal interfaces in animals and humans 90%
- A low-cost protocol for reconditioning of deep-brain neural microelectrodes with material failure for electrophysiology recording 89%
Similar papers in this journal
- An Inexpensive Smartphone-Based Device and Predictive Models for Rapid, Non-Invasive, and Point-of-Care Monitoring of Ocular and Cardiovascular Complications Related to Diabetes 95%
- DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation 94%
- TrajectoryViz: Interactive visualization of treatment trajectories 90%
Similar papers in this journal
- Estimation of Three-Dimensional Chromatin Morphology for Nuclear Classification and Characterisation 96%
- Collection of 2429 constrained headshots of 277 volunteers for deep learning 93%
- Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and Texture Descriptors 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.