MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202541115014 A) filed by Nandha Engineering College, Erode, Tamil Nadu, on Nov. 21, 2025, for 'echohealth ai:detecting organ health from ultrasound sound signatures.'
Inventor(s) include E Padma; S Anand; N. M. Kowseeswarsena; and M. Loga Varshinl.
The application for the patent was published on Jan. 23, under issue no. 04/2026.
According to the abstract released by the Intellectual Property India: "Presents an artificial intelligence-based system for detecting organ health conditions using ultrasound sound signatures instead of traditional ultrasound images. The system records sound data from Doppler and spectral ultrasound scans, cleans and segments the audio, and converts it into Mel-spectrograms and MTCC features. These features are analyzed using a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) layers to classify organs such as the heart, liver, and kidney as normal or abnormal. To ensure transparency, Explainable Al (XAI) methods like Grad-CAM and SHAP are used to highlight important sound regions influencing the diagnosis. The system achieved an accuracy of over 90% and operates efficiently on standard computing or portable ultrasound devices. EchoHealth Al offers a non-invasive, low-cost, and real-time diagnostic soution, particularly beneficial for hospitals, clinics, and rural healthcare centers."
Disclaimer: Curated by HT Syndication.
