Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(3), P. e0296352 - e0296352

Published: March 12, 2024

Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by overlapping symptoms (such fever, cough, sore throat, etc.). Additionally, researchers make use X-rays (CXR), cough sounds, computed tomography (CT) scans diagnose disorders. The present study aims classify nine different disorders, including LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for classifications extracting features from images. Furthermore, proposed CNN employed several new approaches max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), multiple-way data generation (MWDG). scalogram method is utilized transform sounds coughing into visual representation. Before beginning model has been developed, SMOTE approach used calibrate CXR CT well sound images (CSI) CXR, scan, CSI training evaluating come 24 publicly available benchmark illness datasets. classification performance compared with seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, Inception-V3, in addition state-of-the-art (SOTA) classifiers. effectiveness further demonstrated results ablation experiments. was successful achieving an accuracy 99.01%, making it superior both SOTA As result, capable offering significant support radiologists other professionals.

Language: Английский

---

Bridging efficiency and interpretability: Explainable AI for multi-classification of pulmonary diseases utilizing modified lightweight CNNs

Image and Vision Computing, Journal Year: 2025, Volume and Issue: unknown, P. 105553 - 105553

Published: April 1, 2025

Language: Английский

---

RANCANG BANGUN ALAT UKUR KADAR GULA DALAM DARAH NON INVASIVE MENGGUNAKAN ESP32 DAN BLYNK

Rabit Jurnal Teknologi dan Sistem Informasi Univrab, Journal Year: 2024, Volume and Issue: 9(2), P. 361 - 371

Published: July 12, 2024

Kompabilitas microcontroller ESP32 dalam implementasi Internet of Thing (IoT) hampir mencakup segala bidang. Memiliki potensi memonitoring kadar gula darah secara non-invasive dengan adanya Sensor Photodioda dan lampu LED Infared serta jari tangan sebagai objek pengukuran tanpa perlu melukai pasien atau invasive Tujuan untuk meningkatkan pelayanan kesehatan Masyarakat terutama Upaya mencegah diabetes melitus. juga memiliki kompabilitas pemanfaatan Blynk yang mana dapat digunakan menjadi media memonitor ditampilkan di monitor computer maupun smarphone membuka private Blynk, intensitas Cahaya menggunakan fotodioda bahan utama Rancang bangun Alat Ukur Kadar Gula Dalam Darah Non Invasive Menggunakan Metode Prototyping memanfaatkan dilakukan percobaan melihat kinerja perbandingan akan akurasi Glukometer pada umumnya penerapan bidang Kesehatan. prototype ukur dilakukan, Perhitungan serapan dihasilkan oleh kombinasi dari Lampu mengambil sampel pengguna langsung mudah diterapkan sistem blynk mempermudah proses pemantauan Komputer pengguna. Hasil Akurasi keseluruhan Non-invasive didapatkan total sebesar 95% beberapa dilakukan.

---

Comprehensive Lung Sounds Classification Using Advanced Pre-Processing Techniques: Application in Deep Learning Models for Abnormality Detection

Published: Jan. 1, 2024

Language: Английский

---

Pneumonia Image Classification Using DenseNet Architecture

Information, Journal Year: 2024, Volume and Issue: 15(10), P. 611 - 611

Published: Oct. 6, 2024

Pulmonary diseases, including pneumonia, represent a significant health challenge and are often diagnosed using X-rays. This study investigates the effectiveness of artificial intelligence (AI) in enhancing diagnostic capabilities X-ray imaging. Using Python PyTorch framework, we developed trained several deep learning models based on DenseNet architectures (DenseNet121, DenseNet169, DenseNet201) dataset comprising 5856 annotated images classified into two categories: Normal (Healthy) Pneumonia. Each model was evaluated its ability to classify with metrics binary accuracy, sensitivity, specificity. The results demonstrated accuracy rates 92% for 97% also showed improvements reduced time disease detection compared traditional methods. underscores potential integrating convolutional neural networks (CNNs) medical imaging enhance precision support clinical decision-making management pulmonary diseases. Further research is encouraged refine these explore their application other domains.

Language: Английский

---

A scoping review of deep learning approaches for lung cancer detection using chest radiographs and computed tomography scans

Biomedical Engineering Advances, Journal Year: 2024, Volume and Issue: 9, P. 100138 - 100138

Published: Dec. 6, 2024

Language: Английский

---

Leveraging DenseNet Features for Machine Learning Based Lung Disease Diagnosis From X-Rays

Published: Nov. 14, 2024

Language: Английский

---