Advancing Cardiac Detection in Chest X-ray Images Using Machine Learning: A Practical Application of AI in Medical Imaging

Objectives: In order to increase diagnostic precision and efficiency in clinical settings, the goal is to assess how well sophisticated convolutional neural networks (CNNs) perform automated cardiac area recognition from chest X-ray pictures. Methods: 496 high-resolution DICOM chest X-ray images (1024 x 1024) had been used as the dataset. Images were preprocessed, which included augmentation (e.g., scaling, rotation, contrast correction), normalization, and resizing. Metrics including Mean Squared Error (MSE) and Intersection over Union (IoU) were used to train and compare many CNN architectures (AlexNet, GoogLeNet, VGG-16, ResNet-18, and ResNet-50). The Adam optimizer was used in the training phase, with a batch size of 32 and 100 epochs. Validation was done on 96 images, and performance was measured with IoU scores and bounding box prediction accuracy. Results: ResNet-50 outperformed the other models, with 93.2% accuracy and a mean IoU of 0.84 with very little variability. In terms of localization accuracy and training stability, the model outperformed alternative designs and demonstrated strong bounding box prediction abilities. The reliability of ResNet-50 in pinpointing specific cardiac regions under various imaging conditions is demonstrated by these results. Conclusions: The study concludes by highlighting the revolutionary potential of deep learning in automating the detection of cardiac regions in chest X-rays. The best model turned out to be ResNet-50, which presented a big stride in incorporating AI-based solutions into diagnostic processes, especially in environments with limited resources. Combining detection and segmentation for improved diagnostic insights should be investigated in future studies.