Transforming Pediatric Healthcare with Generative AI: A Hybrid CNN Approach for Pneumonia Detection DOI Open Access
Sotir Sotirov, Daniela Orozova,

Boris Angelov

и другие.

Electronics, Год журнала: 2025, Номер 14(9), С. 1878 - 1878

Опубликована: Май 5, 2025

Pneumonia is one of the leading causes morbidity and mortality in children, making its early detection critical for effective treatment. The objective this study to develop evaluate a hybrid deep learning framework that combines convolutional neural networks with intuitionistic fuzzy estimators enhance accuracy, sensitivity, robustness pneumonia pediatric chest X-rays. main background use (IFEs). model integrates powerful feature extraction capabilities CNNs uncertainty handling decision-making strengths logic. By incorporating an IFE, better equipped deal ambiguity noise medical imaging data, resulting more accurate robust detection. Experimental results on X-ray datasets demonstrate effectiveness proposed method, achieving higher sensitivity specificity compared traditional CNN approaches. system achieved classification accuracy 94.93%, confirming strong diagnostic performance. In conclusion, offers promising tool assist healthcare professionals diagnosis children.

Язык: Английский

Transforming Pediatric Healthcare with Generative AI: A Hybrid CNN Approach for Pneumonia Detection DOI Open Access
Sotir Sotirov, Daniela Orozova,

Boris Angelov

и другие.

Electronics, Год журнала: 2025, Номер 14(9), С. 1878 - 1878

Опубликована: Май 5, 2025

Pneumonia is one of the leading causes morbidity and mortality in children, making its early detection critical for effective treatment. The objective this study to develop evaluate a hybrid deep learning framework that combines convolutional neural networks with intuitionistic fuzzy estimators enhance accuracy, sensitivity, robustness pneumonia pediatric chest X-rays. main background use (IFEs). model integrates powerful feature extraction capabilities CNNs uncertainty handling decision-making strengths logic. By incorporating an IFE, better equipped deal ambiguity noise medical imaging data, resulting more accurate robust detection. Experimental results on X-ray datasets demonstrate effectiveness proposed method, achieving higher sensitivity specificity compared traditional CNN approaches. system achieved classification accuracy 94.93%, confirming strong diagnostic performance. In conclusion, offers promising tool assist healthcare professionals diagnosis children.

Язык: Английский

Процитировано

0