Systematic Literature Review: Deep Learning Pada Citra Sinar-X Paru Untuk Klasifikasi Penyakit DOI Creative Commons

Calvin Rinaldy Leonard,

Ingrid Nurtanio, Anugrayani Bustamin

et al.

Techno Com, Journal Year: 2024, Volume and Issue: 23(3), P. 512 - 531

Published: Aug. 23, 2024

Paru-paru merupakan organ vital dalam tubuh manusia. mengangkut oksigen ke dan mengeluarkan karbondioksida keluar dari tubuh. Proses pertukaran karbon dioksida ini membuat paru-paru rentan terjangkit oleh virus, bakteri jamur. dapat berbagai jenis penyakit seperti pneumonia, tuberkulosis, kanker, ataupun covid-19. Dalam proses diagnosa tersebut, seringkali terjadi perbedaan antar dokter. Melalui tantangan diperlukan sistem pembelajaran mesin yang menjadi pihak ketiga untuk melakukan klasifikasi kondisi. Salah satu metode modern digunakan yaitu Metode deep learning. Convolutional Neural Network adalah salah banyaknya learning CNN telah terbukti menghasilkan akurasi tinggi memproses gambar. Banyaknya penelitian menggunakan mengolah citra sinar-X paru dorongan mencari gap dengan SLR (Systematic Literature Review). Diagram PRISMA juga memilih mendokumentasikan 93 paper relevan hingga 22 sesuai lingkup subjek CNN. Hasil diperoleh informasi terkait dataset digunakan, hanya 1 data primer, sisanya sekunder. Selain itu, transfer pilihan terpopuler mengembangkan paru. Kata kunci: Deep Learning, Paru-paru, Sinar-X, SLR,

XSE-TomatoNet: An Explainable AI based Tomato Leaf Disease Classification Method Using EfficientNetB0 with Squeeze-and-Excitation Blocks and Multi-Scale Feature Fusion DOI Creative Commons
Md Assaduzzaman, Prayma Bishshash, Md. Asraful Sharker Nirob

et al.

MethodsX, Journal Year: 2025, Volume and Issue: unknown, P. 103159 - 103159

Published: Jan. 1, 2025

Language: Английский

Citations

1
Quality prediction of seabream (SPARUS AURATA) by DEEP learning algorithms and explainable artificial intelligence DOI
İsmail Yüksel GENÇ, Remzi Gürfidan, Tuncay Yi̇ği̇t

et al.

Food Chemistry, Journal Year: 2025, Volume and Issue: 474, P. 143150 - 143150

Published: Jan. 31, 2025

Language: Английский

Citations

1
Multi-axis transformer based U-Net with class balanced ensemble model for lung disease classification using X-ray images DOI Creative Commons
Suresh Maruthai, Tamilvizhi Thanarajan,

T. Ramesh

et al.

Journal of X-Ray Science and Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 26, 2025

Background: Chest X-rays are an essential diagnostic tool for identifying chest disorders because of its high sensitivity in detecting pathological anomalies the lungs. Classification models based on conventional Convolutional Neural Networks (CNNs) adversely affected due to their localization bias. Objective: In this paper, a new Multi-Axis Transformer U-Net with Class Balanced Ensemble (MaxTU-CBE) is proposed improve multi-label classification performance. Methods: This may be first attempt simultaneously integrate benefits hierarchical into encoder and decoder traditional U-shaped structure improving semantic segmentation superiority lung image. Results: A key element MaxTU-CBE Contextual Fusion Engine (CFE), which uses self-attention mechanism efficiently create global interdependence between features various scales. Also, deep CNN incorporate ensemble learning address issue class unbalanced learning. Conclusions: According experimental findings, our suggested outperforms competing BiDLSTM classifier by 1.42% CBIR-CSNN techniques 5.2%

Language: Английский

Citations

0
A multi-stage deep learning approach for comprehensive lung disease classification from x-ray images DOI Creative Commons
G. Divya Deepak, Subraya Krishna Bhat

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127220 - 127220

Published: March 1, 2025

Language: Английский

Citations

0
Exploring Attributions in Convolutional Neural Networks for Cow Identification DOI Creative Commons

Dimitar Tanchev,

Alexander Marazov, Gergana Balieva

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 3622 - 3622

Published: March 26, 2025

Face recognition and identification is a method that well established in traffic monitoring, security, human biodata analysis, etc. Regarding the current development implementation of digitalization all spheres public life, new approaches are being sought to use opportunities high technology advancements animal husbandry enhance sector’s sustainability. Using machine learning present study aims investigate possibilities for creation model visual face farm animals (cows) could be used future applications manage health, welfare, productivity at herd individual levels real-time. This provides preliminary results from an ongoing research project, which employs attribution methods identify parts facial image contribute most cow using triplet loss network. A dataset identifying cows environments was therefore created by taking digital images holdings with intensive breeding systems. After normalizing images, they were subsequently segmented into background regions. Several then explored analyzing attributions examine whether or regions have greater influence on network’s performance animal.

Language: Английский

Citations

0
Enhancing Alzheimer’s Disease Detection: An Explainable Machine Learning Approach with Ensemble Techniques DOI Creative Commons
Eram Mahamud, Md Assaduzzaman,

Jahirul Islam

et al.

Intelligence-Based Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 100240 - 100240

Published: April 1, 2025

Language: Английский

Citations

0
An Efficient Explainability of Deep Models on Medical Images DOI Creative Commons
Salim Khiat, Sidi Ahmed Mahmoudi, Sédrick Stassin

et al.

Algorithms, Journal Year: 2025, Volume and Issue: 18(4), P. 210 - 210

Published: April 9, 2025

Nowadays, Artificial Intelligence (AI) has revolutionized many fields and the medical field is no exception. Thanks to technological advancements emergence of Deep Learning (DL) techniques AI brought new possibilities significant improvements practice. Despite excellent results DL models in terms accuracy performance, they remain black boxes as do not provide meaningful insights into their internal functioning. This where Explainable (XAI) comes in, aiming underlying workings these box models. In this present paper visual explainability deep on chest radiography images are addressed. research uses two datasets, first COVID-19, viral pneumonia, normality (healthy patients) second pulmonary opacities. Initially pretrained CNN (VGG16, VGG19, ResNet50, MobileNetV2, Mixnet EfficientNetB7) used classify images. Then, methods (GradCAM, LIME, Vanilla Gradient, Gradient Integrated SmoothGrad) performed understand explain decisions made by The obtained show that MobileNetV2 VGG16 best for respectively. As methods, were subjected doctors validated calculating mean opinion score. deemed GradCAM, LIME most effective providing understandable accurate explanations.

Language: Английский

Citations

0
An explainable AI-based blood cell classification using optimized convolutional neural network DOI Creative Commons

Oahidul Islam,

Md Assaduzzaman, Md. Zahid Hasan

et al.

Journal of Pathology Informatics, Journal Year: 2024, Volume and Issue: 15, P. 100389 - 100389

Published: July 3, 2024

White blood cells (WBCs) are a vital component of the immune system. The efficient and precise classification WBCs is crucial for medical professionals to diagnose diseases accurately. This study presents an enhanced convolutional neural network (CNN) detecting with help various image pre-processing techniques. Various techniques, such as padding, thresholding, erosion, dilation, masking, utilized minimize noise improve feature enhancement. Additionally, performance further by experimenting architectural structures hyperparameters optimize proposed model. A comparative evaluation conducted compare model three transfer learning models, including Inception V3, MobileNetV2, DenseNet201.The results indicate that outperforms existing achieving testing accuracy 99.12%, precision 99%, F1-score 99%. In addition, We SHAP (Shapley Additive explanations) LIME (Local Interpretable Model-agnostic Explanations) techniques in our interpretability model, providing valuable insights into how makes decisions. Furthermore, has been explained using Grad-CAM Grad-CAM++ which class-discriminative localization approach, trust transparency. performed slightly better than identifying predicted area's location. Finally, most integrated end-to-end (E2E) system, accessible through both web Android platforms classify cell.

Language: Английский

Citations

3
Systematic Literature Review: Deep Learning Pada Citra Sinar-X Paru Untuk Klasifikasi Penyakit DOI Creative Commons

Calvin Rinaldy Leonard,

Ingrid Nurtanio, Anugrayani Bustamin

et al.

Techno Com, Journal Year: 2024, Volume and Issue: 23(3), P. 512 - 531

Published: Aug. 23, 2024

Paru-paru merupakan organ vital dalam tubuh manusia. mengangkut oksigen ke dan mengeluarkan karbondioksida keluar dari tubuh. Proses pertukaran karbon dioksida ini membuat paru-paru rentan terjangkit oleh virus, bakteri jamur. dapat berbagai jenis penyakit seperti pneumonia, tuberkulosis, kanker, ataupun covid-19. Dalam proses diagnosa tersebut, seringkali terjadi perbedaan antar dokter. Melalui tantangan diperlukan sistem pembelajaran mesin yang menjadi pihak ketiga untuk melakukan klasifikasi kondisi. Salah satu metode modern digunakan yaitu Metode deep learning. Convolutional Neural Network adalah salah banyaknya learning CNN telah terbukti menghasilkan akurasi tinggi memproses gambar. Banyaknya penelitian menggunakan mengolah citra sinar-X paru dorongan mencari gap dengan SLR (Systematic Literature Review). Diagram PRISMA juga memilih mendokumentasikan 93 paper relevan hingga 22 sesuai lingkup subjek CNN. Hasil diperoleh informasi terkait dataset digunakan, hanya 1 data primer, sisanya sekunder. Selain itu, transfer pilihan terpopuler mengembangkan paru. Kata kunci: Deep Learning, Paru-paru, Sinar-X, SLR,

Citations

0