Journal: Diagnostics

Article Title: Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

doi: 10.3390/diagnostics14060629

Figure Lengend Snippet: The performance of transfer learning on the Kaggle dataset.

Article Snippet: Xception attained a peak accuracy of 95%, and ResNet50V2 achieved an impressive 96%, demonstrating the effectiveness of transfer learning on the Kaggle ASD and TYUIA datasets.

Techniques:

Journal: Diagnostics

Article Title: Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

doi: 10.3390/diagnostics14060629

Figure Lengend Snippet: The performance of transfer learning on the TYUIA dataset.

Article Snippet: Xception attained a peak accuracy of 95%, and ResNet50V2 achieved an impressive 96%, demonstrating the effectiveness of transfer learning on the Kaggle ASD and TYUIA datasets.

Techniques:

Journal: Diagnostics

Article Title: Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

doi: 10.3390/diagnostics14060629

Figure Lengend Snippet: Graphical representations of training and validation accuracies of ( a ) ResNet50V2, ( b ) MobileNetV2, and ( c ) Xception model and training and validation losses of ( d ) ResNet50V2, ( e ) MobileNetV2, and ( f ) Xception model for face alignment.

Article Snippet: Xception attained a peak accuracy of 95%, and ResNet50V2 achieved an impressive 96%, demonstrating the effectiveness of transfer learning on the Kaggle ASD and TYUIA datasets.

Techniques: Biomarker Discovery

Journal: Diagnostics

Article Title: Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

doi: 10.3390/diagnostics14060629

Figure Lengend Snippet: The performance of transfer learning on the TYUIA dataset.

Article Snippet: Xception attained a peak accuracy of 95%, and ResNet50V2 achieved an impressive 96%, demonstrating the effectiveness of transfer learning on the Kaggle ASD and TYUIA datasets.

Techniques:

Journal: Diagnostics

Article Title: Innovative Strategies for Early Autism Diagnosis: Active Learning and Domain Adaptation Optimization

doi: 10.3390/diagnostics14060629

Figure Lengend Snippet: Grad-CAM representation of a random sample of T2 ( a ) misclassified using w 1 , ( b ) rightly predicted using w 2 , ( c ) rightly predicted using w 12 (active learning), ( d ) misclassified using w 1 , ( e ) misclassified using w 2 , and ( f ) predicted using w 12 (active learning) for the Xception model.

Article Snippet: Xception attained a peak accuracy of 95%, and ResNet50V2 achieved an impressive 96%, demonstrating the effectiveness of transfer learning on the Kaggle ASD and TYUIA datasets.

Techniques:

Journal: Scientific Reports

Article Title: Diabetic retinopathy detection via exudates and hemorrhages segmentation using iterative NICK thresholding, watershed, and Chi 2 feature ranking

doi: 10.1038/s41598-025-90048-6

Figure Lengend Snippet: A summary of DR prescreening techniques and reported performances.

Article Snippet: Bhuiyan et al. , The cloud-based screening model was developed. Neural network architectures and logistic model trees: Xception, Inception-V3, Inception-Resnet-V2 and Logistic model trees (LMT) were employed , 88,702 images from Kaggle dataset , Sensitivity , 99.21.

Techniques: Biomarker Discovery, Plasmid Preparation, Diagnostic Assay, Software, Extraction, Selection

Journal: Neural Computing & Applications

Article Title: VGGCOV19-NET: automatic detection of COVID-19 cases from X-ray images using modified VGG19 CNN architecture and YOLO algorithm

doi: 10.1007/s00521-022-06918-x

Figure Lengend Snippet: Comparison of the recommended VGGCOV19-NET COVID-19 diagnosis method with other CNN methods developed using radiology images

Article Snippet: Khan et al. [ ] classified three classes with a new Xception CNN architecture-based CNN model with an accuracy ratio of 95%, Ahammed et al. [ ] classified three classes with the deep CNN model they created with accuracy of 94%, Apostolopoulos and Mpesiana [ ] classified three classes with the pre-trained VGG19 architecture with accuracy of 93.48%, Aslan et al. [ ] classified three classes with the hybrid CNN architecture with accuracy of 98.70%, Hira et al. [ ] classified three classes with the specially ResNeXt-50 with accuracy of 97.55%, and Wang et al. [ ] classified three classes with the deep CNN model they called COVID-Net with an accuracy of 93.3%.

Techniques: Comparison, Biomarker Discovery, Modification, Imaging

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Flow of the Xception architecture, illustrating the depthwise separable convolutions that optimize computational efficiency while maintaining high accuracy .

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques:

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Performance assessment of transfer learning: Xception.

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques:

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Performance matrices for base model + transfer learning.

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques: Biomarker Discovery

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Performance assessment of fine-tuned transfer learning: Xception.

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques:

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Performance matrices for fine-tuned transfer learning model.

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques: Biomarker Discovery

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Comparison with other state-of-art model.

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques: Comparison

Journal: Life

Article Title: Brain Tumor Detection and Prediction in MRI Images Utilizing a Fine-Tuned Transfer Learning Model Integrated Within Deep Learning Frameworks

doi: 10.3390/life15030327

Figure Lengend Snippet: Prediction for tumor (1/0) using fine-tuned transfer learning: Xception.

Article Snippet: Proposed , Fine-Tuned Transfer Learning Xception , Kaggle , 0.9611.

Techniques:

Journal: Digital Health

Article Title: Enhancing diabetic retinopathy classification using deep learning

doi: 10.1177/20552076231203676

Figure Lengend Snippet: Evaluation of the system's efficiency against prior studies using the APTOS dataset.

Article Snippet: In addition, Liu et al. employed several TL models including EfficientNetB4, EfficientNetB5, NASNetLarge, Xception, and InceptionResNet-V2 to predict DR from the EyePACS dataset.

Techniques: Plasmid Preparation