Pollen Grain Classification Based on Ensemble Transfer Learning on the Cretan Pollen Dataset

Tsiknakis, Nikos; Savvidaki, Elisavet; Manikis, Georgios C.; Gotsiou, Panagiota; Remoundou, Ilektra; Marias, Kostas; Alissandrakis, Eleftherios; Vidakis, Nikolas

doi:10.3390/plants11070919

Cited by 9 publications

(3 citation statements)

References 19 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their results demonstrate an accuracy of approximately 97% for the diagnosis of the disease. Tsiknakis et al [ 21 ] used a similar ensemble to classify an image dataset with 20 categories. The authors used a voting ensemble strategy and a combination of InceptionV3, Xception, ResNet and Inception–ResNet to classify images to twenty categories, achieving an AUC close to 100%.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for the Differential Diagnosis between Transient Osteoporosis and Avascular Necrosis of the Hip

et al. 2022

Self Cite

View full text Add to dashboard Cite

Differential diagnosis between avascular necrosis (AVN) and transient osteoporosis of the hip (TOH) can be complicated even for experienced MSK radiologists. Our study attempted to use MR images in order to develop a deep learning methodology with the use of transfer learning and a convolutional neural network (CNN) ensemble, for the accurate differentiation between the two diseases. An augmented dataset of 210 hips with TOH and 210 hips with AVN was used to finetune three ImageNet-trained CNNs (VGG-16, InceptionResNetV2, and InceptionV3). An ensemble decision was reached in a hard-voting manner by selecting the outcome voted by at least two of the CNNs. Inception-ResNet-V2 achieved the highest AUC (97.62%) similar to the model ensemble, followed by InceptionV3 (AUC of 96.82%) and VGG-16 (AUC 96.03%). Precision for the diagnosis of AVN and recall for the detection of TOH were higher in the model ensemble compared to Inception-ResNet-V2. Ensemble performance was significantly higher than that of an MSK radiologist and a fellow (P < 0.001). Deep learning was highly successful in distinguishing TOH from AVN, with a potential to aid treatment decisions and lead to the avoidance of unnecessary surgery.

show abstract

Section: Discussionmentioning

confidence: 99%

“…A transfer learning strategy was utilized as previously published [ 20 , 21 ]. Briefly, three convolutional neural network (CNN) architectures were utilized—InceptionV3, VGG-16, and Inception-ResNetV2—and their initial weights were acquired using transfer learning from the ImageNet dataset [ 22 ].…”

Section: Methodsmentioning

confidence: 99%

Deep Learning for the Differential Diagnosis between Transient Osteoporosis and Avascular Necrosis of the Hip

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…To boost the segmentation performance, three distinct ensembling strategies were used, namely 5-fold cross-validation, test time augmentation (TTA), and result fusion from the two exploited models. All these techniques have shown promising results for medical image classification and segmentation tasks in former studies [13,[16][17][18]. Instead of using the entire training set to train a single model, it was divided randomly into five subsets.…”

Section: First Placementioning

confidence: 99%

FUSeg: The Foot Ulcer Segmentation Challenge

Wang,

Mahbod,

Ellinger

et al. 2024

Information

View full text Add to dashboard Cite

Wound care professionals provide proper diagnosis and treatment with heavy reliance on images and image documentation. Segmentation of wound boundaries in images is a key component of the care and diagnosis protocol since it is important to estimate the area of the wound and provide quantitative measurement for the treatment. Unfortunately, this process is very time-consuming and requires a high level of expertise, hence the need for automatic wound measurement methods. Recently, automatic wound segmentation methods based on deep learning have shown promising performance; yet, they heavily rely on large training datasets. A few wound image datasets were published including the Diabetic Foot Ulcer Challenge dataset, the Medetec wound dataset, and WoundDB. Existing public wound image datasets suffer from small size and a lack of annotation. There is a need to build a fully annotated dataset to benchmark wound segmentation methods. To address these issues, we propose the Foot Ulcer Segmentation Challenge (FUSeg), organized in conjunction with the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). It contains 1210 pixel-wise annotated foot ulcer images collected over 2 years from 889 patients. The submitted algorithms are reviewed in this paper and the dataset can be accessed through the Foot Ulcer Segmentation Challenge website.

show abstract