Ensemble learning of deep learning and traditional machine learning approaches for skin lesion segmentation and classification

Khan, Adil H.; Iskandar, Dayang Nurfatimah Awang; Al‐Asad, Jawad F.; Mewada, Hiren; Sherazi, Muhammad Abid

doi:10.1002/cpe.6907

Cited by 9 publications

(2 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The challenging problem of skin lesion segmentation has also been solved by exploring ensemble approaches. Different ensemble-based approaches have been explored in the literature [ 15 ]. Deep learning and machine learning algorithms were used in an ensemble to classify skin lesions in this study.…”

Section: Literature Reviewmentioning

confidence: 99%

Skin Lesion Segmentation Using an Ensemble of Different Image Processing Methods

et al. 2023

View full text Add to dashboard Cite

In recent times, there has been a huge increase in the average number of cases of skin cancer per year, which sometimes become life threatening for humans. Early detection of various skin diseases through automated detection techniques plays a crucial role. However, the presence of numerous artefacts makes this task challenging. Dermoscopic images exhibit various variations, including hair artefacts, markers, and ill-defined boundaries. These artefacts make automatic analysis of skin lesion quite a difficult task. To address these issues, it is essential to have an accurate and efficient automated method which will delineate a skin lesion from the rest of the image. Unfortunately, due to the presence of several types of skin artefacts, there is no such thresholding method that can provide a sufficient segmentation result for every type of skin lesion. To overcome this limitation, an ensemble-based method is proposed that selects the optimal thresholding based on an objective function. A group of state-of-the-art different thresholding methods such as Otsu, Kapur, Harris hawk, and grey level are used. The proposed method obtained superior results (dice score = 0.89 with p-value ≤ 0.05) as compared to other state-of-the-art methods (Otsu = 0.79, Kapur = 0.80, Harris hawk = 0.60, grey level = 0.69, active contour model = 0.72). The experiments conducted in this study utilize the ISIC 2016 dataset, which is publicly available and specifically designed for skin-related research. Accurate segmentation will help in the early detection of many skin diseases.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Skin Lesion Segmentation Using an Ensemble of Different Image Processing Methods

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In some circumstances, deep learning approaches or conventional methods alone may not be superior to ensemble methods. For instance, a study [37], demonstrated that, for the segmentation of skin lesions, a combination of deep learning and conventional techniques produced superior results to either methodology used alone. Standard and deep learning methods will be used depending on the particular application.…”

Section: Implementing Lgbm For Segmentationmentioning

confidence: 99%

Light Gradient-Boosting Machine Edge Detection With Cropping Layer for Semantic Segmentation of Pancreas

Bakasa,

Viriri

2023

AAIML

View full text Add to dashboard Cite

Anatomical variations in shape and volume metrics make pancreas medical image processing one of the most difficult subjects. Image processing in pancreas Computed Tomography (CT) is required to detect the class of pancreas anomaly accurately, reducing the possibility of a fatal outcome. It is estimated that a misunderstanding of radiology images accounts for 40% to 54% of all negligence claims. Machine learning advancements have created opportunities to train algorithms to learn patterns in pancreas images and use that knowledge to predict the pancreatic ductal adenocarcinoma (PDAC) overall survival rate. This paper performs feature extraction on CT pancreas images using edge detection techniques. Non-Local Means (NLM) are applied to the images to remove noise and smoothen them to highlight the defect. The experiments achieved an Intersection over Union (AOU) of 0.79 and an accuracy of 0.96. The images are then passed through the cropping layer to remove unwanted sections. The new train set is obtained from aggregating features from the edge detection feature extraction techniques and was then pruned to only eight features using the Principal Component Analysis technique. The train set was loaded into Light Gradient-boosting Machine (LGBM) to train the model to segment all the images.

show abstract

Revolutionizing Colon Histopathology Glandular Segmentation Using an Ensemble Network With Watershed Algorithm

Roy,

Gupta,

Goswami

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Colorectal adenocarcinoma, the most prevalent form of colon cancer, originates in the glandular structures of the intestines, presenting histopathological abnormalities in affected tissues. Accurate gland segmentation is crucial for identifying these potentially fatal abnormalities. While recent methodologies have shown success in segmenting glands in benign tissues, their efficacy diminishes when applied to malignant tissue segmentation. This study aims to develop a robust learning algorithm using a convolutional neural network (CNN) to segment glandular structures in colon histology images. The methodology employs a CNN based on the U‐Net architecture, augmented by a weighted ensemble network that integrates DenseNet 169, Inception V3, and Efficientnet B3 as backbone models. Additionally, the segmented gland boundaries are refined using the watershed algorithm. Evaluation on the Warwick‐QU dataset demonstrates promising results for the ensemble model, by achieving an F1 score of 0.928 and 0.913, object dice coefficient of 0.923 and 0.911, and Hausdorff distances of 38.97 and 33.76 on test sets A and B, respectively. These results are compared with outcomes from the GlaS challenge (MICCAI 2015) and existing research findings. Furthermore, our model is validated with a publicly available dataset named LC25000, and visual inspection reveals promising results, further validating the efficacy of our approach. The proposed ensemble methodology underscores the advantages of amalgamating diverse models, highlighting the potential of ensemble techniques to enhance segmentation tasks beyond individual model capabilities.

show abstract

Ensemble learning of deep learning and traditional machine learning approaches for skin lesion segmentation and classification

Cited by 9 publications

References 55 publications

Skin Lesion Segmentation Using an Ensemble of Different Image Processing Methods

Skin Lesion Segmentation Using an Ensemble of Different Image Processing Methods

Light Gradient-Boosting Machine Edge Detection With Cropping Layer for Semantic Segmentation of Pancreas

Revolutionizing Colon Histopathology Glandular Segmentation Using an Ensemble Network With Watershed Algorithm

Contact Info

Product

Resources

About