A Review of Computer-Aided Expert Systems for Breast Cancer Diagnosis

Liew, Xin Yu; Hameed, Nazia; Clos, Jérémie

doi:10.3390/cancers13112764

Cited by 24 publications

(11 citation statements)

References 143 publications

(222 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For maximum accuracy, a mix of geometric, intensity, geometry, and texture information retrieved from curvelet coefficients is used [93,94].…”

Section: Number Ofmentioning

confidence: 99%

Multidirectional Analysis of Curvelet Against Skin Cancer

Kolekar,

Razak

et al. 2024

Preprint

View full text Add to dashboard Cite

An elevated chance of getting another melanoma is associated with a personal history of the disease. Individuals who have already had a melanoma have a 2–5% probability of getting another one later. Compared to individuals whose initial melanoma was superficial spreading melanoma, those whose first melanoma was lentigo maligns melanoma or nodular melanoma are at a greater peril of emerging a secondary dominant cancer. Melanoma risk is double in those with a special antiquity of squamous cell carcinoma. The likelihood of getting melanoma is doubled if you have a particular times past of basal cell carcinoma. In addition, melanoma risk is higher in persons with actinic keratosis than in those without the condition. An automated technique for classifying melanoma, or skin cancer, is proposed in this work. An image of gathered data is used as the input for the proposed system, and various image handling methods remain smeared to improve the picture's characteristics. The curvelet technique is used to separate benign from malignant skin cancer and to collect relevant data from these pictures so that the classifier may be trained and tested. The basic wrapper curvelet's coefficients are the characteristics that are utilized for classification. Curvelet works well with images that have cartoon edges and aligned textures. In a database of digital photos, the three-layer back-propagation neural network classifier with curvelet has 75.6% recognition accuracy.

show abstract

“…For maximum accuracy, a mix of geometric, intensity, geometry, and texture information retrieved from curvelet coefficients is used [93,94].…”

Section: Number Ofmentioning

confidence: 99%

Multidirectional Analysis of Curvelet Against Skin Cancer

Kolekar,

Razak

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…where net pj = ∑ k w ji o pi + θ j is the total input to node j including a bias term θ j and the parameter η is the learning rate. Finally, additional momentum is added to the learning equation, resulting in (13).…”

Section: Classificationmentioning

confidence: 99%

“…The structure and characteristics of breast abnormalities make the detection of abnormalities challenging. Consequently, CAD systems were developed to identify breast malignancies and assist medical professionals in the efficient interpretation of medical images with increased accuracy and speed [13,14]. The role of CAD systems is to solve the challenge of interpreting mammogram images for the effective diagnosis of cancer [15,16].…”

Section: Introductionmentioning

confidence: 99%

Breast Cancer Detection Using Mammogram Images with Improved Multi-Fractal Dimension Approach and Feature Fusion

Zebari

Ibrahim²,

Zeebaree

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Breast cancer detection using mammogram images at an early stage is an important step in disease diagnostics. We propose a new method for the classification of benign or malignant breast cancer from mammogram images. Hybrid thresholding and the machine learning method are used to derive the region of interest (ROI). The derived ROI is then separated into five different blocks. The wavelet transform is applied to suppress noise from each produced block based on BayesShrink soft thresholding by capturing high and low frequencies within different sub-bands. An improved fractal dimension (FD) approach, called multi-FD (M-FD), is proposed to extract multiple features from each denoised block. The number of features extracted is then reduced by a genetic algorithm. Five classifiers are trained and used with the artificial neural network (ANN) to classify the extracted features from each block. Lastly, the fusion process is performed on the results of five blocks to obtain the final decision. The proposed approach is tested and evaluated on four benchmark mammogram image datasets (MIAS, DDSM, INbreast, and BCDR). We present the results of single- and double-dataset evaluations. Only one dataset is used for training and testing in the single-dataset evaluation, whereas two datasets (one for training, and one for testing) are used in the double-dataset evaluation. The experiment results show that the proposed method yields better results on the INbreast dataset in the single-dataset evaluation, whilst better results are obtained on the remaining datasets in the double-dataset evaluation. The proposed approach outperforms other state-of-the-art models on the Mini-MIAS dataset.

show abstract

“…In recent years, radiomics has developed rapidly with the extraction of quantitative metrics-the so-called radiomic features-within medical images to capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving (2). For example, using machine learning (ML) techniques, the information from pathology images can be extracted by automatically extracting quantitative pathological features for high-throughput judgment (3)(4)(5)(6), which has the potential to increase the accuracy, consistency, and reliability of prostate cancer diagnosis using histopathology. There are two types of features in the field of ML: hand-crafted features based on traditional ML and learned features based on deep learning (DL) (7)(8)(9).…”

Section: Introductionmentioning

confidence: 99%

Fusing hand-crafted and deep-learning features in a convolutional neural network model to identify prostate cancer in pathology images

Huang

Zhang

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

Prostate cancer can be diagnosed by prostate biopsy using transectal ultrasound guidance. The high number of pathology images from biopsy tissues is a burden on pathologists, and analysis is subjective and susceptible to inter-rater variability. The use of machine learning techniques could make prostate histopathology diagnostics more precise, consistent, and efficient overall. This paper presents a new classification fusion network model that was created by fusing eight advanced image features: seven hand-crafted features and one deep-learning feature. These features are the scale-invariant feature transform (SIFT), speeded up robust feature (SURF), oriented features from accelerated segment test (FAST) and rotated binary robust independent elementary features (BRIEF) (ORB) of local features, shape and texture features of the cell nuclei, the histogram of oriented gradients (HOG) feature of the cavities, a color feature, and a convolution deep-learning feature. Matching, integrated, and fusion networks are the three essential components of the proposed deep-learning network. The integrated network consists of both a backbone and an additional network. When classifying 1100 prostate pathology images using this fusion network with different backbones (ResNet-18/50, VGG-11/16, and DenseNet-121/201), we discovered that the proposed model with the ResNet-18 backbone achieved the best performance in terms of the accuracy (95.54%), specificity (93.64%), and sensitivity (97.27%) as well as the area under the receiver operating characteristic curve (98.34%). However, each of the assessment criteria for these separate features had a value lower than 90%, which demonstrates that the suggested model combines differently derived characteristics in an effective manner. Moreover, a Grad-CAM++ heatmap was used to observe the differences between the proposed model and ResNet-18 in terms of the regions of interest. This map showed that the proposed model was better at focusing on cancerous cells than ResNet-18. Hence, the proposed classification fusion network, which combines hand-crafted features and a deep-learning feature, is useful for computer-aided diagnoses based on pathology images of prostate cancer. Because of the similarities in the feature engineering and deep learning for different types of pathology images, the proposed method could be used for other pathology images, such as those of breast, thyroid cancer.

show abstract

A Review of Computer-Aided Expert Systems for Breast Cancer Diagnosis

Cited by 24 publications

References 143 publications

Multidirectional Analysis of Curvelet Against Skin Cancer

Multidirectional Analysis of Curvelet Against Skin Cancer

Breast Cancer Detection Using Mammogram Images with Improved Multi-Fractal Dimension Approach and Feature Fusion

Fusing hand-crafted and deep-learning features in a convolutional neural network model to identify prostate cancer in pathology images

Contact Info

Product

Resources

About