Cancer Detection System Research Articles

Clinical-grade endometrial cancer detection system via whole-slide images using deep learning.

The accurate pathological diagnosis of endometrial cancer (EC) improves the curative effect and reduces the mortality rate. Deep learning has demonstrated expert-level performance in pathological diagnosis of a variety of organ systems using whole-slide images (WSIs). It is urgent to build the deep learning system for endometrial cancer detection using WSIs. The deep learning model was trained and validated using a dataset of 601 WSIs from PUPH. The model performance was tested on three independent datasets containing a total of 1,190 WSIs. For the retrospective test, we evaluated the model performance on 581 WSIs from PUPH. In the prospective study, 317 consecutive WSIs from PUPH were collected from April 2022 to May 2022. To further evaluate the generalizability of the model, 292 WSIs were gathered from PLAHG as part of the external test set. The predictions were thoroughly analyzed by expert pathologists. The model achieved an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.928, 0.924, and 0.801, respectively, on 1,190 WSIs in classifying EC and non-EC. On the retrospective dataset from PUPH/PLAGH, the model achieved an AUC, sensitivity, and specificity of 0.948/0.971, 0.928/0.947, and 0.80/0.938, respectively. On the prospective dataset, the AUC, sensitivity, and specificity were, in order, 0.933, 0.934, and 0.837. Falsely predicted results were analyzed to further improve the pathologists' confidence in the model. The deep learning model achieved a high degree of accuracy in identifying EC using WSIs. By pre-screening the suspicious EC regions, it would serve as an assisted diagnostic tool to improve working efficiency for pathologists.

Harnessing insect olfactory neural circuits for detecting and discriminating human cancers

There is overwhelming evidence that presence of cancer alters cellular metabolic processes, and these changes are manifested in emitted volatile organic compound (VOC) compositions of cancer cells. Here, we take a novel forward engineering approach by developing an insect olfactory neural circuit-based VOC sensor for cancer detection. We obtained oral cancer cell culture VOC-evoked extracellular neural responses from in vivo insect (locust) antennal lobe neurons. We employed biological neural computations of the antennal lobe circuitry for generating spatiotemporal neuronal response templates corresponding to each cell culture VOC mixture, and employed these neuronal templates to distinguish oral cancer cell lines (SAS, Ca9-22, and HSC-3) vs. a non-cancer cell line (HaCaT). Our results demonstrate that three different human oral cancers can be robustly distinguished from each other and from a non-cancer oral cell line. By using high-dimensional population neuronal response analysis and leave-one-trial-out methodology, our approach yielded high classification success for each cell line tested. Our analyses achieved 76–100% success in identifying cell lines by using the population neural response (n = 194) collected for the entire duration of the cell culture study. We also demonstrate this cancer detection technique can distinguish between different types of oral cancers and non-cancer at different time-matched points of growth. This brain-based cancer detection approach is fast as it can differentiate between VOC mixtures within 250 ms of stimulus onset. Our brain-based cancer detection system comprises a novel VOC sensing methodology that incorporates entire biological chemosensory arrays, biological signal transduction, and neuronal computations in a form of a forward-engineered technology for cancer VOC detection.

Breast cancer classification on thermograms using deep CNN and transformers

ABSTRACT Breast thermography is a screening approach for breast cancer detection by measuring the breast skin temperature. Breast cancer is the most common cancer among women and can affect either women or men. Its early diagnosis and treatment reduce deaths and increase survival chances. The use of deep learning algorithms and techniques has made it easier to detect breast cancer in its early stages, but some challenges remain. In this work, we propose a breast cancer detection system. In the first step, TransUNet, a vision-based Transformer, is used to segment the breast region and separate it from the rest of the body. In the second step, four different models such as EfficientNet-B7, ResNet-50, VGG-16 and DenseNet-201 are used to classify the dataset into three types: healthy, sick, and unknown. The best accuracy achieved is 97.26%, sensitivity of 97.26% and specificity of each class healthy, sick, unknown is 100%, 96.94% and 99.72% respectively with the ResNet-50 model.

An Intelligent Classification System for Cancer Detection Based on DNA Methylation Using ML and Semantic Knowledge in Healthcare.

To consistently assess a patient's internal and external wellness and diagnose chronic conditions like cancer, Alzheimer's disease, and cardiovascular disease, wearable sensing devices are being used. Wearable technologies and networking websites have become incredibly common in the medical sector in recent times. The condition of a patient's health can be influenced by a number of factors, including psychological response, emotional stability, and anxiety levels, which can be evaluated using social network analysis based on graph theory-based techniques and these ideas, known as "social network analysis" (SNA) are used to study relationship phenomena. Therefore, numerous uses for SNA in health research are possible, ranging from social science to exact science. For example, it can be used to research cooperative networks of healthcare providers and hazard-prone behaviors, infectious disease transmission, and the spread of initiatives for health promotion and prevention. Recently, a number of machine learning-based healthcare solutions have been proposed to track chronic illnesses utilizing data from social networks and wearable monitoring devices. In our suggested approach, we are using an intelligent system with the assistance of wearable sensors for the classification of cancer based on DNA methylation, an important epigenetic process in the human genome that controls gene expression and has been connected to a number of health issues. A mixed-sampling imbalanced data ensemble classification technique is created with the help of biomedical sensors to address the problem of class imbalance and high dimensionality in the Cancer Genome Atlas (TCGA) massive data. This technique is based on the Intelligent Synthetic Minority Oversampling (SMOTE) algorithm. The false-negative rate significantly rises as a result of this, to give a larger data set, a new minority class sample will be first obtained. The noise created during the sample expansion process is actually any data that has been acquired, preserved, or altered in a way that prevents the system that initially conceived it from accessing or utilizing it. Noisy data boosts the amount of space needed excessively and can also drastically influence the findings of any data collection investigation and therefore can also affect the sample sets of one or the other class, resulting in the class imbalance which acts as a common problem in ML datasets. The Tomek Link method is then used to eliminate this noise, producing a reasonably balanced data set. Each layer selects two random forest structures using the cascading forest structure of the deep forest (GC-Forest) algorithm to increase the generalization ability of the model and create the final classification model. Experiments using DNA methylation data collected by employing biosensors from six tumor patients reveal that the mixed-sampling unbalanced data ensemble classification technique may increase the sensitivity to the minority class while maintaining the majority class's classification accuracy.

A Review on Thermal Imaging-Based Breast Cancer Detection Using Deep Learning

Breast cancer is the most common form of cancer in women. Its aggressive nature has made it one of the chief factors of high female mortality. Therefore, this has motivated research to achieve early diagnosis since it is the best strategy for patient survival. Currently, mammography is the gold standard for detecting breast cancer. However, it is expensive, unsuitable for dense breasts, and an invasive process that exposes the patient to radiation. Infrared thermography is gaining popularity as a screening modality for the early detection of breast cancer. It is a noninvasive and cost-effective modality that allows health practitioners to observe the temperature profile of the breast region for signs of cancerous tumors. Deep learning has emerged as a powerful computational tool for the early detection of breast cancer in radiology. As such, this study presents a review that shows existing work on deep learning-based Computer-aided Diagnosis (CADx) systems for breast cancer detection. In the same context, it reflects on classification utilizing breast thermograms. It first provides an overview of infrared thermography, details on available breast thermogram datasets, and then segmentation techniques applied to these thermograms. We also provide a brief overview of deep neural networks. Finally, it reviews works adopting Deep Neural Networks (DNNs) for breast thermogram classification.

Non-small cell lung cancer diagnosis aid with histopathological images using Explainable Deep Learning techniques

BackgroundLung cancer has the highest mortality rate in the world, twice as high as the second highest. On the other hand, pathologists are overworked and this is detrimental to the time spent on each patient, diagnostic turnaround time, and their success rate. ObjectiveIn this work, we design, implement, and evaluate a diagnostic aid system for non-small cell lung cancer detection, using Deep Learning techniques. MethodsThe classifier developed is based on Artificial Intelligence techniques, obtaining an automatic classification result between healthy, adenocarcinoma and squamous cell carcinoma, given an histopathological image from lung tissue. Moreover, a report module based on Explainable Deep Learning techniques is included and gives the pathologist information about the image’s areas used to classify the sample and the confidence of belonging to each class. ResultsThe results show a system accuracy between 97.11 and 99.69%, depending on the number of classes classified, and a value of the area under ROC curve between 99.77 and 99.94%. ConclusionsThe classification results obtain a substantial improvement according to previous works. Thanks to the given report, the time spent by the pathologist and the diagnostic turnaround time can be reduced.

Development and Characterization of Skin Phantoms at Microwave Frequencies

Realistic tissue-mimicking phantoms are required for experimental evaluation and validation of microwave reflectometry prototype systems for skin cancer detection before performing any tests on human subjects. These phantoms must accurately emulate the dielectric properties for both healthy and malignant skin tissues. In this work, we develop and experimentally investigate multiple skin phantoms with tumor inclusions in the frequency range of 0.5–26.5 GHz. These heterogeneous phantoms are realized by varying the tumor size and placement relative to the skin. The tumors with irregular borders are also investigated. For analyzing the effect of underlying skin on dielectric properties, two skin thicknesses are considered: 8 mm and 2.5 mm. The proposed heterogeneous phantoms are developed using inexpensive materials: oil, gelatin, deionized water and formaldehyde. The dielectric properties of fabricated phantoms are characterized with Keysight performance probe connected with a FieldFox handheld vector network analyzer. Our results demonstrate that the dielectric properties of the developed phantoms closely agree with those of the excised malignant human tissues reported in the literature over the entire frequency range of 0.5–26.5 GHz and can be hence reliably used for experimental validation in studies towards microwave-based diagnostics of skin lesions.

Breast lesion detection using an anchor-free network from ultrasound images with segmentation-based enhancement

The survival rate of breast cancer patients is closely related to the pathological stage of cancer. The earlier the pathological stage, the higher the survival rate. Breast ultrasound is a commonly used breast cancer screening or diagnosis method, with simple operation, no ionizing radiation, and real-time imaging. However, ultrasound also has the disadvantages of high noise, strong artifacts, low contrast between tissue structures, which affect the effective screening of breast cancer. Therefore, we propose a deep learning based breast ultrasound detection system to assist doctors in the diagnosis of breast cancer. The system implements the automatic localization of breast cancer lesions and the diagnosis of benign and malignant lesions. The method consists of two steps: 1. Contrast enhancement of breast ultrasound images using segmentation-based enhancement methods. 2. An anchor-free network was used to detect and classify breast lesions. Our proposed method achieves a mean average precision (mAP) of 0.902 on the datasets used in our experiment. In detecting benign and malignant tumors, precision is 0.917 and 0.888, and recall is 0.980 and 0.963, respectively. Our proposed method outperforms other image enhancement methods and an anchor-based detection method. We propose a breast ultrasound image detection system for breast cancer detection. The system can locate and diagnose benign and malignant breast lesions. The test results on single dataset and mixed dataset show that the proposed method has good performance.

A cloud-based deep learning model in heterogeneous data integration system for lung cancer detection in medical industry 4.0

Currently, lung cancer has become one of the most common and deadliest types of cancer. Due to its severity, many countries are now encouraging their at-risk citizens to test and treat lung cancer early. Lung cancer has been worse for poor regions or countries, whose citizens are more susceptible to lung cancer, as the local medical resources and healthcare provider level are inadequate. In recent years, this situation can be significantly improved by leveraging the existing datasets about lung cancer in developed countries. However, due to the poor synchronization of data collection methods, the collected data is heterogeneous, and can't be readily used. Artificial intelligence (AI), big data, cloud computing, and the internet of things accelerate the 4th revolution in the medical industry, and we called it medical industry 4.0. In the medical industry 4.0, lung cancer can be early detected by using a very intelligent approach. In this paper, using AI and cloud platform techniques in the medical industry 4.0, we propose an intelligent detection system including data integration, detection, historical cases comparison, similar cases inquiry, and retrieval for lung cancer. In this system, doctors can integrate the heterogeneous data at hand, and source a large amount of integrated data as a reference when treating the patient. A cloud-based deep learning model is integrated into this system, and then a content-based image retrieval system for similarity comparison is used. Finally, some public datasets are used to train and test this system, and results prove its performance is better than that of some baseline approaches. Then the similar case finding is evaluated with cosine similarity and all similarities reach over 0.93. The heterogeneous data integration system creates a good effect in helping doctors and patients access better diagnosis and treatment for lung cancer.

Microwave 3D Imaging System Featuring the Phase Coherence Factor for Improved Beamforming.

This paper presents an improved radar-based imaging system for breast cancer detection that features p-slot ultrawideband antennae in a 32-array set-up. The improved reconstruction algorithm incorporates the phase coherence factor (PCF) into the conventional delay and sum (DAS) beamforming algorithm, thus effectively suppressing noise arising from the side- and gratinglobe interferences. The system is tested by using several breast models fabricated from chemical mixtures formulated on the basis of realistic human tissues. Each model is placed in a hemispherical breast radome that was fabricated from polylactide material and surrounded by 32 p-slot antennae mounted in four concentric layers. These antennae are connected to an 8.5 GHz vector network analyser through two 16-channel multiplexers that automatically switch different combinations of transmitter and receiver pairs in a sequential manner. The system can accurately detect 5 mm tumours in a complex and homogeneously dense 3D breast model with an average signal-to-clutter ratio and full-width half-maximum of 7.0 dB and 2.3 mm, respectively. These values are more competitive than the values of other beamforming algorithms, even with contrasts as low as 1:2. The proposed PCF-weighted DAS is the best-performing algorithm amongst the tested beamforming techniques. This research paves the way for a clinical trial involving human subjects. Our laboratory is planning such a trial as part of future work.

An Improved Deep CNN For an Early and Accurate Skin Cancer Detection and Diagnosis System

Skin cancer is considered to be the most common and dangerous type of cancer. Information technology techniques are required to detect and diagnose skin cancer. Therefore, there is a need for an early and accurate skin cancer diagnosis and detection by employing an efficient deep learning technique. This research work proposes automatic diagnosis of skin cancer by employing Deep Convolution Neural Network (DCNN). The distinguishing feature of this research is it employs DCNN with 12 nested processing layers increasing the diagnosis and detection of skin cancer accuracy. Beside neural network, machine learning techniques of naïve Bayes and random forest are also utilized to detect skin cancer. This research work results concluded that the deep learning technique are more effective than machine learning in terms of skin cancer detection. By applying Naïve Bayesian on the proposed system accuracy of 96% were achieved, similarly for Random Forest method, an accuracy of 97% were achieved. The accuracy of 99.5% were achieved by applying Deep CNN network. The performance of proposed system has been compared with other research work and it is concluded that it shows the higher performance compared to all conventional systems.

SCDC-Net: Skin Cancer Detection and Classification using Deep Q Neural Network with Hybrid Features

Skin cancer is one of the most severe malignancies that may affect individuals of all ages. It can affect people of all races and ethnicities. Thus, early detection and treatment of skin cancer have the potential to save millions of lives. Because of the high degree of similarity between skin lesions, conventional machine learning approaches failed to provide the highest possible detection and classification accuracy in the skin cancer detection and classification (SCDC) system. To achieve the robust performance, this work is presented a SCDC-Net by employing deep learning, transfer learning models with hybrid features. Initially, UG-Net based transfer learning model is developed by combining generative adversarial networks (GAN) and U-Net. Here, UG-Net is used to remove hair from skin lesions and also preprocess enhances lesion. In addition, Hybrid U-Net (HU-Net) is used to localize the disease effected area of skin cancer. Further, various hybrid features are extracted from the segmented output by employing the gray-level cooccurrence matrix (GLCM) based texture characteristics, the discrete wavelet transform (DWT)-based low-level features, and the computation of image statistics for the texture, low-level, and colour features, respectively. In order to ensure the highest possible performance of the system, a deep q neural network (DQNN) was constructed for the classification of skin cancer using GLCM, DWT, and statistical colour features. The simulation results shows that the proposed method resulted in superior subjective and objective performance as compared to state of art approaches on ISIC-2019 public challenge dataset.

Semi-supervised vision transformer with adaptive token sampling for breast cancer classification.

Various imaging techniques combined with machine learning (ML) models have been used to build computer-aided diagnosis (CAD) systems for breast cancer (BC) detection and classification. The rise of deep learning models in recent years, represented by convolutional neural network (CNN) models, has pushed the accuracy of ML-based CAD systems to a new level that is comparable to human experts. Existing studies have explored the usage of a wide spectrum of CNN models for BC detection, and supervised learning has been the mainstream. In this study, we propose a semi-supervised learning framework based on the Vision Transformer (ViT). The ViT is a model that has been validated to outperform CNN models on numerous classification benchmarks but its application in BC detection has been rare. The proposed method offers a custom semi-supervised learning procedure that unifies both supervised and consistency training to enhance the robustness of the model. In addition, the method uses an adaptive token sampling technique that can strategically sample the most significant tokens from the input image, leading to an effective performance gain. We validate our method on two datasets with ultrasound and histopathology images. Results demonstrate that our method can consistently outperform the CNN baselines for both learning tasks. The code repository of the project is available at https://github.com/FeiYee/Breast-area-TWO.

Extrinsically evolved system for breast cancer detection

Extrinsically evolved system for breast cancer detection

Lung Cancer Segmentation and Classification Using Integration of Convolutional Neural Network & Unet Network Over CT Images: A Deep Learning Approach

Purpose: Cellular breakdown in the lungs screening is a cycle that is utilized to recognize the presence of cancer in the lungs in any case. Mostly it occurs among the elderly, especially smokers. Lung infections are lung-affecting illnesses that impede the respiratory mechanism. Cellulose breakdown in the lungs is one of the top causes of mortality in people all over the globe. Early recognition can improve endurance chances. As the world is revolutionizing with so many emerging technologies and one of the most popular technology is Deep Learning (DL) which has shown tremendous development in medical fields. So this paper brings an effective deep learning framework for lung cancer detection. Objective: To develop a CAD system for efficient lung cancer detection from CT images using a combination of CNN and UNET. For improving accuracy in the proposed system a better feature extraction and feature selection techniques is incorporate, i.e., by using autoencoder and selection based on Kernal function for effective boostings. Methodology: For this deep learning framework, the following are the stages. (a) Data Collection from the popular repository IQ-OTHNCCD lung cancer dataset which contains CT images of a total of 1198 from 110 CT slice cases, (b) Preprocessing CT images with an alpha-trimmed mean filter and CLAHE for improved enhancement, (c) Segmentation using CNN for segmenting the cancer regions) with the use of an autoencoder, extracting characteristics like area, perimeter, centroid, and mean intensity) feature selection using kernel function and finally f) classification using UNet network. Findings/Result: In terms of accuracy, sensitivity, specificity, recall, precision, F1-score, detection rate, TPR, FPR, and computation time, experiments are carried out on a range of cutting-edge models, and our suggested model surpasses them all (accuracy:0.95, sensitivity:0.97, specificity:0.98, detection rate:0.94). Originality: This paper is incorporating 2 neural networks over main stages such as segmentation and classification which eventually improves the quality of the model higher and also these are performed over real-time public medical records which shows the novelty of the model. Paper type: Methodology paper

A Neural Network and Optimization Based Lung Cancer Detection System in CT Images.

One of the most common causes of death from cancer for both women and men is lung cancer. Lung nodules are critical for the screening of cancer and early recognition permits treatment and enhances the rate of rehabilitation in patients. Although a lot of work is being done in this area, an increase in accuracy is still required to swell patient persistence rate. However, traditional systems do not segment cancer cells of different forms accurately and no system attained greater reliability. An effective screening procedure is proposed in this work to not only identify lung cancer lesions rapidly but to increase accuracy. In this procedure, Otsu thresholding segmentation is utilized to accomplish perfect isolation of the selected area, and the cuckoo search algorithm is utilized to define the best characteristics for partitioning cancer nodules. By using a local binary pattern, the relevant features of the lesion are retrieved. The CNN classifier is designed to spot whether a lung lesion is malicious or non-malicious based on the retrieved features. The proposed framework achieves an accuracy of 96.97% percent. The recommended study reveals that accuracy is improved, and the results are compiled using Particle swarm optimization and genetic algorithms.

Malignant Melanoma Classification using GLCM and SVM

In today’s modern world, Skin cancer is the most common cause of death amongst humans. Skin cancer is abnormal growth of skin cells most often develops on body exposed to the sunlight, but can occur anywhere on the body. Most of the skin cancers are curable at early stages. So, an early and fast detection of skin cancer can save the patient’s life. With the new technology, early detection of skin cancer is possible at initial stage. Formal method for diagnosis skin cancer detection is Biopsy method. It is done by removing skin cells and that sample goes to various laboratory testing. It is painful and time-consuming process. We have proposed skin cancer detection system using Support Vector Machine (SVM) for early detection of skin cancer disease. It is more advantageous to patients. The diagnosing methodology uses Image processing methods and SVM algorithm. The dermoscopy image of skin cancer is taken and it goes under various pre-processing technique for noise removal and image enhancement. Then the image is undergone to segmentation using Thresholding method. Some features of image have to be extracted using GLCM methodology. These features are given as the input to classifier. Support vector Machine (SVM) is used for classification purpose. It classifies the given image into cancerous or non-cancerous.

Pseudoprospective Paraclinical Interaction of Radiology Residents With a Deep Learning System for Prostate Cancer Detection: Experience, Performance, and Identification of the Need for Intermittent Recalibration.

The aim of this study was to estimate the prospective utility of a previously retrospectively validated convolutional neural network (CNN) for prostate cancer (PC) detection on prostate magnetic resonance imaging (MRI). The biparametric (T2-weighted and diffusion-weighted) portion of clinical multiparametric prostate MRI from consecutive men included between November 2019 and September 2020 was fully automatically and individually analyzed by a CNN briefly after image acquisition (pseudoprospective design). Radiology residents performed 2 research Prostate Imaging Reporting and Data System (PI-RADS) assessments of the multiparametric dataset independent from clinical reporting (paraclinical design) before and after review of the CNN results and completed a survey. Presence of clinically significant PC was determined by the presence of an International Society of Urological Pathology grade 2 or higher PC on combined targeted and extended systematic transperineal MRI/transrectal ultrasound fusion biopsy. Sensitivities and specificities on a patient and prostate sextant basis were compared using the McNemar test and compared with the receiver operating characteristic (ROC) curve of CNN. Survey results were summarized as absolute counts and percentages. A total of 201 men were included. The CNN achieved an ROC area under the curve of 0.77 on a patient basis. Using PI-RADS ≥3-emulating probability threshold (c3), CNN had a patient-based sensitivity of 81.8% and specificity of 54.8%, not statistically different from the current clinical routine PI-RADS ≥4 assessment at 90.9% and 54.8%, respectively ( P = 0.30/ P = 1.0). In general, residents achieved similar sensitivity and specificity before and after CNN review. On a prostate sextant basis, clinical assessment possessed the highest ROC area under the curve of 0.82, higher than CNN (AUC = 0.76, P = 0.21) and significantly higher than resident performance before and after CNN review (AUC = 0.76 / 0.76, P ≤ 0.03). The resident survey indicated CNN to be helpful and clinically useful. Pseudoprospective paraclinical integration of fully automated CNN-based detection of suspicious lesions on prostate multiparametric MRI was demonstrated and showed good acceptance among residents, whereas no significant improvement in resident performance was found. General CNN performance was preserved despite an observed shift in CNN calibration, identifying the requirement for continuous quality control and recalibration.

Automated prostate cancer grading and diagnosis system using deep learning-based Yolo object detection algorithm

Purpose:Developing an artificial intelligence-based prostate cancer detection and diagnosis system that can automatically determine important regions and accurately classify the determined regions on an input biopsy image. Method:The Yolo general-purpose object detection algorithm was utilized to detect important regions (for the localization task) and to grade the detected regions (for the classification task). The algorithm was re-trained with our prostate cancer dataset. The dataset was created by annotating 500 real prostate tissue biopsy images. The dataset was split into train/test parts as 450/50 real prostate tissue images, respectively, before the data augmentation process. Next, the training set consisting of 450 labeled biopsy images was pre-processed with the data augmentation method. This way, the number of biopsy images in the dataset was increased from 450 to 1776. Then, the algorithm was trained with the dataset and the automatic prostate cancer detection and diagnosis tool was developed. Results:The developed tool was tested with two test sets. The first test set contains 50 images that are similar to the train set. Hence, 97% detection and classification accuracy has been achieved. The second test set contains 137 completely different real prostate tissue biopsy images, thus, 89% detection accuracy has been achieved. Conclusion:In this study, an automatic prostate cancer detection and diagnosis tool was developed. The test results show that high-accuracy (high-performance) prostate cancer diagnosis tools can be developed using AI (computer vision) methods such as object detection algorithms. These systems can decrease the inter-observer variability among pathologists, and help prevent the time delay in the diagnosis phase.

Hybrid optimization algorithm based feature selection for mammogram images and detecting the breast mass using multilayer perceptron classifier

AbstractBreast cancer is the second most frequent malignant tumor in the world. Early findings of breast cancer can significantly improve treatment effectiveness. Manual methods of breast cancer diagnosis are prone to human fault and inaccuracy, and they take time. A computer‐aided diagnosis can assist radiologists in making better choices by overcoming the disadvantages of manual methods. One of the significant steps in the breast cancer diagnosis process is feature selection. In recent decades, many studies have proposed numerous hybrid optimization methods to select the optimal features in the breast cancer detection system. However, many hybrid optimization algorithms are trapped in local optima and have slow convergence speed. Thus, it reduces the classification accuracy. For resolving these issues, this work proposes a hybrid optimization algorithm that combines the grasshopper optimization algorithm and the crow search algorithm for feature selection and classification of the breast mass with multilayer perceptron. The simulation is experimented with using MATLAB 2019a. The efficacy of the proposed hybrid grasshopper optimization‐crow search algorithm with multilayer perceptron system is compared to multilayer perceptron based algorithms of enhanced and adaptive genetic algorithm, teaching learning‐based whale optimization algorithm, butterfly optimization algorithm, whale optimization algorithm, and grasshopper optimization algorithm. From the results obtained, the proposed grasshopper optimization‐crow search algorithm with the multilayer perceptron method outperforms the comparative models in terms of classification accuracy (97.1%), sensitivity (98%), and specificity (95.4%) for the mammographic image analysis society dataset.