Detecting breast cancer using artificial intelligence: Convolutional neural network

Abstract

BACKGROUND: One of the most broadly founded approaches to envisage cancer treatment relies upon a pathologist’s efficiency to visually inspect the appearances of bio-markers on the invasive tumor tissue section. Lately, deep learning techniques have radically enriched the ability of computers to identify objects in images fostering the prospect for fully automated computer-aided diagnosis. Given the noticeable role of nuclear structure in cancer detection, AI’s pattern recognizing ability can expedite the diagnostic process. OBJECTIVE: In this study, we propose and implement an image classification technique to identify breast cancer. METHODS: We implement the convolutional neural network (CNN) on breast cancer image data set to identify invasive ductal carcinoma (IDC). RESULT: The proposed CNN model after data augmentation yielded 78.4% classification accuracy. 16% of IDC (-) were predicted incorrectly (false negative) whereas 25% of IDC (+) were predicted incorrectly (false positive). CONCLUSION: The results achieved by the proposed approach have shown that it is feasible to employ a convolutional neural network particularly for breast cancer classification tasks. However, a common problem in any artificial intelligence algorithm is its dependence on the data set. Therefore, the performance of the proposed model might not be generalized.

AI-Enabled Classification of Head and Neck Tumors using Convolutional Neural Networks with Dynamic Optical Contrast Imaging

“…al noted a 76% accuracy in delineating breast cancer with an input of 162 breast cancer histological slides, and Mohsen et al noted an 87.2% accuracy in delineating brain cancer tissue with an input of 66 MRI images. 20,21 It is well established that the accuracy of CNN models improve as larger training data are inputted, 22 and we anticipate an increased accuracy as we continue to enroll patients into our study. Currently, the CNN model consists of only 3 convolutional layers for extracting features used for the final output tumor classification, resulting in a limited performance on unseen data input as shown in the validation curves of Figure 7.…”

Artificial intelligence: Potential tool to subside SARS-CoV-2 pandemic

“…2 ). In most cases, it is utilized in three major areas, which include issues related to the nervous system, cardiovascular complications, and cancer [ [1] , [2] , [3] , [4] ]. AI techniques such as DL, ML and cognitive computers help indicate early developments of cardiovascular disease [ 5 ].…”

“…Extracting the full potential of AI also subsequently requires big data, in which the current information on healthcare and COVID-19 would serve as an excellent source. DL as another subclass of AI utilizes multiple layers of algorithms, making its learning models even more complex in comparison to ML [ 4 ]. By utilizing multiple layers of compressed raw data, DL takes advantage of the multiple algorithms provided in order to produce the desired output [ 5 ].…”

Blockchain integrated multi-agent system for breast cancer diagnosis

“…The manual method of detecting the breast tumors: malignant and benign is very complicated and time-consuming process as they share similar structures. The artificial intelligence techniques can give a reliable and faster approach for detecting breast cancer in patients [34], [35]. The artificial intelligence techniques are used in prediction of breast cancer either from the medical images [36]- [43] or from the datasets containing categorical and numerical values [44], [45].…”