A Survey on Application of Machine Learning Algorithms in Cancer Prediction and Prognosis

Deepti, _; Ray, Susmita

doi:10.1007/978-981-15-5616-6_25

Cited by 3 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The processed features at an LSTM unit in the network pass the contextual state information to the next unit. When fusing these GLCMs through this LSTM-based deep neural architecture, the correlation of adjacent slices gives an advantage over other fusion methods that use CNNs [39], which ignore the spatial information among the slices. Each LSTM unit needs to wait for the previous LSTM unit output and this can cause a long processing time because CT scans consists of long series of slices.…”

Section: Methodsmentioning

confidence: 99%

“…A fuzzy Cmeans clustering method is used to determine lung cancer nodules, and a modified CNN algorithm based on the bat algorithm was introduced to classify lung cancer effectively. The analysis by Deepti [39] revealed the essence of machine learning algorithms in predicting and detecting different cancer types. Riquelme et al [40] assessed the advanced learning algorithms and architectures for automated detection systems applied in lung cancer detection.…”

Section: Related Studiesmentioning

confidence: 99%

“…The results presented in Table 4 indicate the effectiveness of the LSTM-based deep fusion structure applied on the stack of 3D-GLCMs extracted from VSs of nodules. Instead of performing 3D-GLCM calculations using on the whole CT scan volume like Deepti [39], in this study the 3D-GLCM calculations are confined to the VSs. This not only decrease the calculation costs, but fusing these sequential features in the proposed LSTM-based deep structure leads to a superior performance to similar methods like that of Tan et al [48].…”

Section: Plos Onementioning

confidence: 99%

See 2 more Smart Citations

Deep fusion of gray level co-occurrence matrices for lung nodule classification

2022

View full text Add to dashboard Cite

Lung cancer is a serious threat to human health, with millions dying because of its late diagnosis. The computerized tomography (CT) scan of the chest is an efficient method for early detection and classification of lung nodules. The requirement for high accuracy in analyzing CT scan images is a significant challenge in detecting and classifying lung cancer. In this paper, a new deep fusion structure based on the long short-term memory (LSTM) has been introduced, which is applied to the texture features computed from lung nodules through new volumetric grey-level-co-occurrence-matrices (GLCMs), classifying the nodules into benign, malignant, and ambiguous. Also, an improved Otsu segmentation method combined with the water strider optimization algorithm (WSA) is proposed to detect the lung nodules. WSA-Otsu thresholding can overcome the fixed thresholds and time requirement restrictions in previous thresholding methods. Extended experiments are used to assess this fusion structure by considering 2D-GLCM based on 2D-slices and approximating the proposed 3D-GLCM computations based on volumetric 2.5D-GLCMs. The proposed methods are trained and assessed through the LIDC-IDRI dataset. The accuracy, sensitivity, and specificity obtained for 2D-GLCM fusion are 94.4%, 91.6%, and 95.8%, respectively. For 2.5D-GLCM fusion, the accuracy, sensitivity, and specificity are 97.33%, 96%, and 98%, respectively. For 3D-GLCM, the accuracy, sensitivity, and specificity of the proposed fusion structure reached 98.7%, 98%, and 99%, respectively, outperforming most state-of-the-art counterparts. The results and analysis also indicate that the WSA-Otsu method requires a shorter execution time and yields a more accurate thresholding process.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Studiesmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

Deep fusion of gray level co-occurrence matrices for lung nodule classification

2022

View full text Add to dashboard Cite

show abstract

“…Such treatment modalities have been associated with a reduction of BC growth and spread, reduction in breast cancer mortality, and an increase in survival rates, thereby saving the life of BC patients [24]. Researchers are increasingly using Machine Learning (ML) approaches for modelling the progression and treatment of cancer due to its ability to detect key features from complex datasets [25,26]. The application of ML models for the prediction and prognosis of disease development has become an irrevocable part of cancer research.…”

Section: Introductionmentioning

confidence: 99%

Improving Invasive Breast Cancer Care Using Machine Learning Technology

Yedjou¹,

Tchounwou²,

Grigsby³

et al. 2022

J Biomed Res Environ Sci

View full text Add to dashboard Cite

Breast Cancer (BC) is the most common malignancy in women worldwide. In the United States, the lifetime risk of developing an invasive form of breast cancer is 12.5% among women. BC arises in the lining cells (epithelium) of the ducts or lobules in the glandular tissue of the breast. The goal of the present study was to use Machine Learning (ML) as a novel technology to assess and compare the invasive forms of BC including, infiltrating ductal carcinoma, infiltrating lobular carcinoma, and mucinous carcinoma. To achieve this goal, we used ML algorithms and collected a dataset of 334 BC patients available at https://www.kaggle.com/amandam1/breastcancerdataset and interpreted this dataset based on the form of BC, age, sex, tumor stages, surgery type, and survival rate. Among the 334 patients, 70% were diagnosed with infiltrating ductal carcinoma, 27% with infiltrating lobular carcinoma, and 3% with mucinous carcinoma. Overall, out of 334 BC patients: 64 (19.16%) were in stage I, 189 (56.59%) in stage II, and 81 (24.25%) in stage III. Sixty-six, 67, 96, and 105 patients underwent lumpectomy, simple mastectomy, modified radical mastectomy, and other types of surgery, respectively. The survival rates were 83.4% for stage I, 79.1% for stage II, and 77% for stage III. Findings from the present study demonstrated that ML provides an important tool to curate large amount of BC data, as well as a scientific means to improve BC outcomes.

show abstract