Lung Cancer Prediction Using Robust Machine Learning and Image Enhancement Methods on Extracted Gray-Level Co-Occurrence Matrix Features

Hussain, Lal; Alsolai, Hadeel; Hassine, Siwar Ben Haj; Nour, Mohamed K.; Duhayyim, Mesfer Al; Hilal, Anwer Mustafa; Salama, Ahmed S.; Motwakel, Abdelwahed; Yaseen, Ishfaq; Rizwanullah, Mohammed

doi:10.3390/app12136517

Cited by 18 publications

(7 citation statements)

References 69 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, both the HF and LF are considered. GLCM [26,27] and DWT [28,29] were used so as to obtain the necessary HF. The outcomes of these methods can be obtained by using Eq.…”

Section: Feature Extraction and Integrationmentioning

confidence: 99%

Enhanced Karyotyping Through Deep Learning-Assisted Segmentation and Classification of Chromosomal Cells

Sekar,

Sankaran

2024

View full text Add to dashboard Cite

The escalating prevalence of genetic disorders in humans underscores the criticality of early detection. Current clinical methodologies, such as cellular activity assessment and chromosomal examination, are widely employed for early-stage prediction of these disorders. However, traditional approaches to chromosomal cell (CC) examination are intricate and labor-intensive. This study proposes a novel deep learning framework (DLF) to overcome these challenges by precisely and efficiently segmenting and classifying CCs. As part of this scheme, images are collected and resized, the DLF is trained using the selected images, segmentation and deep feature extraction of the CC are performed. The proposed methodology involves image collection and resizing, training the DLF with chosen images, CC segmentation and feature extraction and multiclass classification and performance verification. This work implements the VGG-UNet plan to examine the chosen CC images collected from the Biomedical Imaging Laboratory (BioImLab). An experimental inquiry is being carried out on 5474 images and the achieved findings are addressed. The findings of this research suggest that the presented work help to provide a detection accuracy of >98% with the K-Nearest Neighbor supported classifier. This research can be expanded in the future to detect the genetic disorder based on the information obtained from the CC.

show abstract

“…In this work, both the HF and LF are considered. GLCM [26,27] and DWT [28,29] were used so as to obtain the necessary HF. The outcomes of these methods can be obtained by using Eq.…”

Section: Feature Extraction and Integrationmentioning

confidence: 99%

Enhanced Karyotyping Through Deep Learning-Assisted Segmentation and Classification of Chromosomal Cells

Sekar,

Sankaran

2024

View full text Add to dashboard Cite

show abstract

“…The difference in image pixels with the highest and the lowest intensity values can be used to determine contrast. This research utilized contrast stretching by increasing the intensity value to obtain clearer images [19], [20]. The contrast enhancement process was performed using the MATLAB program.…”

Section: A Image Acquisition B Preprocessingmentioning

confidence: 99%

Klasifikasi Penyakit Daun Kopi Robusta Menggunakan Metode SVM dengan Ekstraksi Ciri GLCM

Agus Supriyanto,

R. Rizal Isnanto,

Oky Dwi Nurhayati

2023

Jurnal Nasional Teknik Elektro dan Teknologi Informasi

View full text Add to dashboard Cite

Tanaman kopi merupakan sumber pendapatan bagi beberapa petani di Indonesia dan berperan penting sebagai penghasil devisa negara. Produksi tanaman kopi dapat menurun akibat serangan hama dan penyakit. Beberapa penyakit yang sering terjadi pada tanaman kopi adalah penyakit pada daun, berupa bercak daun (Cercospora coffeicola) dan karat daun (Hemileia vastatrix). Penelitian yang dilakukan bertujuan untuk mengenali jenis penyakit pada daun kopi robusta dan mengetahui hasil klasifikasi. Penerapan teknologi pengolahan citra berbasis machine learning menggunakan metode klasifikasi support vector machine (SVM) berdasarkan ekstraksi ciri gray level co-occurrence matrix (GLCM) menjadi solusi yang diusulkan. Prapengolahan diperlukan sebelum dilakukannya pengolahan untuk meningkatkan kualitas citra supaya mudah dianalisis. Kemudian, dilakukan segmentasi menggunakan k-means clustering. Proses segmentasi k-means clustering dengan tiga cluster digunakan untuk membedakan bagian yang terdampak penyakit bercak daun atau karat daun dengan bagian yang tidak terdampak penyakit. Metode GLCM digunakan sebagai ekstraksi ciri, berdasarkan fitur angular second moment (ASM) atau energi, kontras, korelasi, inverse different moment (IDM) atau homogenitas, dan entropi dengan sudut 0°, 45°, 90°, dan 135°, serta jarak antar piksel 1 sampai 3 piksel. Metode SVM digunakan sebagai klasifikasi dengan kernel linear, polinomial, dan Radial Basis Function (RBF) Gaussian. Penelitian ini menggunakan citra bercak daun dan karat daun, dengan jumlah data latih 320 citra dan data uji 80 citra. Hasil pengujian terbaik diperoleh pada kernel RBF Gaussian dengan tingkat akurasi terbaik sebesar 97,5%, presisi 95,24%, recall 100%, dan F1-score 97,56%.

show abstract

“…With that they have computed the texture features for predicting the lung cancer detection. Among the various machine learning algorithms, SVM Gaussian , RBF, Decision Tree, SVM Polynomial, Naïve Bayesthe SVM Gaussian , RBF and SVM Polynomial provided the highest performance with an accuracy of 99.89% in predicting the lung cancer [5].…”

Section: Literature Surveymentioning

confidence: 99%

Machine Learning Approaches in Early Lung Cancer Prediction: A Comprehensive Review

Krishna

2023

IJSREM

View full text Add to dashboard Cite

Diagnosing cancer at an early stage helps the doctors for the successful treatment of the disease. Lung Cancer, a leading cause of cancer-related deaths globally, has emphasized the importance of early detection to enhance patient survival outcomes. This paper offers a comprehensive review of various machine learning algorithms employed in the prediction and early detection of lung cancer. Through a diligent survey of recent literature, we evaluated the effectiveness of techniques ranging from ensemble learning methods to regression and classification algorithms. Several studies exhibited promising results, with some algorithms achieving accuracies upwards of 99%. Particularly, SVM, Logistic Regression and ensemble methods consistently demonstrated high prediction accuracies across multiple datasets. However, there remains substantial potential to expand on these findings, especially in the domain of hybrid model development, real time predictions and seamless clinical integrations. This review underscores the transformative role of ML in Lung Cancer diagnostics and charts a course for future exploration in this critical medical domain. Keywords: Machine Learning, Lung Cancer, Classification Algorithm, SVM, Random Forest, XGBoost

show abstract

Lung Cancer Prediction Using Robust Machine Learning and Image Enhancement Methods on Extracted Gray-Level Co-Occurrence Matrix Features

Cited by 18 publications

References 69 publications

Enhanced Karyotyping Through Deep Learning-Assisted Segmentation and Classification of Chromosomal Cells

Enhanced Karyotyping Through Deep Learning-Assisted Segmentation and Classification of Chromosomal Cells

Klasifikasi Penyakit Daun Kopi Robusta Menggunakan Metode SVM dengan Ekstraksi Ciri GLCM

Machine Learning Approaches in Early Lung Cancer Prediction: A Comprehensive Review

Contact Info

Product

Resources

About