Cancer Cell Segmentation Based on Unsupervised Clustering and Deep Learning

Sikder, Juel; Das, Utpol Kanti; Anwar, Afsah

doi:10.1007/978-3-030-68154-8_53

Cited by 9 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this purpose, the system has to apply pre-processing stages before applying classification. When image features are extracted using an activation function, then extracted image features passed to the classifier and the previously created classifier classifies the test image [1]. 8) Predict class label: When the classifier classifies the test image, the classifier predicts a label that represents which class the test image belongs to.…”

Section: ) Classification Of the Test Cancer Cellmentioning

confidence: 99%

“…In the system, the cancerous area is identified with the pixel intensity having ones and the non-cancerous area identified with the pixel intensity zeros [1]. The percentage of the cancerous area is calculated with the ratio of the cancerous area and the total test image are as follows:…”

Section: Area Calculationmentioning

confidence: 99%

“…This research used Convolutional Neural Network(CNN) for classification purposes. It takes the help of the resnet50 architecture that uses fc1000 layers for this deep classification of the testing image [1]. The authors implement an idea that turns the machine into a human brain.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Supervised Learning-based Cancer Detection

Sikder¹,

Das²,

Chakma³

2021

IJACSA

Self Cite

View full text Add to dashboard Cite

The segmentation, detection and extraction of the infected tumor from Magnetic Resonance Imaging (MRI) images are the key concerns for radiologists or clinical experts. But it is tedious and time consuming and its accuracy depends on their experience only. This paper suggest a new methodology segmentation, recognition, classification and detection of different types of cancer cells from both MRI and RGB (Red, Green, Blue) images are performed using supervised learning, Convolutional Neural Network (CNN) and morphological operations. In this methodology, CNN is used to classify cancer types and semantic segmentation to segment cancer cells. The system trained using the pixel labeled the ground truth where every image labeled as cancerous and non-cancerous. The system trained with 70% images and validated and tested with the rest 30%. Finally, the segmented cancer region is extracted and its percentage area is calculated. The research examined on the MATLAB platform on MRI and RGB images of the infected cell of BreCaHAD dataset for breast cancer, SN-AM Dataset for leukemia, Lung and Colon Cancer Histopathological Images dataset for lung cancer and Brain MRI Images for Brain Tumor Detection dataset for brain cancer.

show abstract

Section: ) Classification Of the Test Cancer Cellmentioning

confidence: 99%

Section: Area Calculationmentioning

confidence: 99%

See 1 more Smart Citation

Supervised Learning-based Cancer Detection

Sikder¹,

Das²,

Chakma³

2021

IJACSA

Self Cite

View full text Add to dashboard Cite

show abstract

“…K-means clustering is an unsupervised learning algorithm that is used enormously. The method is used to define k samples, one for each cluster [14]. The next step is to assign each point of input data into the nearest cluster.…”

Section: Image Segmentationmentioning

confidence: 99%

“…Similarly, it continued its classification steps until all categories were tested. From this last classification, the test image is classified as the true categorized class [14].…”

Section: E Classification Using Multi-svmsmentioning

confidence: 99%

Fish Disease Detection System: A Case Study of Freshwater Fishes of Bangladesh

Sikder¹,

Sarek²,

Das³

2021

IJACSA

Self Cite

View full text Add to dashboard Cite

The proposed system is designed for automatic detection and classification of fish diseases in freshwater especially Rangamati Kaptai Lake and Sunamganj Hoar area of Bangladesh. Our experimental result is indicating that the proposed approach is significantly an accurate and automatic detection and recognition of fish diseases. This study presents fish disease detection based on the K-means and C-means fuzzy logic clustering method to segment the filtering image. Gabor's Filters and Gray Level Co-occurrence Matrix (GLCM) are used to extracts the features from the segmented regions. Finally Multi-Support Vector Machine (M-SVMs) is used for classification of the test image. The proposed system demonstrated a comparison between K-means clustering and C-means fuzzy logic. The proposed methodology gave 96.48% accuracy using K-means and 97.90% using C-means fuzzy logic which is the highest accuracy rate to compare other existing methods. The proposed system has been experimented in the MATLAB environment on infected fish images of Rangamati Kaptai Lake and Sumangan Hoar area. It is a challenging task of fisheries farming in Hoar areas and Lake areas to detect fish diseases initially. The proposed methodology can detect and classify different fish diseases in early stages and also contributes to improved results for fish disease detection.

show abstract