Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM
An adenocarcinoma is a type of malignant cancerous tissue that forms from a glandular structure in epithelial tissue. Analyzed stained microscopic biopsy images were used to perform image manipulation and extract significant features for support vector machine (SVM) classification, to predict the Gl...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/15/2969 |
| _version_ | 1819083551924027392 |
|---|---|
| author | Subrata Bhattacharjee Hyeon-Gyun Park Cho-Hee Kim Deekshitha Prakash Nuwan Madusanka Jae-Hong So Nam-Hoon Cho Heung-Kook Choi |
| author_facet | Subrata Bhattacharjee Hyeon-Gyun Park Cho-Hee Kim Deekshitha Prakash Nuwan Madusanka Jae-Hong So Nam-Hoon Cho Heung-Kook Choi |
| author_sort | Subrata Bhattacharjee |
| collection | DOAJ |
| description | An adenocarcinoma is a type of malignant cancerous tissue that forms from a glandular structure in epithelial tissue. Analyzed stained microscopic biopsy images were used to perform image manipulation and extract significant features for support vector machine (SVM) classification, to predict the Gleason grading of prostate cancer (PCa) based on the morphological features of the cell nucleus and lumen. Histopathology biopsy tissue images were used and categorized into four Gleason grade groups, namely Grade 3, Grade 4, Grade 5, and benign. The first three grades are considered malignant. K-means and watershed algorithms were used for color-based segmentation and separation of overlapping cell nuclei, respectively. In total, 400 images, divided equally among the four groups, were collected for SVM classification. To classify the proposed morphological features, SVM classification based on binary learning was performed using linear and Gaussian classifiers. The prediction model yielded an accuracy of 88.7% for malignant vs. benign, 85.0% for Grade 3 vs. Grade 4, 5, and 92.5% for Grade 4 vs. Grade 5. The SVM, based on biopsy-derived image features, consistently and accurately classified the Gleason grading of prostate cancer. All results are comparatively better than those reported in the literature. |
| first_indexed | 2024-12-21T20:34:22Z |
| format | Article |
| id | doaj.art-fe131b20e667415bb4a9b3e4b3ef0647 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T20:34:22Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fe131b20e667415bb4a9b3e4b3ef06472022-12-21T18:51:09ZengMDPI AGApplied Sciences2076-34172019-07-01915296910.3390/app9152969app9152969Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVMSubrata Bhattacharjee0Hyeon-Gyun Park1Cho-Hee Kim2Deekshitha Prakash3Nuwan Madusanka4Jae-Hong So5Nam-Hoon Cho6Heung-Kook Choi7Department of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment of Digital Anti-Aging Healthcare, Inje University, Gimhae 50834, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaDepartment of Digital Anti-Aging Healthcare, Inje University, Gimhae 50834, KoreaDepartment of Pathology, Yonsei University Hospital, Seoul 03722, KoreaDepartment of Computer Engineering, u-AHRC, Inje University, Gimhae 50834, KoreaAn adenocarcinoma is a type of malignant cancerous tissue that forms from a glandular structure in epithelial tissue. Analyzed stained microscopic biopsy images were used to perform image manipulation and extract significant features for support vector machine (SVM) classification, to predict the Gleason grading of prostate cancer (PCa) based on the morphological features of the cell nucleus and lumen. Histopathology biopsy tissue images were used and categorized into four Gleason grade groups, namely Grade 3, Grade 4, Grade 5, and benign. The first three grades are considered malignant. K-means and watershed algorithms were used for color-based segmentation and separation of overlapping cell nuclei, respectively. In total, 400 images, divided equally among the four groups, were collected for SVM classification. To classify the proposed morphological features, SVM classification based on binary learning was performed using linear and Gaussian classifiers. The prediction model yielded an accuracy of 88.7% for malignant vs. benign, 85.0% for Grade 3 vs. Grade 4, 5, and 92.5% for Grade 4 vs. Grade 5. The SVM, based on biopsy-derived image features, consistently and accurately classified the Gleason grading of prostate cancer. All results are comparatively better than those reported in the literature.https://www.mdpi.com/2076-3417/9/15/2969prostate cancerhistopathologymicroscopictissue imagesegmentationmorphologicalquantitativeclassificationSVM |
| spellingShingle | Subrata Bhattacharjee Hyeon-Gyun Park Cho-Hee Kim Deekshitha Prakash Nuwan Madusanka Jae-Hong So Nam-Hoon Cho Heung-Kook Choi Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM Applied Sciences prostate cancer histopathology microscopic tissue image segmentation morphological quantitative classification SVM |
| title | Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM |
| title_full | Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM |
| title_fullStr | Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM |
| title_full_unstemmed | Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM |
| title_short | Quantitative Analysis of Benign and Malignant Tumors in Histopathology: Predicting Prostate Cancer Grading Using SVM |
| title_sort | quantitative analysis of benign and malignant tumors in histopathology predicting prostate cancer grading using svm |
| topic | prostate cancer histopathology microscopic tissue image segmentation morphological quantitative classification SVM |
| url | https://www.mdpi.com/2076-3417/9/15/2969 |
| work_keys_str_mv | AT subratabhattacharjee quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT hyeongyunpark quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT choheekim quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT deekshithaprakash quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT nuwanmadusanka quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT jaehongso quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT namhooncho quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm AT heungkookchoi quantitativeanalysisofbenignandmalignanttumorsinhistopathologypredictingprostatecancergradingusingsvm |