Computer-Aided Diagnosis System for Detection of Stomach Cancer with Image Processing Techniques

Yaşar, Ali; Sarıtaş, İsmail; Korkmaz, Hüseyin Anıl

doi:10.1007/s10916-019-1203-y

Cited by 26 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning has been applied to detect many types of cancer, such as colorectal cancer [6] and breast cancer [7], with high accuracy. In the field of gastric cancer, machine learning is mainly applied for analyzing endoscopic images, which are obtained through invasive procedures [8,9]. In contrast, detection of routine blood, biochemical, and tumor markers is noninvasive and inexpensive.…”

Section: Introductionmentioning

confidence: 99%

Application of machine learning in the diagnosis of gastric cancer based on noninvasive characteristics

et al. 2020

View full text Add to dashboard Cite

Background The diagnosis of gastric cancer mainly relies on endoscopy, which is invasive and costly. The aim of this study is to develop a predictive model for the diagnosis of gastric cancer based on noninvasive characteristics. Aims To construct a predictive model for the diagnosis of gastric cancer with high accuracy based on noninvasive characteristics. Methods A retrospective study of 709 patients at Zhejiang Provincial People's Hospital was conducted. Variables of age, gender, blood cell count, liver function, kidney function, blood lipids, tumor markers and pathological results were analyzed. We used gradient boosting decision tree (GBDT), a type of machine learning method, to construct a predictive model for the diagnosis of gastric cancer and evaluate the accuracy of the model. Results Of the 709 patients, 398 were diagnosed with gastric cancer; 311 were health people or diagnosed with benign gastric disease. Multivariate analysis showed that gender, age, neutrophil lymphocyte ratio, hemoglobin, albumin, carcinoembryonic antigen (CEA), carbohydrate antigen 125 (CA125) and carbohydrate antigen 199 (CA199) were independent characteristics associated with gastric cancer. We constructed a predictive model using GBDT, and the area under the receiver operating characteristic curve (AUC) of the model was 91%. For the test dataset, sensitivity was 87.0% and specificity 84.1% at the optimal threshold value of 0.56. The overall accuracy was 83.0%. Positive and negative predictive values were 83.0% and 87.8%, respectively. Conclusion We construct a predictive model to diagnose gastric cancer with high sensitivity and specificity. The model is noninvasive and may reduce the medical cost.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of machine learning in the diagnosis of gastric cancer based on noninvasive characteristics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Based on the survey by the American Cancer Society, the trend in the 5-year relative survival rate of gastric cancer has been gradually rising but remains at a low level, at approximately 29% [ 2 ]. Gastric cancer is highly malignant due to its extensive metastatic ability to form metastases in a variety of organs, such as the lymphatic glands, liver, and ovaries [ 3 ]. Most malignant gastric cancers (about 95%) are of the adenocarcinoma histological type, which include intestinal and diffuse types that are classified based on the Lauren classification [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Use of a Four-miRNA Panel as a Biomarker for the Diagnosis of Stomach Adenocarcinoma

Chen

Peng

et al. 2020

Disease Markers

View full text Add to dashboard Cite

Background. MicroRNAs (miRNAs) have been applied to cancer diagnosis taking into account their role in tumorigenesis. The main purpose of our study was to confirm the possibility of using miRNAs as noninvasive biomarkers for stomach adenocarcinoma (STAD) diagnosis. Methods. A total of 246 participants (130 STAD patients and 116 healthy controls (HCs)) were enrolled in this 3-phase study. Five STAD pools and 3 HC pools (with 4 participants in each pool) were used for the screening of the 28 miRNAs using quantitative reverse transcription-polymerase chain reaction (qRT-PCR). The training phase (30 STAD patients vs. 24 HCs) and validation phase (80 STAD patients vs. 80 HCs) were used to further verify the identity of these miRNAs. Kaplan–Meier survival analysis and bioinformatics analysis were also used. Results. The expression levels of miR-125b-5p and miR-196a-5p were upregulated in STAD serum, compared with the HCs, while miR-1-3p and miR-149-5p showed the opposite result. A four-serum miRNA panel was constructed, and the area under the receiver operating characteristic curve (AUC) was found to be 0.892 (95% CI: 0.834 to 0.936, sensitivity = 86.25 % , specificity = 78.75 % ). Only miR-125b-5p expression showed a significant difference between STAD patients and NCs in the survival analysis. The neurotrophin signaling pathway was associated with 4 miRNAs identified in STAD patients. Conclusion. The four-serum miRNA panel has great potential to be used as a noninvasive biomarker for STAD diagnosis.

show abstract

“…Computer-aided diagnosis (CAD) plays a vital role in medical imaging, allowing accurate results to be obtained in minimal time [ 13 , 19 , 20 , 21 ]. Various computer techniques are being used in medical imaging for the automatic detection of diseases.…”

Section: Related Workmentioning

confidence: 99%

“…Various computer techniques are being used in medical imaging for the automatic detection of diseases. Artificial intelligence (AI) and its applications such as machine learning and deep learning are the best examples [ 13 , 19 , 22 , 23 ].…”

Section: Related Workmentioning

confidence: 99%

“…Selection of the frames containing abnormalities is also a difficult task because typically only 5% of the frames contain abnormalities [ 8 ]. Several researchers [ 3 , 6 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ] have suggested different solutions for the automated detection of stomach diseases. However, due to the resemblance of different symptoms including color, shape, texture, etc., it is challenging to accurately classify the type of infection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Deep Learning Model for Endoscopic Lesion Detection and Classification Using Endoscopy Videos

et al. 2021

View full text Add to dashboard Cite

In medical imaging, the detection and classification of stomach diseases are challenging due to the resemblance of different symptoms, image contrast, and complex background. Computer-aided diagnosis (CAD) plays a vital role in the medical imaging field, allowing accurate results to be obtained in minimal time. This article proposes a new hybrid method to detect and classify stomach diseases using endoscopy videos. The proposed methodology comprises seven significant steps: data acquisition, preprocessing of data, transfer learning of deep models, feature extraction, feature selection, hybridization, and classification. We selected two different CNN models (VGG19 and Alexnet) to extract features. We applied transfer learning techniques before using them as feature extractors. We used a genetic algorithm (GA) in feature selection, due to its adaptive nature. We fused selected features of both models using a serial-based approach. Finally, the best features were provided to multiple machine learning classifiers for detection and classification. The proposed approach was evaluated on a personally collected dataset of five classes, including gastritis, ulcer, esophagitis, bleeding, and healthy. We observed that the proposed technique performed superbly on Cubic SVM with 99.8% accuracy. For the authenticity of the proposed technique, we considered these statistical measures: classification accuracy, recall, precision, False Negative Rate (FNR), Area Under the Curve (AUC), and time. In addition, we provided a fair state-of-the-art comparison of our proposed technique with existing techniques that proves its worthiness.

show abstract

Computer-Aided Diagnosis System for Detection of Stomach Cancer with Image Processing Techniques

Cited by 26 publications

References 16 publications

Application of machine learning in the diagnosis of gastric cancer based on noninvasive characteristics

Application of machine learning in the diagnosis of gastric cancer based on noninvasive characteristics

Use of a Four-miRNA Panel as a Biomarker for the Diagnosis of Stomach Adenocarcinoma

Hybrid Deep Learning Model for Endoscopic Lesion Detection and Classification Using Endoscopy Videos

Contact Info

Product

Resources

About