Machine learning based gray-level co-occurrence matrix early warning system enables accurate detection of colorectal cancer pelvic bone metastases on MRI

Abstract

ObjectiveThe mortality of colorectal cancer patients with pelvic bone metastasis is imminent, and timely diagnosis and intervention to improve the prognosis is particularly important. Therefore, this study aimed to build a bone metastasis prediction model based on Gray level Co-occurrence Matrix (GLCM) - based Score to guide clinical diagnosis and treatment.MethodsWe retrospectively included 614 patients with colorectal cancer who underwent pelvic multiparameter magnetic resonance image(MRI) from January 2015 to January 2022 in the gastrointestinal surgery department of Gezhouba Central Hospital of Sinopharm. GLCM-based Score and Machine learning algorithm, that is,artificial neural net7work model(ANNM), random forest model(RFM), decision tree model(DTM) and support vector machine model(SVMM) were used to build prediction model of bone metastasis in colorectal cancer patients. The effectiveness evaluation of each model mainly included decision curve analysis(DCA), area under the receiver operating characteristic (AUROC) curve and clinical influence curve(CIC).ResultsWe captured fourteen categories of radiomics data based on GLCM for variable screening of bone metastasis prediction models. Among them, Haralick_90, IV_0, IG_90, Haralick_30, CSV, Entropy and Haralick_45 were significantly related to the risk of bone metastasis, and were listed as candidate variables of machine learning prediction models. Among them, the prediction efficiency of RFM in combination with Haralick_90, Haralick_all, IV_0, IG_90, IG_0, Haralick_30, CSV, Entropy and Haralick_45 in training set and internal verification set was [AUC: 0.926,95% CI: 0.873-0.979] and [AUC: 0.919,95% CI: 0.868-0.970] respectively. The prediction efficiency of the other four types of prediction models was between [AUC: 0.716,95% CI: 0.663-0.769] and [AUC: 0.912,95% CI: 0.859-0.965].ConclusionThe automatic segmentation model based on diffusion-weighted imaging(DWI) using depth learning method can accurately segment the pelvic bone structure, and the subsequently established radiomics model can effectively detect bone metastases within the pelvic scope, especially the RFM algorithm, which can provide a new method for automatically evaluating the pelvic bone turnover of colorectal cancer patients.

Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis

“…While a majority of the papers utilized a modification of the U-Net segmentation algorithm, other alternative architectures included non-convolutional Artificial Neural Network models ( 41 ), voxel-wise classification ( 33 ), AdaBoost algorithms and Chan-Vese algorithms ( 37 ), CNN with bagging and boosting ( 44 ), and V-Net ( 34 , 65 ). These alternative algorithms achieved DSCs or AUCs above 0.7, which is on par with the median performance of the U-Net models.…”

Spatial assessments in texture analysis: what the radiologist needs to know

“…In oncologic imaging, radiomics analysis has shown great utility in evaluating features of intratumoral heterogeneity, which may correspondingly reflect tumor behavior (4, 5, 7-9, 11, 13, 14, 35, 47, 48). There is a growing body of literature to suggest that radiomics-based machine learning algorithms perform well with various classification tasks, including differentiating benign from malignant lesions, stratifying lesions by tumor grade, predicting risk of distant metastases, and predicting overall survival (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13). Additional work suggests that subtle differences in the underlying texture grayscale may also correlate well with tumoral genetic and phenotypic variations, furthering the case for potential future integrations of radiomics classifiers as risk stratification schema in prospective clinical workflows (31,35,49,50).…”

“…Quantitative assessments of imaging texture characteristics have been successfully applied to answer a variety of clinicallyrelevant queries ranging from lesion classification to disease prognostication, often in the form of radiomics-based machine learning decision classifiers (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13). While some approaches have previously relied on filtering of high-dimensionality data to identify the most contributory features or classes of features (14)(15)(16)(17), recent studies have demonstrated a subset of texture metrics well-equipped to detect regions of heterogeneity in the imaging grayscale (4,9) (Supplementary Table S1).…”

Refining Content-Based Segmentation for Prediction of Coffee Bean Quality

“…The CBIR method helps produce coffee beans that comply with the standardization requirements for defects. Several studies have been carried out, such as [3] [4] [5], which used the CBIR technique with 90 image data and a precession rate of 55.20%.In their research [3], they also use Arabica coffee bean samples in several regions in Indonesia, one of which is the coffee beans from South Kalimantan, North Sumatra, East Java, and West Java, as used in our works. Our experiments indicate that the achieved precision or accuracy stands at 85.4%, surpassing the levels observed in certain prior studies.…”