Dataset Information

A New Classification of Benign, Premalignant, and Malignant Endometrial Tissues Using Machine Learning Applied to 1413 Candidate Variables.

ABSTRACT: Benign normal (NL), premalignant (endometrial intraepithelial neoplasia, EIN) and malignant (cancer, EMCA) endometria must be precisely distinguished for optimal management. EIN was objectively defined previously as a regression model incorporating manually traced histologic variables to predict clonal growth and cancer outcomes. Results from this early computational study were used to revise subjective endometrial precancer diagnostic criteria currently in use. We here use automated feature segmentation and updated machine learning algorithms to develop a new classification algorithm. Endometrial tissue from 148 patients was randomly separated into 72-patient training and 76-patient validation cohorts encompassing all 3 diagnostic classes. We applied image analysis software to keratin stained endometrial tissues to automatically segment whole-slide digital images into epithelium, cells, and nuclei and extract corresponding variables. A total of 1413 variables were culled to 75 based on random forest classification performance in a 3-group (NL, EIN, EMCA) model. This algorithm correctly classifies cases with 3-class error rates of 0.04 (training set) and 0.058 (validation set); and 2-class (NL vs. EIN+EMCA) error rate of 0.016 (training set) and 0 (validation set). The 4 most heavily weighted variables are surrogates of those previously identified in manual-segmentation machine learning studies (stromal and epithelial area percentages, and normalized epithelial surface lengths). Lesser weighted predictors include gland and lumen axis lengths and ratios, and individual cell measures. Automated image analysis and random forest classification algorithms can classify normal, premalignant, and malignant endometrial tissues. Highest predictive variables overlap with those discovered independently in early models based on manual segmentation.

SUBMITTER: Downing MJ

PROVIDER: S-EPMC6884662 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesTo develop and validate machine learning models to distinguish between benign and malignant bone lesions and compare the performance to radiologists.MethodsIn 880 patients (age 33.1 ± 19.4 years, 395 women) diagnosed with malignant (n = 213, 24.2%) or benign (n = 667, 75.8%) primary bone tumors, preoperative radiographs were obtained, and the diagnosis was established using histopathology. Data was split 70%/15%/15% for training, validation, and internal testing. Additionally, 96 patients from another institution were obtained for external testing. Machine learning models were developed and validated using radiomic features and demographic information. The performance of each model was evaluated on the test sets for accuracy, area under the curve (AUC) from receiver operating characteristics, sensitivity, and specificity. For comparison, the external test set was evaluated by two radiology residents and two radiologists who specialized in musculoskeletal tumor imaging.ResultsThe best machine learning model was based on an artificial neural network (ANN) combining both radiomic and demographic information achieving 80% and 75% accuracy at 75% and 90% sensitivity with 0.79 and 0.90 AUC on the internal and external test set, respectively. In comparison, the radiology residents achieved 71% and 65% accuracy at 61% and 35% sensitivity while the radiologists specialized in musculoskeletal tumor imaging achieved an 84% and 83% accuracy at 90% and 81% sensitivity, respectively.ConclusionsAn ANN combining radiomic features and demographic information showed the best performance in distinguishing between benign and malignant bone lesions. The model showed lower accuracy compared to specialized radiologists, while accuracy was higher or similar compared to residents.Key points• The developed machine learning model could differentiate benign from malignant bone tumors using radiography with an AUC of 0.90 on the external test set. • Machine learning models that used radiomic features or demographic information alone performed worse than those that used both radiomic features and demographic information as input, highlighting the importance of building comprehensive machine learning models. • An artificial neural network that combined both radiomic and demographic information achieved the best performance and its performance was compared to radiology readers on an external test set.

Project description:Intra-tumor heterogeneity (ITH) has been studied at the morphologic, genomic, and transcriptomic level, but not proteomic level. Recent advances in mass spectrometric (MS) proteome quantification techniques, exemplified by SWATH-MS, a massively parallel targeting method, now also support precise quantitative proteomic comparisons across multiple samples, thus identifying molecular and implied functional differences. Here we used SWATH-MS to analyze the proteome profiles of a set of fresh-frozen prostate tissue samples derived from radical prostatectomy specimens. A high confidence set of 1,906 proteins were consistently quantified across 60 biopsy-level tissue samples from three prostatectomy patients, each consisting of 1.0 mm punch biopsies from histologically malignant (acinar and ductal adenocarcinoma) and matching benign prostatic hyperplasia tissues. The quantitative protein profiles allowed independent quantification of the degree of intra-tumor heterogeneity for each protein in benign and malignant tissues. We found that while majority of the proteins showed comparably low intra-tumor variability, 122 proteins were highly variable in malignant and/or matching benign tissues. We observed that proteins that varied between patients or tissue types also tended to be highly variable within prostate tissues, suggesting that these variability patterns will be a critical selection criterion in future protein biomarker studies. The data also permitted investigation of the heterogeneity of multiple biochemical pathways. The high variability of several of the pathways, including Glypican-1 network, alpha-linolenic acid metabolism and celecoxib pathway, explained contradictory results regarding them in the literature. In conclusion, we demonstrated a methodology for investigating proteomic intra-tumor heterogeneity from biopsy-level tissue samples, and quantified the degree of intra-tumor heterogeneity of 1,906 proteins in prostate tumors. The method and data presented here have advanced our understanding of tumor biology and offered critical insights for future biomarker development.

Dataset Information

A New Classification of Benign, Premalignant, and Malignant Endometrial Tissues Using Machine Learning Applied to 1413 Candidate Variables.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets