Rapid identification of human ovarian cancer in second harmonic generation images using radiomics feature analyses and tree-based pipeline optimization tool

Ovarian cancer identification technology based on deep learning and second harmonic generation imaging

Ovarian cancer is among the most common gynecological cancers and the eighth leading cause of cancer-related deaths among women worldwide. Surgery is among the most important options for cancer treatment. During surgery, a biopsy is generally required to screen for lesions; however, traditional case examinations are time consuming and laborious and require extensive experience and knowledge from pathologists. Therefore, this study proposes a simple, fast, and label-free ovarian cancer diagnosis method that combines second harmonic generation (SHG) imaging and deep learning. Unstained fresh human ovarian tissues were subjected to SHG imaging and accurately characterized using the Pyramid Vision Transformer V2 (PVTv2) model. The results showed that the SHG imaged collagen fibers could quantify ovarian cancer. In addition, the PVTv2 model could accurately differentiate the 3240 SHG images obtained from our imaging collection into benign, normal, and malignant images, with a final accuracy of 98.4%. These results demonstrate the great potential of SHG imaging techniques combined with deep learning models for diagnosing the diseased ovarian tissues.

CT-Based Radiomics and Machine Learning for Differentiating Benign, Borderline, and Early-Stage Malignant Ovarian Tumors

To explore the value of CT-based radiomics model in the differential diagnosis of benign ovarian tumors (BeOTs), borderline ovarian tumors (BOTs), and early malignant ovarian tumors (eMOTs). The retrospective research was conducted with pathologically confirmed 258 ovarian tumor patients from January 2014 to February 2021. The patients were randomly allocated to a training cohort (n = 198) and a test cohort (n = 60). By providing a three-dimensional (3D) characterization of the volume of interest (VOI) at the maximum level of images, 4238 radiomic features were extracted from the VOI per patient. The Wilcoxon-Mann-Whitney (WMW) test, least absolute shrinkage and selection operator (LASSO), and support vector machine (SVM) were employed to select the radiomic features. Five machine learning (ML) algorithms were applied to construct three-class diagnostic models. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the radiomics models. The test cohort was used to verify the generalization ability of the radiomics models. The receiver-operating characteristic (ROC) was used to evaluate diagnostic performance of radiomics model. Global and discrimination performance of five models was evaluated by average area under the ROC curve (AUC). The average ROC indicated that random forest (RF) diagnostic model in training cohort demonstrated the best diagnostic performance (micro/macro average AUC, 0.98/0.99), which was then confirmed with by LOOCV (micro/macro average AUC, 0.89/0.88) and external validation (test cohort) (micro/macro average AUC, 0.81/0.79). Our proposed CT-based radiomics diagnostic models may effectively assist in preoperatively differentiating BeOTs, BOTs, and eMOTs.

Association of collagen deep learning classifier with prognosis and chemotherapy benefits in stage II-III colon cancer

The current tumor-node-metastasis staging system does not provide sufficient prognostic prediction or adjuvant chemotherapy benefit information for stage II-III colon cancer (CC) patients. Collagen in the tumor microenvironment affects the biological behaviors and chemotherapy response of cancer cells. Hence, in this study, we proposed a collagen deep learning (collagen^DL) classifier based on the 50-layer residual network model for predicting disease-free survival (DFS) and overall survival (OS). The collagen^DL classifier was significantly associated with DFS and OS (P < 0.001). The collagen^DL nomogram, integrating the collagen^DL classifier and three clinicopathologic predictors, improved the prediction performance, which showed satisfactory discrimination and calibration. These results were independently validated in the internal and external validation cohorts. In addition, high-risk stage II and III CC patients with high-collagen^DL classifier, rather than low-collagen^DL classifier, exhibited a favorable response to adjuvant chemotherapy. In conclusion, the collagen^DL classifier could predict prognosis and adjuvant chemotherapy benefits in stage II-III CC patients.

Predicting Hepatotoxicity Associated with Low-Dose Methotrexate Using Machine Learning

An accurate prediction of the hepatotoxicity associated with low-dose methotrexate can provide evidence for a reasonable treatment choice. This study aimed to develop a machine learning-based prediction model to predict hepatotoxicity associated with low-dose methotrexate and explore the associated risk factors. Eligible patients with immune system disorders, who received low-dose methotrexate at West China Hospital between 1 January 2018, and 31 December 2019, were enrolled. A retrospective review of the included patients was conducted. Risk factors were selected from multiple patient characteristics, including demographics, admissions, and treatments. Eight algorithms, including eXtreme Gradient Boosting (XGBoost), AdaBoost, CatBoost, Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), Tree-based Pipeline Optimization Tool (TPOT), Random Forest (RF), and Artificial Neural Network (ANN), were used to establish the prediction model. A total of 782 patients were included, and hepatotoxicity was detected in 35.68% (279/782) of the patients. The Random Forest model with the best predictive capacity was chosen to establish the prediction model (receiver operating characteristic curve 0.97, accuracy 64.33%, precision 50.00%, recall 32.14%, and F1 39.13%). Among the 15 risk factors, the highest score was a body mass index of 0.237, followed by age (0.198), the number of drugs (0.151), and the number of comorbidities (0.144). These factors demonstrated their importance in predicting hepatotoxicity associated with low-dose methotrexate. Using machine learning, this novel study established a predictive model for low-dose methotrexate-related hepatotoxicity. The model can improve medication safety in patients taking methotrexate in clinical practice.

Post-operative anastomotic leakage and collagen changes in patients with rectal cancer undergoing neoadjuvant chemotherapy vs chemoradiotherapy

Background

A significant difference in the anastomotic leakage (AL) rate has been observed between patients with locally advanced rectal cancer who have undergone preoperative chemotherapy and those undergoing preoperative chemoradiotherapy. This study aimed to quantitatively analyse collagen structural changes caused by preoperative chemoradiotherapy and illuminate the relationship between collagen changes and AL.

Methods

Anastomotic distal and proximal "doughnut" specimens from the Sixth Affiliated Hospital of Sun Yat-sen University (Guangzhou, China) were quantitatively assessed for collagen structural changes between patients with and without preoperative radiotherapy using multiphoton imaging. Then, patients treated with preoperative chemoradiotherapy were used as a training cohort to construct an AL-SVM classifier by the Mann-Whitney U test and support vector machine (SVM). An independent test cohort from the Fujian Province Cancer Hospital (Fuzhou, China) was used to validate the AL-SVM classifier.

Results

A total of 207 patients were included from the Sixth Affiliated Hospital of Sun Yat-sen University. The AL rate in the preoperative chemoradiotherapy group (n = 107) was significantly higher than that in the preoperative chemotherapy group (n = 100) (21.5% vs 7.0%, P = 0.003). A fully quantitative analysis showed notable morphological and spatial distribution feature changes in collagen in the preoperative chemoradiotherapy group. Then, the patients who received preoperative chemoradiotherapy were used as a training cohort to construct the AL-SVM classifier based on five collagen features and the tumor distance from the anus. The AL-SVM classifier showed satisfactory discrimination and calibration with areas under the curve of 0.907 and 0.856 in the training and test cohorts, respectively.

Conclusions

The collagen structure may be notably altered by preoperative radiotherapy. The AL-SVM classifier was useful for the individualized prediction of AL in rectal cancer patients undergoing preoperative chemoradiotherapy.

Automatic Feature Construction Based on Genetic Programming for Survival Prediction in Lung Cancer Using CT Images

In the radiomics workflow, machine learning builds classification models from a set of input features. However, some features can be irrelevant and redundant, reducing the classification performance. This paper proposes using the Genetic Programming (GP) algorithm to automatically construct a reduced number of independent and relevant radiomic features. The proposed method is applied to patients affected by Non-Small Cell Lung Cancer (NSCLC) with pre-operative computed tomography (CT) images to predict the two-year survival by the use of linear classifiers. The model built using GP features is compared with benchmark models built using traditional features. The use of the GP algorithm increased classification performance: [Formula: see text] for the proposed model vs. [Formula: see text] and 0.64 for the benchmark models. Hence, the proposed approach better stratifies patients at high and low risk according to their overall postoperative survival time.

Association of the Collagen Signature with Pathological Complete Response in Rectal Cancer Patients

Collagen in the tumor microenvironment is recognized as a potential biomarker for predicting treatment response. This study investigated whether the collagen features are associated with pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients receiving neoadjuvant chemoradiotherapy (nCRT) and develop and validate a prediction model for individualized prediction of pCR. The prediction model was developed in a primary cohort (353 consecutive patients). In total, 142 collagen features were extracted from the multiphoton image of pretreatment biopsy, and the least absolute shrinkage and selection operator (Lasso) regression was applied for feature selection and collagen signature building. A nomogram was developed using multivariable analysis. The performance of the nomogram was assessed with respect to its discrimination, calibration, and clinical utility. An independent cohort (163 consecutive patients) was used to validate the model. The collagen signature comprised four collagen features significantly associated with pCR both in the primary and validation cohorts (p < 0.001). Predictors in the individualized prediction nomogram included the collagen signature and clinicopathological predictors. The nomogram showed good discrimination with area under the ROC curve (AUC) of 0.891 in the primary cohort and good calibration. Application of the nomogram in the validation cohort still gave good discrimination (AUC = 0.908) and good calibration. Decision curve analysis demonstrated that the nomogram was clinically useful. In conclusion, the collagen signature in the tumor microenvironment of pretreatment biopsy is significantly associated with pCR. The nomogram based on the collagen signature and clinicopathological predictors could be used for individualized prediction of pCR in LARC patients before nCRT.

Machine learning-based rapid diagnosis of human borderline ovarian cancer on second-harmonic generation images

Regarding growth pattern and cytological characteristics, borderline ovarian tumors fall between benign and malignant, but they tend to develop malignancy. Currently, it is difficult to accurately diagnose ovarian cancer using common medical imaging methods, and histopathological examination is routinely used to obtain a definitive diagnosis. However, such examination requires experienced pathologists, being labor-intensive, time-consuming, and possibly leading to interobserver bias. By using second-harmonic generation imaging and k-nearest neighbors classifier in conjunction with automated machine learning tree-based pipeline optimization tool, we developed a computer-aided diagnosis method to classify ovarian tissues as being malignant, benign, borderline, and normal, obtaining areas under the receiver operating characteristic curve of 1.00, 0.99, 0.98, and 0.97, respectively. These results suggest that diagnosis based on second-harmonic generation images and machine learning can support the rapid and accurate detection of ovarian cancer in clinical practice.

A Nomogram Based on a Collagen Feature Support Vector Machine for Predicting the Treatment Response to Neoadjuvant Chemoradiotherapy in Rectal Cancer Patients

BACKGROUND

The relationship between collagen features (CFs) in the tumor microenvironment and the treatment response to neoadjuvant chemoradiotherapy (nCRT) is still unknown. This study aimed to develop and validate a perdition model based on the CFs and clinicopathological characteristics to predict the treatment response to nCRT among locally advanced rectal cancer (LARC) patients.

METHODS

In this multicenter, retrospective analysis, 428 patients were included and randomly divided into a training cohort (299 patients) and validation cohort (129 patients) [7:3 ratio]. A total of 11 CFs were extracted from a multiphoton image of pretreatment biopsy, and a support vector machine (SVM) was then used to construct a CFs-SVM classifier. A prediction model was developed and presented with a nomogram using multivariable analysis. Further validation of the nomogram was performed in the validation cohort.

RESULTS

The CFs-SVM classifier, which integrated collagen area, straightness, and crosslink density, was significantly associated with treatment response. Predictors contained in the nomogram included the CFs-SVM classifier and clinicopathological characteristics by multivariable analysis. The CFs nomogram demonstrated good discrimination, with area under the receiver operating characteristic curves (AUROCs) of 0.834 in the training cohort and 0.854 in the validation cohort. Decision curve analysis indicated that the CFs nomogram was clinically useful. Moreover, compared with the traditional clinicopathological model, the CFs nomogram showed more powerful discrimination in determining the response to nCRT.

CONCLUSIONS

The CFs-SVM classifier based on CFs in the tumor microenvironment is associated with treatment response, and the CFs nomogram integrating the CFs-SVM classifier and clinicopathological characteristics is useful for individualized prediction of the treatment response to nCRT among LARC patients.

Radiomics and radiogenomics in ovarian cancer: a literature review

Ovarian cancer remains one of the most lethal gynecological cancers in the world despite extensive progress in the areas of chemotherapy and surgery. Many studies have postulated that this is because of the profound heterogeneity that underpins response to therapy and prognosis. Standard imaging evaluation using CT or MRI does not take into account this tumoral heterogeneity especially in advanced stages with peritoneal carcinomatosis. As such, newly emergent fields in the assessment of tumor heterogeneity have been proposed using radiomics to evaluate the whole tumor burden heterogeneity as opposed to single biopsy sampling. This review provides an overview of radiomics, radiogenomics, and proteomics and examines the use of these newly emergent fields in assessing tumor heterogeneity and its implications in ovarian cancer.

The clinical classification of patients with COVID-19 pneumonia was predicted by Radiomics using chest CT

In 2020, the new type of coronal pneumonitis became a pandemic in the world, and has firstly been reported in Wuhan, China. Chest CT is a vital component in the diagnostic algorithm for patients with suspected or confirmed COVID-19 infection. Therefore, it is necessary to conduct automatic and accurate detection of COVID-19 by chest CT.The clinical classification of patients with COVID-19 pneumonia was predicted by Radiomics using chest CT.From the COVID-19 cases in our institution, 136 moderate patients and 83 severe patients were screened, and their clinical and laboratory data on admission were collected for statistical analysis. Initial CT Radiomics were modeled by automatic machine learning, and diagnostic performance was evaluated according to AUC, TPR, TNR, PPV and NPV of the subjects. At the same time, the initial CT main features of the two groups were analyzed semi-quantitatively, and the results were statistically analyzed.There was a statistical difference in age between the moderate group and the severe group. The model cohort showed TPR 96.9%, TNR 99.1%, PPV98.4%, NPV98.2%, and AUC 0.98. The test cohort showed TPR 94.4%, TNR100%, PPV100%, NPV96.2%, and AUC 0.97. There was statistical difference between the two groups with grade 1 score (P = .001), the AUC of grade 1 score, grade 2 score, grade 3 score and CT score were 0.619, 0.519, 0.478 and 0.548, respectively.Radiomics' Auto ML model was built by CT image of initial COVID -19 pneumonia, and it proved to be effectively used to predict the clinical classification of COVID-19 pneumonia. CT features have limited ability to predict the clinical typing of Covid-19 pneumonia.