Optimisation and evaluation of the random forest model in the efficacy prediction of chemoradiotherapy for advanced cervical cancer based on radiomics signature from high-resolution T2 weighted images

Computed tomography-based radiomics modeling to predict patient overall survival in cervical cancer with intensity-modulated radiotherapy combined with concurrent chemotherapy

ObjectiveThe objective of this study was to develop a predictive model combining radiomic characteristics and clinical features to forecast overall survival in cervical cancer patients treated with intensity-modulated radiotherapy and concurrent chemotherapy.MethodsIn this retrospective observational study, 159 patients were divided into a training group (n = 95) and a validation group (n = 64). Radiomic characteristics were extracted from contrast-enhanced computed tomography scans. The least absolute shrinkage and selection operator regression analysis was used to filter the extracted radiomic characteristics and reduce the dimensionality of the data. A radiomic score was calculated from the selected features, and multivariate Cox regression models were established to analyze overall survival. A nomogram combining radiomic score and clinical features was developed, and its reliability was assessed using the area under the receiver operating characteristic curve.ResultsFour radiomic characteristics and two clinical features were extracted for overall survival analysis. A nomogram combining these factors was developed and validated, showing good performance with a high C-index. Patients were categorized as low-risk or high-risk for overall survival based on a cut-off value.ConclusionsOur model combining computed tomography-extracted radiomic characteristics and clinical features shows good potential for evaluating overall survival in cervical cancer patients treated with intensity-modulated radiotherapy and concurrent chemotherapy.

Development of a radiomic model for cervical cancer staging based on pathologically verified, retrospective metastatic lymph node data

BACKGROUND

Cervical cancer is a major cause of morbidity and mortality among gynecological malignancies. Diagnostic imaging of lymph node (LN) metastasis for prognosis and staging is used; however, the accuracy in classifying the stage needs to improve.

PURPOSE

To examine the accuracy of AI-based radiomics in diagnosis, prognosis assessment and predicting the diagnostic value of radiomics for pelvic LN metastasis in cervical cancer patients.

MATERIAL AND METHODS

The study included 118 female patients with 660 LNs and 118 merged LNs. Four imaging histology models-decision tree, random forest, logistic regression, and support vector machine (SVM)-were created in this study. The imaging histology features were extracted from both the independent and merged LN groups. The AUC values for the test sets and the training sets of the four imaging histology models were compared for the independent LN group and the merged LN group. The DeLong test was used to compare the models.

RESULT

The imaging histology prediction model developed in the merged LN group outperformed the independent LN group in terms of test set AUC (0.668 vs. 0.535 for decision tree, 0.841 vs. 0.627 for logistic regression, 0.785 vs. 0.637 for random forest, 0.85 vs. 0.648 for SVM) and accuracy (0.754 vs. 0.676 for decision tree, 0.780 vs. 0.671 for random forest, 0.848 vs. 0.685 for logistic regression, 0.822 vs. 0.657 for SVM).

CONCLUSION

The constructed SVM imaging histology model for the merged LN group might be advantageous in predicting pelvic LN metastasis in cervical cancer.

Comprehensive assessment of postoperative recurrence and survival in patients with cervical cancer

BACKGROUND

The prediction of postoperative recurrence and survival in cervical cancer patients has been a major clinical challenge. The combination of clinical parameters, inflammatory markers, intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI), and MRI-derived radiomics is expected to support the prediction of recurrence-free survival (RFS), disease-free survival (DFS), tumor-specific survival (CSS), and overall survival (OS) of cervical cancer patients after surgery.

METHODS

A retrospective analysis of 181 cervical cancer patients with continuous follow-up was completed. The parameters of IVIM-DWI and radiomics were measured, analyzed, and screened. The LASSO regularization was used to calculate the radiomics score (Rad-score). Multivariate Cox regression analysis was used to construct nomogram models for predicting postoperative RFS, DFS, CSS, and OS in cervical cancer patients, with internal and external validation.

RESULTS

Clinical stage, parametrial infiltration, internal irradiation, D-value, and Rad-score were independent prognostic factors for RFS; Squamous cell carcinoma antigen, internal irradiation, D-value, f-value and Rad-score were independent prognostic factors for DFS; Maximum tumor diameter, lymph node metastasis, platelets, D-value and Rad-score were independent prognostic factors for CSS; Lymph node metastasis, systemic inflammation response index, D-value and Rad-score were independent prognostic factors for OS. The AUCs of each model predicting RFS, DFS, CSS, and OS at 1, 3, and 5 years were 0.985, 0.929, 0.910 and 0.833, 0.818, 0.816 and 0.832, 0.863, 0.891 and 0.804, 0.812, 0.870, respectively.

CONCLUSIONS

Nomograms based on clinical and imaging parameters showed high clinical value in predicting postoperative RFS, DFS, CSS, and OS of cervical cancer patients and can be used as prognostic markers.

Rapid detection of liver metastasis risk in colorectal cancer patients through blood test indicators

Introduction

Colorectal cancer (CRC) is one of the most common malignancies, with liver metastasis being its most common form of metastasis. The diagnosis of colorectal cancer liver metastasis (CRCLM) mainly relies on imaging techniques and puncture biopsy techniques, but there is no simple and quick early diagnosisof CRCLM.

Methods

This study aims to develop a method for rapidly detecting the risk of liver metastasis in CRC patients through blood test indicators based on machine learning (ML) techniques, thereby improving treatment outcomes. To achieve this, blood test indicators from 246 CRC patients and 256 CRCLM patients were collected and analyzed, including routine blood tests, liver function tests, electrolyte tests, renal function tests, glucose determination, cardiac enzyme profiles, blood lipids, and tumor markers. Six commonly used ML models were used for CRC and CRCLM classification and optimized by using a feature selection strategy.

Results

The results showed that AdaBoost algorithm can achieve the highest accuracy of 89.3% among the six models, which improved to 91.1% after feature selection strategy, resulting with 20 key markers.

Conclusions

The results demonstrate that the combination of machine learning techniques with blood markers is feasible and effective for the rapid diagnosis of CRCLM, significantly im-proving diagnostic ac-curacy and patient prognosis.

Wavelet radiomics features from multiphase CT images for screening hepatocellular carcinoma: analysis and comparison

Early detection of liver malignancy based on medical image analysis plays a crucial role in patient prognosis and personalized treatment. This task, however, is challenging due to several factors, including medical data scarcity and limited training samples. This paper presents a study of three important aspects of radiomics feature from multiphase computed tomography (CT) for classifying hepatocellular carcinoma (HCC) and other focal liver lesions: wavelet-transformed feature extraction, relevant feature selection, and radiomics features-based classification under the inadequate training samples. Our analysis shows that combining radiomics features extracted from the wavelet and original CT domains enhance the classification performance significantly, compared with using those extracted from the wavelet or original domain only. To facilitate the multi-domain and multiphase radiomics feature combination, we introduce a logistic sparsity-based model for feature selection with Bayesian optimization and find that the proposed model yields more discriminative and relevant features than several existing methods, including filter-based, wrapper-based, or other model-based techniques. In addition, we present analysis and performance comparison with several recent deep convolutional neural network (CNN)-based feature models proposed for hepatic lesion diagnosis. The results show that under the inadequate data scenario, the proposed wavelet radiomics feature model produces comparable, if not higher, performance metrics than the CNN-based feature models in terms of area under the curve.

Prediction of therapeutic response of unresectable hepatocellular carcinoma to hepatic arterial infusion chemotherapy based on pretherapeutic MRI radiomics and Albumin-Bilirubin score

PURPOSE

To construct and validate a combined nomogram model based on magnetic resonance imaging (MRI) radiomics and Albumin-Bilirubin (ALBI) score to predict therapeutic response in unresectable hepatocellular carcinoma (HCC) patients treated with hepatic arterial infusion chemotherapy (HAIC).

METHODS

The retrospective study was conducted on 112 unresectable HCC patients who underwent pretherapeutic MRI examinations. Patients were randomly divided into training (n = 79) and validation cohorts (n = 33). A total of 396 radiomics features were extracted from the volume of interest of the primary lesion by the Artificial Kit software. The least absolute shrinkage and selection operator (LASSO) regression was applied to identify optimal radiomic features. After feature selection, three models, including the clinical, radiomics, and combined models, were developed to predict the non-response of unresectable HCC to HAIC treatment. The performance of these models was evaluated by the receiver operating characteristic curve. According to the most efficient model, a nomogram was established, and the performance of which was also assessed by calibration curve and decision curve analysis. Kaplan-Meier curve and log-rank test were performed to evaluate the Progression-free survival (PFS).

RESULTS

Using the LASSO regression, we ultimately selected three radiomics features from T2-weighted images to construct the radiomics score (Radscore). Only the ALBI score was an independent factor associated with non-response in the clinical model (P = 0.033). The combined model, which included the ALBI score and Radscore, achieved better performance in the prediction of non-response, with an AUC of 0.79 (95% CI 0.68-0.90) and 0.75 (95% CI 0.58-0.92) in the training and validation cohorts, respectively. The nomogram based on the combined model also had good discrimination and calibration (P = 0.519 for the training cohort and P = 0.389 for the validation cohort). The Kaplan-Meier analysis also demonstrate that the high-score patients had significantly shorter PFS than the low-score patients (P = 0.031) in the combined model, with median PFS 6.0 vs 9.0 months.

CONCLUSION

The nomogram based on the combined model consisting of MRI radiomics and ALBI score could be used as a biomarker to predict the therapeutic response of unresectable HCC after HAIC.

Evaluating Histological Subtypes Classification of Primary Lung Cancers on Unenhanced Computed Tomography Based on Random Forest Model

Lung cancer is the leading cause of cancer-related death in many countries, and an accurate histopathological diagnosis is of great importance in subsequent treatment. The aim of this study was to establish the random forest (RF) model based on radiomic features to automatically classify and predict lung adenocarcinoma (ADC), lung squamous cell carcinoma (SCC), and small cell lung cancer (SCLC) on unenhanced computed tomography (CT) images. Eight hundred and fifty-two patients (mean age: 61.4, range: 29-87, male/female: 536/316) with preoperative unenhanced CT and postoperative histopathologically confirmed primary lung cancers, including 525 patients with ADC, 161 patients with SCC, and 166 patients with SCLC, were included in this retrospective study. Radiomic features were extracted, selected, and then used to establish the RF classification model to analyse and classify primary lung cancers into three subtypes, including ADC, SCC, and SCLC according to histopathological results. The training (446 ADC, 137 SCC, and 141 SCLC) and testing cohorts (79 ADC, 24 SCC, and 25 SCLC) accounted for 85% and 15% of the whole datasets, respectively. The prediction performance of the RF classification model was evaluated by F1 scores and the receiver operating characteristic (ROC) curve. On the testing cohort, the areas under the ROC curve (AUC) of the RF model in classifying ADC, SCC, and SCLC were 0.74, 0.77, and 0.88, respectively. The F1 scores achieved 0.80, 0.40, and 0.73 in ADC, SCC, and SCLC, respectively, and the weighted average F1 score was 0.71. In addition, for the RF classification model, the precisions were 0.72, 0.64, and 0.70; the recalls were 0.86, 0.29, and 0.76; and the specificities were 0.55, 0.96, and 0.92 in ADC, SCC, and SCLC. The primary lung cancers were feasibly and effectively classified into ADC, SCC, and SCLC based on the combination of RF classification model and radiomic features, which has the potential for noninvasive predicting histological subtypes of primary lung cancers.

Recurrence risk stratification for locally advanced cervical cancer using multi-modality transformer network

Objectives

Recurrence risk evaluation is clinically significant for patients with locally advanced cervical cancer (LACC). We investigated the ability of transformer network in recurrence risk stratification of LACC based on computed tomography (CT) and magnetic resonance (MR) images.

Methods

A total of 104 patients with pathologically diagnosed LACC between July 2017 and December 2021 were enrolled in this study. All patients underwent CT and MR scanning, and their recurrence status was identified by the biopsy. We randomly divided patients into training cohort (48 cases, non-recurrence: recurrence = 37: 11), validation cohort (21 cases, non-recurrence: recurrence = 16: 5), and testing cohort (35 cases, non-recurrence: recurrence = 27: 8), upon which we extracted 1989, 882 and 315 patches for model's development, validation and evaluation, respectively. The transformer network consisted of three modality fusion modules to extract multi-modality and multi-scale information, and a fully-connected module to perform recurrence risk prediction. The model's prediction performance was assessed by six metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, f1-score, sensitivity, specificity and precision. Univariate analysis with F-test and T-test were conducted for statistical analysis.

Results

The proposed transformer network is superior to conventional radiomics methods and other deep learning networks in both training, validation and testing cohorts. Particularly, in testing cohort, the transformer network achieved the highest AUC of 0.819 ± 0.038, while four conventional radiomics methods and two deep learning networks got the AUCs of 0.680 ± 0.050, 0.720 ± 0.068, 0.777 ± 0.048, 0.691 ± 0.103, 0.743 ± 0.022 and 0.733 ± 0.027, respectively.

Conclusions

The multi-modality transformer network showed promising performance in recurrence risk stratification of LACC and may be used as an effective tool to help clinicians make clinical decisions.

Intracavitary brachytherapy with additional Heyman capsules in the treatment of cervical cancer

PURPOSE

Brachytherapy is a mandatory component of primary radiochemotherapy in cervical cancer. The dose can be applied with a traditional intracavitary approach (IC alone) or with multiple catheter brachytherapy to optimize dose distribution in an individual concept. We therefore evaluated whether the utilization of a tandem-ring applicator plus additional intracavitary applicators (add IC) provides an advantage over the traditional IC alone approach, as this method is less time consuming and less invasive compared to a combined intracavitary/interstitial brachytherapy.

METHODS

Twenty three procedures of intracavitary brachytherapy for cervical cancer with additional intracavitary applicators performed in seven patients treated between 2016 and 2018 in our institution were included in this study. Plans were optimized for D90 HR-CTV with and without the utilization of the additional applicators and compared by statistical analysis.

RESULTS

D90 for HR-CTV was 5.71 Gy (±1.17 Gy) for fractions optimized with add IC approach and 5.29 Gy (±1.24 Gy) for fractions without additional applicators (p < 0.01). This translates to a calculated mean EQD2 HR-CTV D90 of 80.72 Gy (±8.34 Gy) compared to 77.84 Gy (±8.49 Gy) after external beam therapy and four fractions of brachytherapy for add IC and IC alone, respectively (p < 0.01). The predictive value of improved coverage of HR-CTV in the first fraction was high.

CONCLUSION

In a subgroup of cases, the addition of intracavitary Heyman capsules can be an alternative to interstitial brachytherapy to improve the plan quality compared to standard IC alone brachytherapy. The benefit from the addition of applicators in the first fraction is predictive for the following fractions.

MRI-Based Radiomics Models to Discriminate Hepatocellular Carcinoma and Non-Hepatocellular Carcinoma in LR-M According to LI-RADS Version 2018

Differentiating hepatocellular carcinoma (HCC) from other primary liver malignancies in the Liver Imaging Reporting and Data System (LI-RADS) M (LR-M) tumours noninvasively is critical for patient treatment options, but visual evaluation based on medical images is a very challenging task. This study aimed to evaluate whether magnetic resonance imaging (MRI) models based on radiomics features could further improve the ability to classify LR-M tumour subtypes. A total of 102 liver tumours were defined as LR-M by two radiologists based on LI-RADS and were confirmed to be HCC (n = 31) and non-HCC (n = 71) by surgery. A radiomics signature was constructed based on reproducible features using the max-relevance and min-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) logistic regression algorithms with tenfold cross-validation. Logistic regression modelling was applied to establish different models based on T2-weighted imaging (T2WI), arterial phase (AP), portal vein phase (PVP), and combined models. These models were verified independently in the validation cohort. The area under the curve (AUC) of the models based on T2WI, AP, PVP, T2WI + AP, T2WI + PVP, AP + PVP, and T2WI + AP + PVP were 0.768, 0.838, 0.778, 0.880, 0.818, 0.832, and 0.884, respectively. The combined model based on T2WI + AP + PVP showed the best performance in the training cohort and validation cohort. The discrimination efficiency of each radiomics model was significantly better than that of junior radiologists’ visual assessment (p < 0.05; Delong). Therefore, the MRI-based radiomics models had a good ability to discriminate between HCC and non-HCC in LR-M tumours, providing more options to improve the accuracy of LI-RADS classification.

Development of a random forest model for hypotension prediction after anesthesia induction for cardiac surgery

BACKGROUND

Hypotension after the induction of anesthesia is known to be associated with various adverse events. The involvement of a series of factors makes the prediction of hypotension during anesthesia quite challenging.

AIM

To explore the ability and effectiveness of a random forest (RF) model in the prediction of post-induction hypotension (PIH) in patients undergoing cardiac surgery.

METHODS

Patient information was obtained from the electronic health records of the Second Affiliated Hospital of Hainan Medical University. The study included patients, ≥ 18 years of age, who underwent cardiac surgery from December 2007 to January 2018. An RF algorithm, which is a supervised machine learning technique, was employed to predict PIH. Model performance was assessed by the area under the curve (AUC) of the receiver operating characteristic. Mean decrease in the Gini index was used to rank various features based on their importance.

RESULTS

Of the 3030 patients included in the study, 1578 (52.1%) experienced hypotension after the induction of anesthesia. The RF model performed effectively, with an AUC of 0.843 (0.808-0.877) and identified mean blood pressure as the most important predictor of PIH after anesthesia. Age and body mass index also had a significant impact.

CONCLUSION

The generated RF model had high discrimination ability for the identification of individuals at high risk for a hypotensive event during cardiac surgery. The study results highlighted that machine learning tools confer unique advantages for the prediction of adverse post-anesthesia events.

Radiomic Score as a Potential Imaging Biomarker for Predicting Survival in Patients With Cervical Cancer

OBJECTIVES

Accurate prediction of prognosis will help adjust or optimize the treatment of cervical cancer and benefit the patients. We aimed to investigate the incremental value of radiomics when added to the FIGO stage in predicting overall survival (OS) in patients with cervical cancer.

METHODS

This retrospective study included 106 patients with cervical cancer (FIGO stage IB1-IVa) between October 2017 and May 2019. Patients were randomly divided into a training cohort (n = 74) and validation cohort (n = 32). All patients underwent contrast-enhanced computed tomography (CT) prior to treatment. The ITK-SNAP software was used to delineate the region of interest on pre-treatment standard-of-care CT scans. We extracted 792 two-dimensional radiomic features by the Analysis Kit (AK) software. Pearson correlation coefficient analysis and Relief were used to detect the most discriminatory features. The radiomic signature (i.e., Radscore) was constructed via Adaboost with Leave-one-out cross-validation. Prognostic models were built by Cox regression model using Akaike information criterion (AIC) as the stopping rule. A nomogram was established to individually predict the OS of patients. Patients were then stratified into high- and low-risk groups according to the Youden index. Kaplan-Meier curves were used to compare the survival difference between the high- and low-risk groups.

RESULTS

Six textural features were identified, including one gray-level co-occurrence matrix feature and five gray-level run-length matrix features. Only the FIGO stage and Radscore were independent risk factors associated with OS (p < 0.05). The C-index of the FIGO stage in the training and validation cohorts was 0.703 (95% CI: 0.572-0.834) and 0.700 (95% CI: 0.526-0.874), respectively. Correspondingly, the C-index of Radscore was 0.794 (95% CI: 0.707-0.880) and 0.754 (95% CI: 0.623-0.885). The incorporation of the FIGO stage and Radscore achieved better performance, with a C-index of 0.830 (95% CI: 0.738-0.922) and 0.772 (95% CI: 0.615-0.929), respectively. The nomogram based on the FIGO stage and Radscore could individually predict the OS probability with good discrimination and calibration. The high-risk patients had shorter OS compared with the low-risk patients (p < 0.05).

CONCLUSION

Radiomics has the potential for noninvasive risk stratification and may improve the prediction of OS in patients with cervical cancer when added to the FIGO stage.

Structured Reporting of Computed Tomography in the Staging of Neuroendocrine Neoplasms: A Delphi Consensus Proposal

BACKGROUND

Structured reporting (SR) in radiology is becoming increasingly necessary and has been recognized recently by major scientific societies. This study aims to build structured CT-based reports in Neuroendocrine Neoplasms during the staging phase in order to improve communication between the radiologist and members of multidisciplinary teams.

MATERIALS AND METHODS

A panel of expert radiologists, members of the Italian Society of Medical and Interventional Radiology, was established. A Modified Delphi process was used to develop the SR and to assess a level of agreement for all report sections. Cronbach's alpha (Cα) correlation coefficient was used to assess internal consistency for each section and to measure quality analysis according to the average inter-item correlation.

RESULTS

The final SR version was built by including n=16 items in the "Patient Clinical Data" section, n=13 items in the "Clinical Evaluation" section, n=8 items in the "Imaging Protocol" section, and n=17 items in the "Report" section. Overall, 54 items were included in the final version of the SR. Both in the first and second round, all sections received more than a good rating: a mean value of 4.7 and range of 4.2-5.0 in the first round and a mean value 4.9 and range of 4.9-5 in the second round. In the first round, the Cα correlation coefficient was a poor 0.57: the overall mean score of the experts and the sum of scores for the structured report were 4.7 (range 1-5) and 728 (mean value 52.00 and standard deviation 2.83), respectively. In the second round, the Cα correlation coefficient was a good 0.82: the overall mean score of the experts and the sum of scores for the structured report were 4.9 (range 4-5) and 760 (mean value 54.29 and standard deviation 1.64), respectively.

CONCLUSIONS

The present SR, based on a multi-round consensus-building Delphi exercise following in-depth discussion between expert radiologists in gastro-enteric and oncological imaging, derived from a multidisciplinary agreement between a radiologist, medical oncologist and surgeon in order to obtain the most appropriate communication tool for referring physicians.