Radiomics models based on enhanced computed tomography to distinguish clear cell from non-clear cell renal cell carcinomas

Interpretable multiphasic CT-based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study

BACKGROUND

To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.

MATERIALS AND METHODS

In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.

RESULTS

A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The "original_shape_Flatness" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.

CONCLUSIONS

The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.

Radiomics-based machine learning approach for the prediction of grade and stage in upper urinary tract urothelial carcinoma: a step towards virtual biopsy

OBJECTIVES

Upper tract urothelial carcinoma (UTUC) is a rare, aggressive lesion, with early detection a key to its management. This study aimed to utilise computed tomographic urogram data to develop machine learning models for predicting tumour grading and staging in upper urothelial tract carcinoma patients and to compare these predictions with histopathological diagnosis used as reference standards.

METHODS

Protocol-based computed tomographic urogram data from 106 patients were obtained and visualised in 3D. Digital segmentation of the tumours was conducted by extracting textural radiomics features. They were further classified using 11 predictive models. The predicted grades and stages were compared to the histopathology of radical nephroureterectomy specimens.

RESULTS

Classifier models worked well in mining the radiomics data and delivered satisfactory predictive machine learning models. The multilayer panel showed 84% sensitivity and 93% specificity while predicting UTUC grades. The Logistic Regression model showed a sensitivity of 83% and a specificity of 76% while staging. Similarly, other classifier algorithms [e.g. Support Vector classifier (SVC)] provided a highly accurate prediction while grading UTUC compared to clinical features alone or ureteroscopic biopsy histopathology.

CONCLUSION

Data mining tools could handle medical imaging datasets from small (<2 cm) tumours for UTUC. The radiomics-based machine learning algorithms provide a potential tool to model tumour grading and staging with implications for clinical practice and the upgradation of current paradigms in cancer diagnostics.

CLINICAL RELEVANCE

Machine learning based on radiomics features can predict upper tract urothelial cancer grading and staging with significant improvement over ureteroscopic histopathology. The study showcased the prowess of such emerging tools in the set objectives with implications towards virtual biopsy.

Al-Atawi A, Alwageed HS, Mehmood G, Khan F, Innab N. Detection of renal cell hydronephrosis in ultrasound kidney images: a study on the efficacy of deep convolutional neural networks

In the realm of medical imaging, the early detection of kidney issues, particularly renal cell hydronephrosis, holds immense importance. Traditionally, the identification of such conditions within ultrasound images has relied on manual analysis, a labor-intensive and error-prone process. However, in recent years, the emergence of deep learning-based algorithms has paved the way for automation in this domain. This study aims to harness the power of deep learning models to autonomously detect renal cell hydronephrosis in ultrasound images taken in close proximity to the kidneys. State-of-the-art architectures, including VGG16, ResNet50, InceptionV3, and the innovative Novel DCNN, were put to the test and subjected to rigorous comparisons. The performance of each model was meticulously evaluated, employing metrics such as F1 score, accuracy, precision, and recall. The results paint a compelling picture. The Novel DCNN model outshines its peers, boasting an impressive accuracy rate of 99.8%. In the same arena, InceptionV3 achieved a notable 90% accuracy, ResNet50 secured 89%, and VGG16 reached 85%. These outcomes underscore the Novel DCNN's prowess in the realm of renal cell hydronephrosis detection within ultrasound images. Moreover, this study offers a detailed view of each model's performance through confusion matrices, shedding light on their abilities to categorize true positives, true negatives, false positives, and false negatives. In this regard, the Novel DCNN model exhibits remarkable proficiency, minimizing both false positives and false negatives. In conclusion, this research underscores the Novel DCNN model's supremacy in automating the detection of renal cell hydronephrosis in ultrasound images. With its exceptional accuracy and minimal error rates, this model stands as a promising tool for healthcare professionals, facilitating early-stage diagnosis and treatment. Furthermore, the model's convergence rate and accuracy hold potential for enhancement through further exploration, including testing on larger and more diverse datasets and investigating diverse optimization strategies.

Development and Validation of a Radiomics Nomogram for Liver Metastases Originating from Gastric and Colorectal Cancer

The origin of metastatic liver tumours (arising from gastric or colorectal sources) is closely linked to treatment choices and survival prospects. However, in some instances, the primary lesion remains elusive even after an exhaustive diagnostic investigation. Consequently, we have devised and validated a radiomics nomogram for ascertaining the primary origin of liver metastases stemming from gastric cancer (GCLMs) and colorectal cancer (CCLMs). This retrospective study encompassed patients diagnosed with either GCLMs or CCLMs, comprising a total of 277 GCLM cases and 278 CCLM cases. Radiomic characteristics were derived from venous phase computed tomography (CT) scans, and a radiomics signature (RS) was computed. Multivariable regression analysis demonstrated that gender (OR = 3.457; 95% CI: 2.102-5.684; p < 0.001), haemoglobin levels (OR = 0.976; 95% CI: 0.967-0.986; p < 0.001), carcinoembryonic antigen (CEA) levels (OR = 0.500; 95% CI: 0.307-0.814; p = 0.005), and RS (OR = 2.147; 95% CI: 1.127-4.091; p = 0.020) exhibited independent associations with GCLMs as compared to CCLMs. The nomogram, combining RS with clinical variables, demonstrated strong discriminatory power in both the training (AUC = 0.71) and validation (AUC = 0.78) cohorts. The calibration curve, decision curve analysis, and clinical impact curves revealed the clinical utility of this nomogram and substantiated its enhanced diagnostic performance.

Multi-phase-combined CECT radiomics models for Fuhrman grade prediction of clear cell renal cell carcinoma

Objective

This study aimed to evaluate the effectiveness of multi-phase-combined contrast-enhanced CT (CECT) radiomics methods for noninvasive Fuhrman grade prediction of clear cell renal cell carcinoma (ccRCC).

Methods

A total of 187 patients with four-phase CECT images were retrospectively enrolled and then were categorized into training cohort (n=126) and testing cohort (n=61). All patients were confirmed as ccRCC by histopathological reports. A total of 110 3D classical radiomics features were extracted from each phase of CECT for individual ccRCC lesion, and contrast-enhanced variation features were also calculated as derived radiomics features. These features were concatenated together, and redundant features were removed by Pearson correlation analysis. The discriminative features were selected by minimum redundancy maximum relevance method (mRMR) and then input into a C-support vector classifier to build multi-phase-combined CECT radiomics models. The prediction performance was evaluated by the area under the curve (AUC) of receiver operating characteristic (ROC).

Results

The multi-phase-combined CECT radiomics model showed the best prediction performance (AUC=0.777) than the single-phase CECT radiomics model (AUC=0.711) in the testing cohort (p value=0.039).

Conclusion

The multi-phase-combined CECT radiomics model is a potential effective way to noninvasively predict Fuhrman grade of ccRCC. The concatenation of first-order features and texture features extracted from corticomedullary phase and nephrographic phase are discriminative feature representations.

An Explainable Radiogenomic Framework to Predict Mutational Status of KRAS and EGFR in Lung Adenocarcinoma Patients

The complex pathobiology of lung cancer, and its spread worldwide, has prompted research studies that combine radiomic and genomic approaches. Indeed, the early identification of genetic alterations and driver mutations affecting the tumor is fundamental for correctly formulating the prognosis and therapeutic response. In this work, we propose a radiogenomic workflow to detect the presence of KRAS and EGFR mutations using radiomic features extracted from computed tomography images of patients affected by lung adenocarcinoma. To this aim, we investigated several feature selection algorithms to identify the most significant and uncorrelated sets of radiomic features and different classification models to reveal the mutational status. Then, we employed the SHAP (SHapley Additive exPlanations) technique to increase the understanding of the contribution given by specific radiomic features to the identification of the investigated mutations. Two cohorts of patients with lung adenocarcinoma were used for the study. The first one, obtained from the Cancer Imaging Archive (TCIA), consisted of 60 cases (25% EGFR, 23% KRAS); the second one, provided by the Azienda Ospedaliero-Universitaria 'Ospedali Riuniti' of Foggia, was composed of 55 cases (16% EGFR, 28% KRAS). The best-performing models proposed in our study achieved an AUC of 0.69 and 0.82 on the validation set for predicting the mutational status of EGFR and KRAS, respectively. The Multi-layer Perceptron model emerged as the top-performing model for both oncogenes, in some cases outperforming the state of the art. This study showed that radiomic features can be associated with EGFR and KRAS mutational status in patients with lung adenocarcinoma.

Effectiveness of Radiomic ZOT Features in the Automated Discrimination of Oncocytoma from Clear Cell Renal Cancer

Background: Benign renal tumors, such as renal oncocytoma (RO), can be erroneously diagnosed as malignant renal cell carcinomas (RCC), because of their similar imaging features. Computer-aided systems leveraging radiomic features can be used to better discriminate benign renal tumors from the malignant ones. The purpose of this work was to build a machine learning model to distinguish RO from clear cell RCC (ccRCC). Method: We collected CT images of 77 patients, with 30 cases of RO (39%) and 47 cases of ccRCC (61%). Radiomic features were extracted both from the tumor volumes identified by the clinicians and from the tumor’s zone of transition (ZOT). We used a genetic algorithm to perform feature selection, identifying the most descriptive set of features for the tumor classification. We built a decision tree classifier to distinguish between ROs and ccRCCs. We proposed two versions of the pipeline: in the first one, the feature selection was performed before the splitting of the data, while in the second one, the feature selection was performed after, i.e., on the training data only. We evaluated the efficiency of the two pipelines in cancer classification. Results: The ZOT features were found to be the most predictive by the genetic algorithm. The pipeline with the feature selection performed on the whole dataset obtained an average ROC AUC score of 0.87 ± 0.09. The second pipeline, in which the feature selection was performed on the training data only, obtained an average ROC AUC score of 0.62 ± 0.17. Conclusions: The obtained results confirm the efficiency of ZOT radiomic features in capturing the renal tumor characteristics. We showed that there is a significant difference in the performances of the two proposed pipelines, highlighting how some already published radiomic analyses could be too optimistic about the real generalization capabilities of the models.

Radiogenomics in Renal Cancer Management-Current Evidence and Future Prospects

Renal cancer management is challenging from diagnosis to treatment and follow-up. In cases of small renal masses and cystic lesions the differential diagnosis of benign or malignant tissues has potential pitfalls when imaging or even renal biopsy is applied. The recent artificial intelligence, imaging techniques, and genomics advancements have the ability to help clinicians set the stratification risk, treatment selection, follow-up strategy, and prognosis of the disease. The combination of radiomics features and genomics data has achieved good results but is currently limited by the retrospective design and the small number of patients included in clinical trials. The road ahead for radiogenomics is open to new, well-designed prospective studies, with large cohorts of patients required to validate previously obtained results and enter clinical practice.

Dissecting order amidst chaos of programmed cell deaths: construction of a diagnostic model for KIRC using transcriptomic information in blood-derived exosomes and single-cell multi-omics data in tumor microenvironment

Background

Kidney renal clear cell carcinoma (KIRC) is the most frequently diagnosed subtype of renal cell carcinoma (RCC); however, the pathogenesis and diagnostic approaches for KIRC remain elusive. Using single-cell transcriptomic information of KIRC, we constructed a diagnostic model depicting the landscape of programmed cell death (PCD)-associated genes, namely cell death-related genes (CDRGs).

Methods

In this study, six CDRG categories, including apoptosis, necroptosis, autophagy, pyroptosis, ferroptosis, and cuproptosis, were collected. RNA sequencing (RNA-seq) data of blood-derived exosomes from the exoRBase database, RNA-seq data of tissues from The Cancer Genome Atlas (TCGA) combined with control samples from the GTEx databases, and single-cell RNA sequencing (scRNA-seq) data from the Gene Expression Omnibus (GEO) database were downloaded. Next, we intersected the differentially expressed genes (DEGs) of the KIRC cohort from exoRBase and the TCGA databases with CDRGs and DEGs obtained from single-cell datasets, further screening out the candidate biomarker genes using clinical indicators and machine learning methods and thus constructing a diagnostic model for KIRC. Finally, we investigated the underlying mechanisms of key genes and their roles in the tumor microenvironment using scRNA-seq, single-cell assays for transposase-accessible chromatin sequencing (scATAC-seq), and the spatial transcriptomics sequencing (stRNA-seq) data of KIRC provided by the GEO database.

Result

We obtained 1,428 samples and 216,155 single cells. After the rational screening, we constructed a 13-gene diagnostic model for KIRC, which had high diagnostic efficacy in the exoRBase KIRC cohort (training set: AUC = 1; testing set: AUC = 0.965) and TCGA KIRC cohort (training set: AUC = 1; testing set: AUC = 0.982), with an additional validation cohort from GEO databases presenting an AUC value of 0.914. The results of a subsequent analysis revealed a specific tumor epithelial cell of TRIB3^high subset. Moreover, the results of a mechanical analysis showed the relatively elevated chromatin accessibility of TRIB3 in tumor epithelial cells in the scATAC data, while stRNA-seq verified that TRIB3 was predominantly expressed in cancer tissues.

Conclusions

The 13-gene diagnostic model yielded high accuracy in KIRC screening, and TRIB3^high tumor epithelial cells could be a promising therapeutic target for KIRC.

Computed tomography‐based radiomics prediction of CTLA4 expression and prognosis in clear cell renal cell carcinoma

OBJECTIVES

To predict CTLA4 expression levels and prognosis of clear cell renal cell carcinoma (ccRCC) by constructing a computed tomography-based radiomics model and establishing a nomogram using clinicopathologic factors.

METHODS

The clinicopathologic parameters and genomic data were extracted from 493 ccRCC cases of the Cancer Genome Atlas (TCGA)-KIRC database. Univariate and multivariate Cox regression and Kaplan-Meier analysis were performed for prognosis analysis. Cibersortx was applied to evaluate the immune cell composition. Radiomic features were extracted from the TCGA/the Cancer Imaging Archive (TCIA) (n = 102) datasets. The support vector machine (SVM) was employed to establish the radiomics signature for predicting CTLA4 expression. Receiver operating characteristic curve (ROC), decision curve analysis (DCA), and precision-recall curve were utilized to assess the predictive performance of the radiomics signature. Correlations between radiomics score (RS) and selected features were also evaluated. An RS-based nomogram was constructed to predict prognosis.

RESULTS

CTLA4 was significantly overexpressed in ccRCC tissues and was related to lower overall survival. A higher CTLA4 expression was independently linked to the poor prognosis (HR = 1.458, 95% CI 1.13-1.881, p = 0.004). The radiomics model for the prediction of CTLA4 expression levels (AUC = 0.769 in the training set, AUC = 0.724 in the validation set) was established using seven radiomic features. A significant elevation in infiltrating M2 macrophages was observed in the RS high group (p < 0.001). The predictive efficiencies of the RS-based nomogram measured by AUC were 0.826 at 12 months, 0.805 at 36 months, and 0.76 at 60 months.

CONCLUSIONS

CTLA4 mRNA expression status in ccRCC could be predicted noninvasively using a radiomics model based on nephrographic phase contrast-enhanced CT images. The nomogram established by combining RS and clinicopathologic factors could predict overall survival for ccRCC patients. Our findings may help stratify prognosis of ccRCC patients and identify those who may respond best to ICI-based treatments.

Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols

Introduction

This study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear cell renal cell carcinomas (ccRCC) that is robust against institutional imaging protocols and scanners.

Materials and methods

Preoperative unenhanced (UN), corticomedullary (CM), and excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) were extracted from the tumor volumes in each contrast phase. For the ML analysis, the cases were randomly split into training and test sets with a 3:1 ratio. Highly correlated RFs were filtered out based on Pearson’s correlation coefficient (r > 0.95). Intraclass correlation coefficient analysis was used to select RFs with excellent reproducibility (ICC ≥ 0.90). The most predictive RFs were selected by the least absolute shrinkage and selection operator (LASSO). A support vector machine algorithm-based binary classifier (SVC) was constructed to predict tumor types and its performance was evaluated based-on receiver operating characteristic curve (ROC) analysis. The “Kidney Tumor Segmentation 2019” (KiTS19) publicly available dataset was used during external validation of the model. The performance of the SVC was also compared with an expert radiologist’s.

Results

The training set consisted of 121 ccRCCs and 38 non-ccRCCs, while the independent internal test set contained 40 ccRCCs and 13 non-ccRCCs. For external validation, 50 ccRCCs and 23 non-ccRCCs were identified from the KiTS19 dataset with the available UN, CM, and EX phase CTs. After filtering out the highly correlated and poorly reproducible features, the LASSO algorithm selected 10 CM phase RFs that were then used for model construction. During external validation, the SVC achieved an area under the ROC curve (AUC) value, accuracy, sensitivity, and specificity of 0.83, 0.78, 0.80, and 0.74, respectively. UN and/or EX phase RFs did not further increase the model’s performance. Meanwhile, in the same comparison, the expert radiologist achieved similar performance with an AUC of 0.77, an accuracy of 0.79, a sensitivity of 0.84, and a specificity of 0.69.

Conclusion

Radiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.

Differential Diagnosis of Type 1 and Type 2 Papillary Renal Cell Carcinoma Based on Enhanced CT Radiomics Nomogram

Objectives

To construct a contrast-enhanced CT-based radiomics nomogram that combines clinical factors and a radiomics signature to distinguish papillary renal cell carcinoma (pRCC) type 1 from pRCC type 2 tumours.

Methods

A total of 131 patients with 60 in pRCC type 1 and 71 in pRCC type 2 were enrolled and divided into training set (n=91) and testing set (n=40). Patient demographics and enhanced CT imaging characteristics were evaluated to set up a clinical factors model. A radiomics signature was constructed and radiomics score (Rad-score) was calculated by extracting radiomics features from contrast-enhanced CT images in corticomedullary phase (CMP) and nephrographic phase (NP). A radiomics nomogram was then built by incorporating the Rad-score and significant clinical factors according to multivariate logistic regression analysis. The diagnostic performance of the clinical factors model, radiomics signature and radiomics nomogram was evaluated on both the training and testing sets.

Results

Three validated features were extracted from the CT images and used to construct the radiomics signature. Boundary blurring as an independent risk factor for tumours was used to build clinical factors model. The AUC value of the radiomics nomogram, which was based on the selected clinical factors and Rad-score, were 0.855 and 0.831 in the training and testing sets, respectively. The decision curves of the radiomics nomogram and radiomics signature in the training set indicated an overall net benefit over the clinical factors model.

Conclusion

Radiomics nomogram combining clinical factors and radiomics signature is a non-invasive prediction method with a good prediction for pRCC type 1 tumours and type 2 tumours preoperatively and has some significance in guiding clinicians selecting subsequent treatment plans.

A Machine Learning and Radiomics Approach in Lung Cancer for Predicting Histological Subtype

Lung cancer is one of the deadliest diseases worldwide. Computed Tomography (CT) images are a powerful tool for investigating the structure and texture of lung nodules. For a long time, trained radiologists have performed the grading and staging of cancer severity by relying on radiographic images. Recently, radiomics has been changing the traditional workflow for lung cancer staging by providing the technical and methodological means to analytically quantify lesions so that more accurate predictions could be performed while reducing the time required from each specialist to perform such tasks. In this work, we implemented a pipeline for identifying a radiomic signature composed of a reduced number of features to discriminate between adenocarcinomas and other cancer types. In addition, we also investigated the reproducibility of this radiomic study analysing the performances of the classification models on external validation data. In detail, we first considered two publicly available datasets, namely D1 and D2, composed of n = 262 and n = 89 samples, respectively. Ten significant features, according to univariate AUC evaluated on D1, were retained. Mann–Whitney U tests recognised three of these features to have a statistically different distribution, with a p-value < 0.05. Then, we collected n = 51 CT images from patients with lung nodules at the Azienda Ospedaliero—Universitaria “Policlinico Riuniti” in Foggia. Resident radiologists manually annotated the lung lesions in images to allow the subsequent analysis of the malignancy regions. We designed a pipeline for feature extraction from the Volumes of Interest in order to generate a third dataset, i.e., D3. Several experiments have been performed showing that the selected radiomic signature not only allowed the discrimination of lung adenocarcinoma from other cancer types independently from the input dataset used for training the models, but also allowed reaching good classification performances also on external validation data; in fact, the radiomic signature computed on D1 and evaluated on the local cohort allowed reaching an AUC of 0.70 (p<0.001) for the task of predicting the histological subtype.

Preoperative Differentiation of Uterine Leiomyomas and Leiomyosarcomas: Current Possibilities and Future Directions

The distinguishing of uterine leiomyosarcomas (ULMS) and uterine leiomyomas (ULM) before the operation and histopathological evaluation of tissue is one of the current challenges for clinicians and researchers. Recently, a few new and innovative methods have been developed. However, researchers are trying to create different scales analyzing available parameters and to combine them with imaging methods with the aim of ULMs and ULM preoperative differentiation ULMs and ULM. Moreover, it has been observed that the technology, meaning machine learning models and artificial intelligence (AI), is entering the world of medicine, including gynecology. Therefore, we can predict the diagnosis not only through symptoms, laboratory tests or imaging methods, but also, we can base it on AI. What is the best option to differentiate ULM and ULMS preoperatively? In our review, we focus on the possible methods to diagnose uterine lesions effectively, including clinical signs and symptoms, laboratory tests, imaging methods, molecular aspects, available scales, and AI. In addition, considering costs and availability, we list the most promising methods to be implemented and investigated on a larger scale.

Evaluating Rumor Debunking Effectiveness During the COVID-19 Pandemic Crisis: Utilizing User Stance in Comments on Sina Weibo

Background: The spread of rumors related to COVID-19 on social media has posed substantial challenges to public health governance, and thus exposing rumors and curbing their spread quickly and effectively has become an urgent task. This study aimed to assist in formulating effective strategies to debunk rumors and curb their spread on social media.

Methods: A total of 2,053 original postings and 100,348 comments that replied to the postings of five false rumors related to COVID-19 (dated from January 20, 2020, to June 28, 2020) belonging to three categories, authoritative, social, and political, on Sina Weibo in China were randomly selected. To study the effectiveness of different debunking methods, a new annotation scheme was proposed that divides debunking methods into six categories: denial, further fact-checking, refutation, person response, organization response, and combination methods. Text classifiers using deep learning methods were built to automatically identify four user stances in comments that replied to debunking postings: supporting, denying, querying, and commenting stances. Then, based on stance responses, a debunking effectiveness index (DEI) was developed to measure the effectiveness of different debunking methods.

Results: The refutation method with cited evidence has the best debunking effect, whether used alone or in combination with other debunking methods. For the social category of Car rumor and political category of Russia rumor, using the refutation method alone can achieve the optimal debunking effect. For authoritative rumors, a combination method has the optimal debunking effect, but the most effective combination method requires avoiding the use of a combination of a debunking method where the person or organization defamed by the authoritative rumor responds personally and the refutation method.

Conclusion: The findings provide relevant insights into ways to debunk rumors effectively, support crisis management of false information, and take necessary actions in response to rumors amid public health emergencies.

Integrative Analysis of Histopathological Images and Genomic Data in Colon Adenocarcinoma

Background

Colon adenocarcinoma (COAD) is one of the most common malignant tumors in the world. The histopathological features are crucial for the diagnosis, prognosis, and therapy of COAD.

Methods

We downloaded 719 whole-slide histopathological images from TCIA, and 459 corresponding HTSeq-counts mRNA expression and clinical data were obtained from TCGA. Histopathological image features were extracted by CellProfiler. Prognostic image features were selected by the least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM) algorithms. The co-expression gene module correlated with prognostic image features was identified by weighted gene co-expression network analysis (WGCNA). Random forest was employed to construct an integrative prognostic model and calculate the histopathological-genomic prognosis factor (HGPF).

Results

There were five prognostic image features and one co-expression gene module involved in the model construction. The time-dependent receiver operating curve showed that the prognostic model had a significant prognostic value. Patients were divided into high-risk group and low-risk group based on the HGPF. Kaplan-Meier analysis indicated that the overall survival of the low-risk group was significantly better than the high-risk group.

Conclusions

These results suggested that the histopathological image features had a certain ability to predict the survival of COAD patients. The integrative prognostic model based on the histopathological images and genomic features could further improve the prognosis prediction in COAD, which may assist the clinical decision in the future.