Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response.

BACKGROUNDS: Since breast cancer patients respond diversely to immunotherapy, there is an urgent need to explore novel biomarkers to precisely predict clinical responses and enhance therapeutic efficacy. The purpose of our present research was to construct and independently validate a biomarker of tumor microenvironment (TME) phenotypes via a machine learning-based radiomics way. The interrelationship between the biomarker, TME phenotypes and recipients' clinical response was also revealed. METHODS: In this retrospective multi-cohort investigation, five separate cohorts of breast cancer patients were recruited to measure breast cancer TME phenotypes via a radiomics signature, which was constructed and validated by integrating RNA-seq data with DCE-MRI images for predicting immunotherapy response. Initially, we constructed TME phenotypes using RNA-seq of 1089 breast cancer patients in the TCGA database. Then, parallel DCE-MRI images and RNA-seq of 94 breast cancer patients obtained from TCIA were applied to develop a radiomics-based TME phenotypes signature using random forest in machine learning. The repeatability of the radiomics signature was then validated in an internal validation set. Two additional independent external validation sets were analyzed to reassess this signature. The Immune phenotype cohort (n = 158) was divided based on CD8 cell infiltration into immune-inflamed and immune-desert phenotypes; these data were utilized to examine the relationship between the immune phenotypes and this signature. Finally, we utilized an Immunotherapy-treated cohort with 77 cases who received anti-PD-1/PD-L1 treatment to evaluate the predictive efficiency of this signature in terms of clinical outcomes. RESULTS: The TME phenotypes of breast cancer were separated into two heterogeneous clusters: Cluster A, an "immune-inflamed" cluster, containing substantial innate and adaptive immune cell infiltration, and Cluster B, an "immune-desert" cluster, with modest TME cell infiltration. We constructed a radiomics signature for the TME phenotypes ([AUC] = 0.855; 95% CI 0.777-0.932; p < 0.05) and verified it in an internal validation set (0.844; 0.606-1; p < 0.05). In the known immune phenotypes cohort, the signature can identify either immune-inflamed or immune-desert tumor (0.814; 0.717-0.911; p < 0.05). In the Immunotherapy-treated cohort, patients with objective response had higher baseline radiomics scores than those with stable or progressing disease (p < 0.05); moreover, the radiomics signature achieved an AUC of 0.784 (0.643-0.926; p < 0.05) for predicting immunotherapy response. CONCLUSIONS: Our imaging biomarker, a practicable radiomics signature, is beneficial for predicting the TME phenotypes and clinical response in anti-PD-1/PD-L1-treated breast cancer patients. It is particularly effective in identifying the "immune-desert" phenotype and may aid in its transformation into an "immune-inflamed" phenotype.

A non-invasive artificial intelligence model for identifying axillary pathological complete response to neoadjuvant chemotherapy in breast cancer: a secondary analysis to multicenter clinical trial.

BACKGROUND: This study aims to develop a stacking model for accurately predicting axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) using longitudinal MRI in breast cancer. METHODS: We included patients with node-positive breast cancer who received NAC following surgery from January 2012 to June 2022. We collected MRIs before and after NAC, and extracted radiomics features from the tumour, peritumour, and ALN regions. The Mann-Whitney U test, least absolute shrinkage and selection operator, and Boruta algorithm were used to select features. We utilised machine learning techniques to develop three single-modality models and a stacking model for predicting ALN response to NAC. RESULTS: This study consisted of a training cohort (n = 277), three external validation cohorts (n = 313, 164, and 318), and a prospective cohort (n = 81). Among the 1153 patients, 60.62% achieved ypN0. The stacking model achieved excellent AUCs of 0.926, 0.874, and 0.862 in the training, external validation, and prospective cohort, respectively. It also showed lower false-negative rates (FNRs) compared to radiologists, with rates of 14.40%, 20.85%, and 18.18% (radiologists: 40.80%, 50.49%, and 63.64%) in three cohorts. Additionally, there was a significant difference in disease-free survival between high-risk and low-risk groups (p < 0.05). CONCLUSIONS: The stacking model can accurately predict ALN status after NAC in breast cancer, showing a lower false-negative rate than radiologists. TRIAL REGISTRATION NUMBER: The clinical trial numbers were NCT03154749 and NCT04858529.

Noninvasive Artificial Intelligence System for Early Predicting Residual Cancer Burden during Neoadjuvant Chemotherapy in Breast Cancer.

OBJECTIVE: To develop an artificial intelligence (AI) system for the early prediction of residual cancer burden (RCB) scores during neoadjuvant chemotherapy (NAC) in breast cancer. SUMMARY BACKGROUND DATA: RCB III indicates drug resistance in breast cancer, and early detection methods are lacking. METHODS: This study enrolled 1048 patients with breast cancer from four institutions, who were all receiving NAC. Magnetic resonance images were collected at the pre- and mid-NAC stages, and radiomics and deep learning features were extracted. A multitask AI system was developed to classify patients into three groups (RCB 0-I, II, and III ) in the primary cohort (PC, n=335). Feature selection was conducted using the Mann-Whitney U- test, Spearman analysis, least absolute shrinkage and selection operator regression, and the Boruta algorithm. Single-modality models were developed followed by model integration. The AI system was validated in three external validation cohorts. (EVCs, n=713). RESULTS: Among the patients, 442 (42.18%) were RCB 0-I, 462 (44.08%) were RCB II and 144 (13.74%) were RCB III. Model-I achieved an area under the curve (AUC) of 0.975 in the PC and 0.923 in the EVCs for differentiating RCB III from RCB 0-II. Model-II distinguished RCB 0-I from RCB II-III, with an AUC of 0.976 in the PC and 0.910 in the EVCs. Subgroup analysis confirmed that the AI system was consistent across different clinical T stages and molecular subtypes. CONCLUSIONS: The multitask AI system offers a noninvasive tool for the early prediction of RCB scores in breast cancer, supporting clinical decision-making during NAC.

Noninvasive Assessment of Diabetic Kidney Disease With MRI: Hype or Hope?

Owing to the increasing prevalence of diabetic mellitus, diabetic kidney disease (DKD) is presently the leading cause of chronic kidney disease and end-stage renal disease worldwide. Early identification and disease interception is of paramount clinical importance for DKD management. However, current diagnostic, disease monitoring and prognostic tools are not satisfactory, due to their low sensitivity, low specificity, or invasiveness. Magnetic resonance imaging (MRI) is noninvasive and offers a host of contrast mechanisms that are sensitive to pathophysiological changes and risk factors associated with DKD. MRI tissue characterization involves structural and functional information including renal morphology (kidney volume (TKV) and parenchyma thickness using T1- or T2-weighted MRI), renal microstructure (diffusion weighted imaging, DWI), renal tissue oxygenation (blood oxygenation level dependent MRI, BOLD), renal hemodynamics (arterial spin labeling and phase contrast MRI), fibrosis (DWI) and abdominal or perirenal fat fraction (Dixon MRI). Recent (pre)clinical studies demonstrated the feasibility and potential value of DKD evaluation with MRI. Recognizing this opportunity, this review outlines key concepts and current trends in renal MRI technology for furthering our understanding of the mechanisms underlying DKD and for supplementing clinical decision-making in DKD. Progress in preclinical MRI of DKD is surveyed, and challenges for clinical translation of renal MRI are discussed. Future directions of DKD assessment and renal tissue characterization with (multi)parametric MRI are explored. Opportunities for discovery and clinical break-through are discussed including biological validation of the MRI findings, large-scale population studies, standardization of DKD protocols, the synergistic connection with data science to advance comprehensive texture analysis, and the development of smart and automatic data analysis and data visualization tools to further the concepts of virtual biopsy and personalized DKD precision medicine. We hope that this review will convey this vision and inspire the reader to become pioneers in noninvasive assessment and management of DKD with MRI. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 2.

An MRI-based scoring system for pretreatment risk stratification in locally advanced rectal cancer.

BACKGROUND: Accurately assessing the risk of recurrence in patients with locally advanced rectal cancer (LARC) before treatment is important for the development of treatment strategies. The purpose of this study is to develop an MRI-based scoring system to predict the risk of recurrence in patients with LARC. METHODS: This was a multicenter observational study that enrolled participants who underwent neoadjuvant chemoradiotherapy. To evaluate the risk of recurrence in these patients, we developed the mrDEC scoring system and assessed inter-reader agreement. Additionally, we plotted Kaplan-Meier curves to compare the 3-year disease-free survival (DFS) and 5-year overall survival (OS) rates among patients with different mrDEC scores. RESULTS: A total of 1287 patients with LARC were included in this study. We observed substantial inter-reader agreement for mrDEC. Based on the mrDEC scores ranging from 0 to 3, the patients were categorized into four groups. The 3-year DFS rates for the groups were 91.0%, 79.5%, 65.5%, and 44.0% (P < 0.0001), respectively, and the 5-year OS rates were 92.9%, 87.1%, 74.8%, and 44.5%, respectively (P < 0.0001). CONCLUSIONS: The mrDEC scoring system proved to be an effective tool for predicting the prognosis of patients with LARC and can assist clinicians in clinical decision-making.

Deep Learning for Fully Automated Prediction of Overall Survival in Patients Undergoing Resection for Pancreatic Cancer: A Retrospective Multicenter Study.

OBJECTIVE: To develop an imaging-derived biomarker for prediction of overall survival (OS) of pancreatic cancer by analyzing preoperative multiphase contrast-enhanced computed topography (CECT) using deep learning. BACKGROUND: Exploiting prognostic biomarkers for guiding neoadjuvant and adjuvant treatment decisions may potentially improve outcomes in patients with resectable pancreatic cancer. METHODS: This multicenter, retrospective study included 1516 patients with resected pancreatic ductal adenocarcinoma (PDAC) from 5 centers located in China. The discovery cohort (n=763), which included preoperative multiphase CECT scans and OS data from 2 centers, was used to construct a fully automated imaging-derived prognostic biomarker-DeepCT-PDAC-by training scalable deep segmentation and prognostic models (via self-learning) to comprehensively model the tumor-anatomy spatial relations and their appearance dynamics in multiphase CECT for OS prediction. The marker was independently tested using internal (n=574) and external validation cohorts (n=179, 3 centers) to evaluate its performance, robustness, and clinical usefulness. RESULTS: Preoperatively, DeepCT-PDAC was the strongest predictor of OS in both internal and external validation cohorts [hazard ratio (HR) for high versus low risk 2.03, 95% confidence interval (CI): 1.50-2.75; HR: 2.47, CI: 1.35-4.53] in a multivariable analysis. Postoperatively, DeepCT-PDAC remained significant in both cohorts (HR: 2.49, CI: 1.89-3.28; HR: 2.15, CI: 1.14-4.05) after adjustment for potential confounders. For margin-negative patients, adjuvant chemoradiotherapy was associated with improved OS in the subgroup with DeepCT-PDAC low risk (HR: 0.35, CI: 0.19-0.64), but did not affect OS in the subgroup with high risk. CONCLUSIONS: Deep learning-based CT imaging-derived biomarker enabled the objective and unbiased OS prediction for patients with resectable PDAC. This marker is applicable across hospitals, imaging protocols, and treatments, and has the potential to tailor neoadjuvant and adjuvant treatments at the individual level.

Axillary ultrasound after neoadjuvant therapy reduces the false-negative rate of sentinel lymph node biopsy in patients with cytologically node-positive breast cancer.

OBJECTIVES: This study aimed to determine whether post-neoadjuvant therapy (NAT) axillary ultrasound (AUS) could reduce the false-negative rate (FNR) of sentinel lymph node biopsy (SLNB). We also performed subgroup analyses to identify the appropriate patient for SLNB. METHODS: A total of 220 patients with cytologically proven axillary node-positive breast cancer who underwent both SLNB and axillary lymph node dissection (ALND) after NAT were included. We calculated the FNR of SLNB. In the case of post-NAT AUS results available, AUS was classified as negative or positive. Then the FNR of post-NAT AUS combined with SLNB was evaluated. Subgroup analyses based on the number of sentinel lymph nodes removed, molecular subtypes, and the clinical N stage were also performed. RESULTS: The overall axillary lymph node pathological complete response rate was 45.5% (100/220). The FNR of SLNB alone was 15.8% (95%CI: 9.2 to 22.5%). Post-NAT AUS results were available for 181 patients. When combined negative post-NAT AUS results and SLNB, the FNR was reduced to 7.5% (95%CI: 2.4 to 12.7%). Subgroup analyses of the FNR for SLNB alone and negative post-NAT AUS combined with SLNB were shown as follows: in cases patients with less than three sentinel lymph nodes (SLNs) and at least three SLNs removed, the FNR was decreased from 24.5 to 13.2%, and 9.0 to 5.0%, respectively. The FNR was decreased from 20.8 to 10.5% in HR+/HER2+subgroup, 21.4 to 16.7% in HR-/HER2+subgroup, 15.9 to 7.0% in HR+/HER2- subgroup, and 0% in HR-/HER2- subgroup, respectively. For cN1 patients, the FNR was decreased from 18.1 to 12.1% while 17.1 to 3.6% for cN2 patients and 0% for cN3 patients. CONCLUSION: Using negative post-NAT AUS may help to decrease the FNR and improve patient selection for SLNB.

MRI-based Quantification of Intratumoral Heterogeneity for Predicting Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer.

Background Breast cancer is highly heterogeneous, resulting in different treatment responses to neoadjuvant chemotherapy (NAC) among patients. A noninvasive quantitative measure of intratumoral heterogeneity (ITH) may be valuable for predicting treatment response. Purpose To develop a quantitative measure of ITH on pretreatment MRI scans and test its performance for predicting pathologic complete response (pCR) after NAC in patients with breast cancer. Materials and Methods Pretreatment MRI scans were retrospectively acquired in patients with breast cancer who received NAC followed by surgery at multiple centers from January 2000 to September 2020. Conventional radiomics (hereafter, C-radiomics) and intratumoral ecological diversity features were extracted from the MRI scans, and output probabilities of imaging-based decision tree models were used to generate a C-radiomics score and ITH index. Multivariable logistic regression analysis was used to identify variables associated with pCR, and significant variables, including clinicopathologic variables, C-radiomics score, and ITH index, were combined into a predictive model for which performance was assessed using the area under the receiver operating characteristic curve (AUC). Results The training data set was comprised of 335 patients (median age, 48 years [IQR, 42-54 years]) from centers A and B, and 590, 280, and 384 patients (median age, 48 years [IQR, 41-55 years]) were included in the three external test data sets. Molecular subtype (odds ratio [OR] range, 4.76-8.39 [95% CI: 1.79, 24.21]; all P < .01), ITH index (OR, 30.05 [95% CI: 8.43, 122.64]; P < .001), and C-radiomics score (OR, 29.90 [95% CI: 12.04, 81.70]; P < .001) were independently associated with the odds of achieving pCR. The combined model showed good performance for predicting pCR to NAC in the training data set (AUC, 0.90) and external test data sets (AUC range, 0.83-0.87). Conclusion A model that combined an index created from pretreatment MRI-based imaging features quantitating ITH, C-radiomics score, and clinicopathologic variables showed good performance for predicting pCR to NAC in patients with breast cancer. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Rauch in this issue.

jSRC: a flexible and accurate joint learning algorithm for clustering of single-cell RNA-sequencing data.

Single-cell RNA-sequencing (scRNA-seq) explores the transcriptome of genes at cell level, which sheds light on revealing the heterogeneity and dynamics of cell populations. Advances in biotechnologies make it possible to generate scRNA-seq profiles for large-scale cells, requiring effective and efficient clustering algorithms to identify cell types and informative genes. Although great efforts have been devoted to clustering of scRNA-seq, the accuracy, scalability and interpretability of available algorithms are not desirable. In this study, we solve these problems by developing a joint learning algorithm [a.k.a. joints sparse representation and clustering (jSRC)], where the dimension reduction (DR) and clustering are integrated. Specifically, DR is employed for the scalability and joint learning improves accuracy. To increase the interpretability of patterns, we assume that cells within the same type have similar expression patterns, where the sparse representation is imposed on features. We transform clustering of scRNA-seq into an optimization problem and then derive the update rules to optimize the objective of jSRC. Fifteen scRNA-seq datasets from various tissues and organisms are adopted to validate the performance of jSRC, where the number of single cells varies from 49 to 110 824. The experimental results demonstrate that jSRC significantly outperforms 12 state-of-the-art methods in terms of various measurements (on average 20.29% by improvement) with fewer running time. Furthermore, jSRC is efficient and robust across different scRNA-seq datasets from various tissues. Finally, jSRC also accurately identifies dynamic cell types associated with progression of COVID-19. The proposed model and methods provide an effective strategy to analyze scRNA-seq data (the software is coded using MATLAB and is free for academic purposes; https://github.com/xkmaxidian/jSRC).

An artificial intelligence-based ecological index for prognostic evaluation of colorectal cancer.

BACKGROUND AND OBJECTIVE: In the tumor microenvironment (TME), the dynamic interaction between tumor cells and immune cells plays a critical role in predicting the prognosis of colorectal cancer. This study introduces a novel approach based on artificial intelligence (AI) and immunohistochemistry (IHC)-stained whole-slide images (WSIs) of colorectal cancer (CRC) patients to quantitatively assess the spatial associations between tumor cells and immune cells. To achieve this, we employ the Morisita-Horn ecological index (Mor-index), which allows for a comprehensive analysis of the spatial distribution patterns between tumor cells and immune cells within the TME. MATERIALS AND METHODS: In this study, we employed a combination of deep learning technology and traditional computer segmentation methods to accurately segment the tumor nuclei, immune nuclei, and stroma nuclei within the tumor regions of IHC-stained WSIs. The Mor-index was used to assess the spatial association between tumor cells and immune cells in TME of CRC patients by obtaining the results of cell nuclei segmentation. A discovery cohort (N = 432) and validation cohort (N = 137) were used to evaluate the prognostic value of the Mor-index for overall survival (OS). RESULTS: The efficacy of our method was demonstrated through experiments conducted on two datasets comprising a total of 569 patients. Compared to other studies, our method is not only superior to the QuPath tool but also produces better segmentation results with an accuracy of 0.85. Mor-index was quantified automatically by our method. Survival analysis indicated that the higher Mor-index correlated with better OS in the discovery cohorts (HR for high vs. low 0.49, 95% CI 0.27-0.77, P = 0.0014) and validation cohort (0.21, 0.10-0.46, < 0.0001). CONCLUSION: This study provided a novel AI-based approach to segmenting various nuclei in the TME. The Mor-index can reflect the immune status of CRC patients and is associated with favorable survival. Thus, Mor-index can potentially make a significant role in aiding clinical prognosis and decision-making.

Diffusion-Weighted Magnetic Resonance Imaging and Morphological Characteristics Evaluation for Outcome Prediction of Primary Debulking Surgery for Advanced High-Grade Serous Ovarian Carcinoma.

BACKGROUND: Preoperative assessment of whether a successful primary debulking surgery (PDS) can be performed in patients with advanced high-grade serous ovarian carcinoma (HGSOC) remains a challenge. A reliable model to precisely predict resectability is highly demanded. PURPOSE: To investigate the value of diffusion-weighted MRI (DW-MRI) combined with morphological characteristics to predict the PDS outcome in advanced HGSOC patients. STUDY TYPE: Prospective. SUBJECTS: A total of 95 consecutive patients with histopathologically confirmed advanced HGSOC (ranged from 39 to 77 years). FIELDS STRENGTH/SEQUENCE: A 3.0 T, readout-segmented echo-planar DWI. ASSESSMENT: The MRI morphological characteristics of the primary ovarian tumor, a peritoneal carcinomatosis index (PCI) derived from DWI (DWI-PCI) and histogram analysis of the primary ovarian tumor and the largest peritoneal carcinomatosis were assessed by three radiologists. Three different models were developed to predict the resectability, including a clinicoradiologic model combing MRI morphological characteristic with ascites and CA125 level; DWI-PCI alone; and a fusion model combining the clinical-morphological information and DWI-PCI. STATISTICAL TESTS: Multivariate logistic regression analyses, receiver operating characteristic (ROC) curve, net reclassification index (NRI) and integrated discrimination improvement (IDI) were used. A P < 0.05 was considered to be statistically significant. RESULTS: Sixty-seven cases appeared as a definite mass, whereas 28 cases as an infiltrative mass. The morphological characteristics and DWI-PCI were independent factors for predicting the resectability, with an AUC of 0.724 and 0.824, respectively. The multivariable predictive model consisted of morphological characteristics, CA-125, and the amount of ascites, with an incremental AUC of 0.818. Combining the application of a clinicoradiologic model and DWI-PCI showed significantly higher AUC of 0.863 than the ones of each of them implemented alone, with a positive NRI and IDI. DATA CONCLUSIONS: The combination of two clinical factors, MRI morphological characteristics and DWI-PCI provide a reliable and valuable paradigm for the noninvasive prediction of the outcome of PDS. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

Using Machine Learning Methods to Assess Lymphovascular Invasion and Survival in Breast Cancer: Performance of Combining Preoperative Clinical and MRI Characteristics.

BACKGROUND: Preoperative assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) is of high clinical relevance for treatment decision-making and prognosis. PURPOSE: To investigate the associations of preoperative clinical and magnetic resonance imaging (MRI) characteristics with LVI and disease-free survival (DFS) by using machine learning methods in patients with IBC. STUDY TYPE: Retrospective. POPULATION: Five hundred and seventy-five women (range: 24-79 years) with IBC who underwent preoperative MRI examinations at two hospitals, divided into the training (N = 386) and validation datasets (N = 189). FIELD STRENGTH/SEQUENCE: Axial fat-suppressed T2-weighted turbo spin-echo sequence and dynamic contrast-enhanced with fat-suppressed T1-weighted three-dimensional gradient echo imaging. ASSESSMENT: MRI characteristics (clinical T stage, breast edema score, MRI axillary lymph node status, multicentricity or multifocality, enhancement pattern, adjacent vessel sign, and increased ipsilateral vascularity) were reviewed independently by three radiologists. Logistic regression (LR), eXtreme Gradient Boosting (XGBoost), k-Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms were used to establish the models by combing preoperative clinical and MRI characteristics for assessing LVI status in the training dataset, and the methods were further applied in the validation dataset. The LVI score was calculated using the best-performing of the four models to analyze the association with DFS. STATISTICAL TESTS: Chi-squared tests, variance inflation factors, receiver operating characteristics (ROC), Kaplan-Meier curve, log-rank, Cox regression, and intraclass correlation coefficient were performed. The area under the ROC curve (AUC) and hazard ratios (HR) were calculated. A P-value <0.05 was considered statistically significant. RESULTS: The model established by the XGBoost algorithm had better performance than LR, SVM, and KNN models, achieving an AUC of 0.832 (95% confidence interval [CI]: 0.789, 0.876) in the training dataset and 0.838 (95% CI: 0.775, 0.901) in the validation dataset. The LVI score established by the XGBoost model was an independent indicator of DFS (adjusted HR: 2.66, 95% CI: 1.22-5.80). DATA CONCLUSION: The XGBoost model based on preoperative clinical and MRI characteristics may help to investigate the LVI status and survival in patients with IBC. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Non-invasive prediction of microsatellite instability in colorectal cancer by a genetic algorithm-enhanced artificial neural network-based CT radiomics signature.

OBJECTIVE: The stratification of microsatellite instability (MSI) status assists clinicians in making treatment decisions for colorectal cancer (CRC) patients. This study aimed to establish a CT-based radiomics signature to predict MSI status in patients with CRC. METHODS: A total of 837 CRC patients who underwent preoperative enhanced CT and had available MSI status data were recruited from two hospitals. Radiomics features were extracted from segmented tumours, and a series of data balancing and feature selection strategies were used to select MSI-related features. Finally, an MSI-related radiomics signature was constructed using a genetic algorithm-enhanced artificial neural network model. Combined and clinical models were constructed using multivariate logistic regression analyses by integrating the clinical factors with or without the signature. A Kaplan-Meier survival analysis was conducted to explore the prognostic information of the signature in patients with CRC. RESULTS: Ten features were selected to construct a signature which showed robust performance in both the internal and external validation cohorts, with areas under the curves (AUC) of 0.788 and 0.775, respectively. The performance of the signature was comparable to that of the combined model (AUCs of 0.777 and 0.767, respectively) and it outperformed the clinical model constituting age and tumour location (AUCs of 0.768 and 0.623, respectively). Survival analysis demonstrated that the signature could stratify patients with stage II CRC according to prognosis (HR: 0.402, p = 0.029). CONCLUSIONS: This study built a robust radiomics signature for identifying the MSI status of CRC patients, which may assist individualised treatment decisions. KEY POINTS: • Our well-designed modelling strategies helped overcome the problem of data imbalance caused by the low incidence of MSI. • Genetic algorithm-enhanced artificial neural network-based CT radiomics signature can effectively distinguish the MSI status of CRC patients. • Kaplan-Meier survival analysis demonstrated that our signature could significantly stratify stage II CRC patients into high- and low-risk groups.

CT morphological features for predicting the risk of lymph node metastasis in T1 colorectal cancer.

OBJECTIVES: The aim of this study is to evaluate the feasibility of clinicopathological characteristics and computed tomography (CT) morphological features in predicting lymph node metastasis (LNM) for patients with T1 colorectal cancer (CRC). METHODS: A total of 144 patients with T1 CRC who underwent CT scans and surgical resection were retrospectively included in our study. The clinicopathological characteristics and CT morphological features were assessed by two observers. Univariate and multiple logistic regression analyses were used to identify significant LNM predictive variables. Then a model was developed using the independent predictive factors. The predictive model was subjected to bootstrapping validation (1000 bootstrap resamples) to calculate the calibration curve and relative C-index. RESULTS: LNM were found in 30/144 patients (20.83%). Four independent risk factors were determined in the multiple logistic regression analysis, including presence of necrosis (adjusted odds ratio [OR] = 10.32, 95% confidence interval [CI] 1.96-54.3, p = 0.004), irregular outer border (adjusted OR = 5.94, 95% CI 1.39-25.45, p = 0.035), and heterogeneity enhancement (adjusted OR = 7.35, 95% CI 3.11-17.38, p = 0.007), as well as tumor location (adjusted ORright-sided colon = 0.05 [0.01-0.60], p = 0.018; adjusted ORrectum = 0.22 [0.06-0.83], p = 0.026). In the internal validation cohort, the model showed good calibration and good discrimination with a C-index of 0.89. CONCLUSIONS: There are significant associations between lymphatic metastasis status and tumor location as well as CT morphologic features in T1 CRC, which could help the doctor make decisions for additional surgery after endoscopic resection. KEY POINTS: • LNM more frequently occurs in left-sided T1 colon cancer than in right-sided T1 colon and rectal cancer. • CT morphologic features are risk factors for LNM of T1 CRC, which may be related to fundamental biological behaviors. • The combination of tumor location and CT morphologic features can more effectively assist in predicting LNM in patients with T1 CRC, and decrease the rate of unnecessary extra surgeries after endoscopic resection.

Prediction of platinum resistance for advanced high-grade serous ovarian carcinoma using MRI-based radiomics nomogram.

OBJECTIVE: This study aimed to explore the value of a radiomics nomogram to identify platinum resistance and predict the progression-free survival (PFS) of patients with advanced high-grade serous ovarian carcinoma (HGSOC). MATERIALS AND METHODS: In this multicenter retrospective study, 301 patients with advanced HGSOC underwent radiomics features extraction from the whole primary tumor on contrast-enhanced T1WI and T2WI. The radiomics features were selected by the support vector machine-based recursive feature elimination method, and then the radiomics signature was generated. Furthermore, a radiomics nomogram was developed using the radiomics signature and clinical characteristics by multivariable logistic regression. The predictive performance was evaluated using receiver operating characteristic analysis. The net reclassification index (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA) were used to compare the clinical utility and benefits of different models. RESULTS: Five features significantly correlated with platinum resistance were selected to construct the radiomics model. The radiomics nomogram, combining radiomics signatures with three clinical characteristics (FIGO stage, CA-125, and residual tumor), had a higher area under the curve (AUC) compared with the clinical model alone (AUC: 0.799 vs 0.747), with positive NRI and IDI. The net benefit of the radiomics nomogram is typically higher than clinical-only and radiomics-only models. Kaplan-Meier survival analysis showed that the radiomics nomogram-defined high-risk groups had shorter PFS compared with the low-risk groups in patients with advanced HGSOC. CONCLUSIONS: The radiomics nomogram can identify platinum resistance and predict PFS. It helps make the personalized management of advanced HGSOC. KEY POINTS: • The radiomics-based approach has the potential to identify platinum resistance and can help make the personalized management of advanced HGSOC. • The radiomics-clinical nomogram showed improved performance compared with either of them alone for predicting platinum-resistant HGSOC. • The proposed nomogram performed well in predicting the PFS time of patients with low-risk and high-risk HGSOC in both training and testing cohorts.

An integrated deep learning model for the prediction of pathological complete response to neoadjuvant chemotherapy with serial ultrasonography in breast cancer patients: a multicentre, retrospective study.

BACKGROUND: The biological phenotype of tumours evolves during neoadjuvant chemotherapy (NAC). Accurate prediction of pathological complete response (pCR) to NAC in the early-stage or posttreatment can optimize treatment strategies or improve the breast-conserving rate. This study aimed to develop and validate an autosegmentation-based serial ultrasonography assessment system (SUAS) that incorporated serial ultrasonographic features throughout the NAC of breast cancer to predict pCR. METHODS: A total of 801 patients with biopsy-proven breast cancer were retrospectively enrolled from three institutions and were split into a training cohort (242 patients), an internal validation cohort (197 patients), and two external test cohorts (212 and 150 patients). Three imaging signatures were constructed from the serial ultrasonographic features before (pretreatment signature), during the first-second cycle of (early-stage treatment signature), and after (posttreatment signature) NAC based on autosegmentation by U-net. The SUAS was constructed by subsequently integrating the pre, early-stage, and posttreatment signatures, and the incremental performance was analysed. RESULTS: The SUAS yielded a favourable performance in predicting pCR, with areas under the receiver operating characteristic curve (AUCs) of 0.927 [95% confidence interval (CI) 0.891-0.963] and 0.914 (95% CI 0.853-0.976), compared with those of the clinicopathological prediction model [0.734 (95% CI 0.665-0.804) and 0.610 (95% CI 0.504-0.716)], and radiologist interpretation [0.632 (95% CI 0.570-0.693) and 0.724 (95% CI 0.644-0.804)] in the external test cohorts. Furthermore, similar results were also observed in the early-stage treatment of NAC [AUC 0.874 (0.793-0.955)-0.897 (0.851-0.943) in the external test cohorts]. CONCLUSIONS: We demonstrate that autosegmentation-based SAUS integrating serial ultrasonographic features throughout NAC can predict pCR with favourable performance, which can facilitate individualized treatment strategies.

The Crohn's-like lymphoid reaction density: a new artificial intelligence quantified prognostic immune index in colon cancer.

BACKGROUND: The Crohn's-like lymphoid reaction (CLR) is manifested as peritumoral lymphocytes aggregation in colon cancer, which is a major component of the host immune response to cancer. However, the lack of a unified and objective CLR evaluation standard limits its clinical application. We, therefore, developed a deep learning model for the fully automated CLR density quantification on routine hematoxylin and eosin (HE)-stained whole-slide images (WSIs) and further investigated its prognostic validity for patient stratification. METHODS: The CLR density was calculated by using a deep learning method on HE-stained WSIs. A training (N = 279) and a validation (N = 194) cohorts were used to evaluate the prognostic value of CLR density for overall survival (OS). RESULT: The fully automated quantified CLR density was an independent prognostic factor, with high CLR density associated with increased OS in the discovery (HR 0.58, 95% CI 0.38-0.89, P = 0.012) and validation cohort (0.45, 0.23-0.88, 0.020). Integrating CLR density into a Cox model with other risk factors showed improved prognostic capability. CONCLUSION: We developed a new immune indicator (CLR density) quantified by a deep learning method to evaluate the lymphocytes aggregation in colon cancer. The CLR density was demonstrated its predictive value for OS in two independent cohorts. This approach allows for the objective and standardized quantification while reducing pathologists' workload. Therefore, this fully automated standardized method of CLR evaluation had potential clinical value.

Automated whole-slide images assessment of immune infiltration in resected non-small-cell lung cancer: towards better risk-stratification.

BACKGROUND: High immune infiltration is associated with favourable prognosis in patients with non-small-cell lung cancer (NSCLC), but an automated workflow for characterizing immune infiltration, with high validity and reliability, remains to be developed. METHODS: We performed a multicentre retrospective study of patients with completely resected NSCLC. We developed an image analysis workflow for automatically evaluating the density of CD3+ and CD8+ T-cells in the tumour regions on immunohistochemistry (IHC)-stained whole-slide images (WSIs), and proposed an immune scoring system "I-score" based on the automated assessed cell density. RESULTS: A discovery cohort (n = 145) and a validation cohort (n = 180) were used to assess the prognostic value of the I-score for disease-free survival (DFS). The I-score (two-category) was an independent prognostic factor after adjusting for other clinicopathologic factors. Compared with a low I-score (two-category), a high I-score was associated with significantly superior DFS in the discovery cohort (adjusted hazard ratio [HR], 0.54; 95% confidence interval [CI] 0.33-0.86; P = 0.010) and validation cohort (adjusted HR, 0.57; 95% CI 0.36-0.92; P = 0.022). The I-score improved the prognostic stratification when integrating it into the Cox proportional hazard regression models with other risk factors (discovery cohort, C-index 0.742 vs. 0.728; validation cohort, C-index 0.695 vs. 0.685). CONCLUSION: This automated workflow and immune scoring system would advance the clinical application of immune microenvironment evaluation and support the clinical decision making for patients with resected NSCLC.

Multi-scale pathology image texture signature is a prognostic factor for resectable lung adenocarcinoma: a multi-center, retrospective study.

BACKGROUND: Tumor histomorphology analysis plays a crucial role in predicting the prognosis of resectable lung adenocarcinoma (LUAD). Computer-extracted image texture features have been previously shown to be correlated with outcome. However, a comprehensive, quantitative, and interpretable predictor remains to be developed. METHODS: In this multi-center study, we included patients with resectable LUAD from four independent cohorts. An automated pipeline was designed for extracting texture features from the tumor region in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) at multiple magnifications. A multi-scale pathology image texture signature (MPIS) was constructed with the discriminative texture features in terms of overall survival (OS) selected by the LASSO method. The prognostic value of MPIS for OS was evaluated through univariable and multivariable analysis in the discovery set (n = 111) and the three external validation sets (V1, n = 115; V2, n = 116; and V3, n = 246). We constructed a Cox proportional hazards model incorporating clinicopathological variables and MPIS to assess whether MPIS could improve prognostic stratification. We also performed histo-genomics analysis to explore the associations between texture features and biological pathways. RESULTS: A set of eight texture features was selected to construct MPIS. In multivariable analysis, a higher MPIS was associated with significantly worse OS in the discovery set (HR 5.32, 95%CI 1.72-16.44; P = 0.0037) and the three external validation sets (V1: HR 2.63, 95%CI 1.10-6.29, P = 0.0292; V2: HR 2.99, 95%CI 1.34-6.66, P = 0.0075; V3: HR 1.93, 95%CI 1.15-3.23, P = 0.0125). The model that integrated clinicopathological variables and MPIS had better discrimination for OS compared to the clinicopathological variables-based model in the discovery set (C-index, 0.837 vs. 0.798) and the three external validation sets (V1: 0.704 vs. 0.679; V2: 0.728 vs. 0.666; V3: 0.696 vs. 0.669). Furthermore, the identified texture features were associated with biological pathways, such as cytokine activity, structural constituent of cytoskeleton, and extracellular matrix structural constituent. CONCLUSIONS: MPIS was an independent prognostic biomarker that was robust and interpretable. Integration of MPIS with clinicopathological variables improved prognostic stratification in resectable LUAD and might help enhance the quality of individualized postoperative care.

Artificial intelligence for quantifying immune infiltrates interacting with stroma in colorectal cancer.

BACKGROUND: We proposed an artificial intelligence-based immune index, Deep-immune score, quantifying the infiltration of immune cells interacting with the tumor stroma in hematoxylin and eosin-stained whole-slide images of colorectal cancer. METHODS: A total of 1010 colorectal cancer patients from three centers were enrolled in this retrospective study, divided into a primary (N = 544) and a validation cohort (N = 466). We proposed the Deep-immune score, which reflected both tumor stroma proportion and the infiltration of immune cells in the stroma region. We further analyzed the correlation between the score and CD3+ T cells density in the stroma region using immunohistochemistry-stained whole-slide images. Survival analysis was performed using the Cox proportional hazard model, and the endpoint of the event was the overall survival. RESULT: Patients were classified into 4-level score groups (score 1-4). A high Deep-immune score was associated with a high level of CD3+ T cells infiltration in the stroma region. In the primary cohort, survival analysis showed a significant difference in 5-year survival rates between score 4 and score 1 groups: 87.4% vs. 58.2% (Hazard ratio for score 4 vs. score 1 0.27, 95% confidence interval 0.15-0.48, P < 0.001). Similar trends were observed in the validation cohort (89.8% vs. 67.0%; 0.31, 0.15-0.62, < 0.001). Stratified analysis showed that the Deep-immune score could distinguish high-risk and low-risk patients in stage II colorectal cancer (P = 0.018). CONCLUSION: The proposed Deep-immune score quantified by artificial intelligence can reflect the immune status of patients with colorectal cancer and is associate with favorable survival. This digital pathology-based finding might advocate change in risk stratification and consequent precision medicine.