Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: a multicenter, retrospective study

Radiomic analysis reveals diverse prognostic and molecular insights into the response of breast cancer to neoadjuvant chemotherapy: a multicohort study

BACKGROUND

Breast cancer patients exhibit various response patterns to neoadjuvant chemotherapy (NAC). However, it is uncertain whether diverse tumor response patterns to NAC in breast cancer patients can predict survival outcomes. We aimed to develop and validate radiomic signatures indicative of tumor shrinkage and therapeutic response for improved survival analysis.

METHODS

This retrospective, multicohort study included three datasets. The development dataset, consisting of preoperative and early NAC DCE-MRI data from 255 patients, was used to create an imaging signature-based multitask model for predicting tumor shrinkage patterns and pathological complete response (pCR). Patients were categorized as pCR, nonpCR with concentric shrinkage (CS), or nonpCR with non-CS, with prediction performance measured by the area under the curve (AUC). The prognostic validation dataset (n = 174) was used to assess the prognostic value of the imaging signatures for overall survival (OS) and recurrence-free survival (RFS) using a multivariate Cox model. The gene expression data (genomic validation dataset, n = 112) were analyzed to determine the biological basis of the response patterns.

RESULTS

The multitask learning model, utilizing 17 radiomic signatures, achieved AUCs of 0.886 for predicting tumor shrinkage and 0.760 for predicting pCR. Patients who achieved pCR had the best survival outcomes, while nonpCR patients with a CS pattern had better survival than non-CS patients did, with significant differences in OS and RFS (p = 0.00012 and p = 0.00063, respectively). Gene expression analysis highlighted the involvement of the IL-17 and estrogen signaling pathways in response variability.

CONCLUSIONS

Radiomic signatures effectively predict NAC response patterns in breast cancer patients and are associated with specific survival outcomes. The CS pattern in nonpCR patients indicates better survival.

Pretreatment Sarcopenia and MRI-Based Radiomics to Predict the Response of Neoadjuvant Chemotherapy in Triple-Negative Breast Cancer

The association between sarcopenia and the effectiveness of neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) remains uncertain. This study aims to examine the potential of sarcopenia as a predictive factor for the response to NAC in TNBC, and to assess whether its combination with MRI radiomic signatures can improve the predictive accuracy. We collected clinical and pathological information, as well as pretreatment breast MRI and abdominal CT images, of 121 patients with TNBC who underwent NAC at our hospital between January 2012 and September 2021. The presence of pretreatment sarcopenia was assessed using the L3 skeletal muscle index. Clinical models were constructed based on independent risk factors identified by univariate regression analysis. Radiomics data were extracted on breast MRI images and the radiomics prediction models were constructed. We integrated independent risk factors and radiomic features to build the combined models. The results of this study demonstrated that sarcopenia is an independent predictive factor for NAC efficacy in TNBC. The combination of sarcopenia and MRI radiomic signatures can further improve predictive performance.

Longitudinal Image Data for Outcome Modeling

In oncology, medical imaging is crucial for diagnosis, treatment planning and therapy execution. Treatment responses can be complex and varied and are known to involve factors of treatment, patient characteristics and tumor microenvironment. Longitudinal image analysis is able to track temporal changes, aiding in disease monitoring, treatment evaluation, and outcome prediction. This allows for the enhancement of personalized medicine. However, analyzing longitudinal 2D and 3D images presents unique challenges, including image registration, reliable segmentation, dealing with variable imaging intervals, and sparse data. This review presents an overview of techniques and methodologies in longitudinal image analysis, with a primary focus on outcome modeling in radiation oncology.

Time-Series MR Images Identifying Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Using a Deep Learning Approach

BACKGROUND

Pathological complete response (pCR) is an essential criterion for adjusting follow-up treatment plans for patients with breast cancer (BC). The value of the visual geometry group and long short-term memory (VGG-LSTM) network using time-series dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for pCR identification in BC is unclear.

PURPOSE

To identify pCR to neoadjuvant chemotherapy (NAC) using deep learning (DL) models based on the VGG-LSTM network.

STUDY TYPE

Retrospective.

POPULATION

Center A: 235 patients (47.7 ± 10.0 years) were divided 7:3 into training (n = 164) and validation set (n = 71). Center B: 150 patients (48.5 ± 10.4 years) were used as test set.

FIELD STRENGTH/SEQUENCE

3-T, T2-weighted spin-echo sequence imaging, and gradient echo DCE sequence imaging.

ASSESSMENT

Patients underwent MRI examinations at three sequential time points: pretreatment, after three cycles of treatment, and prior to surgery, with tumor regions of interest manually delineated. Histopathology was the gold standard. We used VGG-LSTM network to establish seven DL models using time-series DCE-MR images: pre-NAC images (t0 model), early NAC images (t1 model), post-NAC images (t2 model), pre-NAC and early NAC images (t0 + t1 model), pre-NAC and post-NAC images (t0 + t2 model), pre-NAC, early NAC and post-NAC images (t0 + t1 + t2 model), and the optimal model combined with the clinical features and imaging features (combined model). The models were trained and optimized on the training and validation set, and tested on the test set.

STATISTICAL TESTS

The DeLong, Student's t-test, Mann-Whitney U, Chi-squared, Fisher's exact, Hosmer-Lemeshow tests, decision curve analysis, and receiver operating characteristics analysis were performed. P < 0.05 was considered significant.

RESULTS

Compared with the other six models, the combined model achieved the best performance in the test set yielding an AUC of 0.927.

DATA CONCLUSION

The combined model that used time-series DCE-MR images, clinical features and imaging features shows promise for identifying pCR in BC.

LEVEL OF EVIDENCE: 4

TECHNICAL EFFICACY

Stage 4.

Pooled analysis of NeoCARH and NeoCART trials: patient-reported outcomes in patients with early-stage breast cancer receiving platinum-based or anthracycline-based neoadjuvant chemotherapy

PURPOSE

Anthracycline-based or platinum-based neoadjuvant chemotherapy belongs to the standard treatment for early-stage breast cancer (EBC) that is either triple-negative or human epidermal growth factor receptor 2 positive (HER2 +). Currently, there is a paucity of data comparing their impact on health-related quality of life (HRQoL).

METHODS

Triple-negative or HER2 + EBC from our two prospective randomized controlled trials, neoCARH and neoCART, were divided into two groups based on the neoadjuvant chemotherapy regimens they received: anthracycline-based or platinum-based group. HRQoL was the exploratory endpoint in these two trials, which was assessed using the European Organization for Research and Treatment of Cancer Quality of Life-Core30 and Breast23 questionnaires. The primary variable of interest was the C30 summary score (C30-SumSc). Assessments were carried out at baseline, after neoadjuvant chemotherapy, and 1 year and 2 years after diagnosis.

RESULTS

The mean questionnaires' compliance rate was 95.0%. After neoadjuvant chemotherapy, 210 patients had evaluable HRQoL data, the mean least square change from baseline for the platinum-based group was - 15.997 (95% confidence interval (CI): - 17.877 to - 14.117), and it was - 20.156 (95% CI: - 22.053 to - 18.258) for the anthracycline-based group (difference: 4.159, 95% CI: 1.462 to 6.855, P = 0.003, minimal important difference = 3). For the majority of the domains of interest assessed by the C30 and BR23 questionnaires, the platinum-based group demonstrated superior outcomes in comparison to the anthracycline-based group.

CONCLUSION

Patients receiving platinum-based or anthracycline-based regimens both experienced worsened HRQoL after neoadjuvant chemotherapy; however, the former provided relatively better HRQoL compared with the latter.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov: NCT03140553. Registered 4 May 2017 (neoCARH). NCT03154749. Registered 16 May 2017 (neoCART).

CEMRI-Based Quantification of Intratumoral Heterogeneity for Predicting Aggressive Characteristics of Hepatocellular Carcinoma Using Habitat Analysis: Comparison and Combination of Deep Learning

RATIONALE AND OBJECTIVES

To explore both an intratumoral heterogeneity (ITH) model based on habitat analysis and a deep learning (DL) model based on contrast-enhanced magnetic resonance imaging (CEMRI) and validate its efficiency for predicting microvascular invasion (MVI) and pathological differentiation in hepatocellular carcinoma (HCC).

METHODS

CEMRI images were retrospectively obtained from 277 HCCs in 265 patients. Habitat analysis and DL features were extracted from the CEMRI images and selected with the least absolute shrinkage and selection operator approach to develop ITH and DL models, respectively, and these robust features were then integrated to design a fusion model for predicting MVI and poorly differentiated HCC (pHCC). The predictive value of the three models was assessed using the area under the receiver operating characteristic curve (AUC).

RESULTS

The training and validation sets comprised 221 HCCs and 56 HCCs, respectively. The ITH and DL models presented AUC values of (0.90 vs. 0.87) for predicting MVI in the training set, with AUC values of 0.86 and 0.83 in the validation set. The AUC values of the ITH model to predict pHCC were 0.90 and 0.86 in the two sets, respectively; they were 0.84 and 0.80 for the DL model. The fusion model yielded the best performance for predicting MVI and pHCC in the training set (AUC=0.95, 0.90) and in the validation set (AUC=0.89, 0.87), respectively.

CONCLUSION

A fusion model integrating ITH and DL features derived from CEMRI images can serve as an excellent imaging biomarker for predicting aggressive characteristics in HCC.

The value of CT radiomics combined with deep transfer learning in predicting the nature of gallbladder polypoid lesions

BACKGROUND

Computed tomography (CT) radiomics combined with deep transfer learning was used to identify cholesterol and adenomatous gallbladder polyps that have not been well evaluated before surgery.

PURPOSE

To investigate the potential of various machine learning models, incorporating radiomics and deep transfer learning, in predicting the nature of cholesterol and adenomatous gallbladder polyps.

MATERIAL AND METHODS

A retrospective analysis was conducted on clinical and imaging data from 100 patients with cholesterol or adenomatous polyps confirmed by surgery and pathology at our hospital between September 2015 and February 2023. Preoperative contrast-enhanced CT radiomics combined with deep learning features were utilized, and t-tests and least absolute shrinkage and selection operator (LASSO) cross-validation were employed for feature selection. Subsequently, 11 machine learning algorithms were utilized to construct prediction models, and the area under the ROC curve (AUC), accuracy, and F1 measure were used to assess model performance, which was validated in a validation group.

RESULTS

The Logistic algorithm demonstrated the most effective prediction in identifying polyp properties based on 10 radiomics combined with deep learning features, achieving the highest AUC (0.85 in the validation group, 95% confidence interval = 0.68-1.0). In addition, the accuracy (0.83 in the validation group) and F1 measure (0.76 in the validation group) also indicated strong performance.

CONCLUSION

The machine learning radiomics combined with deep learning model based on enhanced CT proves valuable in predicting the characteristics of cholesterol and adenomatous gallbladder polyps. This approach provides a more reliable basis for preoperative diagnosis and treatment of these conditions.

A comprehensive overview of metaplastic breast cancer: Features and treatments

Metaplastic breast cancer is a rare, aggressive, and chemotherapy-resistant subtype of breast cancers, accounting for less than 1% of invasive breast cancers, characterized by adenocarcinoma with spindle cells, squamous epithelium, and/or mesenchymal tissue differentiation. The majority of metaplastic breast cancers exhibit the characteristics of triple-negative breast cancer and have unfavorable prognoses with a lower survival rate. This subtype often displays gene alterations in the PI3K/AKT pathway, Wnt/β-catenin pathway, and cell cycle dysregulation and demonstrates epithelial-mesenchymal transition, immune response changes, TP53 mutation, EGFR amplification, and so on. Currently, the optimal treatment of metaplastic breast cancer remains uncertain. This article provides a comprehensive review on the clinical features, molecular characteristics, invasion and metastasis patterns, and prognosis of metaplastic breast cancer, as well as recent advancements in treatment strategies.

The use of longitudinal CT-based radiomics and clinicopathological features predicts the pathological complete response of metastasized axillary lymph nodes in breast cancer

BACKGROUND

Accurate assessment of axillary status after neoadjuvant therapy for breast cancer patients with axillary lymph node metastasis is important for the selection of appropriate subsequent axillary treatment decisions. Our objectives were to accurately predict whether the breast cancer patients with axillary lymph node metastases could achieve axillary pathological complete response (pCR).

METHODS

We collected imaging data to extract longitudinal CT image features before and after neoadjuvant chemotherapy (NAC), analyzed the correlation between radiomics and clinicopathological features, and developed models to predict whether patients with axillary lymph node metastasis can achieve axillary pCR after NAC. The clinical utility of the models was determined via decision curve analysis (DCA). Subgroup analyses were also performed. Then, a nomogram was developed based on the model with the best predictive efficiency and clinical utility and was validated using the calibration plots.

RESULTS

A total of 549 breast cancer patients with metastasized axillary lymph nodes were enrolled in this study. 42 independent radiomics features were selected from LASSO regression to construct a logistic regression model with clinicopathological features (LR radiomics-clinical combined model). The AUC of the LR radiomics-clinical combined model prediction performance was 0.861 in the training set and 0.891 in the testing set. For the HR + /HER2 - , HER2 + , and Triple negative subtype, the LR radiomics-clinical combined model yields the best prediction AUCs of 0.756, 0.812, and 0.928 in training sets, and AUCs of 0.757, 0.777 and 0.838 in testing sets, respectively.

CONCLUSIONS

The combination of radiomics features and clinicopathological characteristics can effectively predict axillary pCR status in NAC breast cancer patients.

Predicting Osteoporosis and Osteopenia by Fusing Deep Transfer Learning Features and Classical Radiomics Features Based on Single-Source Dual-energy CT Imaging

RATIONALE AND OBJECTIVES

To develop and validate a predictive model for osteoporosis and osteopenia prediction by fusing deep transfer learning (DTL) features and classical radiomics features based on single-source dual-energy computed tomography (CT) virtual monochromatic imaging.

METHODS

A total of 606 lumbar vertebrae with dual-energy CT imaging and quantitative CT (QCT) evaluation were included in the retrospective study and randomly divided into the training (n = 424) and validation (n = 182) cohorts. Radiomics features and DTL features were extracted from 70-keV monochromatic CT images, followed by feature selection and model construction, radiomics and DTL features models were established. Then, we integrated the selected two types of features into a features fusion model. We developed a two-level classifier for the hierarchical pairwise classification of each vertebra. All the vertebrae were first classified into osteoporosis and non-osteoporosis groups, then non-osteoporosis group was classified into osteopenia and normal groups. QCT was used as reference. The predictive performance and clinical usefulness of three models were evaluated and compared.

RESULTS

The area under the curve (AUC) of the features fusion, radiomics and DTL models for the classification between osteoporosis and non-osteoporosis were 0.981, 0.999, 0.997 in the training cohort and 0.979, 0.943, 0.848 in the validation cohort. Furthermore, the AUCs of the previously mentioned models for the differentiation between osteopenia and normal were 0.994, 0.971, 0.996 in the training cohort and 0.990, 0.968, 0.908 in the validation cohort. The overall accuracy of the previously mentioned models for two-level classifications was 0.979, 0.955, 0.908 in the training cohort and 0.918, 0.885, 0.841 in the validation cohort. Decision curve analysis showed that all models had high clinical value.

CONCLUSION

The feature fusion model can be used for osteoporosis and osteopenia prediction with improved predictive ability over a radiomics model or a DTL model alone.

Prediction of prostate cancer aggressiveness using magnetic resonance imaging radiomics: a dual-center study

PURPOSE

The Gleason score (GS) and positive needles are crucial aggressive indicators of prostate cancer (PCa). This study aimed to investigate the usefulness of magnetic resonance imaging (MRI) radiomics models in predicting GS and positive needles of systematic biopsy in PCa.

MATERIAL AND METHODS

A total of 218 patients with pathologically proven PCa were retrospectively recruited from 2 centers. Small-field-of-view high-resolution T2-weighted imaging and post-contrast delayed sequences were selected to extract radiomics features. Then, analysis of variance and recursive feature elimination were applied to remove redundant features. Radiomics models for predicting GS and positive needles were constructed based on MRI and various classifiers, including support vector machine, linear discriminant analysis, logistic regression (LR), and LR using the least absolute shrinkage and selection operator. The models were evaluated with the area under the curve (AUC) of the receiver-operating characteristic.

RESULTS

The 11 features were chosen as the primary feature subset for the GS prediction, whereas the 5 features were chosen for positive needle prediction. LR was chosen as classifier to construct the radiomics models. For GS prediction, the AUC of the radiomics models was 0.811, 0.814, and 0.717 in the training, internal validation, and external validation sets, respectively. For positive needle prediction, the AUC was 0.806, 0.811, and 0.791 in the training, internal validation, and external validation sets, respectively.

CONCLUSIONS

MRI radiomics models are suitable for predicting GS and positive needles of systematic biopsy in PCa. The models can be used to identify aggressive PCa using a noninvasive, repeatable, and accurate diagnostic method.

Deep learning or radiomics based on CT for predicting the response of gastric cancer to neoadjuvant chemotherapy: a meta-analysis and systematic review

Background

Artificial intelligence (AI) models, clinical models (CM), and the integrated model (IM) are utilized to evaluate the response to neoadjuvant chemotherapy (NACT) in patients diagnosed with gastric cancer.

Objective

The objective is to identify the diagnostic test of the AI model and to compare the accuracy of AI, CM, and IM through a comprehensive summary of head-to-head comparative studies.

Methods

PubMed, Web of Science, Cochrane Library, and Embase were systematically searched until September 5, 2023, to compile English language studies without regional restrictions. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) criteria. Forest plots were utilized to illustrate the findings of diagnostic accuracy, while Hierarchical Summary Receiver Operating Characteristic curves were generated to estimate sensitivity (SEN) and specificity (SPE). Meta-regression was applied to analyze heterogeneity across the studies. To assess the presence of publication bias, Deeks' funnel plot and an asymmetry test were employed.

Results

A total of 9 studies, comprising 3313 patients, were included for the AI model, with 7 head-to-head comparative studies involving 2699 patients. Across the 9 studies, the pooled SEN for the AI model was 0.75 (95% confidence interval (CI): 0.66, 0.82), and SPE was 0.77 (95% CI: 0.69, 0.84). Meta-regression was conducted, revealing that the cut-off value, approach to predicting response, and gold standard might be sources of heterogeneity. In the head-to-head comparative studies, the pooled SEN for AI was 0.77 (95% CI: 0.69, 0.84) with SPE at 0.79 (95% CI: 0.70, 0.85). For CM, the pooled SEN was 0.67 (95% CI: 0.57, 0.77) with SPE at 0.59 (95% CI: 0.54, 0.64), while for IM, the pooled SEN was 0.83 (95% CI: 0.79, 0.86) with SPE at 0.69 (95% CI: 0.56, 0.79). Notably, there was no statistical difference, except that IM exhibited higher SEN than AI, while maintaining a similar level of SPE in pairwise comparisons. In the Receiver Operating Characteristic analysis subgroup, the CT-based Deep Learning (DL) subgroup, and the National Comprehensive Cancer Network (NCCN) guideline subgroup, the AI model exhibited higher SEN but lower SPE compared to the IM. Conversely, in the training cohort subgroup and the internal validation cohort subgroup, the AI model demonstrated lower SEN but higher SPE than the IM. The subgroup analysis underscored that factors such as the number of cohorts, cohort type, cut-off value, approach to predicting response, and choice of gold standard could impact the reliability and robustness of the results.

Conclusion

AI has demonstrated its viability as a tool for predicting the response of GC patients to NACT Furthermore, CT-based DL model in AI was sensitive to extract tumor features and predict the response. The results of subgroup analysis also supported the above conclusions. Large-scale rigorously designed diagnostic accuracy studies and head-to-head comparative studies are anticipated.

Systematic review registration

PROSPERO, CRD42022377030.

Development and validation of a multi-modal ultrasomics model to predict response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

OBJECTIVES

To assess the performance of multi-modal ultrasomics model to predict efficacy to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC) and compare with the clinical model.

MATERIALS AND METHODS

This study retrospectively included 106 patients with LARC who underwent total mesorectal excision after nCRT between April 2018 and April 2023 at our hospital, randomly divided into a training set of 74 and a validation set of 32 in a 7: 3 ratios. Ultrasomics features were extracted from the tumors' region of interest of B-mode ultrasound (BUS) and contrast-enhanced ultrasound (CEUS) images based on PyRadiomics. Mann-Whitney U test, spearman, and least absolute shrinkage and selection operator algorithms were utilized to reduce features dimension. Five models were built with ultrasomics and clinical analysis using multilayer perceptron neural network classifier based on python. Including BUS, CEUS, Combined_1, Combined_2 and Clinical models. The diagnostic performance of models was assessed with the area under the curve (AUC) of the receiver operating characteristic. The DeLong testing algorithm was utilized to compare the models' overall performance.

RESULTS

The AUC (95% confidence interval [CI]) of the five models in the validation cohort were as follows: BUS 0.675 (95%CI: 0.481-0.868), CEUS 0.821 (95%CI: 0.660-0.983), Combined_1 0.829 (95%CI: 0.673-0.985), Combined_2 0.893 (95%CI: 0.780-1.000), and Clinical 0.690 (95%CI: 0.509-0.872). The Combined_2 model was the best in the overall prediction performance, showed significantly better compared to the Clinical model after DeLong testing (P < 0.01). Both univariate and multivariate logistic regression analyses showed that age (P < 0.01) and clinical stage (P < 0.01) could be an independent predictor of efficacy after nCRT in patients with LARC.

CONCLUSION

The ultrasomics model had better diagnostic performance to predict efficacy to nCRT in patients with LARC than the Clinical model.

Automated and reusable deep learning (AutoRDL) framework for predicting response to neoadjuvant chemotherapy and axillary lymph node metastasis in breast cancer using ultrasound images: a retrospective, multicentre study

Background

Previous deep learning models have been proposed to predict the pathological complete response (pCR) and axillary lymph node metastasis (ALNM) in breast cancer. Yet, the models often leveraged multiple frameworks, required manual annotation, and discarded low-quality images. We aimed to develop an automated and reusable deep learning (AutoRDL) framework for tumor detection and prediction of pCR and ALNM using ultrasound images with diverse qualities.

Methods

The AutoRDL framework includes a You Only Look Once version 5 (YOLOv5) network for tumor detection and a progressive multi-granularity (PMG) network for pCR and ALNM prediction. The training cohort and the internal validation cohort were recruited from Guangdong Provincial People's Hospital (GPPH) between November 2012 and May 2021. The two external validation cohorts were recruited from the First Affiliated Hospital of Kunming Medical University (KMUH), between January 2016 and December 2019, and Shunde Hospital of Southern Medical University (SHSMU) between January 2014 and July 2015. Prior to model training, super-resolution via iterative refinement (SR3) was employed to improve the spatial resolution of low-quality images from the KMUH. We developed three models for predicting pCR and ALNM: a clinical model using multivariable logistic regression analysis, an image model utilizing the PMG network, and a combined model that integrates both clinical and image data using the PMG network.

Findings

The YOLOv5 network demonstrated excellent accuracy in tumor detection, achieving average precisions of 0.880-0.921 during validation. In terms of pCR prediction, the combined modelpost-SR3 outperformed the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.833 vs 0.822 vs 0.806 vs 0.790 vs 0.712, all p < 0.05) in the external validation cohort (KMUH). Consistently, the combined modelpost-SR3 exhibited the highest accuracy in ALNM prediction, surpassing the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.825 vs 0.806 vs 0.802 vs 0.787 vs 0.703, all p < 0.05) in the external validation cohort 1 (KMUH). In the external validation cohort 2 (SHSMU), the combined model also showed superiority over the clinical and image models (0.819 vs 0.712 vs 0.806, both p < 0.05).

Interpretation

Our proposed AutoRDL framework is feasible in automatically predicting pCR and ALNM in real-world settings, which has the potential to assist clinicians in optimizing individualized treatment options for patients.

Funding

National Key Research and Development Program of China (2023YFF1204600); National Natural Science Foundation of China (82227802, 82302306); Clinical Frontier Technology Program of the First Affiliated Hospital of Jinan University, China (JNU1AF-CFTP-2022-a01201); Science and Technology Projects in Guangzhou (202201020022, 2023A03J1036, 2023A03J1038); Science and Technology Youth Talent Nurturing Program of Jinan University (21623209); and Postdoctoral Science Foundation of China (2022M721349).

Differentiation of early relapse and late relapse in intermediate- and high-risk neuroblastoma with an 18F-FDG PET/CT-based radiomics nomogram

OBJECTIVES

To develop and validate an 18F-FDG PET/CT-based radiomics nomogram for differentiating early relapse and late relapse of intermediate- and high-risk neuroblastoma (NB).

METHODS

A total of eighty-five patients with relapsed NB who underwent 18F-FDG PET/CT were retrospectively evaluated. All selected patients were randomly assigned to the training set and the validation set in a 7:3 ratio. Tumors were segmented using the 3D slicer, followed by radiomics features extraction. Features selection was performed using random forest, and the radiomics score was constructed by logistic regression analysis. Clinical risk factors were identified, and the clinical model was constructed using logistic regression analysis. A radiomics nomogram was constructed by combining the radiomics score and clinical risk factors, and its performance was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).

RESULTS

Finally, the 12 most important radiomics features were used for modeling, with an area under the curve (AUC) of 0.835 and 0.824 in the training and validation sets, respectively. Age at diagnosis and International Neuroblastoma Pathology Classification were determined as clinical risk factors to construct the clinical model. In addition, the nomogram achieved an AUC of 0.902 and 0.889 for identifying early relapse in the training and validation sets, respectively, which is higher than the clinical model (AUC of 0.712 and 0.588, respectively). The predicted early relapse and actual early relapse in the calibration curves were in good agreement. The DCA showed that the radiomics nomogram was clinically useful.

CONCLUSION

Our 18F-FDG PET/CT-based radiomics nomogram can well predict early relapse and late relapse of intermediate- and high-risk NB, which contributes to follow-up and management in clinical practice.

Multiple Machine-Learning Fusion Model Based on Gd-EOB-DTPA-Enhanced MRI and Aminotransferase-to-Platelet Ratio and Gamma-Glutamyl Transferase-to-Platelet Ratio to Predict Microvascular Invasion in Solitary Hepatocellular Carcinoma: A Multicenter Study

Background

Currently, it is still confused whether preoperative aminotransferase-to-platelet ratio (APRI) and gamma-glutamyl transferase-to-platelet ratio (GPR) can predict microvascular invasion (MVI) in solitary hepatocellular carcinoma (HCC). We aimed to develop and validate a machine-learning integration model for predicting MVI using APRI, GPR and gadoxetic acid disodium (Gd-EOB-DTPA) enhanced MRI.

Methods

A total of 314 patients from XinQiao Hospital of Army Medical University were divided chronologically into training set (n = 220) and internal validation set (n = 94), and recurrence-free survival was determined to follow up after surgery. Seventy-three patients from Chongqing University Three Gorges Hospital and Luzhou People's Hospital served as external validation set. Overall, 387 patients with solitary HCC were analyzed as whole dataset set. Least absolute shrinkage and selection operator, tenfold cross-validation and multivariate logistic regression were used to gradually filter features. Six machine-learning models and an ensemble of the all models (ENS) were built. The area under the receiver operating characteristic curve (AUC) and decision curve analysis were used to evaluate model's performance.

Results

APRI, GPR, HBPratio3 ([liver SI‒tumor SI]/liver SI), PLT, peritumoral enhancement, non-smooth margin and peritumoral hypointensity were independent risk factors for MVI. Six machine-learning models showed good performance for predicting MVI in training set (AUCs range, 0.793-0.875), internal validation set (0.715-0.832), external validation set (0.636-0.746) and whole dataset set (0.756-0.850). The ENS achieved the highest AUCs (0.879 vs 0.858 vs 0.839 vs 0.851) in four cohorts with excellent calibration and more net benefit. Subgroup analysis indicated that ENS obtained excellent AUCs (0.900 vs 0.809 vs 0.865 vs 0.908) in HCC >5cm, ≤5cm, ≤3cm and ≤2cm cohorts. Kaplan‒Meier survival curves indicated that ENS achieved excellent stratification for MVI status.

Conclusion

The APRI and GPR may be new potential biomarkers for predicting MVI of HCC. The ENS achieved optimal performance for predicting MVI in different sizes HCC and may aid in the individualized selection of surgical procedures.

Neoadjuvant Chemotherapy and Neoadjuvant Chemotherapy With Immunotherapy Result in Different Tumor Shrinkage Patterns in Triple-Negative Breast Cancer

PURPOSE

This study aims to explore whether neoadjuvant chemotherapy with immunotherapy (NACI) leads to different tumor shrinkage patterns, based on magnetic resonance imaging (MRI), compared to neoadjuvant chemotherapy (NAC) alone in patients with triple-negative breast cancer (TNBC). Additionally, the study investigates the relationship between tumor shrinkage patterns and treatment efficacy was investigated.

METHODS

This retrospective study included patients with TNBC patients receiving NAC or NACI from January 2019 until July 2021 at our center. Pre- and post-treatment MRI results were obtained for each patient, and tumor shrinkage patterns were classified into three categories as follows: 1) concentric shrinkage (CS); 2) diffuse decrease; and 3) no change. Tumor shrinkage patterns were compared between the NAC and NACI groups, and the relevance of the patterns to treatment efficacy was assessed.

RESULTS

Of the 99 patients, 65 received NAC and 34 received NACI. The CS pattern was observed in 53% and 20% of patients in the NAC and NACI groups, respectively. Diffuse decrease pattern was observed in 36% and 68% of patients in the NAC and NACI groups. The association between the treatment regimens (NAC and NACI) and tumor shrinkage patterns was statistically significant (p = 0.004). The postoperative pathological complete response (pCR) rate was 45% and 82% in the NAC and NACI groups (p < 0.001), respectively. In the NACI group, 17% of patients with the CS pattern and 56% of those with the diffuse decrease pattern achieved pCR (p = 0.903). All tumor shrinkage patterns were associated with achieved a high pCR rate in the NACI group.

CONCLUSION

Our study demonstrates that the diffuse decrease pattern of tumor shrinkage is more common following NACI than that following NAC. Furthermore, our findings suggest that all tumor shrinkage patterns are associated with a high pCR rate in patients with TNBC treated with NACI.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT04909554.

Classification of superficial suspected lymph nodes: non-invasive radiomic model based on multiphase contrast-enhanced ultrasound for therapeutic options of lymphadenopathy

Background

Accurate determination of the types of lymphadenopathy is of great importance in disease diagnosis and treatment and is usually confirmed by pathological findings. Radiomics is a non-invasive tool that can extract quantitative information from medical images. Our study was designed to develop a non-invasive radiomic approach based on multiphase contrast-enhanced ultrasound (CEUS) images for the classification of different types of lymphadenopathy.

Methods

A total of 426 patients with superficial suspected lymph nodes (LNs) from three centres were grouped into a training cohort (n=190), an internal testing cohort (n=127), and an external testing cohort (n=109). The radiomic features were extracted from the prevascular phase, vascular phase, and postvascular phase of the CEUS images. Model 1 (the conventional feature model), model 2 (the multiphase radiomics model), and model 3 (the combined feature model) were established for lymphadenopathy classification. The area under the curve (AUC) and confusion matrix were used to evaluate the performance of the three models. The usefulness of the models was assessed in different threshold probabilities by decision curve analysis.

Results

There were 139 patients (32.6%) with benign LNs, 110 patients (25.8%) with lymphoma, and 177 patients (41.5%) with metastatic LNs in our population. Finally, twenty features were selected to construct the radiomics models for these three types of lymphadenopathy. Model 2 integrating multiphase images of the CEUS yielded the AUCs of 0.838, 0.739, and 0.733 in the training cohort, internal testing cohort, and external testing cohort, respectively. After the combination of conventional features and radiomic features, the AUCs of model 3 improved to 0.943, 0.823 and 0.785 in the training cohort, internal testing cohort, and external testing cohort. Besides, model 3 had an accuracy of 81.05%, sensitivity of 80%, and specificity of 90.43% in the training cohort. Model performance was further confirmed in the internal testing cohort and external testing cohort.

Conclusions

We constructed a combined feature model using a series of CEUS images for the classification of the lymphadenopathies. For patients with superficial suspected LNs, this model can help clinicians make a decision on the LN type noninvasively and choose appropriate treatments.

Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study

Introduction: Early predictive pathological complete response (pCR) is beneficial for optimizing neoadjuvant chemotherapy (NAC) strategies for breast cancer. The hematoxylin and eosin (HE)-stained slices of biopsy tissues contain a large amount of information on tumor epithelial cells and stromal. The fusion of pathological image features and clinicopathological features is expected to build a model to predict pCR of NAC in breast cancer. Methods: We retrospectively collected a total of 440 breast cancer patients from three hospitals who underwent NAC. HE-stained slices of biopsy tissues were scanned to form whole-slide images (WSIs), and pathological images of representative regions of interest (ROI) of each WSI were selected at different magnifications. Based on several different deep learning models, we propose a novel feature extraction method on pathological images with different magnifications. Further, fused with clinicopathological features, a multimodal breast cancer NAC pCR prediction model based on a support vector machine (SVM) classifier was developed and validated with two additional validation cohorts (VCs). Results: Through experimental validation of several different deep learning models, we found that the breast cancer pCR prediction model based on the SVM classifier, which uses the VGG16 model for feature extraction of pathological images at ×20 magnification, has the best prediction efficacy. The area under the curve (AUC) of deep learning pathological model (DPM) were 0.79, 0.73, and 0.71 for TC, VC1, and VC2, respectively, all of which exceeded 0.70. The AUCs of clinical model (CM), a clinical prediction model established by using clinicopathological features, were 0.79 for TC, 0.73 for VC1, and 0.71 for VC2, respectively. The multimodal deep learning clinicopathological model (DPCM) established by fusing pathological images and clinicopathological features improved the AUC of TC from 0.79 to 0.84. The AUC of VC2 improved from 0.71 to 0.78. Conclusion: Our study reveals that pathological images of HE-stained slices of pre-NAC biopsy tissues can be used to build a pCR prediction model. Combining pathological images and clinicopathological features can further enhance the predictive efficacy of the model.

Detecting anteriorly displaced temporomandibular joint discs using super-resolution magnetic resonance imaging: a multi-center study

Background: Magnetic resonance imaging (MRI) plays a crucial role in diagnosing anterior disc displacement (ADD) of the temporomandibular joint (TMJ). The primary objective of this study is to enhance diagnostic accuracy in two common disease subtypes of ADD of the TMJ on MRI, namely, ADD with reduction (ADDWR) and ADD without reduction (ADDWoR). To achieve this, we propose the development of transfer learning (TL) based on Convolutional Neural Network (CNN) models, which will aid in accurately identifying and distinguishing these subtypes. Methods: A total of 668 TMJ MRI scans were obtained from two medical centers. High-resolution (HR) MRI images were subjected to enhancement through a deep TL, generating super-resolution (SR) images. Naive Bayes (NB) and Logistic Regression (LR) models were applied, and performance was evaluated using receiver operating characteristic (ROC) curves. The model's outcomes in the test cohort were compared with diagnoses made by two clinicians. Results: The NB model utilizing SR reconstruction with 400 × 400 pixel images demonstrated superior performance in the validation cohort, exhibiting an area under the ROC curve (AUC) of 0.834 (95% CI: 0.763-0.904) and an accuracy rate of 0.768. Both LR and NB models, with 200 × 200 and 400 × 400 pixel images after SR reconstruction, outperformed the clinicians' diagnoses. Conclusion: The ResNet152 model's commendable AUC in detecting ADD highlights its potential application for pre-treatment assessment and improved diagnostic accuracy in clinical settings.

Multiparametric Approach to Breast Cancer With Emphasis on Magnetic Resonance Imaging in the Era of Personalized Breast Cancer Treatment

ABSTRACT

A multiparametric approach to breast cancer imaging offers the advantage of integrating the diverse contributions of various parameters. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is the most important MRI sequence for breast imaging. The vascularity and permeability of lesions can be estimated through the use of semiquantitative and quantitative parameters. The increased use of ultrafast DCE-MRI has facilitated the introduction of novel kinetic parameters. In addition to DCE-MRI, diffusion-weighted imaging provides information associated with tumor cell density, with advanced diffusion-weighted imaging techniques such as intravoxel incoherent motion, diffusion kurtosis imaging, and time-dependent diffusion MRI opening up new horizons in microscale tissue evaluation. Furthermore, T2-weighted imaging plays a key role in measuring the degree of tumor aggressiveness, which may be related to the tumor microenvironment. Magnetic resonance imaging is, however, not the only imaging modality providing semiquantitative and quantitative parameters from breast tumors. Breast positron emission tomography demonstrates superior spatial resolution to whole-body positron emission tomography and allows comparable delineation of breast cancer to MRI, as well as providing metabolic information, which often precedes vascular and morphological changes occurring in response to treatment. The integration of these imaging-derived factors is accomplished through multiparametric imaging. In this article, we explore the relationship among the key imaging parameters, breast cancer diagnosis, and histological characteristics, providing a technical and theoretical background for these parameters. Furthermore, we review the recent studies on the application of multiparametric imaging to breast cancer and the significance of the key imaging parameters.

Risk stratification of papillary thyroid cancers using multidimensional machine learning

BACKGROUND

Papillary thyroid cancer (PTC) is one of the most common endocrine malignancies with different risk levels. However, preoperative risk assessment of PTC is still a challenge in the worldwide. Here, the authors first report a Preoperative Risk Assessment Classifier for PTC (PRAC-PTC) by multidimensional features including clinical indicators, immune indices, genetic feature, and proteomics.

MATERIALS AND METHODS

The 558 patients collected from June 2013 to November 2020 were allocated to three groups: the discovery set [274 patients, 274 formalin-fixed paraffin-embedded (FFPE)], the retrospective test set (166 patients, 166 FFPE), and the prospective test set (118 patients, 118 fine-needle aspiration). Proteomic profiling was conducted by FFPE and fine-needle aspiration tissues from the patients. Preoperative clinical information and blood immunological indices were collected. The BRAFV600E mutation were detected by the amplification refractory mutation system.

RESULTS

The authors developed a machine learning model of 17 variables based on the multidimensional features of 274 PTC patients from a retrospective cohort. The PRAC-PTC achieved areas under the curve (AUC) of 0.925 in the discovery set and was validated externally by blinded analyses in a retrospective cohort of 166 PTC patients (0.787 AUC) and a prospective cohort of 118 PTC patients (0.799 AUC) from two independent clinical centres. Meanwhile, the preoperative predictive risk effectiveness of clinicians was improved with the assistance of PRAC-PTC, and the accuracies reached at 84.4% (95% CI: 82.9-84.4) and 83.5% (95% CI: 82.2-84.2) in the retrospective and prospective test sets, respectively.

CONCLUSION

This study demonstrated that the PRAC-PTC that integrating clinical data, gene mutation information, immune indices, high-throughput proteomics and machine learning technology in multicentre retrospective and prospective clinical cohorts can effectively stratify the preoperative risk of PTC and may decrease unnecessary surgery or overtreatment.

Early Identification of Pathologic Complete Response to Neoadjuvant Chemotherapy Using Multiphase DCE-MRI by Siamese Network in Breast Cancer: A Longitudinal Multicenter Study

BACKGROUND

Siamese network (SN) using longitudinal DCE-MRI for pathologic complete response (pCR) identification lack a unified approach to phases selection.

PURPOSE

To identify pCR in early-stage NAC, using SN with longitudinal DCE-MRI and introducing IPS for phases selection.

STUDY TYPE

Multicenter, longitudinal.

POPULATION

Center A: 162 female patients (50.63 ± 8.41 years) divided 7:3 into training and internal validation cohorts. Center B: 61 female patients (50.08 ± 7.82 years) were used as an external validation cohort.

FIELD STRENGTH/SEQUENCE

Center A: single vendor 3.0 T with a compressed-sensing volume interpolated breath-hold examination sequence. Center B: single vendor 1.5 T with volume interpolated breath-hold examination sequence.

ASSESSMENT

Patients underwent DCE-MRI before and after two NAC cycles, with tumor regions of interest (ROI) manually delineated. Histopathology was the reference for pCR identification. Models developed included a clinical one, four SN models based on IPS-selected phases, and integrated models combining clinical and SN features.

STATISTICAL TESTS

Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The DeLong test was used to compare AUCs. Net reclassification improvement and integrated discrimination improvement (IDI) tests were employed for performance comparison. P < 0.05 was considered significant.

RESULTS

In internal and external validation cohorts, the clinical model showed AUCs of 0.760 and 0.718. SN and integrated models, with increasing phases via IPS, achieved AUCs ranging from 0.813 to 0.951 and 0.818 to 0.922. Notably, SN-3 and integrated-3 and integrated-4 outperformed the clinical model. However, input phases beyond 20% did not significantly enhance performance (IDI test: SN-4 vs. SN-3, P = 0.314 and 0.630; integrated-4 vs. integrated-3, P = 0.785 and 0.709).

DATA CONCLUSION

The longitudinal multiphase DCE-MRI based on the SN demonstrates promise for identifying pCR in breast cancer.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 4.

18F-FDG PET/CT-based deep learning radiomics predicts 5-years disease-free survival after failure to achieve pathologic complete response to neoadjuvant chemotherapy in breast cancer

BACKGROUND

This study aimed to assess whether a combined model incorporating radiomic and depth features extracted from PET/CT can predict disease-free survival (DFS) in patients who failed to achieve pathologic complete response (pCR) after neoadjuvant chemotherapy.

RESULTS

This study retrospectively included one hundred and five non-pCR patients. After a median follow-up of 71 months, 15 and 7 patients experienced recurrence and death, respectively. The primary tumor volume underwent feature extraction, yielding a total of 3644 radiomic features and 4096 depth features. The modeling procedure employed Cox regression for feature selection and utilized Cox proportional-hazards models to make predictions on DFS. Time-dependent receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) were utilized to evaluate and compare the predictive performance of different models. 2 clinical features (RCB, cT), 4 radiomic features, and 7 depth features were significant predictors of DFS and were included to develop models. The integrated model incorporating RCB, cT, and radiomic and depth features extracted from PET/CT images exhibited the highest accuracy for predicting 5-year DFS in the training (AUC 0.943) and the validation cohort (AUC 0.938).

CONCLUSION

The integrated model combining radiomic and depth features extracted from PET/CT images can accurately predict 5-year DFS in non-pCR patients. It can help identify patients with a high risk of recurrence and strengthen adjuvant therapy to improve survival.

Deep learning-based radiomic nomogram to predict risk categorization of thymic epithelial tumors: A multicenter study

PURPOSE

The study was aimed to develop and evaluate a deep learning-based radiomics to predict the histological risk categorization of thymic epithelial tumors (TETs), which can be highly informative for patient treatment planning and prognostic assessment.

METHOD

A total of 681 patients with TETs from three independent hospitals were included and separated into derivation cohort and external test cohort. Handcrafted and deep learning features were extracted from preoperative contrast-enhanced CT images and selected to build three radiomics signatures (radiomics signature [Rad_Sig], deep learning signature [DL_Sig] and deep learning radiomics signature [DLR_Sig]) to predict risk categorization of TETs. A deep learning-based radiomic nomogram (DLRN) was then depicted to visualize the classification evaluation. The performance of predictive models was compared using the receiver operating characteristic and decision curve analysis (DCA).

RESULTS

Among three radiomics signatures, DLR_Sig demonstrated optimum performance with an AUC of 0.883 for the derivation cohort and 0.749 for the external test cohort. Combining DLR_Sig with age and gender, DLRN was depict and exhibited optimum performance among all radiomics models with an AUC of 0.965, accuracy of 0.911, sensitivity of 0.921 and specificity of 0.902 in the derivation cohort, and an AUC of 0.786, accuracy of 0.774, sensitivity of 0.778 and specificity of 0.771 in the external test cohort. The DCA showed that DLRN had greater clinical benefit than other radiomics signatures.

CONCLUSIONS

Our study developed and validated a DLRN to accurately predict the risk categorization of TETs, which has potential to facilitate individualized treatment and improve patient prognosis evaluation.

Preoperative prediction of tumor budding in rectal cancer using multiple machine learning algorithms based on MRI T2WI radiomics

Objective

This study aimed to explore the radiomics model based on magnetic resonance imaging (MRI) T2WI and compare the value of different machine algorithms in preoperatively predicting tumor budding (TB) grading in rectal cancer.

Methods

A retrospective study was conducted on 266 patients with preoperative rectal MRI examinations, who underwent complete surgical resection and confirmed pathological diagnosis of rectal cancer. Among them, patients from Qingdao West Coast Hospital were assigned as the training group (n=172), while patients from other hospitals were assigned as the external validation group (n=94). Regions of interest (ROIs) were delineated, and image features were extracted and dimensionally reduced using the Least Absolute Shrinkage and Selection Operator (LASSO). Eight machine algorithms were used to construct the models, and the diagnostic performance of the models was evaluated and compared using receiver operating characteristic (ROC) curves and the area under the curve (AUC), as well as clinical utility assessment using decision curve analysis (DCA).

Results

A total of 1197 features were extracted, and after feature selection and dimension reduction, 11 image features related to TB grading were obtained. Among the eight algorithm models, the support vector machine (SVM) algorithm achieved the best diagnostic performance, with accuracy, sensitivity, and specificity of 0.826, 0.949, and 0.723 in the training group, and 0.713, 0.579, and 0.804 in the validation group, respectively. DCA demonstrated the clinical utility of this radiomics model.

Conclusion

The radiomics model based on MR T2WI can provide an effective and noninvasive method for preoperative TB grading assessment in patients with rectal cancer.

Comprehensive scientometrics and visualization study profiles lymphoma metabolism and identifies its significant research signatures

Background

There is a wealth of poorly utilized unstructured data on lymphoma metabolism, and scientometrics and visualization study could serve as a robust tool to address this issue. Hence, it was implemented.

Methods

After strict quality control, numerous data regarding the lymphoma metabolism were mined, quantified, cleaned, fused, and visualized from documents (n = 2925) limited from 2013 to 2022 using R packages, VOSviewer, and GraphPad Prism.

Results

The linear fitting analysis generated functions predicting the annual publication number (y = 31.685x - 63628, R² = 0.93614, Prediction in 2027: 598) and citation number (y = 1363.7x - 2746019, R² = 0.94956, Prediction in 2027: 18201). In the last decade, the most academically performing author, journal, country, and affiliation were Meignan Michel (n = 35), European Journal of Nuclear Medicine and Molecular Imaging (n = 1653), USA (n = 3114), and University of Pennsylvania (n = 86), respectively. The hierarchical clustering based on unsupervised learning further divided research signatures into five clusters, including the basic study cluster (Cluster 1, Total Link Strength [TLS] = 1670, Total Occurrence [TO] = 832) and clinical study cluster (Cluster 3, TLS = 3496, TO = 1328). The timeline distribution indicated that radiomics and artificial intelligence (Cluster 4, Average Publication Year = 2019.39 ± 0.21) is a relatively new research cluster, and more endeavors deserve. Research signature burst and linear regression analysis further confirmed the findings above and revealed additional important results, such as tumor microenvironment (a = 0.6848, R² = 0.5194, p = 0.019) and immunotherapy (a = 1.036, R² = 0.6687, p = 0.004). More interestingly, by performing a "Walktrap" algorithm, the community map indicated that the "apoptosis, metabolism, chemotherapy" (Centrality = 12, Density = 6), "lymphoma, pet/ct, prognosis" (Centrality = 11, Density = 1), and "genotoxicity, mutagenicity" (Centrality = 9, Density = 4) are crucial but still under-explored, illustrating the potentiality of these research signatures in the field of the lymphoma metabolism.

Conclusion

This study comprehensively mines valuable information and offers significant predictions about lymphoma metabolism for its clinical and experimental practice.