Multiparametric Analysis of Longitudinal Quantitative MRI data to Identify Distinct Tumor Habitats in Preclinical Models of Breast Cancer

A mathematical model for predicting the spatiotemporal response of breast cancer cells treated with doxorubicin

Tumor heterogeneity contributes significantly to chemoresistance, a leading cause of treatment failure. To better personalize therapies, it is essential to develop tools capable of identifying and predicting intra- and inter-tumor heterogeneities. Biology-inspired mathematical models are capable of attacking this problem, but tumor heterogeneity is often overlooked in in-vivo modeling studies, while phenotypic considerations capturing spatial dynamics are not typically included in in-vitro modeling studies. We present a data assimilation-prediction pipeline with a two-phenotype model that includes a spatiotemporal component to characterize and predict the evolution of in-vitro breast cancer cells and their heterogeneous response to chemotherapy. Our model assumes that the cells can be divided into two subpopulations: surviving cells unaffected by the treatment, and irreversibly damaged cells undergoing treatment-induced death. MCF7 breast cancer cells were previously cultivated in wells for up to 1000 hours, treated with various concentrations of doxorubicin and imaged with time-resolved microscopy to record spatiotemporally-resolved cell count data. Images were used to generate cell density maps. Treatment response predictions were initialized by a training set and updated by weekly measurements. Our mathematical model successfully calibrated the spatiotemporal cell growth dynamics, achieving median [range] concordance correlation coefficients of > .99 [.88, >.99] and .73 [.58, .85] across the whole well and individual pixels, respectively. Our proposed data assimilation-prediction approach achieved values of .97 [.44, >.99] and .69 [.35, .79] for the whole well and individual pixels, respectively. Thus, our model can capture and predict the spatiotemporal dynamics of MCF7 cells treated with doxorubicin in an in-vitro setting.

Multi-machine Learning Model Based on Habitat Subregions for Outcome Prediction in Adenomyosis Treated by Uterine Artery Embolization

RATIONALE AND OBJECTIVES

To establish and validate a predictive multi-machine learning model for the long-term efficacy of uterine artery embolization (UAE) in the treatment of adenomyosis based on habitat subregions.

MATERIALS AND METHODS

Patients who underwent UAE for adenomyosis at institution A between November 2015 and June 2018 were included in the training cohort and those at institution B between June 2017 and June 2019 were included in the test cohort. The regions of interest (ROI) were manually segmented on the T2-weighted images (T2WI). The ROIs were subsequently partitioned into habitat subregions using k-means clustering. Radiomic features were extracted from each subregion on T1WI, T2WI, apparent diffusion coefficient, and contrast-enhanced images. The least absolute shrinkage and selection operator (LASSO) was used to select the subregion radiomics features. With the improvement in patients' symptoms at 36 months post-UAE, the habitat subregion features were trained using six machine-learning classifiers. The most suitable classifier was chosen based on model performance to establish the habitat radiomics model (HRM). The efficacy of the model was validated using both the training and test cohorts. Finally, a whole-region radiomics model (WRM) and clinical model (CM) were established. The Delong test was used to compare the predictive performance of the habitat subregion model and the two other models.

RESULTS

The study included 258 patients, 191 in the training cohort and 67 in the test cohort. The ROIs were divided into four habitat subregions. Radiomics features were extracted from different sequence images of the subregions. After LASSO regression, 24 habitat subregion features were included in the model. Based on the receiver operating characteristic curve analysis, the area under the curve (AUC) of the HRM was 0.921 (95% CI, 0.857-0.985, training) and 0.890 (95% CI, 0.736-1.000, test). The AUCs for the WRM were 0.805 (95% CI, 0.737-0.872, training) and 0.693 (95% CI, 0.497-0.889, test). Compared to the HRM, the difference in predictive performance was statistically significant (p = 0.008, training; p = 0.007, test). The AUCs for the CM were 0.788 (95% CI, 0.711-0.866, training) and 0.735 (95% CI, 0.566-0.903, test). Compared to the HRM, there was a statistically significant difference in the training cohort (p = 0.014) but not in the test cohort (p = 0.186).

CONCLUSION

The HRM can predict the long-term efficacy of UAE in the treatment of adenomyosis. The predictive performance was superior to that of both the WRM and CM, serving as an effective tool to assist interventional physicians in clinical decision-making.

Multi-objective Bayesian optimization with enhanced features for adaptively improved glioblastoma partitioning and survival prediction

Glioblastoma, an aggressive brain tumor prevalent in adults, exhibits heterogeneity in its microstructures and vascular patterns. The delineation of its subregions could facilitate the development of region-targeted therapies. However, current unsupervised learning techniques for this task face challenges in reliability due to fluctuations of clustering algorithms, particularly when processing data from diverse patient cohorts. Furthermore, stable clustering results do not guarantee clinical meaningfulness. To establish the clinical relevance of these subregions, we will perform survival predictions using radiomic features extracted from them. Following this, achieving a balance between outcome stability and clinical relevance presents a significant challenge, further exacerbated by the extensive time required for hyper-parameter tuning. In this study, we introduce a multi-objective Bayesian optimization (MOBO) framework, which leverages a Feature-enhanced Auto-Encoder (FAE) and customized losses to assess both the reproducibility of clustering algorithms and the clinical relevance of their outcomes. Specifically, we embed the entirety of these processes within the MOBO framework, modeling both using distinct Gaussian Processes (GPs). The proposed MOBO framework can automatically balance the trade-off between the two criteria by employing bespoke stability and clinical significance losses. Our approach efficiently optimizes all hyper-parameters, including the FAE architecture and clustering parameters, within a few steps. This not only accelerates the process but also consistently yields robust MRI subregion delineations and provides survival predictions with strong statistical validation.

MRI-based habitat imaging in cancer treatment: current technology, applications, and challenges

Extensive efforts have been dedicated to exploring the impact of tumor heterogeneity on cancer treatment at both histological and genetic levels. To accurately measure intra-tumoral heterogeneity, a non-invasive imaging technique, known as habitat imaging, was developed. The technique quantifies intra-tumoral heterogeneity by dividing complex tumors into distinct sub- regions, called habitats. This article reviews the following aspects of habitat imaging in cancer treatment, with a focus on radiotherapy: (1) Habitat imaging biomarkers for assessing tumor physiology; (2) Methods for habitat generation; (3) Efforts to combine radiomics, another imaging quantification method, with habitat imaging; (4) Technical challenges and potential solutions related to habitat imaging; (5) Pathological validation of habitat imaging and how it can be utilized to evaluate cancer treatment by predicting treatment response including survival rate, recurrence, and pathological response as well as ongoing open clinical trials.

Do Habitat MRI and Fractal Analysis Help Distinguish Triple-Negative Breast Cancer From Non-Triple-Negative Breast Carcinoma

Purpose: To determine whether multiparametric MRI-based spatial habitats and fractal analysis can help distinguish triple-negative breast cancer (TNBC) from non-TNBC. Method: Multiparametric DWI and DCE-MRI at 3T were obtained from 142 biopsy- and surgery-proven breast cancer with 148 breast lesions (TNBC = 26 and non-TNBC = 122). The contrast-enhancing lesions were divided into 3 spatial habitats based on perfusion and diffusion patterns using K-means clustering. The fractal dimension (FD) of the tumour subregions was calculated. The accuracy of the habitat segmentation was measured using the Dice index. Inter- and intra-reader reliability were evaluated with the intraclass correlation coefficient (ICC). The ability to predict TNBC status was assessed using the receiver operating characteristic curve. Results: The Dice index for the whole tumour was 0.81 for inter-reader and 0.88 for intra-reader reliability. The inter- and intra-reader reliability were excellent for all 3 tumour habitats and fractal features (ICC > 0.9). TNBC had a lower hypervascular cellular habitat and higher FD 1 compared to non-TNBC (all P < .001). Multivariate analysis confirmed that hypervascular cellular habitat (OR = 0.88) and FD 1 (OR = 1.35) were independently associated with TNBC (all P < .001) after adjusting for rim enhancement, axillary lymph nodes status, and histological grade. The diagnostic model combining hypervascular cellular habitat and FD 1 showed excellent discriminatory ability for TNBC, with an AUC of 0.951 and an accuracy of 91.9%. Conclusions: The fraction of hypervascular cellular habitat and its FD may serve as useful imaging biomarkers for predicting TNBC status.

Habitat Radiomics Based on MRI for Predicting Platinum Resistance in Patients with High-Grade Serous Ovarian Carcinoma: A Multicenter Study

RATIONALE AND OBJECTIVES

This study aims to explore the feasibility of MRI-based habitat radiomics for predicting response of platinum-based chemotherapy in patients with high-grade serous ovarian carcinoma (HGSOC), and compared to conventional radiomics and deep learning models.

MATERIALS AND METHODS

A retrospective study was conducted on HGSOC patients from three hospitals. K-means algorithm was used to perform clustering on T2-weighted images (T2WI), contrast-enhanced T1-weighted images (CE-T1WI), and apparent diffusion coefficient (ADC) maps. After feature extraction and selection, the radiomics model, habitat model, and deep learning model were constructed respectively to identify platinum-resistant and platinum-sensitive patients. A nomogram was developed by integrating the optimal model and clinical independent predictors. The model performance and benefit was assessed using the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI).

RESULTS

A total of 394 eligible patients were incorporated. Three habitats were clustered, a significant difference in habitat 2 (weak enhancement, high ADC values, and moderate T2WI signal) was found between the platinum-resistant and platinum-sensitive groups (P < 0.05). Compared to the radiomics model (0.640) and deep learning model (0.603), the habitat model had a higher AUC (0.710). The nomogram, combining habitat signatures with a clinical independent predictor (neoadjuvant chemotherapy), yielded a highest AUC (0.721) among four models, with positive NRI and IDI.

CONCLUSION

MRI-based habitat radiomics had the potential to predict response of platinum-based chemotherapy in patients with HGSOC. The nomogram combining with habitat signature had a best performance and good model gains for identifying platinum-resistant patients.

Dual anti-HER2/EGFR inhibition synergistically increases therapeutic effects and alters tumor oxygenation in HNSCC

Epidermal growth factor receptor (EGFR), human epidermal growth factor receptor 2 (HER2), and hypoxia are associated with radioresistance. The goal of this study is to study the synergy of anti-HER2, trastuzumab, and anti-EGFR, cetuximab, and characterize the tumor microenvironment components that may lead to increased radiation sensitivity with dual anti-HER2/EGFR therapy in head and neck squamous cell carcinoma (HNSCC). Positron emission tomography (PET) imaging ([89Zr]-panitumumab and [89Zr]-pertuzumab) was used to characterize EGFR and HER2 in HNSCC cell line tumors. HNSCC cells were treated with trastuzumab, cetuximab, or combination followed by radiation to assess for viability and radiosensitivity (colony forming assay, immunofluorescence, and flow cytometry). In vivo, [18F]-FMISO-PET imaging was used to quantify changes in oxygenation during treatment. Bliss Test of Synergy was used to identify combination treatment synergy. Quantifying EGFR and HER2 receptor expression revealed a 50% increase in heterogeneity of HER2 relative to EGFR. In vitro, dual trastuzumab-cetuximab therapy shows significant decreases in DNA damage response and increased response to radiation therapy (p < 0.05). In vivo, tumors treated with dual anti-HER2/EGFR demonstrated decreased tumor hypoxia, when compared to single agent therapies. Dual trastuzumab-cetuximab demonstrates synergy and can affect tumor oxygenation in HNSCC. Combination trastuzumab-cetuximab modulates the tumor microenvironment through reductions in tumor hypoxia and induces sustained treatment synergy.

MRI-based tumor shrinkage patterns after early neoadjuvant therapy in breast cancer: correlation with molecular subtypes and pathological response after therapy

BACKGROUND

MRI-based tumor shrinkage patterns (TSP) after neoadjuvant therapy (NAT) have been associated with pathological response. However, the understanding of TSP after early NAT remains limited. We aimed to analyze the relationship between TSP after early NAT and pathological response after therapy in different molecular subtypes.

METHODS

We prospectively enrolled participants with invasive ductal breast cancers who received NAT and performed pretreatment DCE-MRI from September 2020 to August 2022. Early-stage MRIs were performed after the first (1st-MRI) and/or second (2nd-MRI) cycle of NAT. Tumor shrinkage patterns were categorized into four groups: concentric shrinkage, diffuse decrease (DD), decrease of intensity only (DIO), and stable disease (SD). Logistic regression analysis was performed to identify independent variables associated with pathologic complete response (pCR), and stratified analysis according to tumor hormone receptor (HR)/human epidermal growth factor receptor 2 (HER2) disease subtype.

RESULTS

344 participants (mean age: 50 years, 113/345 [33%] pCR) with 345 tumors (1 bilateral) had evaluable 1st-MRI or 2nd-MRI to comprise the primary analysis cohort, of which 244 participants with 245 tumors had evaluable 1st-MRI (82/245 [33%] pCR) and 206 participants with 207 tumors had evaluable 2nd-MRI (69/207 [33%] pCR) to comprise the 1st- and 2nd-timepoint subgroup analysis cohorts, respectively. In the primary analysis, multivariate analysis showed that early DD pattern (OR = 12.08; 95% CI 3.34-43.75; p < 0.001) predicted pCR independently of the change in tumor size (OR = 1.37; 95% CI 0.94-2.01; p = 0.106) in HR+/HER2- subtype, and the change in tumor size was a strong pCR predictor in HER2+ (OR = 1.61; 95% CI 1.22-2.13; p = 0.001) and triple-negative breast cancer (TNBC, OR = 1.61; 95% CI 1.22-2.11; p = 0.001). Compared with the change in tumor size, the SD pattern achieved a higher negative predictive value in HER2+ and TNBC. The statistical significance of complete 1st-timepoint subgroup analysis was consistent with the primary analysis.

CONCLUSION

The diffuse decrease pattern in HR+/HER2- subtype and stable disease in HER2+ and TNBC after early NAT could serve as additional straightforward and comprehensible indicators of treatment response.

TRIAL REGISTRATION

Trial registration at https://www.chictr.org.cn/ .

REGISTRATION NUMBER

ChiCTR2000038578, registered September 24, 2020.

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.

Fast deep learning reconstruction techniques for preclinical magnetic resonance fingerprinting

We propose a deep learning (DL) model and a hyperparameter optimization strategy to reconstruct T1 and T2 maps acquired with the magnetic resonance fingerprinting (MRF) methodology. We applied two different MRF sequence routines to acquire images of ex vivo rat brain phantoms using a 7-T preclinical scanner. Subsequently, the DL model was trained using experimental data, completely excluding the use of any theoretical MRI signal simulator. The best combination of the DL parameters was implemented by an automatic hyperparameter optimization strategy, whose key aspect is to include all the parameters to the fit, allowing the simultaneous optimization of the neural network architecture, the structure of the DL model, and the supervised learning algorithm. By comparing the reconstruction performances of the DL technique with those achieved from the traditional dictionary-based method on an independent dataset, the DL approach was shown to reduce the mean percentage relative error by a factor of 3 for T1 and by a factor of 2 for T2 , and to improve the computational time by at least a factor of 37. Furthermore, the proposed DL method enables maintaining comparable reconstruction performance, even with a lower number of MRF images and a reduced k-space sampling percentage, with respect to the dictionary-based method. Our results suggest that the proposed DL methodology may offer an improvement in reconstruction accuracy, as well as speeding up MRF for preclinical, and in prospective clinical, investigations.

Structural and practical identifiability of contrast transport models for DCE-MRI

Compartment models are widely used to quantify blood flow and transport in dynamic contrast-enhanced magnetic resonance imaging. These models analyze the time course of the contrast agent concentration, providing diagnostic and prognostic value for many biological systems. Thus, ensuring accuracy and repeatability of the model parameter estimation is a fundamental concern. In this work, we analyze the structural and practical identifiability of a class of nested compartment models pervasively used in analysis of MRI data. We combine artificial and real data to study the role of noise in model parameter estimation. We observe that although all the models are structurally identifiable, practical identifiability strongly depends on the data characteristics. We analyze the impact of increasing data noise on parameter identifiability and show how the latter can be recovered with increased data quality. To complete the analysis, we show that the results do not depend on specific tissue characteristics or the type of enhancement patterns of contrast agent signal.

Potential Antihuman Epidermal Growth Factor Receptor 2 Target Therapy Beneficiaries: The Role of MRI-Based Radiomics in Distinguishing Human Epidermal Growth Factor Receptor 2-Low Status of Breast Cancer

BACKGROUND

Multiparametric MRI radiomics could distinguish human epidermal growth factor receptor 2 (HER2)-positive from HER2-negative breast cancers. However, its value for further distinguishing HER2-low from HER2-negative breast cancers has not been investigated.

PURPOSE

To investigate whether multiparametric MRI-based radiomics can distinguish HER2-positive from HER2-negative breast cancers (task 1) and HER2-low from HER2-negative breast cancers (task 2).

STUDY TYPE

Retrospective.

POPULATION

Task 1: 310 operable breast cancer patients from center 1 (97 HER2-positive and 213 HER2-negative); task 2: 213 HER2-negative patients (108 HER2-low and 105 HER2-zero); 59 patients from center 2 (16 HER2-positive, 27 HER2-low and 16 HER2-zero) for external validation.

FIELD STRENGTH/SEQUENCE

A 3.0 T/T1-weighted contrast-enhanced imaging (T1CE), diffusion-weighted imaging (DWI)-derived apparent diffusion coefficient (ADC).

ASSESSMENT

Patients in center 1 were assigned to a training and internal validation cohort at a 2:1 ratio. Intratumoral and peritumoral features were extracted from T1CE and ADC. After dimensionality reduction, the radiomics signatures (RS) of two tasks were developed using features from T1CE (RS-T1CE), ADC (RS-ADC) alone and T1CE + ADC combination (RS-Com).

STATISTICAL TESTS

Mann-Whitney U tests, the least absolute shrinkage and selection operator, receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

RESULTS

For task 1, RS-ADC yielded higher area under the ROC curve (AUC) in the training, internal, and external validation of 0.767/0.725/0.746 than RS-T1CE (AUC = 0.733/0.674/0.641). For task 2, RS-T1CE yielded higher AUC of 0.765/0.755/0.678 than RS-ADC (AUC = 0.706/0.608/0.630). For both of task 1 and task 2, RS-Com achieved the best performance with AUC of 0.793/0.778/0.760 and 0.820/0.776/0.711, respectively, and obtained higher clinical benefit in DCA compared with RS-T1CE and RS-ADC. The calibration curves of all RS demonstrated a good fitness.

DATA CONCLUSION

Multiparametric MRI radiomics could noninvasively and robustly distinguish HER2-positive from HER2-negative breast cancers and further distinguish HER2-low from HER2-negative breast cancers.

EVIDENCE LEVEL

3.

TECHNICAL EFFICACY

Stage 2.

The effect of tumor vascular remodeling and immune microenvironment activation induced by radiotherapy: quantitative evaluation with magnetic resonance/photoacoustic dual-modality imaging

Background

Tumor radiotherapy combined with immunotherapy for solid tumors has been proposed, but tumor vascular structure abnormalities and immune microenvironment often affect the therapeutic effect of tumor, and multimodal imaging technology can provide more accurate and comprehensive information in tumor research. The purpose of this study was to evaluate the dynamic monitoring of tumor blood vessels and microenvironment induced by radiotherapy by magnetic resonance/photoacoustic (MR/PA) imaging, and to explore its application value in radiotherapy combined with immunotherapy.

Methods

The tumor-bearing mice were randomly allocated into six groups, which received different doses of radiation therapy (2 Gy ×14 or 8 Gy ×3) and anti-programmed death ligand-1 (PD-L1) antibody for two consecutive weeks. MR/PA imaging was used to noninvasively evaluate the response of tumor to different doses of radiotherapy, combined with histopathological techniques to observe the tumor vessels and microenvironment.

Results

The inhibitory effect of high-dose radiotherapy on tumors was significantly greater than that of low-dose radiotherapy, with the MR images revealing that the signal intensity decreased significantly (P<0.05). Compared with those in the other groups, the tumor vascular density decreased significantly (P<0.01), and the vascular maturity index increased significantly in the low-dose group (P<0.05). The PA images showed that the deoxyhemoglobin and total hemoglobin levels decreased and the SO2 level increased after radiation treatment (P<0.05). In addition, the high-dose group had an increased number of tumor-infiltrating lymphocytes (CD4+ T and CD8+ T cells) (P<0.01, P<0.05) and natural killer cells (P<0.001) and increased PD-L1 expression in the tumors (P<0.05). The combination of radiotherapy and immunotherapy increased the survival rate of the mice (P<0.05), and a regimen of an 8 Gy dose of radiation combined with immunotherapy inhibited tumor growth and increased the survival rate of the mice to a greater degree than the 2 Gy radiation dose with immunotherapy combination (P=0.002).

Conclusions

Differential fractionation radiotherapy doses exert biological effects on tumor vascular and the immune microenvironment, and MR/PA can be used to evaluate tumor vascular remodeling after radiotherapy, which has certain value for the clinical applications of radiotherapy combined with immunotherapy.

Vascular phenotyping of the invasive front in breast cancer using a 3D angiogenesis atlas

OBJECTIVE

Vascular remodeling at the invasive tumor front (ITF) plays a critical role in progression and metastasis of triple negative breast cancer (TNBC). Therefore, there is a crucial need to characterize the vascular phenotype (i.e. changes in the structure and function of vasculature) of the ITF and tumor core (TC) in TNBC. This requires high-resolution, 3D structural and functional microvascular data that spans the ITF and TC (i.e. ∼4-5 mm from the tumor's edge). Since such data are often challenging to obtain with most conventional imaging approaches, we employed a unique "3D whole-tumor angiogenesis atlas" derived from orthotopic xenografts to characterize the vascular phenotype of the ITF and TC in TNBC.

METHODS

First, high-resolution (8 μm) computed tomography (CT) images of "whole-tumor" microvasculature were acquired from eight orthotopic TNBC xenografts, of which three tumors were excised at post-inoculation day 21 (i.e. early-stage) and five tumors were excised at post-inoculation day 35 (i.e. advanced-stage). These 3D morphological CT data were combined with soft tissue contrast from MRI as well as functional data generated in silico using image-based hemodynamic modeling to generate a multi-layered "angiogenesis atlas". Employing this atlas, blood vessels were first spatially stratified within the ITF (i.e. ≤1 mm from the tumor's edge) and TC (i.e. >1 mm from the tumor's edge) of each tumor xenograft. Then, a novel method was developed to visualize and characterize microvascular remodeling and perfusion changes in terms of distance from the tumor's edge.

RESULTS

The angiogenesis atlas enabled the 3D visualization of changes in tumor vessel growth patterns, morphology and perfusion within the ITF and TC. Early and advanced stage tumors demonstrated significant differences in terms of their edge-to-center distributions for vascular surface area density, vascular length density, intervessel distance and simulated perfusion density (p ≪ 0.01). Elevated vascular length density, vascular surface area density and perfusion density along the circumference of the ITF was suggestive of a preferential spatial pattern of angiogenic growth in this tumor cohort. Finally, we demonstrated the feasibility of differentiating the vascular phenotypes of ITF and TC in these TNBC xenografts.

CONCLUSIONS

The combination of a 3D angiogenesis atlas and image-based hemodynamic modeling heralds a new approach for characterizing the role of vascular remodeling in cancer and other diseases.

Combination Therapy with Trastuzumab and Niraparib: Quantifying Early Proliferative Alterations in HER2+ Breast Cancer Models

HER2-targeted treatments have improved survival rates in HER2+ breast cancer patients, yet poor responsiveness remains a major clinical obstacle. Recently, HER2+ breast cancer cells, both resistant and responsive to HER2-targeted therapies, have demonstrated sensitivity to poly-(ADP-ribose) polymerase (PARP) inhibition, independent of DNA repair deficiencies. This study seeks to describe biological factors that precede cell viability changes in response to the combination of trastuzumab and PARP inhibition. Treatment response was evaluated in HER2+ and HER2- breast cancer cells. Further, we evaluated the utility of 3'-Deoxy-3'-[18F]-fluorothymidine positron emission tomography ([18F]FLT-PET) imaging for early response assessment in a HER2+ patient derived xenograft (PDX) model of breast cancer. In vitro, we observed decreased cell viability. In vivo, we observed decreased inhibition in tumor growth in combination therapies, compared to vehicle and monotherapy-treated cohorts. Early assessment of cellular proliferation corresponds to endpoint cell viability. Standard summary statistics of [18F]FLT uptake from PET were insensitive to early proliferative changes. Meanwhile, histogram analysis of [18F]FLT uptake indicated the potential translatability of imaging proliferation biomarkers. This study highlights the potential of combined trastuzumab and PARP inhibition in HER2+ breast cancer, while demonstrating a need for optimization of [18F]FLT-PET quantification in heterogeneous models of HER2+ breast cancer.

Mathematical modelling of the dynamics of image-informed tumor habitats in a murine model of glioma

Tumors exhibit high molecular, phenotypic, and physiological heterogeneity. In this effort, we employ quantitative magnetic resonance imaging (MRI) data to capture this heterogeneity through imaging-based subregions or "habitats" in a murine model of glioma. We then demonstrate the ability to model and predict the growth of the habitats using coupled ordinary differential equations (ODEs) in the presence and absence of radiotherapy. Female Wistar rats (N = 21) were inoculated intracranially with 10⁶ C6 glioma cells, a subset of which received 20 Gy (N = 5) or 40 Gy (N = 8) of radiation. All rats underwent diffusion-weighted and dynamic contrast-enhanced MRI at up to seven time points. All MRI data at each visit were subsequently clustered using k-means to identify physiological tumor habitats. A family of four models consisting of three coupled ODEs were developed and calibrated to the habitat time series of control and treated rats and evaluated for predictive capability. The Akaike Information Criterion was used for model selection, and the normalized sum-of-square-error (SSE) was used to evaluate goodness-of-fit in model calibration and prediction. Three tumor habitats with significantly different imaging data characteristics (p < 0.05) were identified: high-vascularity high-cellularity, low-vascularity high-cellularity, and low-vascularity low-cellularity. Model selection resulted in a five-parameter model whose predictions of habitat dynamics yielded SSEs that were similar to the SSEs from the calibrated model. It is thus feasible to mathematically describe habitat dynamics in a preclinical model of glioma using biology-based ODEs, showing promise for forecasting heterogeneous tumor behavior.

Development and verification of radiomics framework for computed tomography image segmentation

BACKGROUND

Radiomics has been considered an imaging marker for capturing quantitative image information (QII). The introduction of radiomics to image segmentation is desirable but challenging.

PURPOSE

This study aims to develop and validate a radiomics-based framework for image segmentation (RFIS).

METHODS

RFIS is designed using features extracted from volume (svfeatures) created by sliding window (swvolume). The 53 svfeatures are extracted from 11 phantom series. Outliers in the svfeature datasets are detected by isolation forest (iForest) and specified as the mean value. The percentage coefficient of variation (%COV) is calculated to evaluate the reproducibility of svfeatures. RFIS is constructed and applied to the gross target volume (GTV) segmentation from the peritumoral region (GTV with a 10 mm margin) to assess its feasibility. The 127 lung cancer images are enrolled. The test-retest method, correlation matrix, and Mann-Whitney U test (p < 0.05) are used to select non-redundant svfeatures of statistical significance from the reproducible svfeatures. The synthetic minority over-sampling technique is utilized to balance the minority group in the training sets. The support vector machine is employed for RFIS construction, which is tuned in the training set using 10-fold stratified cross-validation and then evaluated in the test sets. The swvolumes with the consistent classification results are grouped and merged. Mode filtering is performed to remove very small subvolumes and create relatively large regions of completely uniform character. In addition, RFIS performance is evaluated by the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, specificity, and Dice similarity coefficient (DSC).

RESULTS

30249 phantom and 145008 patient image swvolumes were analyzed. Forty-nine (92.45% of 53) svfeatures represented excellent reproducibility(%COV<15). Forty-five features (91.84% of 49) included five categories that passed test-retest analysis. Thirteen svfeatures (28.89% of 45) svfeatures were selected for RFIS construction. RFIS showed an average (95% confidence interval) sensitivity of 0.848 (95% CI:0.844-0.883), a specificity of 0.821 (95% CI: 0.818-0.825), an accuracy of 83.48% (95% CI: 83.27%-83.70%), and an AUC of 0.906 (95% CI: 0.904-0.908) with cross-validation. The sensitivity, specificity, accuracy, and AUC were equal to 0.762 (95% CI: 0.754-0.770), 0.840 (95% CI: 0.837-0.844), 82.29% (95% CI: 81.90%-82.60%), and 0.877 (95% CI: 0.873-0.881) in the test set, respectively. GTV was segmented by grouping and merging swvolume with identical classification results. The mean DSC after mode filtering was 0.707 ± 0.093 in the training sets and 0.688 ± 0.072 in the test sets.

CONCLUSION

Reproducible svfeatures can capture the differences in QII among swvolumes. RFIS can be applied to swvolume classification, which achieves image segmentation by grouping and merging the swvolume with similar QII.

A Machine Learning Model Based on Unsupervised Clustering Multihabitat to Predict the Pathological Grading of Meningiomas

Purpose

We aim to develop and validate a machine learning model by enhanced MRI to determine the pathological grading of meningiomas with unsupervised clustering image analysis method, which are multihabitat to reflect the inherent heterogeneity of tumors.

Materials and Methods

A total of 120 patients with meningiomas confirmed by postoperative pathology were included in the study, including 60 patients with low-grade meningiomas (WHO grade I) and 60 patients with high-grade meningiomas (WHO grade II and WHO grade III). All patients underwent complete head enhanced magnetic resonance scans before surgery or any anti-tumor treatment. Enrolled patients in the group received surgical resection and obtained postoperative pathological data. The patients in the training group (84 people) and the test group (36 people) were randomly divided into two groups according to the ratio of 7 to 3. Multi-habitat features were extracted from MRI images based on enhanced T1. Machine learning method was used to model, which was used to distinguish high-grade meningioma from low-grade meningioma. At the same time, the obtained machine learning model was calibrated and evaluated.

Results

In patients with low-grade meningioma and high-grade meningioma, we found significant differences in Silhouette coefficient (P<0.05). In the machine learning model, the area under the curve was 0.838 in the training group (sensitivity, 67.65%; specificity, 88.82%) and 0.73 in the test group (sensitivity, 69.05%; specificity, 71.43%). After the analysis of calibration curve and decision curve analysis, the model had shown the potential of great application value.

Conclusions

Multi-habitat analysis based on enhanced MRI (T1) could accurately predict the pathological grading of meningiomas. This unsupervised image-based method could reflect the direct heterogeneity between high-grade meningiomas and low-grade meningiomas, which is of great significance for patients' treatment and prevention of recurrence.

A comparative study of functional MRI in predicting response of regional nodes to induction chemotherapy in patients with nasopharyngeal carcinoma

Purpose

To identify and compare the value of functional MRI (fMRI) in predicting the early response of metastatic cervical lymph nodes (LNs) to induction chemotherapy (IC) in nasopharyngeal carcinoma (NPC) patients.

Methods

This prospective study collected 94 metastatic LNs from 40 consecutive NPC patients treated with IC from January 2021 to May 2021. Conventional diffusion-weighted imaging, diffusion kurtosis imaging, intravoxel incoherent motion, and dynamic contrast-enhanced magnetic resonance imaging were performed before and after IC. The parameter maps apparent diffusion coefficient (ADC), mean diffusion coefficient (MD), mean kurtosis (MK), Dslow, Dfast, perfusion fraction (PF), Ktrans, Ve, and Kep) of the metastatic nodes were calculated by the Functool postprocessing software. All LNs were classified as the responding group (RG) and non-responding group (NRG) according to Response Evaluation Criteria in Solid Tumors 1.1. The fMRI parameters were compared before and after IC and between the RG and the NRG. The significant parameters are fitted by logistic regression analysis to produce new predictive factor (PRE)–predicted probabilities. Logistic regression analysis and receiver operating characteristic (ROC) curves were performed to further identify and compare the efficacy of the parameters.

Results

After IC, the mean values of ADC, MD, and Dslow significantly increased, while MK, Dfast, and Ktrans values decreased dramatically, while no significant difference was detected in Ve and Kep. Compared with NRG, PF-pre and Ktrans-pre values in the RG were higher statistically. The areas under the ROC for the pretreatment PF, Ktrans, and PRE were 0.736, 0.722, and 0.810, respectively, with the optimal cutoff value of 222 × 10-4, 934 × 10-3/min, and 0.6624, respectively.

Conclusions

The pretreatment fMRI parameters PF and Ktrans showed promising potential in predicting the response of the metastatic LNs to IC in NPC patients.

Clinical Trial Registration

This study was approved by the ethics board of the Chinese PLA General Hospital, and registered on 30 January 2021, in the Chinese Clinical Trial Registry; http://www.chictr.org.cn/showproj.aspx?proj=121198, identifier (ChiCTR2100042863).

Integrating mechanism-based modeling with biomedical imaging to build practical digital twins for clinical oncology

Digital twins employ mathematical and computational models to virtually represent a physical object (e.g., planes and human organs), predict the behavior of the object, and enable decision-making to optimize the future behavior of the object. While digital twins have been widely used in engineering for decades, their applications to oncology are only just emerging. Due to advances in experimental techniques quantitatively characterizing cancer, as well as advances in the mathematical and computational sciences, the notion of building and applying digital twins to understand tumor dynamics and personalize the care of cancer patients has been increasingly appreciated. In this review, we present the opportunities and challenges of applying digital twins in clinical oncology, with a particular focus on integrating medical imaging with mechanism-based, tissue-scale mathematical modeling. Specifically, we first introduce the general digital twin framework and then illustrate existing applications of image-guided digital twins in healthcare. Next, we detail both the imaging and modeling techniques that provide practical opportunities to build patient-specific digital twins for oncology. We then describe the current challenges and limitations in developing image-guided, mechanism-based digital twins for oncology along with potential solutions. We conclude by outlining five fundamental questions that can serve as a roadmap when designing and building a practical digital twin for oncology and attempt to provide answers for a specific application to brain cancer. We hope that this contribution provides motivation for the imaging science, oncology, and computational communities to develop practical digital twin technologies to improve the care of patients battling cancer.

Quantifying Tumor Heterogeneity via MRI Habitats to Characterize Microenvironmental Alterations in HER2+ Breast Cancer

This study identifies physiological habitats using quantitative magnetic resonance imaging (MRI) to elucidate intertumoral differences and characterize microenvironmental response to targeted and cytotoxic therapy. BT-474 human epidermal growth factor receptor 2 (HER2+) breast tumors were imaged before and during treatment (trastuzumab, paclitaxel) with diffusion-weighted MRI and dynamic contrast-enhanced MRI to measure tumor cellularity and vascularity, respectively. Tumors were stained for anti-CD31, anti-ɑSMA, anti-CD45, anti-F4/80, anti-pimonidazole, and H&E. MRI data was clustered to identify and label each habitat in terms of vascularity and cellularity. Pre-treatment habitat composition was used stratify tumors into two "tumor imaging phenotypes" (Type 1, Type 2). Type 1 tumors showed significantly higher percent tumor volume of the high-vascularity high-cellularity (HV-HC) habitat compared to Type 2 tumors, and significantly lower volume of low-vascularity high-cellularity (LV-HC) and low-vascularity low-cellularity (LV-LC) habitats. Tumor phenotypes showed significant differences in treatment response, in both changes in tumor volume and physiological composition. Significant positive correlations were found between histological stains and tumor habitats. These findings suggest that the differential baseline imaging phenotypes can predict response to therapy. Specifically, the Type 1 phenotype indicates increased sensitivity to targeted or cytotoxic therapy compared to Type 2 tumors.

Assessing Tumour Haemodynamic Heterogeneity and Response to Choline Kinase Inhibition Using Clustered Dynamic Contrast Enhanced MRI Parameters in Rodent Models of Glioblastoma

To investigate the utility of DCE-MRI derived pharmacokinetic parameters in evaluating tumour haemodynamic heterogeneity and treatment response in rodent models of glioblastoma, imaging was performed on intracranial F98 and GL261 glioblastoma bearing rodents. Clustering of the DCE-MRI-based parametric maps (using Tofts, extended Tofts, shutter speed, two-compartment, and the second generation shutter speed models) was performed using a hierarchical clustering algorithm, resulting in areas with poor fit (reflecting necrosis), low, medium, and high valued pixels representing parameters Ktrans, ve, Kep, vp, τi and Fp. There was a significant increase in the number of necrotic pixels with increasing tumour volume and a significant correlation between ve and tumour volume suggesting increased extracellular volume in larger tumours. In terms of therapeutic response in F98 rat GBMs, a sustained decrease in permeability and perfusion and a reduced cell density was observed during treatment with JAS239 based on Ktrans, Fp and ve as compared to control animals. No significant differences in these parameters were found for the GL261 tumour, indicating that this model may be less sensitive to JAS239 treatment regarding changes in vascular parameters. This study demonstrates that region-based clustered pharmacokinetic parameters derived from DCE-MRI may be useful in assessing tumour haemodynamic heterogeneity with the potential for assessing therapeutic response.

Modulation of the Tumor Microenvironment with Trastuzumab Enables Radiosensitization in HER2+ Breast Cancer

Simple Summary

Trastuzumab and radiation are used clinically to treat HER2-overexpressing breast cancers; however, the mechanistic synergy of anti-HER2 and radiation therapy has not been investigated. In this study, we identify that a subtherapeutic dose of trastuzumab sensitizes the tumor microenvironment to fractionated radiation. This results in longitudinal sustained response by triggering a state of innate immune activation through reduced DNA damage repair and increased tumor oxygenation. As positron emission tomography imaging can be used to longitudinally evaluate changes in tumor hypoxia, synergy of combination therapies is the result of both cellular and molecular changes in the tumor microenvironment.

Abstract

DNA damage repair and tumor hypoxia contribute to intratumoral cellular and molecular heterogeneity and affect radiation response. The goal of this study is to investigate anti-HER2-induced radiosensitization of the tumor microenvironment to enhance fractionated radiotherapy in models of HER2+ breast cancer. This is monitored through in vitro and in vivo studies of phosphorylated γ-H2AX, [¹⁸F]-fluoromisonidazole (FMISO)-PET, and transcriptomic analysis. In vitro, HER2+ breast cancer cell lines were treated with trastuzumab prior to radiation and DNA double-strand breaks (DSB) were quantified. In vivo, HER2+ human cell line or patient-derived xenograft models were treated with trastuzumab, fractionated radiation, or a combination and monitored longitudinally with [¹⁸F]-FMISO-PET. In vitro DSB analysis revealed that trastuzumab administered prior to fractionated radiation increased DSB. In vivo, trastuzumab prior to fractionated radiation significantly reduced hypoxia, as detected through decreased [¹⁸F]-FMISO SUV, synergistically improving long-term tumor response. Significant changes in IL-2, IFN-gamma, and THBS-4 were observed in combination-treated tumors. Trastuzumab prior to fractionated radiation synergistically increases radiotherapy in vitro and in vivo in HER2+ breast cancer which is independent of anti-HER2 response alone. Modulation of the tumor microenvironment, through increased tumor oxygenation and decreased DNA damage response, can be translated to other cancers with first-line radiation therapy.

Comparison of the pre-treatment functional MRI metrics' efficacy in predicting Locoregionally advanced nasopharyngeal carcinoma response to induction chemotherapy

BACKGROUND

Functional MRI (fMRI) parameters analysis has been proven to be a promising tool of predicting therapeutic response to induction chemotherapy (IC) in nasopharyngeal carcinoma (NPC). The study was designed to identify and compare the value of fMRI parameters in predicting early response to IC in patients with NPC.

METHODS

This prospective study enrolled fifty-six consecutively NPC patients treated with IC from January 2021 to May 2021. Conventional diffusion weighted imaging (DWI), diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) protocols were performed before and after IC. Parameters maps (ADC, MD, MK, Dslow, Dfast, PF, Ktrans, Ve and Kep) of the primary tumor were calculated by the Functool post-processing software. The participants were classified as responding group (RG) and non-responding group (NRG) according to Response Evaluation Criteria in Solid Tumors 1.1. The fMRI parameters were compared before and after IC and between RG with NRG. Logistic regression analysis and ROC were performed to further identify and compare the efficacy of the parameters.

RESULTS

After IC, the mean values of ADC(p < 0.001), MD(p < 0.001), Dslow(p = 0.001), PF(p = 0.030) and Ve(p = 0.003) significantly increased, while MK(p < 0.001), Dfast(p = 0.009) and Kep(p = 0.003) values decreased dramatically, while no significant difference was detected in Ktrans(p = 0.130). Compared with NRG, ADC-pre(p < 0.001), MD-pre(p < 0.001) and Dslow-pre(p = 0.002) values in RG were lower, while MK-pre(p = 0.017) values were higher. The areas under the ROC curves for the ADC-pre, MD-pre, MK-pre, Dslow-pre and PRE were 0.885, 0.855, 0.809, 0.742 and 0.912, with the optimal cutoff value of 1210 × 10- 6 mm2/s, 1010 × 10- 6 mm2/s, 832 × 10- 6, 835 × 10- 6 mm2/s and 0.799 respectively.

CONCLUSIONS

The pretreatment conventional DWI (ADC), DKI (MD and MK), and IVIM (Dslow) values derived from fMRI showed a promising potential in predicting the response of the primary tumor to IC in NPC patients.

TRIAL REGISTRATION

This study was approved by ethics board of the Chinese PLA General Hospital, and registered on January 30, 2021, in Chinese Clinical Trial Registry ( ChiCTR2100042863 ).

Quantitative magnetic resonance imaging and tumor forecasting of breast cancer patients in the community setting

This protocol describes a complete data acquisition, analysis and computational forecasting pipeline for employing quantitative MRI data to predict the response of locally advanced breast cancer to neoadjuvant therapy in a community-based care setting. The methodology has previously been successfully applied to a heterogeneous patient population. The protocol details how to acquire the necessary images followed by registration, segmentation, quantitative perfusion and diffusion analysis, model calibration, and prediction. The data collection portion of the protocol requires ~25 min of scanning, postprocessing requires 2-3 h, and the model calibration and prediction components require ~10 h per patient depending on tumor size. The response of individual breast cancer patients to neoadjuvant therapy is forecast by application of a biophysical, reaction-diffusion mathematical model to these data. Successful application of the protocol results in coregistered MRI data from at least two scan visits that quantifies an individual tumor's size, cellularity and vascular properties. This enables a spatially resolved prediction of how a particular patient's tumor will respond to therapy. Expertise in image acquisition and analysis, as well as the numerical solution of partial differential equations, is required to carry out this protocol.

Subregional radiomics analysis for the detection of the EGFR mutation on thoracic spinal metastases from lung cancer

The present study intended to use radiomic analysis of spinal metastasis subregions to detect epidermal growth factor receptor (EGFR) mutation. In total, 94 patients with thoracic spinal metastasis originated from primary lung adenocarcinoma (2017-2020) were studied. All patients underwent T1-weighted (T1W) and T2 fat-suppressed (T2FS) MRI scans. The spinal metastases (tumor region) were subdivided into phenotypically consistent subregions based on patient- and population-level clustering: Three subregions, S1, S2 and S3, and the total tumor region. Radiomics features were extracted from each subregion and from the whole tumor region as well. Least shrinkage and selection operator (LASSO) regression were used for feature selection and radiomics signature definition. Detection performance of S3 was better than all other regions using T1W (AUCs, S1 versus S2 versus S3 versus whole tumor, 0.720 versus 0.764 versus 0.786 versus 0.758) and T2FS (AUCs, S1 versus S2 versus S3 versus whole tumor, 0.791 versus 0.708 versus 0.838 versus 0.797) MRI. The multi-regional radiomics signature derived from the joint of inner subregion S3 from T1W and T2FS MRI achieved the best detection capabilities with AUCs of 0.879 (ACC = 0.774, SEN = 0.838, SPE = 0.840) and 0.777 (ACC = 0.688, SEN = 0.947, SPE = 0.615) in the training and test sets, respectively. Our study revealed that MRI-based radiomic analysis of spinal metastasis subregions has the potential to detect the EGFR mutation in patients with primary lung adenocarcinoma.

Radiological tumor classification across imaging modality and histology

Radiomics refers to the high-throughput extraction of quantitative features from radiological scans and is widely used to search for imaging biomarkers for prediction of clinical outcomes. Current radiomic signatures suffer from limited reproducibility and generalizability, because most features are dependent on imaging modality and tumor histology, making them sensitive to variations in scan protocol. Here, we propose novel radiological features that are specially designed to ensure compatibility across diverse tissues and imaging contrast. These features provide systematic characterization of tumor morphology and spatial heterogeneity. In an international multi-institution study of 1,682 patients, we discover and validate four unifying imaging subtypes across three malignancies and two major imaging modalities. These tumor subtypes demonstrate distinct molecular characteristics and prognoses after conventional therapies. In advanced lung cancer treated with immunotherapy, one subtype is associated with improved survival and increased tumor-infiltrating lymphocytes compared with the others. Deep learning enables automatic tumor segmentation and reproducible subtype identification, which can facilitate practical implementation. The unifying radiological tumor classification may inform prognosis and treatment response for precision medicine.

Integrating Quantitative Assays with Biologically Based Mathematical Modeling for Predictive Oncology

We provide an overview on the use of biological assays to calibrate and initialize mechanism-based models of cancer phenomena. Although artificial intelligence methods currently dominate the landscape in computational oncology, mathematical models that seek to explicitly incorporate biological mechanisms into their formalism are of increasing interest. These models can guide experimental design and provide insights into the underlying mechanisms of cancer progression. Historically, these models have included a myriad of parameters that have been difficult to quantify in biologically relevant systems, limiting their practical insights. Recently, however, there has been much interest calibrating biologically based models with the quantitative measurements available from (for example) RNA sequencing, time-resolved microscopy, and in vivo imaging. In this contribution, we summarize how a variety of experimental methods quantify tumor characteristics from the molecular to tissue scales and describe how such data can be directly integrated with mechanism-based models to improve predictions of tumor growth and treatment response.