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

Research of Ultrasonic Shear Wave Elastography in Evaluating the Efficiency of Neoadjuvant Chemotherapy for Breast Cancer

OBJECTIVE

This study aimed to identify reliable quantitative parameters of ultrasonic shear wave elastography (SWE) that demonstrate advantages in assessing the efficacy of neoadjuvant chemotherapy (NAC) for breast cancer by comparison to conventional ultrasound (US). This research also analyzed the associations between SWE parameters and tumor collagen fibers from post-NAC breast cancer lesions to explore the histological micro-mechanisms of stiffness change for breast cancer after NAC.

METHODS

Forty-Seven breast cancer lesions examined with US and SWE were eligible for enrollment from January 2021 to July 2023. The ultrasonic maximum diameter (Dmax), mean elastic value (Emean), maximum elastic value (Emax), and minimum elastic value (Emin) before and after NAC were determined. Receiver operating characteristic (ROC) curves were drawn to compare the diagnostic efficacy regarding the change rates of the above parameters. Additionally, correlation analyses were performed to examine the relationship between effective SWE quantitative parameters and collagen fibers after NAC.

RESULTS

Among the 47 breast cancer lesions, 24 lesions showed significant pathological responses, while the other 23 lesions exhibited that the pathological responses were nonsignificant. The area under the curve (AUC) of ΔEmin was the lowest (ΔEmin:0.466, ΔDmax: 0.679, ΔEmax: 0.803, and ΔEmean: 0.813). The collagen fiber category showed a significant positive correlation with Emean (r = 0.711) and Emax (r = 0.669) after NAC. However, the collagen fiber content demonstrated no significant correlation with Emean or Emax (p > 0.05).

CONCLUSION

Dmax, Emean, and Emax are valuable parameters for evaluating NAC efficacy, while Emin is not reliable. Emean and Emax demonstrate similar efficacy, both superior to Dmax. The stiffness of post-NAC breast cancer lesions is predominantly related to the category of collagen fibers rather than their content.

Dual-Energy CT-Based Assessment of Thrombotic Heterogeneity for Predicting Stroke Source and Response to Machine Thrombectomy: A Step Toward Visualization Thrombus Treatment

The viability of using thrombus heterogeneity (TH) data derived from dual-energy CT (DECT) as a visual thrombotic biomarker is unclear. The first aim of this study is to develop a quantitative measure of TH on DECT and test its performance for predicting the stroke source (cardiogenic vs. non-cardiogenic) and clinical outcomes (functional status assessed by the modified Rankin Scale score at 90 days) following machine thrombectomy (MT). The second aim is to associate thrombus subregions with the thrombus composition to facilitate visualization of thrombus constituents. Radiomics data are extracted from the whole thrombus and subregions in CT/DECT to construct predictive models. The performances of all models are evaluated and compared in the validation and comparative cohorts. Histopathologic analysis is performed to correlate the subregion data with the actual thrombus composition. This study included 221 and 255 participants who underwent DECT and CT examinations, respectively. DECT outperformed CT in predicting stroke source and clinical outcomes, with the TH-related models showing the highest performance in the validation and comparative cohorts. Thrombus composition is correlated with the different CT/DECT-based subregions, with DECT-habitat_c showing the strongest association. Thrombus subregion analyses may help visualize the related constituents.

Performance of MRI-based radiomics for prediction of residual disease status in patients with nasopharyngeal carcinoma after radical radiotherapy

The purpose of this study was to determine if habitat radiomic features extracted from pretherapy multi-sequence MRI predict residual status in patients with Nasopharyngeal Carcinoma (NPC) after radical radiotherapy. The retrospective study enrolled 179 primary NPC patients, divided into training and validation cohorts at a 7:3 ratio. K-means clustering was employed to segment T2WI, CE-T1WI and FSCE-T1WI images, creating habitats within the volume of interest. Identify relevant features that can recognize NPC residuals. In the training cohort, support vector machine (SVM) models were developed utilizing the radiomic features extracted from each habitat and the entire tumor, selecting the most predictive features for each sequence. SVM models were constructed by combining the optimal radiomic features from each sequences with clinical data. Model performance was compared and validated using receiver operating characteristic (ROC) curves, calibration curves and decision curve analysis (DCA), and differences between models were assessed using the DeLong test. The optimal clustering results revealed 4 habitats in FSCE-T1WI, while 2 habitats in both CE-T1WI and T2WI sequences. In the training cohort, we compared the predictive accuracy of SVM models based on different habitats and total tumor characteristics from three sequences, and found that the features from T2 Hab2, CE-T1 Hab1, and FSCE-T1 Hab4 images showed higher performance. Incorporation of habitat-based radiomic features and clinical variables significantly enhanced the predictive performance. The integrated model exhibits the optimal predictive performance, with the area under the curve (AUC) values of 0.921 (SEN = 0.821, SPE = 0.830) in the training cohort and 0.811 (SEN = 0.778, SPE = 0.722) in the validation cohort. Compared to conventional radiomics, habitat imaging features that distinguish intratumoral heterogeneity have higher predictive value, making them potential non-invasive biomarkers for assessing NPC residual after radiotherapy. Integration of multi-sequence MRI habitat radiomic with clinical parameters further improved predictive accuracy.

MRI-based quantification of intratumoral heterogeneity for intrahepatic mass-forming cholangiocarcinoma grading: a multicenter study

OBJECTIVE

This study aimed to develop a quantitative approach to measure intratumor heterogeneity (ITH) using MRI scans and predict the pathological grading of intrahepatic mass-forming cholangiocarcinoma (IMCC).

METHODS

Preoperative MRI scans from IMCC patients were retrospectively obtained from five academic medical centers, covering the period from March 2018 to April 2024. Radiomic features were extracted from the whole tumor and its subregions, which were segmented using K-means clustering. An ITH index was derived from a habitat model integrating output probabilities of the subregions-based models. Significant variables from clinical laboratory-imaging features, radiomics, and the habitat model were integrated into a predictive model, and its performance was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

The final training and internal validation datasets included 197 patients (median age, 59 years [IQR, 52-65 years]); the external validation dataset included 43 patients (median age, 58.5 years [IQR, 52.25-69.75 years]). The habitat model achieved AUCs of 0.847 (95% CI: 0.783, 0.911) in the training set and 0.753 (95% CI: 0.595, 0.911) in the internal validation set. Furthermore, the combined model, integrating imaging variables, the habitat model, and radiomics model, demonstrated improved predictive performance, with AUCs of 0.895 (95% CI: 0.845, 0.944) in the training dataset, 0.790 (95% CI: 0.65, 0.931) in the internal validation dataset, and 0.815 (95% CI: 0.68, 0.951) in the external validation dataset.

CONCLUSION

The combined model based on MRI-derived quantification of ITH, along with clinical, laboratory, radiological, and radiomic features, showed good performance in predicting IMCC grading.

CRITICAL RELEVANCE STATEMENT

This model, integrating MRI-derived intrahepatic mass-forming cholangiocarcinoma (IMCC) classification metrics with quantitative radiomic analysis of intratumor heterogeneity (ITH), demonstrates enhanced accuracy in tumor grade prediction, advancing risk stratification for clinical decision-making in IMCC management.

KEY POINTS

Grading of intrahepatic mass-forming cholangiocarcinoma (IMCC) is important for risk stratification, clinical decision-making, and personalized therapeutic optimization. Quantitative intratumor heterogeneity can accurately predict the pathological grading of IMCC. This combined model provides higher diagnostic accuracy.

CT-based quantification of intratumoral heterogeneity for predicting distant metastasis in retroperitoneal sarcoma

OBJECTIVES

Retroperitoneal sarcoma (RPS) is highly heterogeneous, leading to different risks of distant metastasis (DM) among patients with the same clinical stage. This study aims to develop a quantitative method for assessing intratumoral heterogeneity (ITH) using preoperative contrast-enhanced CT (CECT) scans and evaluate its ability to predict DM risk.

METHODS

We conducted a retrospective analysis of 274 PRS patients who underwent complete surgical resection and were monitored for ≥ 36 months at two centers. Conventional radiomics (C-radiomics), ITH radiomics, and deep-learning (DL) features were extracted from the preoperative CECT scans and developed single-modality models. Clinical indicators and high-throughput CECT features were integrated to develop a combined model for predicting DM. The performance of the models was evaluated by measuring the receiver operating characteristic curve and Harrell's concordance index (C-index). Distant metastasis-free survival (DMFS) was also predicted to further assess survival benefits.

RESULTS

The ITH model demonstrated satisfactory predictive capability for DM in internal and external validation cohorts (AUC: 0.735, 0.765; C-index: 0.691, 0.729). The combined model that combined clinicoradiological variables, ITH-score, and DL-score achieved the best predictive performance in internal and external validation cohorts (AUC: 0.864, 0.801; C-index: 0.770, 0.752), successfully stratified patients into high- and low-risk groups for DM (p < 0.05).

CONCLUSIONS

The combined model demonstrated promising potential for accurately predicting the DM risk and stratifying the DMFS risk in RPS patients undergoing complete surgical resection, providing a valuable tool for guiding treatment decisions and follow-up strategies.

CRITICAL RELEVANCE STATEMENT

The intratumoral heterogeneity analysis facilitates the identification of high-risk retroperitoneal sarcoma patients prone to distant metastasis and poor prognoses, enabling the selection of candidates for more aggressive surgical and post-surgical interventions.

KEY POINTS

Preoperative identification of retroperitoneal sarcoma (RPS) with a high potential for distant metastasis (DM) is crucial for targeted interventional strategies. Quantitative assessment of intratumoral heterogeneity achieved reasonable performance for predicting DM. The integrated model combining clinicoradiological variables, ITH radiomics, and deep-learning features effectively predicted distant metastasis-free survival.

Biomechanical parameters quantified by MR elastography for predicting response to neoadjuvant chemotherapy and disease-free survival in breast cancer: a prospective longitudinal study

BACKGROUND

Little is known regarding biomechanical properties derived from multifrequency MR elastography temporal changes during neoadjuvant chemotherapy (NAC) and associated with pathologic complete response (pCR) and disease-free survival (DFS) in breast cancer. We aimed to investigate temporal changes in NAC-associated biomechanical parameters and assess biomechanical parameters as a predictor of pCR and DFS in breast cancer.

METHODS

In this prospective longitudinal study, participants with breast cancer who received NAC were enrolled from February 2021 to May 2023. All participants underwent multifrequency MR-elastography at four timepoints: before NAC (T1) and after 2 (T2), 4 (T3), and 6 (T4) cycles. Tomoelastography postprocessing provided biomechanical maps of shear-wave-speed (c) and loss-angle (φ) as proxies of stiffness and viscosity. The biomechanical parameters were validated by means of correlation with histopathologic measurements. Generalized estimating equations were used to compare temporal changes in biomechanical parameters at four time points. Logistic regression was used for pCR analysis and Cox proportional hazards regression was used for survival analysis. Predictive performance was assessed with area under the receiver operating characteristic curve (AUC) analysis.

RESULTS

A total of 235 women (50.6 ± 7.9 years) with 964 scans were enrolled. Biomechanical parameters were supported by positive correlations with pathologic examination-based stroma fraction (c: r =.76, P <.001; φ: r =.49, P =.008) and cellularity (c: r =.58, P =.001; φ: r =.40, P =.035). Progesterone receptor, human epidermal growth factor receptor-2 (HER2), T2-c, and T2-φ were independently associated with pCR (all P <.05). Estrogen receptor, HER2, clinical stage, and change in φ at the early stage of NAC were associated with PFS (all P <.05). The predictive model, which incorporated biomechanical parameters and clinicopathologic characteristics significantly outperformed the clinicopathologic model in predicting pCR (AUC: 0.95, 95% confidence interval [CI]: 0.92, 0.98 vs. 0.79, 95%CI: 0.73, 0.84; P <.001). The predictive model also showed good discrimination ability for DFS (C-index = 0.82, 95%CI: 0.72, 0.90) and stratified prognosis into low-risk and high-risk groups (log-rank, P <.001).

CONCLUSIONS

During NAC, patients with higher tumor stiffness and viscosity are less likely to achieve DFS and pCR. The biomechanical parameters exhibit excellent biological interpretability and serve as valuable biomarkers for predicting pCR and DFS in patients with breast cancer.

Noninvasive prognostic classification of ITH in HCC with multi-omics insights and therapeutic implications

Intratumoral heterogeneity (ITH) is a critical factor associated with treatment failure and disease relapse in hepatocellular carcinoma (HCC). However, decoding ITH in a noninvasive and comprehensive manner remains a notable challenge. In this study involving 851 patients from five centers, we developed a noninvasive prognostic classification for ITH using radiomics based on multisequence MRI, termed radiomics ITH (RITH) phenotypes. The RITH phenotypes highly correlated with prognosis and pathological ITH. In addition, through an integrated multi-omics analysis, we uncovered the molecular mechanisms underlying RITH, notably enhancing its biological interpretability. Specifically, high-RITH tumors demonstrated an enrichment of cancer-associated fibroblasts and activation of extracellular matrix remodeling. Our approach facilitates the noninvasive refined classification of ITH using radiomics and multi-omics, paving the way for tailored treatment strategies in HCC. Extracellular matrix-receptor interaction could be a potential therapeutic target in patients with high-RITH tumors. Given the routine use of radiologic imaging in oncology, our methodology ignites versatile framework for broader application to other solid tumors.

FROP-1 peptide-conjugated ultrasmall superparamagnetic nanoparticles as a targeted T1-weighted MR contrast agent for breast cancer: in vitro study

BACKGROUND

The aim of this study was to produce ultrasmall superparamagnetic iron oxide (USPIO) nanoparticles (NPs) conjugated to the FROP-1 peptide for targeted magnetic resonance imaging (MRI) of breast cancer cell lines and to evaluate its application as a specific and targeted T1-weighted MR imaging contrast agent in vitro. Sodium citrate-stabilized Fe3O4 NPs were conjugated with the FROP-1 peptide by 1-ethyl-3-(3-dimethylaminopropyl) carbide diamide hydrochloride (EDC) to form a novel Fe3O4@FROP-1 specific target contrast agent. The specificity and targeting of Fe3O4@FROP-1 to bind FROP-1 receptors were investigated in vitro by cellular uptake and cellular MR imaging.

RESULTS

In this study, the synthesis of water-soluble ultrasmall Fe3O4 NPs was performed by the co-precipitation method. XRD, TEM, and VSM analyses showed the formation of the Fe3O4 NPs with an average size of about 3.78 ± 0.2 nm. FT-IR spectroscopy approved the conjugation of the FROP-1 peptide with the Fe3O4 NPs. The synthesized Fe3O4@FROP-1 NPs showed good biocompatibility, and the high r1 relaxivity and r2/r1, respectively, were 2.608 mM- 1S- 1 and 1.18. The biocompatibility of the Fe3O4 and Fe3O4@FROP-1 NPs on the MCF-7, SKBR-3, MDA-MB-231, and MCF-10 cell lines was determined using cytotoxicity analysis. The specific targeting effect on the cells was verified by in vitro cellular uptake and cell MR imaging.

CONCLUSION

It was found that the contrast intensity of the Fe3O4@FROP-1 nanoprobe increases as Fe concentration increases. Cellular uptake of the Fe3O4 and Fe3O4@FROP-1 NPs was quantified using ICP-MS. The synthesized NPs had better imaging performance than Dotarem (gadoterate meglumine). The findings showed that Fe3O4@FROP-1 NPs have potential utility as a specific and targeted T1-weighted contrast agent in breast cancer MR imaging.

Habitat Radiomics Based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging for Assessing Axillary Lymph Node Burden in Clinical T1-T2 Stage Breast Cancer: A Multicenter and Interpretable Study

BACKGROUND

Axillary lymph node burden(ALNB) is a critical factor in determining treatment strategies for clinical T1-T2 (cT1-T2) stage breast cancer. However, as ALNB assessment relies on invasive procedures, exploring non-invasive methods is essential.

PURPOSE

To develop and validate a habitat radiomics model for assessing ALNB in cT1-T2 breast cancer, incorporating radiogenomic data to improve interpretability.

STUDY TYPE

Retrospective.

POPULATION

468 patients with cT1-T2 stage breast cancer from two institutions and The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA)-Breast Invasive Carcinoma (BRCA) were included. The cohort was divided into training (n = 173), internal validation (n = 58), external validation (n = 130), and TCGA-BRCA sets (n = 107). Patients were categorized into high nodal burden (HNB; > 3 positive lymph nodes) and non-HNB (≤ 3 positive lymph nodes) groups.

FIELD STRENGTH/SEQUENCE

1.5-T MRI and 3.0-T MRI, and three-dimensional dynamic contrast-enhanced T1-weighted gradient-echo sequences.

ASSESSMENT

Two logistic regression models were developed using habitat-based and clinical features. Model performance was evaluated using the AUC. SHapley Additive exPlanations (SHAP) analysis was employed to identify key features. Radiogenomic analysis, including gene set enrichment and drug sensitivity assessments, was conducted using transcriptomic data from the TCGA-BRCA set.

STATISTICAL TESTS

Pearson correlation, Mann-Whitney U, genetic algorithm, logistic regression, AUC analysis, delong test, and SHAP analysis. A p-value < 0.05 was considered statistically significant.

RESULTS

The Habitat model outperformed the Clinical model (AUCs: 0.840-0.932 vs. 0.558-0.673). The SHAP analysis was used to rank feature importance, with subregion 3 showing the highest average SHAP value. Radiogenomic analysis indicated upregulation of the KEGG ribosome pathway in the HNB group and identified differential drug sensitivity profiles among risk groups.

DATA CONCLUSION

The Habitat model has the potential to assess ALNB in cT1-T2 breast cancer and assist radiologists in axillary diagnosis, which may help reduce the need for unnecessary ALN dissection.

EVIDENCE LEVEL

3. Technical Efficacy: Stage 2.

Habitat analysis of iron deposition in the basal ganglia for diagnosing cognitive impairment in chronic kidney disease: evidence from a case-control study

BACKGROUND

Chronic kidney disease induces alterations in the heterogeneity of iron deposition within the basal ganglia. Quantitative analysis of the heterogeneity of iron deposition within the basal ganglia may be valuable for diagnosing chronic kidney disease-related cognitive impairment.

METHODS

In this prospective observational cohort study, quantitative susceptibility mapping (QSM) was performed in chronic kidney disease patients. Susceptibility values of each nucleus within the basal ganglia were measured. Radiomic features were extracted from habitats of the basal ganglia on QSM images. Habitat-based models for diagnosing cognitive impairment were constructed using the random forest algorithm. Logistic regression was employed to build the clinical model and the combined model. The performance of each model was evaluated by the receiver operating characteristic (ROC) analysis.

RESULTS

A total of 146 patients (mean age, 51 ± 13 years; 92 male) were included, of which 79 had cognitive impairment. The two habitats-based model achieved an area under the curve of 0.926 (95% CI 0.842-1.000) on the test set, the highest among all prediction models. The two-habitat maps indicated that chronic kidney disease had two distinct patterns of impact on iron deposition in the basal ganglia region. The capability of the two habitats-based model to identify chronic kidney disease-related cognitive impairment was significantly superior to that of the susceptibility values measured in various nuclei (all p < 0.05).

CONCLUSIONS

This study innovatively applied a habitat-based quantitative analysis technique to QSM, successfully constructing a model that accurately diagnoses chronic kidney disease-related cognitive impairment.

TRIAL REGISTRATION

This study was approved by the Beijing Friendship Hospital Ethics Board (ClinicalTrials.gov Identifier: NCTO5137470) and conducted in accordance with the Declaration of Helsinki ethical standards.

Early prediction of neoadjuvant therapy response in breast cancer using MRI-based neural networks: data from the ACRIN 6698 trial and a prospective Chinese cohort

BACKGROUND

Early prediction of treatment response to neoadjuvant therapy (NAT) in breast cancer patients can facilitate timely adjustment of treatment regimens. We aimed to develop and validate a MRI-based enhanced self-attention network (MESN) for predicting pathological complete response (pCR) based on longitudinal images at the early stage of NAT.

METHODS

Two imaging datasets were utilized: a subset from the ACRIN 6698 trial (dataset A, n = 227) and a prospective collection from a Chinese hospital (dataset B, n = 245). These datasets were divided into three cohorts: an ACRIN 6698 training cohort (n = 153) from dataset A, an ACRIN 6698 test cohort (n = 74) from dataset A, and an external test cohort (n = 245) from dataset B. The proposed MESN allowed for the integration of multiple timepoint features and extraction of dynamic information from longitudinal MR images before and after early-NAT. We also constructed the Pre model based on pre-NAT MRI features. Clinicopathological characteristics were added to these image-based models to create integrated models (MESN-C and Pre-C), and their performance was evaluated and compared.

RESULTS

The MESN-C yielded area under the receiver operating characteristic curve (AUC) values of 0.944 (95% CI: 0.906 - 0.973), 0.903 (95%CI: 0.815 - 0.965), and 0.861 (95%CI: 0.811 - 0.906) in the ACRIN 6698 training, ACRIN 6698 test and external test cohorts, respectively, which were significantly higher than those of the clinical model (AUC: 0.720 [95%CI: 0.587 - 0.842], 0.738 [95%CI: 0.669 - 0.796] for the two test cohorts, respectively; p < 0.05) and Pre-C (AUC: 0.697 [95%CI: 0.554 - 0.819], 0.726 [95%CI: 0.666 - 0.797] for the two test cohorts, respectively; p < 0.05). High AUCs of the MESN-C maintained in the ACRIN 6698 standard (AUC = 0.853 [95%CI: 0.676 - 1.000]) and experimental (AUC = 0.905 [95%CI: 0.817 - 0.993]) subcohorts, and the interracial and external subcohort (AUC = 0.861 [95%CI: 0.811 - 0.906]). Moreover, the MESN-C increased the positive predictive value from 48.6 to 71.3% compared with Pre-C model, and maintained a high negative predictive value (80.4-86.7%).

CONCLUSION

The MESN-C using longitudinal multiparametric MRI after a short-term therapy achieved favorable performance for predicting pCR, which could facilitate timely adjustment of treatment regimens, increasing the rates of pCR and avoiding toxic effects.

TRIAL REGISTRATION

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

REGISTRATION NUMBER

ChiCTR2000038578, registered September 24, 2020.

ViT-based quantification of intratumoral heterogeneity for predicting the early recurrence in HCC following multiple ablation

OBJECTIVES

This study aimed to develop a quantitative intratumoral heterogeneity (ITH) model for assessing the risk of early recurrence (ER) in pre-treatment multimodal imaging for hepatocellular carcinoma (HCC) patients undergoing ablation treatments.

METHODS

This multi-centre study enrolled 633 HCC patients who underwent ultrasound-guided local ablation between January 2015 and September 2022. Among them, 422, 85, 57 and 69 patients underwent radiofrequency ablation (RFA), microwave ablation (MWA), laser ablation (LA) and irreversible electroporation (IRE) ablation, respectively. Vision-Transformer-based quantitative ITH (ViT-Q-ITH) features were extracted from the US and MRI sequences. Multivariable logistic regression analysis was used to identify variables associated with ER. A combined model integrated clinic-radiologic and ViT-Q-ITH scores. The prediction performance was evaluated concerning calibration, clinical usefulness and discrimination.

RESULTS

The final training cohort and internal validation cohort included 318 patients and 83 patients, respectively, who underwent RFA and MWA. The three external testing cohorts comprised of 106 patients treated with RFA, 57 patients treated with LA and 69 patients who underwent IRE ablation. The combined model showed excellent predictive performance for ER in the training (AUC: .99, 95% CI: .99-1.00), internal validation (AUC: .86, 95% CI: .78-.94), external testing (AUC: .83, 95% CI: .73-.92), LA (AUC: .84, 95% CI: .73-.95) and IRE (AUC: .82, 95% CI: .72-.93) cohorts, respectively. Decision curve analysis further affirmed the clinical utility of the combined model.

CONCLUSIONS

The multimodal-based model, incorporating clinic-radiologic factors and ITH features, demonstrated superior performance in predicting ER among early-stage HCC patients undergoing different ablation modalities.

Artificial Intelligence and Breast Cancer Management: From Data to the Clinic

Breast cancer (BC) remains a significant threat to women's health worldwide. The oncology field had an exponential growth in the abundance of medical images, clinical information, and genomic data. With its continuous advancement and refinement, artificial intelligence (AI) has demonstrated exceptional capabilities in processing intricate multidimensional BC-related data. AI has proven advantageous in various facets of BC management, encompassing efficient screening and diagnosis, precise prognosis assessment, and personalized treatment planning. However, the implementation of AI into precision medicine and clinical practice presents ongoing challenges that necessitate enhanced regulation, transparency, fairness, and integration of multiple clinical pathways. In this review, we provide a comprehensive overview of the current research related to AI in BC, highlighting its extensive applications throughout the whole BC cycle management and its potential for innovative impact. Furthermore, this article emphasizes the significance of constructing patient-oriented AI algorithms. Additionally, we explore the opportunities and potential research directions within this burgeoning field.

MRI-based artificial intelligence models for post-neoadjuvant surgery personalization in breast cancer: a narrative review of evidence from Western Pacific

Breast magnetic resonance imaging (MRI) is the most sensitive imaging method for diagnosing breast cancer and assessing treatment response. Artificial intelligence (AI) and radiomics offer new opportunities to identify patterns in imaging data, supporting personalized post-neoadjuvant surgical decisions. This paper reviewed breast MRI-based AI models for predicting outcomes after neoadjuvant therapy, with a focus on evidence from the Western Pacific region, to evaluate the quality of existing models, discuss their inherent limitations, and outline potential future directions. A literature search in MEDLINE, EMBASE, and Web of Science identified 51 relevant studies in the region, with the majority conducted in China, followed by South Korea and Japan. Most studies focused on predicting pathologic complete response (pCR), with a median sample size of 152 and largely retrospective single-center designs. Model performance was commonly assessed using validation sets, with pooled sensitivity and specificity for pCR prediction showing promising results. Models incorporating multitemporal MRI features were associated with improved accuracy. While MRI-based AI models show potential for guiding surgical planning, improved methodological quality and algorithmic explainability are needed to facilitate clinical translation.

Nomogram for Predicting Neoadjuvant Chemotherapy Response in Breast Cancer Using MRI-based Intratumoral Heterogeneity Quantification

Background Intratumoral heterogeneity (ITH) in breast cancer contributes to treatment failure and relapse. Noninvasive methods to quantify ITH are currently limited. Purpose To quantify ITH in breast cancer using pretreatment MRI, develop a nomogram to predict pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) and recurrence-free survival (RFS), and investigate biologic pathways associated with nomogram scores. Materials and Methods This retrospective study included patients with breast cancer who underwent NAC at nine centers between April 1988 and December 2023. Tumor regions on MRI scans were clustered and integrated with global pixel distribution patterns to calculate ITH scores. A nomogram for predicting pCR was developed using multivariable logistic regression. A survival dataset was used to evaluate the association between nomogram score and RFS, and a genomics dataset was used to explore the relationship between nomogram score and biologic pathways. Results The study included 1448 women (median age, 49 years [IQR, 43-54 years]). To predict pCR to NAC, the 505 patients from center A served as the training set, and the patients from center B, centers C-F, and center G served as three external validation sets (n = 331, 107, and 384, respectively). The survival set included patients from centers A and H (n = 179), and the genomics set included patients from center I (n = 74). The ITH score was an independent predictor of pCR (odds ratio, 0.12 [95% CI: 0.03, 0.43]; P < .001). The nomogram model achieved area under the receiver operating characteristic curve values of 0.82, 0.81, and 0.79, respectively, in the three external validation sets. A lower nomogram score was correlated with poorer RFS (hazard ratio, 4.04 [95% CI: 1.90, 8.60]; P < .001) and was associated with upregulation of biologic pathways related to tumor proliferation. Conclusion A nomogram model combining ITH score and clinicopathologic variables showed good performance in predicting pCR to NAC and RFS. Published under a CC BY 4.0 license. Supplemental material is available for this article.

Contrast-enhanced MRI-based intratumoral heterogeneity assessment for predicting lymph node metastasis in resectable pancreatic ductal adenocarcinoma

OBJECTIVES

To develop and validate a contrast-enhanced MRI-based intratumoral heterogeneity (ITH) model for predicting lymph node (LN) metastasis in resectable pancreatic ductal adenocarcinoma (PDAC).

METHODS

Lesions were encoded into different habitats based on enhancement ratios at arterial, venous, and delayed phases of contrast-enhanced MRI. Habitat models on enhanced ratio mapping and single sequences, radiomic models, and clinical models were developed for evaluating LN metastasis. The performance of the models was evaluated via different metrics. Additionally, patients were stratified into high-risk and low-risk groups based on an ensembled model to assess prognosis after adjuvant therapy.

RESULTS

We developed an ensembled radiomics-habitat-clinical (RHC) model that integrates radiomics, habitat, and clinical data for precise prediction of LN metastasis in PDAC. The RHC model showed strong predictive performance, with area under the curve (AUC) values of 0.805, 0.779, and 0.615 in the derivation, internal validation, and external validation cohorts, respectively. Using an optimal threshold of 0.46, the model effectively stratified patients, revealing significant differences in recurrence-free survival and overall survival (OS) (p = 0.004 and p < 0.001). Adjuvant therapy improved OS in the high-risk group (p = 0.004), but no significant benefit was observed in the low-risk group (p = 0.069).

CONCLUSION

We developed an MRI-based ITH model that provides reliable estimates of LN metastasis for resectable PDAC and may offer additional value in guiding clinical decision-making.

CRITICAL RELEVANCE STATEMENT

This ensemble RHC model facilitates preoperative prediction of LN metastasis in resectable PDAC using contrast-enhanced MRI. This offers a foundation for enhanced prognostic assessment and supports the management of personalized adjuvant treatment strategies.

KEY POINTS

MRI-based habitat models can predict LN metastasis in PDAC. Both the radiomics model and clinical characteristics were useful for predicting LN metastasis in PDAC. The RHC models have the potential to enhance predictive accuracy and inform personalized therapeutic decisions.

Deep learning based on intratumoral heterogeneity predicts histopathologic grade of hepatocellular carcinoma

OBJECTIVES

The potential of medical imaging to non-invasively assess intratumoral heterogeneity (ITH) is increasingly being recognized. This study aimed to investigate the value of the ITH-based deep learning model for preoperative prediction of histopathologic grade in hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

A total of 858 patients from primary cohort and two external cohorts were included. 3.0T or 1.5T axial portal venous phase MRI images were collected. We conducted radiomics feature-driven K-means clustering for automatic partition to reveal ITH. 2.5D and 3D deep learning models based on ResNet architecture were trained to extract deep learning hidden features of each subregion. The selected features were used to train Random Forest classifier, which constructed the feature-fusion model.

RESULTS

The extracted voxel-level radiomics features were unsupervised clustered by K-means to generate three subregions. In the 2.5D deep learning, the feature-fusion model based on ITH had superior predictive efficacy than the whole-tumor model (AUC: 0.82 vs. 0.72; p = 0.004). Even in the validation and external test sets, this model maintained a high AUC of 0.78-0.83, and net reclassification indices indicated that it could improve prediction by 25-28%. Regarding the prognostic value, overall survival (OS) and recurrence-free survival (RFS) could be significantly stratified by the 2.5D feature-fusion model, and multivariable Cox regressions indicated its signature was identified as a risk predictor for OS and RFS (p < 0.05).

CONCLUSION

The ITH-based feature-fusion model provided a non-invasive method for classifying tumor differentiation in HCC, which may serve as a promising strategy for stratification management.

MRI-based intra-tumoral ecological diversity features and temporal characteristics for predicting microvascular invasion in hepatocellular carcinoma

Objective

To investigate the predictive value of radiomics models based on intra-tumoral ecological diversity (iTED) and temporal characteristics for assessing microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC).

Material and Methods

We retrospectively analyzed the data of 398 HCC patients who underwent dynamic contrast-enhanced MRI with Gd-EOB-DTPA (training set: 318; testing set: 80). The tumors were segmented into five distinct habitats using case-level clustering and a Gaussian mixture model was used to determine the optimal clusters based on the Bayesian information criterion to produce an iTED feature vector for each patient, which was used to assess intra-tumoral heterogeneity. Radiomics models were developed using iTED features from the arterial phase (AP), portal venous phase (PVP), and hepatobiliary phase (HBP), referred to as MiTED-AP, MiTED-PVP, and MiTED-HBP, respectively. Additionally, temporal features were derived by subtracting the PVP features from the AP features, creating a delta-radiomics model (MDelta). Conventional radiomics features were also extracted from the AP, PVP, and HBP images, resulting in three models: MCVT-AP, MCVT-PVP, and MCVT-HBP. A clinical-radiological model (CR model) was constructed, and two fusion models were generated by combining the radiomics or/and CR models using a stacking algorithm (fusion_R and fusion_CR). Model performance was evaluated using AUC, accuracy, sensitivity, and specificity.

Results

The MDelta model demonstrated higher sensitivity compared to the MCVT-AP and MCVT-PVP models. No significant differences in performance were observed across different imaging phases for either conventional radiomics (p = 0.096-0.420) or iTED features (p = 0.106-0.744). Similarly, for images from the same phase, we found no significant differences between the performance of conventional radiomics and iTED features (AP: p = 0.158; PVP: p = 0.844; HBP: p = 0.157). The fusion_R and fusion_CR models enhanced MVI discrimination, achieving AUCs of 0.823 (95% CI: 0.816-0.831) and 0.830 (95% CI: 0.824-0.835), respectively.

Conclusion

Delta radiomics features are temporal and predictive of MVI, providing additional predictive information for MVI beyond conventional AP and PVP features. The iTED features provide an alternative perspective in interpreting tumor characteristics and hold the potential to replace conventional radiomics features to some extent for MVI prediction.

The Association Between Tumor Radiomic Analysis and Peritumor Habitat-Derived Radiomic Analysis on Gadoxetate Disodium-Enhanced MRI With Microvascular Invasion in Hepatocellular Carcinoma

BACKGROUND

Hepatocellular carcinoma (HCC) has a poor prognosis, often characterized by microvascular invasion (MVI). Radiomics and habitat imaging offer potential for preoperative MVI assessment.

PURPOSE

To identify MVI in HCC by habitat imaging, tumor radiomic analysis, and peritumor habitat-derived radiomic analysis.

STUDY TYPE

Retrospective.

SUBJECTS

Three hundred eighteen patients (53 ± 11.42 years old; male = 276) with pathologically confirmed HCC (training:testing = 224:94).

FIELD STRENGTH/SEQUENCE

1.5 T, T2WI (spin echo), and precontrast and dynamic T1WI using three-dimensional gradient echo sequence.

ASSESSMENT

Clinical model, habitat model, single sequence radiomic models, the peritumor habitat-derived radiomic model, and the combined models were constructed for evaluating MVI. Follow-up clinical data were obtained by a review of medical records or telephone interviews.

STATISTICAL TESTS

Univariable and multivariable logistic regression, receiver operating characteristic (ROC) curve, calibration, decision curve, Delong test, K-M curves, log rank test. A P-value less than 0.05 (two sides) was considered to indicate statistical significance.

RESULTS

Habitat imaging revealed a positive correlation between the number of subregions and MVI probability. The Radiomic-Pre model demonstrated AUCs of 0.815 (95% CI: 0.752-0.878) and 0.708 (95% CI: 0.599-0.817) for detecting MVI in the training and testing cohorts, respectively. Similarly, the AUCs for MVI detection using Radiomic-HBP were 0.790 (95% CI: 0.724-0.855) for the training cohort and 0.712 (95% CI: 0.604-0.820) for the test cohort. Combination models exhibited improved performance, with the Radiomics + Habitat + Dilation + Habitat 2 + Clinical Model (Model 7) achieving the higher AUC than Model 1-4 and 6 (0.825 vs. 0.688, 0.726, 0.785, 0.757, 0.804, P = 0.013, 0.048, 0.035, 0.041, 0.039, respectively) in the testing cohort. High-risk patients (cutoff value >0.11) identified by this model showed shorter recurrence-free survival.

DATA CONCLUSION

The combined model including tumor size, habitat imaging, radiomic analysis exhibited the best performance in predicting MVI, while also assessing prognostic risk.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Overlooked and underpowered: a meta-research addressing sample size in radiomics prediction models for binary outcomes

OBJECTIVES

To investigate how studies determine the sample size when developing radiomics prediction models for binary outcomes, and whether the sample size meets the estimates obtained by using established criteria.

METHODS

We identified radiomics studies that were published from 01 January 2023 to 31 December 2023 in seven leading peer-reviewed radiological journals. We reviewed the sample size justification methods, and actual sample size used. We calculated and compared the actual sample size used to the estimates obtained by using three established criteria proposed by Riley et al. We investigated which characteristics factors were associated with the sufficient sample size that meets the estimates obtained by using established criteria proposed by Riley et al. RESULTS: We included 116 studies. Eleven out of one hundred sixteen studies justified the sample size, in which 6/11 performed a priori sample size calculation. The median (first and third quartile, Q1, Q3) of the total sample size is 223 (130, 463), and those of sample size for training are 150 (90, 288). The median (Q1, Q3) difference between total sample size and minimum sample size according to established criteria are -100 (-216, 183), and those differences between total sample size and a more restrictive approach based on established criteria are -268 (-427, -157). The presence of external testing and the specialty of the topic were associated with sufficient sample size.

CONCLUSION

Radiomics studies are often designed without sample size justification, whose sample size may be too small to avoid overfitting. Sample size justification is encouraged when developing a radiomics model.

KEY POINTS

Question Sample size justification is critical to help minimize overfitting in developing a radiomics model, but is overlooked and underpowered in radiomics research. Findings Few of the radiomics models justified, calculated, or reported their sample size, and most of them did not meet the recent formal sample size criteria. Clinical relevance Radiomics models are often designed without sample size justification. Consequently, many models are too small to avoid overfitting. It should be encouraged to justify, perform, and report the considerations on sample size when developing radiomics models.

Longitudinal MRI-Driven Multi-Modality Approach for Predicting Pathological Complete Response and B Cell Infiltration in Breast Cancer

Accurately predicting pathological complete response (pCR) to neoadjuvant treatment (NAT) in breast cancer remains challenging due to tumor heterogeneity. This study enrolled 2279 patients across 12 centers and develops a novel multi-modality model integrating longitudinal magnetic resonance imaging (MRI) spatial habitat radiomics, transcriptomics, and single-cell RNA sequencing for predicting pCR. By analyzing tumor subregions on multi-timepoint MRI, the model captures dynamic intra-tumoral heterogeneity during NAT. It shows superior performance over traditional radiomics, with areas under the curve of 0.863, 0.813, and 0.888 in the external validation, immunotherapy, and multi-omics cohorts, respectively. Subgroup analysis shows its robustness across varying molecular subtypes and clinical stages. Transcriptomic and single-cell RNA sequencing analysis reveals that high model scores correlate with increased immune activity, notably elevated B cell infiltration, indicating the biological basis of the imaging model. The integration of imaging and molecular data demonstrates promise in spatial habitat radiomics to monitor dynamic changes in tumor heterogeneity during NAT. In clinical practice, this study provides a noninvasive tool to accurately predict pCR, with the potential to guide treatment planning and improve breast-conserving surgery rates. Despite promising results, the model requires prospective validation to confirm its utility across diverse patient populations and clinical settings.

CT radiomics to predict pathologic complete response after neoadjuvant immunotherapy plus chemoradiotherapy in locally advanced esophageal squamous cell carcinoma

OBJECTIVE

To develop and validate a CT-based radiomics model to predict pathologic complete response (pCR) after neoadjuvant immunotherapy plus chemoradiotherapy (NICRT) in locally advanced esophageal squamous cell carcinoma (ESCC).

METHODS

A total of 105 patients with locally advanced ESCC receiving NICRT from February 2019 to December 2023 were enrolled. Patients were randomly divided into the training cohort and the test cohort at a 3:1 ratio. Enhanced CT scans were obtained before NICRT treatment. The 2D and 3D regions of interest were segmented, and features were extracted, followed by feature selection. Six algorithms were applied to construct the radiomics and clinical models. These models were evaluated by area under curve (AUC), accuracy, sensitivity, and specificity, and their respective optimal algorithms were further compared.

RESULTS

Forty-eight patients (45.75%) achieved pCR after NICRT. The AUC values of three algorithms in 2D radiomics models were higher than those in the 3D radiomics model and clinical model. Among these, the 2D radiomics model based on eXtreme Gradient Boosting (XGBoost) exhibited the best performance, with an AUC of 0.89 (95% CI, 0.81-0.97), accuracy of 0.85, sensitivity of 0.86, and specificity of 0.84 in the training cohort, and an AUC of 0.80 (95% CI, 0.64-0.97), accuracy of 0.77, sensitivity of 0.84, and specificity of 0.69 in the test cohort. Calibration curves also showed good agreement between predicted and actual response, and the decision curve analysis further confirmed its clinical applicability.

CONCLUSION

The 2D radiomics model can effectively predict pCR to NICRT in locally advanced ESCC.

KEY POINTS

Question Can CT-based radiomics predict pathologic complete response (pCR) after neoadjuvant immunotherapy plus chemoradiotherapy (NICRT) in locally advanced esophageal squamous cell carcinoma (ESCC)? Findings The model based on eXtreme Gradient Boosting (XGBoost) performed best, with an AUC of 0.89 in the training and 0.80 in the test cohort. Clinical relevance This CT-based radiomics model exhibits promising performance for predicting pCR to NICRT in locally advanced ESCC, which may be valuable in personalized treatment plan optimization.

Predicting the efficacy of neoadjuvant chemotherapy in breast cancer patients based on ultrasound longitudinal temporal depth network fusion model

OBJECTIVE

The aim of this study was to develop and validate a deep learning radiomics (DLR) model based on longitudinal ultrasound data and clinical features to predict pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer patients.

METHODS

Between January 2018 and June 2023, 312 patients with histologically confirmed breast cancer were enrolled and randomly assigned to a training cohort (n = 219) and a test cohort (n = 93) in a 7:3 ratio. Next, pre-NAC and post-treatment 2-cycle ultrasound images were collected, and radiomics and deep learning features were extracted from NAC pre-treatment (Pre), post-treatment 2 cycle (Post), and Delta (pre-NAC-NAC 2 cycle) images. In the training cohort, to filter features, the intraclass correlation coefficient test, the Boruta algorithm, and the least absolute shrinkage and selection operator (LASSO) logistic regression were used. Single-modality models (Pre, Post, and Delta) were constructed based on five machine-learning classifiers. Finally, based on the classifier with the optimal predictive performance, the DLR model was constructed by combining Pre, Post, and Delta ultrasound features and was subsequently combined with clinical features to develop a combined model (Integrated). The discriminative power, predictive performance, and clinical utility of the models were further evaluated in the test cohort. Furthermore, patients were assigned into three subgroups, including the HR+/HER2-, HER2+, and TNBC subgroups, according to molecular typing to validate the predictability of the model across the different subgroups.

RESULTS

After feature screening, 16, 13, and 10 features were selected to construct the Pre model, Post model, and Delta model based on the five machine learning classifiers, respectively. The three single-modality models based on the XGBoost classifier displayed optimal predictive performance. Meanwhile, the DLR model (AUC of 0.827) was superior to the single-modality model (Pre, Post, and Delta AUCs of 0.726, 0.776, and 0.710, respectively) in terms of prediction performance. Moreover, multivariate logistic regression analysis identified Her-2 status and histological grade as independent risk factors for NAC response in breast cancer. In both the training and test cohorts, the Integrated model, which included Pre, Post, and Delta ultrasound features and clinical features, exhibited the highest predictive ability, with AUC values of 0.924 and 0.875, respectively. Likewise, the Integrated model displayed the highest predictive performance across the different subgroups.

CONCLUSION

The Integrated model, which incorporated pre-NAC treatment and early treatment ultrasound data and clinical features, accurately predicted pCR after NAC in breast cancer patients and provided valuable insights for personalized treatment strategies, allowing for timely adjustment of chemotherapy regimens.

CT radiomics-based intratumoral and intertumoral heterogeneity indicators for prognosis prediction in gastric cancer patients receiving neoadjuvant chemotherapy

OBJECTIVES

CT-based intratumoral and intertumoral heterogeneity indicators were integrated to develop a prognostic model for locally advanced gastric cancer (LAGC) patients undergoing neoadjuvant chemotherapy (NACT).

METHODS

This retrospective study included 568 LAGC patients treated with NACT from two hospitals. The intratumor heterogeneity score (ITHscore) was developed to quantify the intratumoral heterogeneity of LAGCs on CT; intertumoral heterogeneity was characterized by combining the primary tumor (PT) and lymph node (LN) sizes on CT. CT indicators were measured on baseline and posttreatment CT scans; the reduction rates (%Δ) were calculated. The overall survival (OS) of all patients was recorded. Cox regression analysis was used to construct a preoperative survival prediction model (Pre-SPM) based on the baseline indicators and %Δ indicators. The predictive performance of Pre-SPM for OS was assessed. The clinicopathological data, including the ypTNM stage, were also collected to evaluate their impact on OS.

RESULTS

Patients with lower baseline ITHscore had better prognoses (p < 0.001). Approximately 13.01% of patients exhibited contradictory changes in PT and LN sizes. Cox regression analysis selected the baseline ITHscore, baseline PT area, %ΔPT, and %ΔLN to establish the Pre-SPM. In the external validation cohort, the c-index of Pre-SPM for predicting OS was 0.72, while the AUC for predicting 5-year OS was 0.73. After adjusting for the influence of clinicopathological features, including the ypTNM stage, Pre-SPM remained an independent prognostic factor.

CONCLUSION

The Pre-SPM model, combining intratumoral heterogeneity and intertumoral heterogeneity, has the potential to predict the OS of LAGC patients receiving NACT.

KEY POINTS

Question Increased tumor heterogeneity in LAGC affects prognosis, but effective non-invasive CT methods for assessing intratumoral and intertumoral heterogeneity are lacking. Findings ITHscore indicates intratumoral heterogeneity, while changes in PT and LN sizes reflect intertumoral heterogeneity. The Pre-SPM model, integrating both, independently predicts patient outcomes. Clinical relevance Pre-SPM enhances prognosis prediction by quantifying intratumoral and intertumoral heterogeneity, potentially guiding more personalized and effective treatment strategies for patients with LAGC.

Revolutionizing HER-2 assessment: multidimensional radiomics in breast cancer diagnosis

OBJECTIVE

To explore the application value of multidimensional radiomics based on ultrasound imaging in assessing the HER-2 status of breast cancer.

METHODS

We retrospectively analyzed the ultrasound imaging, clinical, and laboratory data of 850 breast cancer patients from two centers. During the study, we first utilized automation technology to accurately delineate the tumor region of interest (ROI) in breast ultrasound imaging. Subsequently, the intra-tumoral ROI was automatically expanded by 1 cm and 2 cm to obtain larger areas including the peritumoral tissues, and further generated three-dimensional volumes of interest (VOI) within and around the tumor. Through the K-means clustering method, we identified the sub-regions of interest within the ROI and extracted corresponding radiomic features using the pyradiomics toolkit. Additionally, we employed an advanced Vision Transformer (VIT) model to perform deep radiomic feature extraction on the ROI. Based on feature selection, we utilized various machine learning algorithms for modeling and analysis to assess the HER-2 status of breast cancer.

RESULTS

After comprehensive comparison and evaluation of multiple models, we found that the diagnostic model based on multidimensional feature fusion exhibited excellent diagnostic performance in assessing the HER-2 status of breast cancer. In the training set, the model achieved an accuracy of 0.949 and an AUC value of 0.990 (95% CI: 0.986-0.995), with outstanding key performance indicators such as sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. The model showed good generalization in the test set, with accuracy 0.747, AUC 0.848 (95% CI: 0.791-0.904), and sensitivity 0.911. Specificity was slightly lower, but other indicators remained high, and the F1 score was 0.703. Calibration and clinical decision curves further confirmed the model's effectiveness and reliability.

CONCLUSION

This study fully demonstrates that multidimensional breast ultrasonography-based radiomic features can effectively assess the HER-2 status of breast cancer. This finding not only provides new evidence for early diagnosis of breast cancer but also offers new ideas and methods for personalized treatment planning and prognosis assessment.

Radiomic Analysis of Magnetic Resonance Imaging for Breast Cancer with TP53 Mutation: A Single Center Study

Background: Radiomics is a non-invasive and cost-effective method for predicting the biological characteristics of tumors. In this study, we explored the association between radiomic features derived from magnetic resonance imaging (MRI) and genetic alterations in patients with breast cancer. Methods: We reviewed electronic medical records of patients with breast cancer patients with available targeted next-generation sequencing data available between August 2018 and May 2021. Substraction imaging of T1-weighted sequences was utilized. The tumor area on MRI was segmented semi-automatically, based on a seeded region growing algorithm. Radiomic features were extracted using the open-source software 3D slicer (version 5.6.1) with PyRadiomics extension. The association between genetic alterations and radiomic features was examined. Results: In total, 166 patients were included in this study. Among the 50 panel genes analyzed, only TP53 mutations were significantly associated with radiomic features. Compared with TP53 wild-type tumors, TP53 mutations were associated with larger tumor size, advanced stage, negative hormonal receptor status, and HER2 positivity. Tumors with TP53 mutations exhibited higher values for Gray Level Non-Uniformity, Dependence Non-Uniformity, and Run Length Non-Uniformity, and lower values for Sphericity, Low Gray Level Emphasis, and Small Dependence Low Gray Level emphasis compared to TP53 wild-type tumors. Six radiomic features were selected to develop a composite radiomics score. Receiver operating characteristic curve analysis showed an area under the curve of 0.786 (95% confidence interval, 0.719-0.854; p < 0.001). Conclusions: TP53 mutations in breast cancer can be predicted using MRI-derived radiomic analysis. Further research is needed to assess whether radiomics can help guide treatment decisions in clinical practice.

Radiomics analysis of thoracic vertebral bone marrow microenvironment changes before bone metastasis of breast cancer based on chest CT

Bone metastasis from breast cancer significantly elevates patient morbidity and mortality, making early detection crucial for improving outcomes. This study utilizes radiomics to analyze changes in the thoracic vertebral bone marrow microenvironment from chest computerized tomography (CT) images prior to bone metastasis in breast cancer, and constructs a model to predict metastasis.

METHODS

This study retrospectively gathered data from breast cancer patients who were diagnosed and continuously monitored for five years from January 2013 to September 2023. Radiomic features were extracted from the bone marrow of thoracic vertebrae on non-contrast chest CT scans. Multiple machine learning algorithms were utilized to construct various radiomics models for predicting the risk of bone metastasis, and the model with optimal performance was integrated with clinical features to develop a nomogram. The effectiveness of this combined model was assessed through receiver operating characteristic (ROC) analysis as well as decision curve analysis (DCA).

RESULTS

The study included a total of 106 patients diagnosed with breast cancer, among whom 37 developed bone metastases within five years. The radiomics model's area under the curve (AUC) for the test set, calculated using logistic regression, is 0.929, demonstrating superior predictive performance compared to alternative machine learning models. Furthermore, DCA demonstrated the potential of radiomics models in clinical application, with a greater clinical benefit in predicting bone metastasis than clinical model and nomogram.

CONCLUSION

CT-based radiomics can capture subtle changes in the thoracic vertebral bone marrow before breast cancer bone metastasis, offering a predictive tool for early detection of bone metastasis in breast cancer.

The value of multiparametric MRI-based habitat imaging for differentiating uterine sarcomas from atypical leiomyomas: a multicentre study

PURPOSE

To explore the feasibility of multiparametric MRI-based habitat imaging for distinguishing uterine sarcoma (US) from atypical leiomyoma (ALM).

METHODS

This retrospective study included the clinical and preoperative MRI data of 69 patients with US and 225 patients with ALM from three hospitals. At both the individual and cohort levels, the K-means and Gaussian mixture model (GMM) algorithms were utilized to perform habitat imaging on MR images, respectively. Specifically, T2-weighted images (T2WI) and contrast-enhanced T1-weighted images (CE-T1WI) were clustered to generate structural habitats, while apparent diffusion coefficient (ADC) maps and CE-T1WI were clustered to create functional habitats. Parameters of each habitat subregion were extracted to construct distinct habitat models. The integrated models were constructed by combining habitat and clinical independent predictors. Model performance was assessed using the area under the curve (AUC).

RESULTS

Abnormal vaginal bleeding, lactate dehydrogenase (LDH), and white blood cell (WBC) counts can serve as clinical independent predictors of US. The GMM-based functional habitat model at the cohort level had the highest mean AUC (0.766) in both the training and validation cohorts, followed by the GMM-based structural habitat model at the cohort level (AUC = 0.760). Within the integrated models, the K-means functional habitat model based on the cohort level achieved the highest mean AUC (0.905) in both the training and validation cohorts.

CONCLUSION

Habitat imaging based on multiparametric MRI has the potential to distinguish US from ALM. The combination of clinical independent predictors with the habitat models can effectively improve the performance.

Safety and efficacy of PD-1 inhibitor (sintilimab) combined with transarterial chemoembolization as the initial treatment in patients with intermediate-stage hepatocellular carcinoma beyond up-to-seven criteria

BACKGROUND

Numerous studies have demonstrated limited survival benefits of transarterial chemoembolization (TACE) alone in the treatment of intermediate-stage hepatocellular carcinoma (HCC) beyond up-to-seven criteria. The advent of immunotherapy, particularly immune checkpoint inhibitors (ICIs), has opened new avenues for HCC treatment. However, TACE combined with ICIs has not been investigated for patients with intermediate-stage HCC beyond the up-to-seven criteria. The study aims to evaluate the efficacy and safety of this treatment strategy for such patients.

METHODS

In this single-arm, prospective, phase II study, we enrolled eligible patients with HCC who were treated with TACE plus programmed cell death protein 1 (PD-1) inhibitors (sintilimab) from April 2021 to February 2023. The study's primary objectives were to assess progression-free survival (PFS) and safety. Secondary objectives included measuring the objective response rate (ORR) and disease control rate (DCR) as per both Response Evaluation Criteria in Solid Tumors (RECIST) V.1.1 and modified RECIST (mRECIST) criteria, as well as overall survival (OS). Additionally, we conducted correlation analyses to identify predictors influencing the efficacy of tumor treatment.

RESULT

20 patients participated in this study, with a median follow-up duration of 22.0 months. Median PFS was 8.4 months (95% CI: 4.7 to 19.7) according to both RECIST V.1.1 and mRECIST. The ORR was 30.0% (95% CI: 14.6% to 51.9%) per RECIST 1.1% and 60% (95% CI: 38.7% to 78.1%) per mRECIST. DCR was 95.0% (95% CI: 76.4% to 99.1%) according to both RECIST V.1.1 and mRECIST. Median OS was not yet reached. Notably, 20% (4/20) of patients underwent successful conversion to curative surgical resection. Treatment-related adverse events (TRAEs) mainly included elevated aspartate aminotransferase levels (19/20, 95.0%), elevated alanine aminotransferase levels (18/20, 90.0%), hypothyroidism (18/20, 90.0%), and reduced appetite (10/20, 50.0%). Among all participants, only one experienced grade 3 TRAE (myocarditis). We employed the Elastic Net regression model to analyze radiomic features from tumor and peritumoral areas to predict the efficacy of this treatment strategy.

CONCLUSION

TACE plus PD-1 inhibitors demonstrated promising efficacy and an acceptable safety profile, suggesting it as a potential treatment option for patients with intermediate-stage HCC beyond up-to-seven criteria. Furthermore, our study indicates that specific image-based features may serve as predictors for patients likely to benefit from this treatment approach.

TRIAL REGISTRATION NUMBER

NCT04842565.

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.

Improved prognostication of overall survival after radiotherapy in lung cancer patients by an interpretable machine learning model integrating lung and tumor radiomics and clinical parameters

BACKGROUND

Accurate prognostication of overall survival (OS) for non-small cell lung cancer (NSCLC) patients receiving definitive radiotherapy (RT) is crucial for developing personalized treatment strategies. This study aims to construct an interpretable prognostic model that combines radiomic features extracted from normal lung and from primary tumor with clinical parameters. Our model aimed to clarify the complex, nonlinear interactions between these variables and enhance prognostic accuracy.

METHODS

We included 661 stage III NSCLC patients from three multi-national datasets: a training set (N = 349), test-set-1 (N = 229), and test-set-2 (N = 83), all undergoing definitive RT. A total of 104 distinct radiomic features were separately extracted from the regions of interest in the lung and the tumor. We developed four predictive models using eXtreme gradient boosting and selected the top 10 features based on the Shapley additive explanations (SHAP) values. These models were the tumor radiomic model (Model-T), lung radiomic model (Model-L), a combined radiomic model (Model-LT), and an integrated model incorporating clinical parameters (Model-LTC). Model performance was evaluated through Harrell's concordance index, Kaplan-Meier survival curves, time-dependent area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Interpretability was assessed using the SHAP framework.

RESULTS

Model-LTC exhibited superior performance, with notable predictive accuracy (C-index: training set, 0.87; test-set-2, 0.76) and time-dependent AUC above 0.75. Complex nonlinear relationships and interactions were evident among the model's variables.

CONCLUSION

The integration of radiomic and clinical factors within an interpretable framework significantly improved OS prediction. The SHAP analysis provided insightful interpretability, enhancing the model's clinical applicability and potential for aiding personalized treatment decisions.

Automated classification of pathological differentiation in head and neck squamous cell carcinoma using combined radiomics models from CET1WI and T2WI

OBJECTIVES

This study aims to develop an automated radiomics-based model to grade the pathological differentiation of head and neck squamous cell carcinoma (HNSCC) and to assess the influence of various magnetic resonance imaging (MRI) sequences on the model's performance.

MATERIALS AND METHODS

We retrospectively analyzed MRI data from 256 patients across two medical centers, including both contrast-enhanced T1-weighted images (CET1WI) and T2-weighted images (T2WI). Regions of interest were delineated for radiomics feature extraction, followed by dimensionality reduction. An XGBoost classifier was then employed to build the predictive model, with its classification efficiency assessed using receiver operating characteristic curves and the area under the curve (AUC).

RESULTS

In validation cohort, the AUC (macro/micro) values for models utilizing CET1WI, T2WI, and the combination of CET1WI and T2WI were 0.801/0.814, 0.741/0.798, and 0.885/0.895, respectively. The AUC for the three differentiations, ranging from well-differentiated to poorly differentiated, were 0.867, 0.909, and 0.837, respectively. The macro/micro precision, recall, and F1 scores of 0.688/0.736, 0.744/0.828, and 0.685/0.779 for the CET1WI + T2WI model.

CONCLUSION

This study demonstrates that constructing a radiomics model based on CET1WI and T2WI sequences can be used to predict the pathological differentiation grading of HNSCC patients.

CLINICAL RELEVANCE

This study suggests that a radiomics model integrating CET1WI and T2WI MRI sequences can effectively predict the pathological differentiation of HNSCC, providing an alternative diagnostic approach through non-invasive preoperative methods.

18F-FDG PET/CT for early prediction of pathological complete response in breast cancer neoadjuvant therapy: a retrospective analysis

BACKGROUND

Neoadjuvant treatment has been developed as a systematic approach for patients with early breast cancer and has resulted in improved breast-conserving rate and survival. However, identifying treatment-sensitive patients at the early phase of therapy remains a problem, hampering disease management and raising the possibility of disease progression during treatment.

METHODS

In this retrospective analysis, we collected 2-deoxy-2-[F-18] fluoro-d-glucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) images of primary tumor sites and axillary areas and reciprocal clinical pathological data from 121 patients who underwent neoadjuvant treatment and surgery in our center. The univariate and multivariate logistic regression analyses were performed to investigate features associated with pathological complete response (pCR). An 18F-FDG PET/CT-based prediction model was trained, and the performance was evaluated by receiver operating characteristic curves (ROC).

RESULTS

The maximum standard uptake values (SUVmax) of 18F-FDG PET/CT were a powerful indicator of tumor status. The SUVmax values of axillary areas were closely related to metastatic lymph node counts (R = 0.62). Moreover, the early SUVmax reduction rates (between baseline and second cycle of neoadjuvant treatment) were statistically different between pCR and non-pCR patients. The early SUVmax reduction rates-based model showed great ability to predict pCR (AUC = 0.89), with all molecular subtypes (HR+HER2-, HR+HER2+, HR-HER2+, and HR-HER2-) considered.

CONCLUSION

Our research proved that the SUVmax reduction rate of 18F-FDG PET/CT contributed to the early prediction of pCR, providing rationales for utilizing PET/CT in NAT in the future.

Intratumoral habitat radiomics based on magnetic resonance imaging for preoperative prediction treatment response to neoadjuvant chemotherapy in nasopharyngeal carcinoma

PURPOSE

The aim of this study is to determine intratumoral habitat regions from multi-sequences magnetic resonance imaging (MRI) and to assess the value of those regions for prediction of patient response to neoadjuvant chemotherapy (NAC) in nasopharyngeal carcinoma (NPC).

MATERIALS AND METHODS

Two hundred and ninety seven patients with NPC were enrolled. Multi-sequences MRI data were used to outline three-dimensional volumes of interest (VOI) of the whole tumor. The original imaging data were divided into two groups, which were resampled to an isotropic resolution of 1 × 1 × 1 mm3 (group_1mm) and 3 × 3 × 3 mm3 (group_3mm). Nineteen radiomics features were computed for each voxel of three sequences in group_3mm, within the tumor region to extract local information. Then, k-means clustering was implemented to segment the whole tumor regions in two groups. After radiomics features were extracted and dimension reduction, habitat models were built using Multi-Layer Perceptron (MLP) algorithm.

RESULTS

Only T stage was included as the clinical model. The habitat3mm model, which included 10 radiomics features, achieved AUCs of 0.752 and 0.724 in the training and validation cohorts, respectively. Given the slightly better outcome of habitat3mm model, nomogram was developed in combination with habitat3mm model and T stage with the AUC of 0.749 and 0.738 in the training and validation cohorts. The decision curve analysis provides further evidence of the nomogram's clinical practicality.

CONCLUSIONS

A nomogram based on intratumoral habitat predicts the efficacy of NAC in NPC patients, offering the potential to improve both the treatment plan and patient outcomes.

Quantification of intratumoral heterogeneity using habitat-based MRI radiomics to identify HER2-positive, -low and -zero breast cancers: a multicenter study

BACKGROUND

Human epidermal growth factor receptor 2-targeted (HER2) therapy with antibody-drug conjugates has proven effective for patients with HER2-low breast cancer. However, intratumoral heterogeneity (ITH) poses a great challenge in identifying HER2-low tumors. ITH signatures were developed by quantifying ITH to differentiate HER2-positive, -low and -zero breast cancers.

METHODS

This retrospective study included 614 patients from two institutions. The study was structured into two primary tasks: task 1 was to differentiate between HER2-positive and -negative tumors, followed by task 2 to differentiate HER2-low and -zero tumors. Whole-tumor radiomics features and habitat radiomics features were extracted from MRI to construct the radiomics and ITH signatures. Multivariable logistic regression analysis was used to determine significant independent predictors. A combined model integrating significant clinicopathologic variables, radiomics signature, and ITH signature was developed for task (1) Subsequently, the better-performing model was established using the same approach for task (2) The area under the receiver operating characteristic curve (AUC) was used to assess the performance of each model.

RESULTS

Task 1 comprised 614 patients (training, n = 348; validation, n = 149; and test cohorts, n = 117). Task 2 encompassed 501 patients (training, n = 283; validation, n = 122; and test cohorts, n = 96). For task1, the ITH signature showed outstanding performance, achieving AUCs of 0.81, 0.81, and 0.81 in the training, validation and test cohorts, respectively. The combined model achieved improved performance, with AUCs of 0.83, 0.84 and 0.83 across the three cohorts, respectively. For task2, the ITH signature maintained superior performance, with AUCs of 0.94, 0.93 and 0.84 across the training, validation and test cohorts, respectively. Multivariable logistic regression analysis indicated that none of the clinicopathologic characteristics were retained as predictors associated with odds of HER2-low tumors.

CONCLUSIONS

Our study developed ITH signatures that quantified ITH using habitat-based MRI radiomics, achieving outstanding performance in differentiating HER2-postive and -negative tumors, and further differentiating HER2-low and -zero breast cancers.

Whole tumour- and subregion-based radiomics of contrast-enhanced mammography in differentiating HER2 expression status of invasive breast cancers: A double-centre pilot study

OBJECTIVES

To explore the value of whole tumour- and subregion-based radiomics of contrast-enhanced mammography (CEM) in differentiating the HER2 expression status of breast cancers.

METHODS

352 patients underwent preoperative CEM from two centres were consecutively enroled and divided into the training, internal validation, and external validation cohorts. The lesions were divided into HER2-positive and HER2-negative groups. Besides the radiological features, radiomics features capturing the whole tumour-based (wITH) and subregion-based intratumoral heterogeneity (sITH) were extracted from the craniocaudal view of CEM recombined images. The XGBoost classifier was applied to develop the radiological, sITH, and wITH models. A combined model was constructed by fusing the prediction results of the three models.

RESULTS

The mean age of the patients was 51.1 ± 10.7 years. Two radiological features, four wITH features, and three sITH features were selected to establish the models. The combined model significantly improved the AUC to 0.80 ± 0.03 (95% CI: 0.73-0.86), 0.79 ± 0.06 (95% CI: 0.67-0.90), and 0.79 ± 0.05 (95% CI: 0.69-0.89) in the training, internal validation, and external validation cohorts, respectively (All P < 0.05). The combined model showed good agreement between the predicted and observed probabilities and favourable net clinical benefit in the validation cohorts.

CONCLUSIONS

Both whole tumour- and subregion-based ITH radiomics features of CEM exhibited potential for differentiating the HER2 expression status. Combining conventional radiological features and ITH features can improve the model's performance.

CT-based conventional radiomics and quantification of intratumoral heterogeneity for predicting benign and malignant renal lesions

BACKGROUND

With the increasing incidence of renal lesions, pretreatment differentiation between benign and malignant lesions is crucial for optimized management. This study aimed to develop a machine learning model utilizing radiomic features extracted from various regions of interest (ROIs), intratumoral ecological diversity features, and clinical factors to classify renal lesions.

METHODS

CT images (arterial phase) of 1,795 renal lesions with confirmed pathology from three hospital sites were split into development (1184, 66%) and test (611, 34%) cohorts by surgery date. Conventional radiomic features were extracted from eight ROIs of arterial phase images. Intratumoral ecological diversity features were derived from intratumoral subregions. The combined model incorporating these features with clinical factors was developed, and its performance was compared with radiologists' interpretation.

RESULTS

Combining intratumoral and peritumoral radiomic features, along with ecological diversity features yielded the highest AUC of 0.929 among all combinations of features extracted from CT scans. After incorporating clinical factors into the features extracted from CT images, our combined model outperformed the interpretation of radiologists in the whole (AUC = 0.946 vs 0.823, P < 0.001) and small renal lesion (AUC = 0.935 vs 0.745, P < 0.001) test cohorts. Furthermore, the combined model exhibited favorable concordance and provided the highest net benefit across threshold probabilities exceeding 60%. In the whole and small renal lesion test cohorts, the AUCs for subgroups with predicted risk below or above 95% sensitivity and specificity cutoffs were 0.974 and 0.978, respectively.

CONCLUSIONS

The combined model, incorporating intratumoral and peritumoral radiomic features, ecological diversity features, and clinical factors showed good performance for distinguishing benign from malignant renal lesions, surpassing radiologists' diagnoses in both whole and small renal lesions. It has the potential to save patients from unnecessary invasive biopsies/surgeries and to enhance clinical decision-making.

Time-Dependent Diffusion MRI Helps Predict Molecular Subtypes and Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer

Background Time-dependent diffusion MRI has the potential to help characterize tumor cell properties; however, to the knowledge of the authors, its usefulness for breast cancer diagnosis and prognostic evaluation is unknown. Purpose To investigate the clinical value of time-dependent diffusion MRI-based microstructural mapping for noninvasive prediction of molecular subtypes and pathologic complete response (pCR) in participants with breast cancer. Materials and Methods Participants with invasive breast cancer who underwent pretreatment with time-dependent diffusion MRI between February 2021 and May 2023 were prospectively enrolled. Four microstructural parameters were estimated using the IMPULSED method (a form of time-dependent diffusion MRI), along with three apparent diffusion coefficient (ADC) measurements and a relative ADC diffusion-weighted imaging parameter. Multivariable logistic regression analysis was used to identify parameters associated with each molecular subtype and pCR. A predictive model based on associated parameters was constructed, and its performance was assessed using the area under the receiver operating characteristic curve (AUC) and compared by using the DeLong test. The time-dependent diffusion MRI parameters were validated based on correlation with pathologic measurements. Results The analysis included 408 participants with breast cancer (mean age, 51.9 years ± 9.1 [SD]). Of these, 221 participants were administered neoadjuvant chemotherapy and 54 (24.4%) achieved pCR. The time-dependent diffusion MRI parameters showed reasonable performance in helping to identify luminal A (AUC, 0.70), luminal B (AUC, 0.78), and triple-negative breast cancer (AUC, 0.72) subtypes and high performance for human epidermal growth factor receptor 2 (HER2)-enriched breast cancer (AUC, 0.85), outperforming ADC measurements (all P < .05). Progesterone receptor status (odds ratio [OR], 0.08; P = .02), HER2 status (OR, 3.36; P = .009), and the cellularity index (OR, 0.01; P = .02) were independently associated with the odds of achieving pCR. The combined model showed high performance for predicting pCR (AUC, 0.88), outperforming ADC measurements and the clinical-pathologic model (AUC, 0.73 and 0.79, respectively; P < .001). The time-dependent diffusion MRI-estimated parameters correlated well with the pathologic measurements (n = 100; r = 0.67-0.81; P < .001). Conclusion Time-dependent diffusion MRI-based microstructural mapping was an effective method for helping to predict molecular subtypes and pCR to neoadjuvant chemotherapy in participants with breast cancer. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Partridge and Xu in this issue.

Habitat Imaging With Tumoral and Peritumoral Radiomics for Prediction of Lung Adenocarcinoma Invasiveness on Preoperative Chest CT: A Multicenter Study

BACKGROUND. Tumor growth processes result in spatial heterogeneity, with the development of tumor subregions (i.e., habitats) having unique biologic characteristics. OBJECTIVE. The purpose of our study was to develop and validate a habitat model combining tumor and peritumoral radiomic features on chest CT for predicting invasiveness of lung adenocarcinoma. METHODS. This retrospective study included 1156 patients (mean age, 57.5 years; 464 men, 692 women), from three centers and a public dataset, who underwent chest CT before lung adenocarcinoma resection (variable date ranges across datasets). Patients from one center formed training (n = 500) and validation (n = 215) sets; patients from the other sources formed three external test sets (n = 249, 113, 79). For each patient, a single nodule was manually segmented on chest CT. The nodule segmentation was combined with an automatically generated 4-mm peritumoral region into a whole-volume volume of interest (VOI). A gaussian mixture model (GMM) identified voxel clusters with similar first-order energy across patients. GMM results were used to divide each patient's whole-volume VOI into multiple habitats, which were defined consistently across patients. Radiomic features were extracted from each habitat. After feature selection, a habitat model was developed for predicting invasiveness, with the use of pathologic assessment as a reference. An integrated model was constructed, combining features extracted from habitats and whole-volume VOIs. Model performance was evaluated, including in subgroups based on nodule density (pure ground-glass, part-solid, and solid). The code for habitat imaging and model construction is publicly available (https://github.com/Shangyoulan/Habitat/). RESULTS. Invasive cancer was diagnosed in 626 of 1156 patients. GMM identified four as the optimal number of voxel clusters and thus of per-patient tumor habitats. The habitat model had an AUC of 0.932 in the validation set and 0.881, 0.880, and 0.764 in the three external test sets. The integrated model had an AUC of 0.947 in the validation set and 0.936, 0.908, and 0.800 in the three external test sets. In the three external test sets combined, across nodule densities, AUCs for the habitat model were 0.836-0.869 and for the integrated model were 0.846-0.917. CONCLUSION. Habitat imaging combining tumoral and peritumoral radiomic features could help predict lung adenocarcinoma invasiveness. Prediction is improved when combining information on tumor subregions and the tumor overall. CLINICAL IMPACT. The findings may aid personalized preoperative assessments to guide clinical decision-making in lung adenocarcinoma.

Prediction of early clinical response to neoadjuvant chemotherapy in Triple-negative breast cancer: Incorporating Radiomics through breast MRI

This study assessed pretreatment breast MRI coupled with machine learning for predicting early clinical responses to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC), focusing on identifying non-responders. A retrospective analysis of 135 TNBC patients (107 responders, 28 non-responders) treated with NAC from January 2015 to October 2022 was conducted. Non-responders were defined according to RECIST guidelines. Data included clinicopathologic factors and clinical MRI findings, with radiomics features from contrast-enhanced T1-weighted images, to train a stacking ensemble of 13 machine learning models. For subgroup analysis, propensity score matching was conducted to adjust for clinical disparities in NAC response. The efficacy of the models was evaluated using the area under the receiver-operating-characteristic curve (AUROC) before and after matching. The model combining clinicopathologic factors and clinical MRI findings achieved an AUROC of 0.752 (95% CI 0.644-0.860) for predicting non-responders, while radiomics-based models showed 0.749 (95% CI 0.614-0.884). An integrated model of radiomics, clinicopathologic factors, and clinical MRI findings reached an AUROC of 0.802 (95% CI 0.699-0.905). After propensity score matching, the hierarchical order of key radiomics features remained consistent. Our study demonstrated the potential of using machine learning models based on pretreatment MRI to non-invasively predict TNBC non-responders to NAC.

MRI radiomics and biological correlations for predicting axillary lymph node burden in early-stage breast cancer

BACKGROUND AND AIMS

Preoperative prediction of axillary lymph node (ALN) burden in patients with early-stage breast cancer is pivotal for individualised treatment. This study aimed to develop a MRI radiomics model for evaluating the ALN burden in early-stage breast cancer and to provide biological interpretability to predictions by integrating radiogenomic data.

METHODS

This study retrospectively analyzed 1211 patients with early-stage breast cancer from four centers, supplemented by data from The Cancer Imaging Archive (TCIA) and Duke University (DUKE). MRI radiomic features were extracted from dynamic contrast-enhanced MRI images and an ALN burden-related radscore was constructed by the backpropagation neural network algorithm. Clinical and combined models were developed, integrating ALN-related clinical variables and radscore. The Kaplan-Meier curve and log-rank test were used to assess the prognostic differences between the predicted high- and low-ALN burden groups in both Center I and DUKE cohorts. Gene set enrichment and immune infiltration analyses based on transcriptomic TCIA and TCIA Breast Cancer dataset were used to investigate the biological significance of the ALN-related radscore.

RESULTS

The MRI radiomics model demonstrated an area under the curve of 0.781-0.809 in three validation cohorts. The predicted high-risk population demonstrated a poorer prognosis (log-rank P < .05 in both cohorts). Radiogenomic analysis revealed migration pathway upregulation and cell differentiation pathway downregulation in the high radscore groups. Immune infiltration analysis confirmed the ability of radiological features to reflect the heterogeneity of the tumor microenvironment.

CONCLUSIONS

The MRI radiomics model effectively predicted the ALN burden and prognosis of early-stage breast cancer. Moreover, radiogenomic analysis revealed key cellular and immune patterns associated with the radscore.

Use of Pretreatment Perfusion MRI-based Intratumoral Heterogeneity to Predict Pathologic Response of Triple-Negative Breast Cancer to Neoadjuvant Chemoimmunotherapy

Background Neoadjuvant chemoimmunotherapy (NACI) has significantly increased the rate of pathologic complete response (pCR) in patients with early-stage triple-negative breast cancer (TNBC), although predictors of response to this regimen have not been identified. Purpose To investigate pretreatment perfusion MRI-based radiomics as a predictive marker for pCR in patients with TNBC undergoing NACI. Materials and Methods This prospective study enrolled women with early-stage TNBC who underwent NACI at two different centers from August 2021 to July 2023. Pretreatment dynamic contrast-enhanced MRI scans obtained using scanners from multiple vendors were analyzed using the Tofts model to segment tumors and analyze pharmacokinetic parameters. Radiomics features were extracted from the rate constant for contrast agent plasma-to-interstitial transfer (or Ktrans), volume fraction of extravascular and extracellular space (Ve), and maximum contrast agent uptake rate (Slopemax) maps and analyzed using unsupervised correlation and least absolute shrinkage and selector operator, or LASSO, to develop a radiomics score. Score effectiveness was assessed using the area under the receiver operating characteristic curve (AUC), and multivariable logistic regression was used to develop a multimodal nomogram for enhanced prediction. The discrimination, calibration, and clinical utility of the nomogram were evaluated in an external test set. Results The training set included 112 female participants from center 1 (mean age, 52 years ± 11 [SD]), and the external test set included 83 female participants from center 2 (mean age, 47 years ± 11). The radiomics score demonstrated an AUC of 0.80 (95% CI: 0.70, 0.89) for predicting pCR. A nomogram incorporating the radiomics score, grade, and Ki-67 yielded an AUC of 0.86 (95% CI: 0.78, 0.94) in the test set. Associations were found between higher radiomics score (>0.25) and tumor size (P < .001), washout enhancement (P = .01), androgen receptor expression (P = .009), and programmed death ligand 1 expression (P = .01), demonstrating a correlation with tumor immune environment in participants with TNBC. Conclusion A radiomics score derived from pharmacokinetic parameters at pretreatment dynamic contrast-enhanced MRI exhibited good performance for predicting pCR in participants with TNBC undergoing NACI, and could potentially be used to enhance clinical decision making. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Rauch in this issue.

Correlation Between Cognitive Impairment and Lenticulostriate Arteries: A Clinical and Radiomics Analysis

Lenticulostriate arteries (LSA) are potentially valuable for studying vascular cognitive impairment. This study aims to investigate correlations between cognitive impairment and LSA through clinical and radiomics features analysis. We retrospectively included 102 patients (mean age 62.5±10.3 years, 60 males), including 58 with mild cognitive impairment (MCI) and 44 with moderate or severe cognitive impairment (MSCI). The MRI images of these patients were subjected to z-score preprocessing, manual regions of interest (ROI) outlining, feature extraction (pyradiomics), feature selection [max-relevance and min-redundancy (mRMR), least absolute shrinkage and selection operator (LASSO), and univariate analysis], model construction (multivariate logistic regression), and evaluation [receiver operating characteristic curve (ROC), decision curve analysis (DCA), and calibration curves (CC)]. In the training dataset (71 patients, 44 MCI) and the test dataset (31 patients, 17 MCI), the area under curve (AUC) of the combined model (training 0.88 [95% CI 0.78, 0.97], test 0.76 [95% CI 0.6, 0.93]) was better than that of the clinical model and the radiomics model. The DCA results demonstrated the highest net yield of the combined model relative to the clinical and radiomics models. In addition, we found that LSA total vessel count (0.79 [95% CI 0.08, 1.59], P = 0.038) and wavelet.HLH_glcm_MCC (-1.2 [95% CI -2.2, -0.4], P = 0.008) were independent predictors of MCI. The model that combines clinical and radiomics features of LSA can predict MCI. Besides, LSA vascular parameters may serve as imaging biomarkers of cognitive impairment.

Diffusion kurtosis imaging-based habitat analysis identifies high-risk molecular subtypes and heterogeneity matching in diffuse gliomas

OBJECTIVE

High-risk types of diffuse gliomas in adults include isocitrate dehydrogenase (IDH) wild-type glioblastomas and grade 4 astrocytomas. Achieving noninvasive prediction of high-risk molecular subtypes of gliomas is important for personalized and precise diagnosis and treatment.

METHODS

We retrospectively collected data from 116 patients diagnosed with adult diffuse gliomas. Multiple high-risk molecular markers were tested, and various habitat models and whole-tumor models were constructed based on preoperative routine and diffusion kurtosis imaging (DKI) sequences to predict high-risk molecular subtypes of gliomas. Feature selection and model construction utilized Least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM). Finally, the Wilcoxon rank-sum test was employed to explore the correlation between habitat quantitative features (intra-tumor heterogeneity score，ITH score) and heterogeneity, as well as high-risk molecular subtypes.

RESULTS

The results showed that the habitat analysis model based on DKI performed remarkably well (with AUC values reaching 0.977 and 0.902 in the training and test sets, respectively). The model's performance was further enhanced when combined with clinical variables. (The AUC values were 0.994 and 0.920, respectively.) Additionally, we found a close correlation between ITH score and heterogeneity, with statistically significant differences observed between high-risk and non-high-risk molecular subtypes.

INTERPRETATION

The habitat model based on DKI is an ideal means for preoperatively predicting high-risk molecular subtypes of gliomas, holding significant value for noninvasively alerting malignant gliomas and those with malignant transformation potential.

A preoperative radiogenomic model based on quantitative heterogeneity for predicting outcomes in triple-negative breast cancer patients who underwent neoadjuvant chemotherapy

BACKGROUND

Triple-negative breast cancer (TNBC) is highly heterogeneous, resulting in different responses to neoadjuvant chemotherapy (NAC) and prognoses among patients. This study sought to characterize the heterogeneity of TNBC on MRI and develop a radiogenomic model for predicting both pathological complete response (pCR) and prognosis.

MATERIALS AND METHODS

In this retrospective study, TNBC patients who underwent neoadjuvant chemotherapy at Fudan University Shanghai Cancer Center were enrolled as the radiomic development cohort (n = 315); among these patients, those whose genetic data were available were enrolled as the radiogenomic development cohort (n = 98). The study population of the two cohorts was randomly divided into a training set and a validation set at a ratio of 7:3. The external validation cohort (n = 77) included patients from the DUKE and I-SPY 1 databases. Spatial heterogeneity was characterized using features from the intratumoral subregions and peritumoral region. Hemodynamic heterogeneity was characterized by kinetic features from the tumor body. Three radiomics models were developed by logistic regression after selecting features. Model 1 included subregional and peritumoral features, Model 2 included kinetic features, and Model 3 integrated the features of Model 1 and Model 2. Two fusion models were developed by further integrating pathological and genomic features (PRM: pathology-radiomics model; GPRM: genomics-pathology-radiomics model). Model performance was assessed with the AUC and decision curve analysis. Prognostic implications were assessed with Kaplan‒Meier curves and multivariate Cox regression.

RESULTS

Among the radiomic models, the multiregional model representing multiscale heterogeneity (Model 3) exhibited better pCR prediction, with AUCs of 0.87, 0.79, and 0.78 in the training, internal validation, and external validation sets, respectively. The GPRM showed the best performance for predicting pCR in the training (AUC = 0.97, P = 0.015) and validation sets (AUC = 0.93, P = 0.019). Model 3, PRM and GPRM could stratify patients by disease-free survival, and a predicted nonpCR was associated with poor prognosis (P = 0.034, 0.001 and 0.019, respectively).

CONCLUSION

Multiscale heterogeneity characterized by DCE-MRI could effectively predict the pCR and prognosis of TNBC patients. The radiogenomic model could serve as a valuable biomarker to improve the prediction performance.

Multiparametric MRI subregion radiomics for preoperative assessment of high-risk subregions in microsatellite instability of rectal cancer patients: a multicenter study

BACKGROUND

Microsatellite instability (MSI) is associated with treatment response and prognosis in patients with rectal cancer (RC). However, intratumoral heterogeneity limits MSI testing in patients with RC. The authors developed a subregion radiomics model based on multiparametric MRI to preoperatively assess high-risk subregions with MSI and predict the MSI status of patients with RC.

METHODS

This retrospective study included 475 patients (training cohort, 382; external test cohort, 93) with RC from two participating hospitals between April 2017 and June 2023. In the training cohort, subregion radiomic features were extracted from multiparametric MRI, which included T2-weighted, T1-weighted, diffusion-weighted, and contrast-enhanced T1-weighted imaging. MSI-related subregion radiomic features, classical radiomic features, and clinicoradiological variables were gathered to build five predictive models using logistic regression. Kaplan-Meier survival analysis was conducted to explore the prognostic information.

RESULTS

Among the 475 patients [median age, 64 years (interquartile range, IQR: 55-70 years); 304 men and 171 women], the prevalence of MSI was 11.16% (53/475). The subregion radiomics model outperformed the classical radiomics and clinicoradiological models in both training [area under the curve (AUC)=0.86, 0.72, and 0.59, respectively] and external test cohorts (AUC=0.83, 0.73, and 0.62, respectively). The subregion-clinicoradiological model combining clinicoradiological variables and subregion radiomic features performed the optimal, with AUCs of 0.87 and 0.85 in the training and external test cohorts, respectively. The 3-year disease-free survival rate of MSI groups predicted based on the model was higher than that of the predicted microsatellite stability groups in both patient cohorts (training, P =0.032; external test, P =0.046).

CONCLUSIONS

The authors developed and validated a model based on subregion radiomic features of multiparametric MRI to evaluate high-risk subregions with MSI and predict the MSI status of RC preoperatively, which may assist in individualized treatment decisions and positioning for biopsy.

Diagnosis and treatment status of inoperable locally advanced breast cancer and the application value of inorganic nanomaterials

Locally advanced breast cancer (LABC) is a heterogeneous group of breast cancer that accounts for 10-30% of breast cancer cases. Despite the ongoing development of current treatment methods, LABC remains a severe and complex public health concern around the world, thus prompting the urgent requirement for innovative diagnosis and treatment strategies. The primary treatment challenges are inoperable clinical status and ineffective local control methods. With the rapid advancement of nanotechnology, inorganic nanoparticles (INPs) exhibit a potential application prospect in diagnosing and treating breast cancer. Due to the unique inherent characteristics of INPs, different functions can be performed via appropriate modifications and constructions, thus making them suitable for different imaging technology strategies and treatment schemes. INPs can improve the efficacy of conventional local radiotherapy treatment. In the face of inoperable LABC, INPs have proposed new local therapeutic methods and fostered the evolution of novel strategies such as photothermal and photodynamic therapy, magnetothermal therapy, sonodynamic therapy, and multifunctional inorganic nanoplatform. This article reviews the advances of INPs in local accurate imaging and breast cancer treatment and offers insights to overcome the existing clinical difficulties in LABC management.