Prediction Of Neoadjuvant Chemotherapy Response Research Articles

Abstract 6933: Decoding the archetypes and eco-hubs of triple-negative breast cancer in responses to chemotherapy

Abstract Triple-negative breast cancer (TNBC) is a highly aggressive type of breast cancer commonly treated with neoadjuvant chemotherapy (NAC). While about 50% of patients achieve a pathological complete response (pCR), the remainder often develop resistance and metastasis, leading poor survivals. Currently, the factors linking pre-treatment cancer cells and the tumor microenvironment (TME) to NAC response are unclear. To investigate this question, we conducted single-cell RNA sequencing on fresh pre-treatment core biopsy samples collected from patients in the ARTEMIS clinical trial. We identified 13 gene expression meta-programs of cancer cells and about 50 cell states of immune and stromal cell types. Based on the cancer cells alone, we identified four TNBC archetypes at patient-level: luminal secretory-associated (LSA), basal-associated (BA), immunoreactive (IR), and luminal androgen receptor (LAR). Notably, the archetype BA and IR were associated with non-pCR and pCR, respectively. Additionally, we found the TNBC ecosystem was composed of eight eco-hubs, reflecting the co-occurrence patterns of cancer and TME cell states. These eco-hubs revealed different cell community across archetypes and NAC outcomes. For example, an eco-hub with a co-occurrence of interferon response-related cancer cells and immune cells was prevalent in the archetype IR and pCR patients. To facilitate a clinical application, we further developed a 13-gene-based machine learning model to predict NAC response. In summary, these results provide new insights into the cellular determinants of TNBC biology and chemotherapeutic response. Citation Format: Yun Yan, Yiyun Lin, Tapsi Kumar, Shanshan Bai, Jianzhuo Li, Tuan Tran, Min Hu, Elizabeth Ravenberg, Maia Rauch, Alyson Clayborn, Alastair Thompson, Bora Lim, Lei Huo, Stacy Moulder, Clinton Yam, Nicholas Navin. Decoding the archetypes and eco-hubs of triple-negative breast cancer in responses to chemotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6933.

HER2-low and tumor infiltrating lymphocytes in triple-negative breast cancer: Are they connected?

Most patients with triple-negative breast cancer (TNBC) are not candidates for targeted therapy, leaving chemotherapy as the primary treatment option. Recently, immunotherapy has demonstrated promising results in TNBC, due to its immunogenicity. In addition, a novel antibody–drug conjugate, namely, trastuzumab-deruxtecan, has shown effectiveness in TNBC patients with low-HER2 expression (HER2-low). These novel treatment options raise the question about the potential association between the density of stromal tumor-infiltrating lymphocytes (sTILs) and the level of HER2 expression. We aimed to evaluate the association between the level of HER2 expression (HER2-low versus HER2-0) and density of sTILs in TNBC patients, and how they impact the response to neoadjuvant chemotherapy (NAC). This was a retrospective multicenter study including all TNBC patients diagnosed between 2018 and 2022. Central pathology review included sTILs percentages and level of HER2 expression. Tumors were reclassified as either HER2-0 (HER2 IHC 0) or HER2-low (IHC 1 + or 2 + with negative reflex test). Various clinicopathologic characteristics, including sTILs density, and response to NAC were compared between HER2-0 and HER2-low cases. In total, 753 TNBC patients were included in this study, of which 292 patients received NAC. Interobserver agreement between the original pathology report and central review was moderate (77% had the same IHC status after reclassification in either HER2-0 or HER2-low; k = 0.45). HER2-low TNBC represented about one third (36%) of the tumors. No significant difference in sTILs density or complete pathologic response rate was found between HER2-0 and HER2-low cases (p = 0.476 and p = 0.339, respectively). The density of sTILs (≥ 10% sTILs vs. < 10%) was independently associated with achieving a pCR (p = 0.011). In conclusion, no significant association was found between HER2-low status and density of sTILs nor response to NAC. Nonetheless, sTILs could be an independent biomarker for predicting NAC response in TNBC patients.

Artificial Intelligence for Breast Ultrasound: AJR Expert Panel Narrative Review.

Breast ultrasound is used in a wide variety of clinical scenarios, including both diagnostic and screening applications. Limitations of ultrasound, however, include its low specificity and, for automated breast ultrasound screening, the time necessary to review whole-breast ultrasound images. As of this writing, four AI tools that are approved or cleared by the FDA address these limitations. Current tools, which are intended to provide decision support for lesion classification and/or detection, have been shown to increase specificity among non-specialists and to decrease interpretation times. Potential future applications include triage of patients with palpable masses in low-resource settings, preoperative prediction of axillary lymph node metastasis, and preoperative prediction of neoadjuvant chemotherapy response. Challenges in the development and clinical deployment of AI for ultrasound include: the limited availability of curated training datasets compared to mammography; the high variability in ultrasound image acquisition due to equipment- and operator-related factors (which may limit algorithm generalizability); and the lack of post-implementation evaluation studies. Furthermore, current AI tools for lesion classification were developed based on 2D data, but diagnostic accuracy could potentially be improved if multimodal ultrasound data were used, such as color Doppler, elastography, cine clips, and 3D imaging.

Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy

Locally advanced breast cancer (LABC) is a severe type of cancer with a poor prognosis, despite advancements in therapy. As the disease is often inoperable, current guidelines suggest upfront aggressive neoadjuvant chemotherapy (NAC). Complete pathological response to chemotherapy is linked to improved survival, but conventional clinical assessments like physical exams, mammography, and imaging are limited in detecting early response. Early detection of tissue response can improve complete pathological response and patient survival while reducing exposure to ineffective and potentially harmful treatments. A rapid, cost-effective modality without the need for exogenous contrast agents would be valuable for evaluating neoadjuvant therapy response. Conventional ultrasound provides information about tissue echogenicity, but image comparisons are difficult due to instrument-dependent settings and imaging parameters. Quantitative ultrasound (QUS) overcomes this by using normalized power spectra to calculate quantitative metrics. This study used a novel transfer learning-based approach to predict LABC response to neoadjuvant chemotherapy using QUS imaging at pre-treatment. Using data from 174 patients, QUS parametric images of breast tumors with margins were generated. The ground truth response to therapy for each patient was based on standard clinical and pathological criteria. The Residual Network (ResNet) deep learning architecture was used to extract features from the parametric QUS maps. This was followed by SelectKBest and Synthetic Minority Oversampling (SMOTE) techniques for feature selection and data balancing, respectively. The Support Vector Machine (SVM) algorithm was employed to classify patients into two distinct categories: nonresponders (NR) and responders (RR). Evaluation results on an unseen test set demonstrate that the transfer learning-based approach using spectral slope parametric maps had the best performance in the identification of nonresponders with precision, recall, F1-score, and balanced accuracy of 100, 71, 83, and 86%, respectively. The transfer learning-based approach has many advantages over conventional deep learning methods since it reduces the need for large image datasets for training and shortens the training time. The results of this study demonstrate the potential of transfer learning in predicting LABC response to neoadjuvant chemotherapy before the start of treatment using quantitative ultrasound imaging. Prediction of NAC response before treatment can aid clinicians in customizing ineffectual treatment regimens for individual patients.

Predicting response to neoadjuvant chemotherapy with liquid biopsies and multiparametric MRI in patients with breast cancer

Accurate prediction of response to neoadjuvant chemotherapy (NAC) can help tailor treatment to individual patients’ needs. Little is known about the combination of liquid biopsies and computer extracted features from multiparametric magnetic resonance imaging (MRI) for the prediction of NAC response in breast cancer. Here, we report on a prospective study with the aim to explore the predictive potential of this combination in adjunct to standard clinical and pathological information before, during and after NAC. The study was performed in four Dutch hospitals. Patients without metastases treated with NAC underwent 3 T multiparametric MRI scans before, during and after NAC. Liquid biopsies were obtained before every chemotherapy cycle and before surgery. Prediction models were developed using penalized linear regression to forecast residual cancer burden after NAC and evaluated for pathologic complete response (pCR) using leave-one-out-cross-validation (LOOCV). Sixty-one patients were included. Twenty-three patients (38%) achieved pCR. Most prediction models yielded the highest estimated LOOCV area under the curve (AUC) at the post-treatment timepoint. A clinical-only model including tumor grade, nodal status and receptor subtype yielded an estimated LOOCV AUC for pCR of 0.76, which increased to 0.82 by incorporating post-treatment radiological MRI assessment (i.e., the “clinical-radiological” model). The estimated LOOCV AUC was 0.84 after incorporation of computer-extracted MRI features, and 0.85 when liquid biopsy information was added instead of the radiological MRI assessment. Adding liquid biopsy information to the clinical-radiological resulted in an estimated LOOCV AUC of 0.86. In conclusion, inclusion of liquid biopsy-derived markers in clinical-radiological prediction models may have potential to improve prediction of pCR after NAC in breast cancer.

Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer

BackgroundPathological complete response (pCR) is associated with favorable prognosis in patients with triple-negative breast cancer (TNBC). However, only 30–40% of TNBC patients treated with neoadjuvant chemotherapy (NAC) show pCR, while the remaining 60–70% show residual disease (RD). The role of the tumor microenvironment in NAC response in patients with TNBC remains unclear. In this study, we developed a machine learning-based two-step pipeline to distinguish between various histological components in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of TNBC tissue biopsies and to identify histological features that can predict NAC response.MethodsH&E-stained WSIs of treatment-naïve biopsies from 85 patients (51 with pCR and 34 with RD) of the model development cohort and 79 patients (41 with pCR and 38 with RD) of the validation cohort were separated through a stratified eightfold cross-validation strategy for the first step and leave-one-out cross-validation strategy for the second step. A tile-level histology label prediction pipeline and four machine-learning classifiers were used to analyze 468,043 tiles of WSIs. The best-trained classifier used 55 texture features from each tile to produce a probability profile during testing. The predicted histology classes were used to generate a histology classification map of the spatial distributions of different tissue regions. A patient-level NAC response prediction pipeline was trained with features derived from paired histology classification maps. The top graph-based features capturing the relevant spatial information across the different histological classes were provided to the radial basis function kernel support vector machine (rbfSVM) classifier for NAC treatment response prediction.ResultsThe tile-level prediction pipeline achieved 86.72% accuracy for histology class classification, while the patient-level pipeline achieved 83.53% NAC response (pCR vs. RD) prediction accuracy of the model development cohort. The model was validated with an independent cohort with tile histology validation accuracy of 83.59% and NAC prediction accuracy of 81.01%. The histological class pairs with the strongest NAC response predictive ability were tumor and tumor tumor-infiltrating lymphocytes for pCR and microvessel density and polyploid giant cancer cells for RD.ConclusionOur machine learning pipeline can robustly identify clinically relevant histological classes that predict NAC response in TNBC patients and may help guide patient selection for NAC treatment.

Breast Multiparametric MRI for Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer: The BMMR2 Challenge.

Purpose To describe the design, conduct, and results of the Breast Multiparametric MRI for prediction of neoadjuvant chemotherapy Response (BMMR2) challenge. Materials and Methods The BMMR2 computational challenge opened on May 28, 2021, and closed on December 21, 2021. The goal of the challenge was to identify image-based markers derived from multiparametric breast MRI, including diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI, along with clinical data for predicting pathologic complete response (pCR) following neoadjuvant treatment. Data included 573 breast MRI studies from 191 women (mean age [±SD], 48.9 years ± 10.56) in the I-SPY 2/American College of Radiology Imaging Network (ACRIN) 6698 trial (ClinicalTrials.gov: NCT01042379). The challenge cohort was split into training (60%) and test (40%) sets, with teams blinded to test set pCR outcomes. Prediction performance was evaluated by area under the receiver operating characteristic curve (AUC) and compared with the benchmark established from the ACRIN 6698 primary analysis. Results Eight teams submitted final predictions. Entries from three teams had point estimators of AUC that were higher than the benchmark performance (AUC, 0.782 [95% CI: 0.670, 0.893], with AUCs of 0.803 [95% CI: 0.702, 0.904], 0.838 [95% CI: 0.748, 0.928], and 0.840 [95% CI: 0.748, 0.932]). A variety of approaches were used, ranging from extraction of individual features to deep learning and artificial intelligence methods, incorporating DCE and DWI alone or in combination. Conclusion The BMMR2 challenge identified several models with high predictive performance, which may further expand the value of multiparametric breast MRI as an early marker of treatment response. Clinical trial registration no. NCT01042379 Keywords: MRI, Breast, Tumor Response Supplemental material is available for this article. © RSNA, 2024.

Predicting Neoadjuvant Treatment Response in Triple-Negative Breast Cancer Using Machine Learning.

Neoadjuvant chemotherapy (NAC) is the standard treatment for early-stage triple negative breast cancer (TNBC). The primary endpoint of NAC is a pathological complete response (pCR). NAC results in pCR in only 30-40% of TNBC patients. Tumor-infiltrating lymphocytes (TILs), Ki67 and phosphohistone H3 (pH3) are a few known biomarkers to predict NAC response. Currently, systematic evaluation of the combined value of these biomarkers in predicting NAC response is lacking. In this study, the predictive value of markers derived from H&E and IHC stained biopsy tissue was comprehensively evaluated using a supervised machine learning (ML)-based approach. Identifying predictive biomarkers could help guide therapeutic decisions by enabling precise stratification of TNBC patients into responders and partial or non-responders. Serial sections from core needle biopsies (n = 76) were stained with H&E and immunohistochemically for the Ki67 and pH3 markers, followed by whole-slide image (WSI) generation. The serial section stains in H&E stain, Ki67 and pH3 markers formed WSI triplets for each patient. The resulting WSI triplets were co-registered with H&E WSIs serving as the reference. Separate mask region-based CNN (MRCNN) models were trained with annotated H&E, Ki67 and pH3 images for detecting tumor cells, stromal and intratumoral TILs (sTILs and tTILs), Ki67+, and pH3+ cells. Top image patches with a high density of cells of interest were identified as hotspots. Best classifiers for NAC response prediction were identified by training multiple ML models and evaluating their performance by accuracy, area under curve, and confusion matrix analyses. Highest prediction accuracy was achieved when hotspot regions were identified by tTIL counts and each hotspot was represented by measures of tTILs, sTILs, tumor cells, Ki67+, and pH3+ features. Regardless of the hotspot selection metric, a complementary use of multiple histological features (tTILs, sTILs) and molecular biomarkers (Ki67 and pH3) resulted in top ranked performance at the patient level. Overall, our results emphasize that prediction models for NAC response should be based on biomarkers in combination rather than in isolation. Our study provides compelling evidence to support the use of ML-based models to predict NAC response in patients with TNBC.

Construction of a risk stratification model integrating ctDNA to predict response and survival in neoadjuvant-treated breast cancer

BackgroundThe pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) of breast cancer is closely related to a better prognosis. However, there are no reliable indicators to accurately identify which patients will achieve pCR before surgery, and a model for predicting pCR to NAC is required.MethodsA total of 269 breast cancer patients in Shandong Cancer Hospital and Liaocheng People’s Hospital receiving anthracycline and taxane-based NAC were prospectively enrolled. Expression profiling using a 457 cancer-related gene sequencing panel (DNA sequencing) covering genes recurrently mutated in breast cancer was carried out on 243 formalin-fixed paraffin-embedded tumor biopsies samples before NAC from 243 patients. The unique personalized panel of nine individual somatic mutation genes from the constructed model was used to detect and analyze ctDNA on 216 blood samples. Blood samples were collected at indicated time points including before chemotherapy initiation, after the 1st NAC and before the 2nd NAC cycle, during intermediate evaluation, and prior to surgery. In this study, we characterized the value of gene profile mutation and circulating tumor DNA (ctDNA) in combination with clinical characteristics in the prediction of pCR before surgery and investigated the prognostic prediction. The median follow-up time for survival analysis was 898 days.ResultsFirstly, we constructed a predictive NAC response model including five single nucleotide variant (SNV) mutations (TP53, SETBP1, PIK3CA, NOTCH4 and MSH2) and four copy number variation (CNV) mutations (FOXP1-gain, EGFR-gain, IL7R-gain, and NFKB1A-gain) in the breast tumor, combined with three clinical factors (luminal A, Her2 and Ki67 status). The tumor prediction model showed good discrimination of chemotherapy sensitivity for pCR and non-pCR with an AUC of 0.871 (95% CI, 0.797–0.927) in the training set, 0.771 (95% CI, 0.649–0.883) in the test set, and 0.726 (95% CI, 0.556–0.865) in an extra test set. This tumor prediction model can also effectively predict the prognosis of disease-free survival (DFS) with an AUC of 0.749 at 1 year and 0.830 at 3 years. We further screened the genes from the tumor prediction model to establish a unique personalized panel consisting of 9 individual somatic mutation genes to detect and analyze ctDNA. It was found that ctDNA positivity decreased with the passage of time during NAC, and ctDNA status can predict NAC response and metastasis recurrence. Finally, we constructed the chemotherapy prediction model combined with the tumor prediction model and pretreatment ctDNA levels, which has a better prediction effect of pCR with the AUC value of 0.961.ConclusionsIn this study, we established a chemotherapy predictive model with a non-invasive tool that is built based on genomic features, ctDNA status, as well as clinical characteristics for predicting pCR to recognize the responders and non-responders to NAC, and also predicting prognosis for DFS in breast cancer. Adding pretreatment ctDNA levels to a model containing gene profile mutation and clinical characteristics significantly improves stratification over the clinical variables alone.

Diagnostic accuracy of radiomics-based machine learning for neoadjuvant chemotherapy response and survival prediction in gastric cancer patients: A systematic review and meta-analysis

BackgroundIn recent years, researchers have explored the use of radiomics to predict neoadjuvant chemotherapy outcomes in gastric cancer (GC). Yet, a lingering debate persists regarding the accuracy of these predictions. Against this backdrop, this study was conducted to examine the accuracy of radiomics in predicting the response to neoadjuvant chemotherapy in GC patients. MethodsAn exhaustive search of relevant studies was conducted in PubMed, Cochrane, Embase, and Web of Science databases up to February 21, 2023. The radiomics quality scoring (RQS) tool was employed to assess study quality. Tumor response to neoadjuvant chemotherapy and survival outcomes were examined as outcome measures. ResultsFourteen studies involving 3,373 GC patients who had received neoadjuvant chemotherapy were incorporated in our meta-analysis. The mean RQS score across all studies was 36.3%, ranging between 0 and 63.9%. On the validation cohort, when the modeling variables were restricted to radiomic features alone, the predictive performance was characterized by a c-index of 0.750 (95% CI: 0.710–0.790), with a sensitivity of 0.67 (95% CI: 0.58–0.75) and a specificity of 0.77 (95% CI: 0.69–0.84) for the prediction of neoadjuvant chemotherapy response. When clinical data was integrated with radiomic features as modeling variables, the predictive performance improved, yielding a c-index of 0.814 (95% CI: 0.780–0.847), a sensitivity of 0.78 [95% CI: 0.70–0.84], and a specificity of 0.73 [95% CI: 0.67–0.79]. ConclusionsRadiomics holds promise to noninvasively predict neoadjuvant chemotherapy response and survival outcomes among patients with locally advanced GC. Additionally, we underscore the need for future multicenter studies and the development of imaging-sourced tools for risk stratification in this patient population.

Delta Radiomics Based on Longitudinal Dual-modal Ultrasound Can Early Predict Response to Neoadjuvant Chemotherapy in Breast Cancer Patients

To develop a monitoring model using radiomics analysis based on longitudinal B-mode ultrasound (BUS) and shear wave elastography (SWE) to early predict pathological response to neoadjuvant chemotherapy (NAC) in breast cancer patients. In this prospective study, 112 breast cancer patients who received NAC between September 2016 and March 2022 were included. The BUS and SWE data of breast cancer were obtained prior to treatment as well as after two and four cycles of NAC. Radiomics features were extracted followed by measuring the changes in radiomics features compared to baseline after the second and fourth cycles of NAC(△R[C2], △R [C4]), respectively. The delta radiomics signatures were established using a support vector machine classifier. The area under receiver operating characteristic curve (AUC) values of △RBUS (C2) and △RBUS (C4) for predicting the response to NAC were 0.83 and 0.84, while those of △RSWE (C2) and △RSWE (C4) were 0.88 and 0.90, respectively. △RSWE exhibited significantly superior performance to △RBUS for predicting NAC response (Delong test, p<0.01). No significant differences were observed in the performances between △R (C2) and △R (C4) based on BUS or SWE data. The longitudinal dual-modal ultrasound radiomics (LDUR) model had an excellent discrimination, good calibration and clinical usefulness, with the AUC, sensitivity and specificity of 0.97, 95.52% and 91.11%, respectively. The LDUR model achieved excellent performance in predicting the pathological response to chemotherapy during the early stages of NAC for breast cancer.

Integrated single-cell and bulk RNA sequencing analysis identifies a neoadjuvant chemotherapy-related gene signature for predicting survival and therapy in breast cancer

Neoadjuvant chemotherapy (NAC) is a well-established treatment modality for locally advanced breast cancer (BC). However, it can also result in severe toxicities while controlling tumors. Therefore, reliable predictive biomarkers are urgently needed to objectively and accurately predict NAC response. In this study, we integrated single-cell and bulk RNA-seq data to identify nine genes associated with the prognostic response to NAC: NDRG1, CXCL14, HOXB2, NAT1, EVL, FBP1, MAGED2, AR and CIRBP. Furthermore, we constructed a prognostic risk model specifically linked to NAC. The clinical independence and generalizability of this model were effectively demonstrated. Additionally, we explore the underlying cancer hallmarks and microenvironment features of this NAC response-related risk score, and further assess the potential impact of risk score on drug response. In summary, our study constructed and validated a nine-gene signature associated with NAC prognosis, which was accomplished through the integration of single-cell and bulk RNA data. The results of our study are of crucial significance in the prediction of the efficacy of NAC in BC, and may have implications for the clinical management of this disease.

Glutathione dynamics is a potential predictive and therapeutic trait for neoadjuvant chemotherapy response in bladder cancer

Radical cystectomy with preoperative cisplatin-based neoadjuvant chemotherapy (NAC) is the standard care for muscle-invasive bladder cancers (MIBCs). However, the complete response rate to this modality remains relatively low, and current clinicopathologic and molecular classifications are inadequate to predict NAC response in patients with MIBC. Here, we demonstrate that dysregulation of the glutathione (GSH) pathway is fundamental for MIBC NAC resistance. Comprehensive analysis of the multicohort transcriptomes reveals that GSH metabolism and immune-response genes are enriched in NAC-resistant and NAC-sensitive MIBCs, respectively. A machine-learning-based tumor/stroma classifier is applied for high-throughput digitalized immunohistochemistry analysis, finding that GSH dynamics proteins, including glutaminase-1, are associated with NAC resistance. GSH dynamics is activated in cisplatin-resistant MIBC cells, and combination treatment with a GSH dynamics modulator and cisplatin significantly suppresses tumor growth in an orthotopic xenograft animal model. Collectively, these findings demonstrate the predictive and therapeutic values of GSH dynamics in determining the NAC response in MIBCs.

The potential role of combined shear wave elastography and superb microvascular imaging for early prediction the pathological response to neoadjuvant chemotherapy in breast cancer.

The potential role of shear wave elastography (SWE) and superb microvascular imaging (SMI) for early assessment of treatment response to neoadjuvant chemotherapy (NAC) in breast cancer remains unexplored. This study aimed to identify potential factors associated with the pathological response to NAC using these advanced ultrasound techniques. Between August 2021 and October 2022, 68 patients with breast cancer undergoing NAC were recruited. Patients underwent conventional ultrasonography, SMI, and SWE examinations at baseline and post-2nd cycle of NAC. Maximum tumor diameter (Dmax), maximum elastic value (Emax), peak systolic velocity (PSV), and resistance index (RI) at baseline and the rate of change of these parameters post-2nd cycle were recorded. After chemotherapy, all patients underwent surgery. Using the Miller-Payne's grade, patients were categorized into response (grades 3, 4, or 5) and non-response (grades 1 or 2) group. Parameters were compared using t-tests at baseline and post-2nd cycle. Binary logistic regression analysis was used to identify variables and their odds ratios (ORs) related to responses and a prediction model was established. ROC curves were drawn to analyze the efficacy of each parameter and their combined model for early NAC response prediction. Among the 68 patients, 15(22.06%) were categorized into the non-response group, whereas 53(77.94%) were categorized into the response group. At baseline, no significant differences were observed between the two groups (p>0.05). Post-2nd cycle of NAC, rates of change of Emax, PSV and RI (ΔEmax, ΔPSV and ΔRI) were higher in responders than non-responders (p<0.05). Binary logistic regression analysis revealed that ΔEmax (OR 0.797 95% CI, 0.683-0.929), ΔPSV (OR 0.926, 95%CI, 0.860-0.998), and ΔRI (OR 0.841, 95%CI, 0.736-0.960) were independently associated with the pathological response of breast cancer after NAC. The combined prediction model exhibited higher accuracy in the early evaluation of the response to NAC (AUC 0.945, 95%CI, 0.873-1.000). SWE and SMI techniques enable early identification of tumor characteristics associated with the pathological response to NAC and may be potentially indicative of an effective response. These factors may eventually be used for the early assessment of NAC treatment for clinical management.

Deep Learning of Multimodal Ultrasound: Stratifying the Response to Neoadjuvant Chemotherapy in Breast Cancer Before Treatment.

Not only should resistance to neoadjuvant chemotherapy (NAC) be considered in patients with breast cancer but also the possibility of achieving a pathologic complete response (PCR) after NAC. Our study aims to develop 2 multimodal ultrasound deep learning (DL) models to noninvasively predict resistance and PCR to NAC before treatment. From January 2017 to July 2022, a total of 170 patients with breast cancer were prospectively enrolled. All patients underwent multimodal ultrasound examination (grayscale 2D ultrasound and ultrasound elastography) before NAC. We combined clinicopathological information to develop 2 DL models, DL_Clinical_resistance and DL_Clinical_PCR, for predicting resistance and PCR to NAC, respectively. In addition, these 2 models were combined to stratify the prediction of response to NAC. In the test cohort, DL_Clinical_resistance had an AUC of 0.911 (95%CI, 0.814-0.979) with a sensitivity of 0.905 (95%CI, 0.765-1.000) and an NPV of 0.882 (95%CI, 0.708-1.000). Meanwhile, DL_Clinical_PCR achieved an AUC of 0.880 (95%CI, 0.751-0.973) and sensitivity and NPV of 0.875 (95%CI, 0.688-1.000) and 0.895 (95%CI, 0.739-1.000), respectively. By combining DL_Clinical_resistance and DL_Clinical_PCR, 37.1% of patients with resistance and 25.7% of patients with PCR were successfully identified by the combined model, suggesting that these patients could benefit by an early change of treatment strategy or by implementing an organ preservation strategy after NAC. The proposed DL_Clinical_resistance and DL_Clinical_PCR models and combined strategy have the potential to predict resistance and PCR to NAC before treatment and allow stratified prediction of NAC response.

ABVS-Based Radiomics for Early Predicting the Efficacy of Neoadjuvant Chemotherapy in Patients with Breast Cancers.

Neoadjuvant chemotherapy (NAC) plays a significant role in breast cancer (BC) management; however, its efficacy varies among patients. Current evaluation methods may lead to delayed treatment alterations, and traditional imaging modalities often yield inaccurate results. Radiomics, an emerging field in medical imaging, offers potential for improved tumor characterization and personalized medicine. Nevertheless, its application in early and accurately predicting NAC response remains underinvestigated. This study aims to develop an automated breast volume scanner (ABVS)-based radiomics model to facilitate early detection of suboptimal NAC response, ultimately promoting personalized therapeutic approaches for BC patients. This retrospective study involved 248 BC patients receiving NAC. Standard guidelines were followed, and patients were classified as responders or non-responders based on treatment outcomes. ABVS images were obtained before and during NAC, and radiomics features were extracted using the PyRadiomics toolkit. Inter-observer consistency and hierarchical feature selection were assessed. Three machine learning classifiers, logistic regression, support vector machine, and random forest, were trained and validated using a five-fold cross-validation with three repetitions. Model performance was comprehensively evaluated based on discrimination, calibration, and clinical utility. Of the 248 BC patients, 157 (63.3%) were responders, and 91 (36.7%) were non-responders. Radiomics feature selection revealed 7 pre-NAC and 6 post-NAC ABVS features, with higher weights for post-NAC features (min >0.05) than pre-NAC (max <0.03). The three post-NAC classifiers demonstrated AUCs of approximately 0.9, indicating excellent discrimination. DCA curves revealed a substantial net benefit when the threshold probability exceeded 40%. Conversely, the three pre-NAC classifiers had AUCs between 0.7 and 0.8, suggesting moderate discrimination and limited clinical utility based on their DCA curves. The ABVS-based radiomics model effectively predicted suboptimal NAC responses in BC patients, with early post-NAC classifiers outperforming pre-NAC classifiers in discrimination and clinical utility. It could enhance personalized treatment and improve patient outcomes in BC management.

Unlocking the Potential of Circulating miRNAs in the Breast Cancer Neoadjuvant Setting: A Systematic Review and Meta-Analysis.

The potential role of circulating microRNAs (miRNAs) as biomarkers in breast cancer (BC) management has been widely reported. However, the numerous discrepancies between studies in this regard hinders the implementation of circulating miRNAs in routine clinical practice. In the context of BC patients undergoing neoadjuvant chemotherapy (NAC), the possibility of predicting NAC response may lead to prognostic improvements by individualizing post-neoadjuvant therapy. In this context, the present meta-analysis aims to clarify circulating miRNAs' predictive role with respect to NAC response among BC patients. We conducted a comprehensive literature search on five medical databases until 16 February 2023. We pooled the effect sizes of each study by applying a random-effects model. Cochran's Q test (p-level of significance set at 0.05) scores and I2 values were assessed to determine between-study heterogeneity. The PROBAST (Prediction Model Risk of Bias Assessment Tool) tool was used to evaluate the selected studies' risk of bias. Overall, our findings support the hypothesis that circulating miRNAs, specifically miR-21-5p and miR-155-5p, may act as predictive biomarkers in the neoadjuvant setting among BC patients. However, due to the limited number of studies included in this meta-analysis and the high degrees of clinical and statistical heterogeneity, further research is required to confirm the predictive power of circulating miR-21-5p and miR-155-5p.

Predicting Neoadjuvant Chemotherapy Response and High-Grade Serous Ovarian Cancer From CT Images in Ovarian Cancer with Multitask Deep Learning: A Multicenter Study

Accurate prediction neoadjuvant chemotherapy (NACT) response in ovarian cancer (OC) is essential for personalized medicine. We aimed to develop and validate a deep learning (DL) model based on pretreatment contrast-enhanced CT (CECT) images for predicting NACT responses and classifying high-grade serous ovarian cancer (HGSOC) to identify patients who may benefit from NACT. This multicenter study, which contained both retrospective and prospective studies, included consecutive OC patients (n = 757) from three hospitals. Using WHO RECIST 1.1 for the reference standard, a total of 587 women with 1761 images were included in the training and validation sets, 67 women with 201 images were included in the prospective sets, and 103 women with 309 images were included in the external sets. A multitask DL model based on the multiperiod CT image was developed to predict NACT response and HGSOC. Logistic regression analysis showed that peritoneal invasion, retinal invasion, and inguinal lymph node metastasis were independent predictors. The DL achieved promising segmentation performances with DICEmean= 0.83 (range: 0.78-0.87). For predicting NACT response, the DL model combined with clinical risk factors obtained area under the receiver operating characteristic curve (AUCs) of 0.87 (0.83-0.89), 0.88 (0.86-0.91), 0.86 (0.82-0.89), and 0.79 (0.75-0.82) in the training, validation, prospective, and external sets, respectively. The AUCs were 0.91 (0.87-0.94), 0.89 (0.86-0.91), 0.80 (0.76-0.84), and 0.80 (0.75-0.85) in four sets in HGSOC classification. The multitask DL model developed using multiperiod CT images exhibited a promising performance for predicting NACT response and HGSOC with OC, which could provide valuable information for individualized treatment.

Deep Learning Model Based on Dual-Modal Ultrasound and Molecular Data for Predicting Response to Neoadjuvant Chemotherapy in Breast Cancer

To carry out radiomics analysis/deep convolutional neural network (CNN) based on B-mode ultrasound (BUS) and shear wave elastography (SWE) to predict response to neoadjuvant chemotherapy (NAC) in breast cancer patients. In this prospective study, 255 breast cancer patients who received NAC between September 2016 and December 2021 were included. Radiomics models were designed using a support vector machine classifier based on US images obtained before treatment, including BUS and SWE. And CNN models also were developed using ResNet architecture. The final predictive model was developed by combining the dual-modal US and independently associated clinicopathologic characteristics. The predictive performances of the models were assessed with five-fold cross-validation. Pretreatment SWE performed better than BUS in predicting the response to NAC for breast cancer for both the CNN and radiomics models (P<0.001). The predictive results of the CNN models were significantly better than the radiomics models, with AUCs of 0.72 versus0.69 for BUS and 0.80 versus 0.77 for SWE, respectively (P=0.003). The CNN model based on the dual-modal US and molecular data exhibited outstanding performance in predicting NAC response, with an accuracy of 83.60%±2.63%, a sensitivity of 87.76%±6.44%, and a specificity of 77.45%±4.38%. The pretreatment CNN model based on the dual-modal US and molecular data achieved excellent performance for predicting the response to chemotherapy in breast cancer. Therefore, this model has the potential to serve as a non-invasive objective biomarker to predict NAC response and aid clinicians with individual treatments.

Use of tumoral LDH to predict residual tumor burden after neoadjuvant chemotherapy in breast cancer.

e12566 Background: The Residual Cancer Burden (RCB) score has been validated as an independent prognostic factor in all subtype of breast cancer after neoadjuvant chemotherapy (NAC). Early prediction of NAC response enable better stratification for selecting chemotherapy. Glucose metabolism in cancer cells produces various glycolytic metabolites which are related to breast cancer prognosis. In this study, we evaluated the association of glucose transporters and enzymes involved in glucose metabolism with clinic-pathological factors for early prediction of NAC response. Methods: RCB scores were retrospectively evaluated from patients with stage I-III breast cancer treated with neoadjuvant chemotherapy. We selected 7 target transporters and enzymes [GLUT1, hexokinase 2 (HK2), lactate dehydrogenase (LDH), MCT1, MCT4, IGF1RA, and IGF1RB] involved in glucose metabolism and evaluated in relationships with pretreatment clinical/pathological characteristics and treatment outcomes including RCB. Results: 236 breast cancer patients who underwent NAC followed by surgery between 2010 and 2016 in Kyungpook National University Chilgok Hospital were included. Among them, 145 (61.4%), 44 (18.6%), and 47 (19.9%) were luminal, HER2-enriched, and TNBC subtypes. RCB 0 was determined 50 (21.2%), 35 (14.8%) RCB I, 91 (38.6%) RCB II and 60 (25.4%) RCB III. After a median follow-up of 98 months, 60 (25.4%) relapses, 43 (18.2%) distant relapses, and 34 (14.4%) deaths were observed. RCB score was significantly associated with disease specific survival (DSS) and overall survival (OS). RCB III were significantly increased risk of relapse (HR=13.517, CI [1.809-101.010], P&lt;0.001). The tumoral expression rates of the target molecules were 76.0, 31.1, 42.1, 54.9, 67.9, 78.4, and 49.8% for GLUT1, HK2, LDH, MCT1, MCT4, IGF1RA, and IGF1RB, respectively. Among them, LDH was significantly associated with RCB III (OR=4.533, P=0.014) and worse disease specific survival (HR=2.29 P=0.019). Conclusions: Tumoral expression of LDH could be considered as an independent biomarker in predicting high risk of relapse (RBC III) and survival in all subtype of breast cancer.