Neoadjuvant Treatment Response Research Articles

Optimizing Neoadjuvant Treatment Response Prediction for Triple-Negative Breast Cancer Using Clinical Trial Data and Deep Auxiliary Learning.

Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer with limited treatment options and poor prognosis. Developing predictive models for TNBC treatment responses is crucial but challenging due to data scarcity and the reliance on cell line data, which limits clinical translational value. Leveraging omics data from clinical trials, particularly through auxiliary learning, offers a potential solution to enhance predictive accuracy and reduce data requirements. In this study, we propose a new approach utilizing deep auxiliary task reweighting learning methods to automatically reweight auxiliary tasks, thereby optimizing the performance of the primary task of predicting TNBC treatment responses. We benchmark various auxiliary learning methods, including ARML, AdaLoss, GradNorm, and OL AUX, against traditional supervised machine learning algorithms and single-task learning baselines. Our results characterize the performance of auxiliary learning across various contexts, including utilizing parallel treatment arms within a multi-arm clinical trial, leveraging treatment arms from different clinical trials, and integrating multiple arms with the same treatment regimens across separate clinical trials. The last scenario also provides an opportunity for validating prediction models on an independent dataset, demonstrating the superior performance of the auxiliary learning models in predicting pathological complete response (pCR) in TNBC patients treated with standardized combinational chemotherapy with Taxane, Anthracycline, and Cyclophosphamide (TAC). Source code and additional resources can be accessed at https://github.com/moonchangin/DeepAux TxPred TNBC.

The role of MRI in muscle-invasive bladder cancer: an update from the last two years.

Muscle invasive bladder cancer (MIBC) is aggressive and requires radical cystectomy and neoadjuvant therapy, yet over 40% of patients face recurrence. The loss of the bladder also significantly reduces quality of life. Accurate staging, crucial for treatment decisions, is typically done through transurethral resection (TURBT), but inconsistencies in pathology affect diagnosis in 25% of cases. MRI is the most precise imaging method for evaluating local tumor invasiveness. This review discusses recent advances in MRI for staging MIBC and predicting responses to neoadjuvant therapy. Vesical imaging - reporting and data system (VI-RADS) accuracy may improve if combined with ADC maps and tumor contact length, while a bi-parametric MRI approach without contrast could reduce side effects without losing diagnostic precision, though evidence is mixed. VI-RADS shows promise in predicting neoadjuvant therapy responses, and the new nacVI-RADS score is in development. Non-Gaussian diffusion-weighted imaging techniques and machine learning could enhance accuracy but need more integration with mpMRI. VI-RADS may assist in evaluating responses in bladder-sparing regimens. Urodrill, an MRI-guided biopsy, aims to replace diagnostic TURBT but needs more accuracy data. MRI in MIBC is evolving, offering potential for accurate local staging and reduced side effects by avoiding TURBT. Predicting neoadjuvant treatment response could guide personalized treatment and bladder preservation. Larger trials are needed to validate these findings.

An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer

Multi-modal image analysis using deep learning (DL) lays the foundation for neoadjuvant treatment (NAT) response monitoring. However, existing methods prioritize extracting multi-modal features to enhance predictive performance, with limited consideration on real-world clinical applicability, particularly in longitudinal NAT scenarios with multi-modal data. Here, we propose the Multi-modal Response Prediction (MRP) system, designed to mimic real-world physician assessments of NAT responses in breast cancer. To enhance feasibility, MRP integrates cross-modal knowledge mining and temporal information embedding strategy to handle missing modalities and remain less affected by different NAT settings. We validated MRP through multi-center studies and multinational reader studies. MRP exhibited comparable robustness to breast radiologists, outperforming humans in predicting pathological complete response in the Pre-NAT phase (ΔAUROC 14% and 10% on in-house and external datasets, respectively). Furthermore, we assessed MRP’s clinical utility impact on treatment decision-making. MRP may have profound implications for enrolment into NAT trials and determining surgery extensiveness.

Contrast-enhanced mammography improves patient access to functional breast imaging.

Imaging research pathways focus increasingly on the development of individualised approaches to breast cancer detection, diagnosis and management. Detection of breast cancer with X-ray mammography may fail in some cancer subtypes with limited changes in morphology/tissue density and in women with dense breasts. International organisations offer recommendations for contrast-enhanced breast imaging, as it provides superior sensitivity for screening, local staging and assessment of neoadjuvant treatment response, when compared with standard X-ray mammography (including tomosynthesis) and breast ultrasound. Arguably, the evidence base is stronger for contrast-enhanced MRI (CE-MRI). Unfortunately, patient access to breast MRI in rural and remote areas is limited by practical limitations and equipment licensing restrictions. Moreover, breast MRI is an expensive test, likely to be out of reach for many women. Contrast-enhanced mammography (CEM) offers an attractive alternative to improve patient access to functional breast imaging. It is a new type of digital, dual energy X-ray mammography that can be performed on most modern units, following a relatively inexpensive hard- and software upgrade. In this paper, we review the rapidly accumulating evidence that CEM can provide similar diagnostic accuracy to CE-MRI, though at a significantly lower cost and offering greater comfort to the patient. The adoption of CEM can help meet the anticipated increased demand for CE-MRI.

Advancing personalized oncology: a systematic review on the integration of artificial intelligence in monitoring neoadjuvant treatment for breast cancer patients.

Despite suffering from the same disease, each patient exhibits a distinct microbiological profile and variable reactivity to prescribed treatments. Most doctors typically use a standardized treatment approach for all patients suffering from a specific disease. Consequently, the challenge lies in the effectiveness of this standardized treatment and in adapting it to each individual patient. Personalized medicine is an emerging field in which doctors use diagnostic tests to identify the most effective medical treatments for each patient. Prognosis, disease monitoring, and treatment planning rely on manual, error-prone methods. Artificial intelligence (AI) uses predictive techniques capable of automating prognostic and monitoring processes, thus reducing the error rate associated with conventional methods. This paper conducts an analysis of current literature, encompassing the period from January 2015 to 2023, based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). In assessing 25 pertinent studies concerning predicting neoadjuvant treatment (NAT) response in breast cancer (BC) patients, the studies explored various imaging modalities (Magnetic Resonance Imaging, Ultrasound, etc.), evaluating results based on accuracy, sensitivity, and area under the curve. Additionally, the technologies employed, such as machine learning (ML), deep learning (DL), statistics, and hybrid models, were scrutinized. The presentation of datasets used for predicting complete pathological response (PCR) was also considered. This paper seeks to unveil crucial insights into the application of AI techniques in personalized oncology, particularly in the monitoring and prediction of responses to NAT for BC patients. Finally, the authors suggest avenues for future research into AI-based monitoring systems.

Prognostic Impact of Thoracic Duct Resection in Patients Who Underwent Transthoracic Esophagectomy Following Neoadjuvant Therapy for Esophageal Squamous Cell Carcinoma: Exploratory Analysis of JCOG1109.

Although several studies have investigated whether thoracic duct (TD) resection improves prognosis, the conclusion remains controversial. JCOG1109 is a three-arm randomized phase III trial to confirm the survival advantage of docetaxel, cisplatin, 5-fluorouracil (DCF), and cisplatin plus 5-fluorouracil (CF) combined with radiotherapy (CF-RT) over CF as neoadjuvant treatment. The study aimed to evaluate the survival impact of TD resection and its association with neoadjuvant treatment and pathological response in patients enrolled in JCOG1109. Clinicopathological factors, surgical results, and prognosis were compared between TD preserved and resected groups. The survival impact of TD resection was also evaluated in the subgroups on the basis of combinations of preoperative therapy and pathological response. Between December 2012 and July 2018, 601 patients were randomized (CF/DCF/CF-RT; 199/202/200) in JCOG1109. Of them, 541 patients underwent esophagectomy (183/181/177), and TD was resected in 265 patients (93/91/81). For the entire cohort, TD resection was not a significant prognostic factor for overall survival in the multivariable analysis (HR 1.20, 95% CI 0.91-1.57). In the subgroup analyses by combinations of neoadjuvant treatment and pathological response, TD resected group had a significantly better overall survival compared with TD preserved group in patients who received DCF and achieved pathological response (HR 0.20, 95% CI 0.07-0.61). The survival benefit of TD resection was not demonstrated in patients with surgically resectable esophageal squamous cell carcinoma enrolled in JCOG1109. The residual tumor burden after neoadjuvant treatment might be linked to the survival impact of TD resection.

Abstract C023: Overcoming chemotherapy resistance in colombian breast cancer women: Studying gene expression, genetic ancestry, and survival impact on breast cancer response to neoadjuvant treatment response

Abstract C023: Overcoming chemotherapy resistance in colombian breast cancer women: Studying gene expression, genetic ancestry, and survival impact on breast cancer response to neoadjuvant treatment response

Impact of Low HER2 Expression on Neoadjuvant Treatment Response in Early Luminal Breast Cancer

Impact of Low HER2 Expression on Neoadjuvant Treatment Response in Early Luminal Breast Cancer

Lymphocyte-to-monocyte, platelet-to-albumin and platelet-to-lymphocyte ratios as prognostic biomarkers for neoadjuvant treatment response in rectal cancer patients

IntroductionSystemic inflammatory response (SIR) indicators are an emerging category of serum biomarkers with significant potential as prognostic and predictive factors in various types of cancers The primary focus of our study was to determine the prognostic value of the lymphocyte-to-monocyte ratio (LMR), platelet-to-albumin ratio (PLR) and platelet-to-albumin ratio (PAR) in evaluating the response to neoadjuvant treatment for patients with rectal cancer. Materials and methodsWe included 99 consecutive patients with rectal cancer which were admitted for surgery in our institution after completing a standard neoadjuvant radio-chemotherapy regimen. Several hematologic parameters, including LMR, PAR and PLR, were calculated by collecting and analyzing blood samples preoperatively. Cases were divided into groups using ROC curve analysis to determine optimal cutoff values for each of the investigated parameters. Treatment response was assessed through histopathological analysis of the resected specimens. ResultsPLR values over 215.2 were correlated with the presence of lymph node metastasis. A similar correlation was observed between PAR values over 41.89 and lymph node positivity. A significant correlation was observed between the presence of tumor budding on histopathological analysis and high-PAR values. A statistically significant correlation between a high PLR and a good response to neoadjuvant treatment was determined. ConclusionsHigh PLR values may be associated with a more favorable treatment response to neoadjuvant radio-chemotherapy. A high PAR may be associated with unfavorable histopathological characteristics. Further studies on these readily available biomarkers are required in order to validate their clinical utility.

Association between homologous recombination deficiency status and carboplatin treatment response in early triple-negative breast cancer.

The aim of this study was to assess homologous recombination deficiency (HRD) status and its correlation with carboplatin treatment response in early triple-negative breast cancer (TNBC) patients. Tumor tissues from 225 consecutive TNBC patients were evaluated with an HRD panel and homologous recombination-related (HRR) gene expression data. HRD positivity was defined as a high HRD score and/or BRCA1/2 pathogenic or likely pathogenic mutation. Clinicopathological factors, neoadjuvant treatment response, and prognosis were analyzed with respect to HRD status in these TNBC patients. HRD positivity was found in 53.3% of patients and was significantly related to high Ki67 levels (P = 0.001). In patients who received neoadjuvant chemotherapy, HRD positivity (P = 0.005) or a high HRD score (P = 0.003) was significantly associated with a greater pathological complete response (pCR) rate, especially in those treated with carboplatin-containing neoadjuvant regimens (HRD positivity vs. negativity: 50.00% vs. 17.65%, P = 0.040). HRD positivity was associated with favorable distant metastasis-free survival (hazard ratio HR 0.49, 95% confidence interval CI 0.26-0.90, P = 0.022) and overall survival (HR 0.45, 95% CI 0.20-0.99, P = 0.049), irrespective of carboplatin treatment. TNBC patients with high HRDs had high Ki67 levels and BRCA mutations. HRD-positive TNBC patients treated with carboplatin had a higher pCR rate. Patients with HRD positivity had a better prognosis, irrespective of carboplatin treatment, warranting further evaluation.

Deep learning model based on endoscopic images predicting treatment response in locally advanced rectal cancer undergo neoadjuvant chemoradiotherapy: a multicenter study

PurposeNeoadjuvant chemoradiotherapy has been the standard practice for patients with locally advanced rectal cancer. However, the treatment response varies greatly among individuals, how to select the optimal candidates for neoadjuvant chemoradiotherapy is crucial. This study aimed to develop an endoscopic image-based deep learning model for predicting the response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer.MethodsIn this multicenter observational study, pre-treatment endoscopic images of patients from two Chinese medical centers were retrospectively obtained and a deep learning-based tumor regression model was constructed. Treatment response was evaluated based on the tumor regression grade and was defined as good response and non-good response. The prediction performance of the deep learning model was evaluated in the internal and external test sets. The main outcome was the accuracy of the treatment prediction model, measured by the AUC and accuracy.ResultsThis deep learning model achieved favorable prediction performance. In the internal test set, the AUC and accuracy were 0.867 (95% CI: 0.847–0.941) and 0.836 (95% CI: 0.818–0.896), respectively. The prediction performance was fully validated in the external test set, and the model had an AUC of 0.758 (95% CI: 0.724–0.834) and an accuracy of 0.807 (95% CI: 0.774–0.843).ConclusionThe deep learning model based on endoscopic images demonstrated exceptional predictive power for neoadjuvant treatment response, highlighting its potential for guiding personalized therapy.

Unveiling the relationship between the UGT2B gene family and neoadjuvant treatment response in patients with HER2-positive breast cancer.

e12651 Background: Achieving a pathological complete response (pCR) following neoadjuvant treatment (NAT) in HER2-positive tumors significantly enhances patient survival, resulting in a remarkable 92% reduction in mortality risk. However, it is crucial to identify biomarkers capable of predicting the NAT response, moving towards more personalized medicine. This approach would enable the identification of patients likely to respond to specific therapies, thereby facilitating the implementation of targeted treatment strategies. Our study aims to identify potential molecular biomarkers predictive of NAT response through a comprehensive analysis of differential gene expression in tissue samples from patients with HER2-positive, hormone receptor (HR)-negative breast cancer. Methods: Total RNA was extracted from FFPE tissue samples from two independent cohorts of women diagnosed with localized or locally advanced HER2-positive, HR-negative breast cancer. These patients underwent NAT in several hospitals in Andalusia, Spain. Standard chemotherapy, including taxanes and/or anthracyclines, and targeted anti-HER2 treatment such as trastuzumab and pertuzumab were administered. The patients were stratified into responders (R), achieving pCR, and non-responders (nR). In a discovery cohort (n=20), RNA hybridization using Clariom D microarray was conducted to discern differentially expressed transcripts between R and nR. Subsequently, gene expression patterns, and related pathways involved in NAT response, were analyzed using Transcriptome Analysis Console (TAC). The selected transcripts then underwent validation through quantitative PCR (qPCR) in an independent cohort (n=40). The area under the receiver operating characteristic (ROC) curve was used to evaluate the sensitivity and specificity of the genes as predictive biomarkers. Results: Microarray analysis of the discovery cohort, revealed 954 differentially expressed transcripts between R and nR, following criteria of fold change greater than 1.5 or less than -1.5 and a p-value below 0.05. Among these, 643 were upregulated, while 311 were downregulated in nR compared to R. Bioinformatic analysis and a comprehensive literature review guided the selection of genes UGT2B10, UGT2B11, UGT2B15, UGT2B17, and UGT2B28 for further investigation. Subsequent qPCR analysis in the validation cohort, demonstrated the overexpression of these genes in non-responders, with statistical significance achieved only for UGT2B15. Conclusions: The UGT2B family genes encode enzymes involved in glucuronidation and metabolic pathways associated with drug detoxification and elimination. Our findings suggest that variations in the UGT2B15 expression may impact the metabolism rate of specific drugs, underscoring the necessity for additional research in this area.

Assessing response and adherence to neoadjuvant treatment in soft tissue sarcomas of the extremities.

e23559 Background: The standard treatment for large, intermediate, and high-grade extremity soft tissue sarcoma (ESTS) involves surgery and radiotherapy. The addition of chemotherapy has improved oncological outcomes, such as reduced recurrence and prolonged survival. However, the relationship between neoadjuvant treatment and tumor response in ESTS is not well understood. Pathological evaluation of viable tumor cells after treatment is an indicator of tumor response, yet the proportion of viable tumor cells remains high, particularly in high-risk sarcomas. Combining radiotherapy with chemotherapy may enhance the response of tumor cells. Objective: This study aims to evaluate the effects of neoadjuvant chemotherapy (NCT) and chemoradiotherapy (CRT) on patients with high-risk ESTS and to determine its impact on the pathological response. Methods: We enrolled adult patients with high-risk ESTS (SARCULATOR OS < 60%) at a single center in Latin America. The study was designed to analyze the pathological response in patients with high-risk sarcomas who underwent neoadjuvant CRT and resection and to correlate these responses with various variables. The treatment response was evaluated using the EORTC–STBSG criteria. Results: Thirty-four patients were recruited, with a median age of 44 years (IQR 23-74). Fifty-two percent had T3 tumors (mean size 18 cm), and 79.4% were diagnosed at stage III. The predominant histological subtypes were synovial sarcoma (35.3%) and dedifferentiated liposarcoma (29.4%). The most used NCT regimen was doxorubicin/ifosfamide (84.4%), with 62.5% receiving a dosage intensity of Q4W, affected by overcapacity, and 25% received Q3W. Concurrent CRT was administered to 64.7% of patients, with a median delay to onset of 36 days due to overcapacity (43.5%). Only 79.4% completed three preoperative cycles of treatment. As for the response, 41.2% had an EORTC-E response, and 17.6% had an EORTC-D response. Grade 3 neutropenia and anemia occurred in 17.2% and 8.8% of patients, respectively. Disease progression during NCT was observed in six patients. No significant difference was found in the pathological response between the Q4W and Q3W dosage intensities (p = 0.62). Conclusions: The impact of NCT on pathological responses was not significantly high, which may be due to the predominant histological type in our series. The main cause of treatment delay at our center was due to overcapacity; however, this did not influence the pathological response relative to dose intensity. Additional follow-up assessments are required to determine the influence on relapse-free and overall survival based on the response after preoperative CRT.

Genomic analysis of the tumor microenvironment in Asian and Native Hawaiian and Pacific Islander patients with triple negative breast cancer.

e12644 Background: Triple negative breast cancer (TNBC) accounts for approximately 10- 20% of breast cancer cases and has the worst overall survival and prognosis compared to other subtypes. Unlike other subtypes, patients with TNBC are responsive to neoadjuvant therapy. A higher percent of stromal tumor infiltrating lymophocytes (sTILs) in the tumor microenvironment of TNBC correlates with an improved prognosis. Previous studies demonstrate that Native Hawaiians and Pacific Islanders (NHPIs) and Asians have equivocal percent of sTILs. Yet NHPIs have a higher mortality rate at 24.9% compared to Asians at 11%. Our study aims to molecularly characterize the tumor microenvironment in a diverse population of patients with TNBC who received neoadjuvant therapy. Methods: Retrospective chart review was conducted on 12 Asians and 12 NHPI patients with early stage TNBC from 2015 to 2022 from a medical oncology clinic within the Hawai’i Pacific Health system. Patient data collected include age at diagnosis of breast cancer, histology, BMI, clinical stage, sTILs, residual cancer burden, neoadjuvant treatment, and pathologic complete response. Core biopsy samples were processed and analyzed using the nCounter Breast Cancer 360 Panel. Further analysis was obtained using the nSolver Advanced Analysis Module. Results: Patient characteristics are listed in the table. Most patients had the basal-like immunosuppressed TNBC subtype. Among differentially expressed genes between races, 31 genes were statistically significant. NHPIs expressed more IL12RB2 and MYC, and Asians expressed more FGFR4 and MLPH. Among responders compared to non-responders, 5 genes were statistically significant. Responders expressed more STC1 and PTGER3, and non-responders expressed more CRAYAB, TMPRSS2, and CHAD. Among old and young patients, 132 genes were statistically significant. Older patients expressed more FUT3 and CKMT1, and younger patients expressed more MMP7 and MIA. Conclusions: In this pilot study, the molecular and genetic differences suggest that the tumor microenvironment may play a role in treatment outcomes between NHPIs and Asians. Further analysis will be conducted to determine the differences in immune cell infiltration. [Table: see text]

Contrast-enhanced pelvic magnetic resonance imaging (MRI) for the prediction of treatment response in mucinous rectal cancer.

In mucinous rectal cancer, it can be difficult to differentiate between cellular and acellular mucin. The purpose of this study was to evaluate, in patients with mucinous rectal cancer, the value of static enhancement (enh) and pharmacokinetic parameters of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) in predicting pathologic complete response. This retrospective cross-sectional study performed at Memorial Sloan Kettering Cancer Center included 43 patients (24 males and 19 females; mean age, 57 years) with mucinous rectal cancer who underwent MRI at baseline as well as after neoadjuvant chemoradiotherapy but before surgical resection between 2008 and 2019. Two radiologists independently segmented tumors on contrast-enhanced axial 3D T1-weighted images and sagittal DCE magnetic resonance images. On contrast-enhanced axial T1-weighted images, the static parameters enh and relative enhancement (renh) were estimated. On DCE images, the pharmacokinetic parameters Ktrans, kep, relative Ktrans (rKtrans), and relative kep (rkep) were estimated. Associations between all parameters with pathologic complete response were tested using Wilcoxon signed-rank tests. Receiver operating characteristic (ROC) analysis was performed to assess the area under the curve (AUC) for each parameter. Of the 43 patients who were included in the study, 42/43 (98%) had evaluable contrast-enhanced axial T1-weighted images and 35/43 (81%) had evaluable DCE images. Of the patients with evaluable contrast-enhanced axial T1-weighted images, 9/42 (21%) had pathologic complete response and 33/42 (79%) did not have pathologic complete response. For reader 1, enh(pre-neoadjuvant chemotherapy), enh(post-neoadjuvant chemotherapy), and renh were significant predictors of pathologic complete response [P=0.045 (AUC =0.73), 0.039 (AUC =0.74), and 0.0042, respectively]. For reader 2, enh(pre-neoadjuvant chemotherapy) and renh were significant predictors [P=0.021 (AUC =0.77) and 0.002, respectively]. For renh, the AUC was 0.83 for reader 1, and 0.82 for reader 2. Meanwhile, of those patients with evaluable DCE images, 9/35 (26%) had pathologic complete response and 26/35 (74%) did not have pathologic complete response. Ktrans(pre-neoadjuvant chemotherapy), kep(pre-neoadjuvant chemotherapy), and rkep were significant predictors [P=0.016 (AUC =0.73), 0.00057 (AUC =0.81), and 0.0096 (AUC =0.74), respectively]. Static and pharmacokinetic parameters of contrast-enhanced MRI show promise to predict neoadjuvant treatment response. Static enh parameters, which are simpler to assess, showed the strongest prediction.

Can the Pathological Response in Patients with Locally Advanced Gastric Cancer Receiving Neoadjuvant Treatment Be Predicted by the CEA/Albumin and CRP/Albumin Ratios?

Background: The purposes of neoadjuvant chemotherapy are to tumor size to improve the tumor removal rate, extend survival, and prevent metastasis. In this study, the importance of CRP/albumin ratio and CEA/albumin ratio in the prediction of neoadjuvant treatment response in gastric cancer patients was evaluated. Methods: This study retrospectively included 135 gastric cancer patients who received neoadjuvant chemotherapy at Çukurova University Balcalı Hospital between January 2018 and December 2023. Preoperative CRP/albumin and CEA/albumin ratios were compared according to treatment response and multivariate logistic regression analysis was performed to determine the potential importance of these ratios in predicting pathological response. Results: The mean age of the 135 patients was 58.79 ± 10.83 (min = 26-max = 78). The CRP/albumin and CEA/albumin ratios were found to be significantly lower in patients who did not respond to neoadjuvant therapy. Each 1-unit increase in the CRP/albumin ratio was associated with a 1.16-fold decrease in the odds of pathological complete response to neoadjuvant therapy. Both CRP/albumin and CEA/albumin ratios were found to be significant in distinguishing neoadjuvant therapy response. The optimal cut-off value was 2.74 for the CRP/albumin ratio (sensitivity = 60%, specificity = 78.4%) and 1.40 for the CEA/albumin ratio (sensitivity = 74.2%, specificity = 67.6%). Values below these cut-off points favored neoadjuvant therapy response. Pathological complete response to neoadjuvant therapy was 4.75 times higher in patients with a CRP/albumin ratio below 2.74 and 5.14 times higher in patients with a CEA/albumin ratio below 1.40. Conclusions: Findings demonstrate that in patients with locally advanced gastric cancer receiving neoadjuvant treatment, CRP/Albumin and CEA/Albumin ratios are significant markers of pathological response.

Machine-learning and mechanistic modeling of metastatic breast cancer after neoadjuvant treatment.

Clinical trials involving systemic neoadjuvant treatments in breast cancer aim to shrink tumors before surgery while simultaneously allowing for controlled evaluation of biomarkers, toxicity, and suppression of distant (occult) metastatic disease. Yet neoadjuvant clinical trials are rarely preceded by preclinical testing involving neoadjuvant treatment, surgery, and post-surgery monitoring of the disease. Here we used a mouse model of spontaneous metastasis occurring after surgical removal of orthotopically implanted primary tumors to develop a predictive mathematical model of neoadjuvant treatment response to sunitinib, a receptor tyrosine kinase inhibitor (RTKI). Treatment outcomes were used to validate a novel mathematical kinetics-pharmacodynamics model predictive of perioperative disease progression. Longitudinal measurements of presurgical primary tumor size and postsurgical metastatic burden were compiled using 128 mice receiving variable neoadjuvant treatment doses and schedules (released publicly at https://zenodo.org/records/10607753). A non-linear mixed-effects modeling approach quantified inter-animal variabilities in metastatic dynamics and survival, and machine-learning algorithms were applied to investigate the significance of several biomarkers at resection as predictors of individual kinetics. Biomarkers included circulating tumor- and immune-based cells (circulating tumor cells and myeloid-derived suppressor cells) as well as immunohistochemical tumor proteins (CD31 and Ki67). Our computational simulations show that neoadjuvant RTKI treatment inhibits primary tumor growth but has little efficacy in preventing (micro)-metastatic disease progression after surgery and treatment cessation. Machine learning algorithms that included support vector machines, random forests, and artificial neural networks, confirmed a lack of definitive biomarkers, which shows the value of preclinical modeling studies to identify potential failures that should be avoided clinically.

Abstract 7607: Single-cell genomics study before and after neoadjuvant therapy for triple-negative breast cancer

Abstract Breast cancer has become the most common malignant tumor globally. Neoadjuvant chemotherapy (NAC) has become an important treatment option for locally advanced breast cancer, capable of eliminating circulating tumor cells (micrometastases) and achieving downstaging objectives. However, even after completing neoadjuvant chemotherapy or receiving local treatment, some patients may still have residual lesions, which are a key factor in distant recurrence and metastasis. The existing clinical biomarker tests such as CEA, CA-153, and imaging methods are unable to accurately assess the condition early on. Although tissue pathology biopsy of tumor specimens is the gold standard for clinical pathological diagnosis, it also has certain limitations. Traditional high-throughput sequencing technology for breast cancer primarily identifies "driver genes" associated with the occurrence and development of breast cancer. However, it has limitations in identifying genomic structural changes and subclones of breast cancer, and it overlooks the heterogeneity among tumor cells. The emergence of single-cell RNA sequencing (scRNA-seq) technology can detect these heterogeneous individuals, decode the heterogeneity of breast cancer cells, refine molecular subtypes, and open up new pathways to overcome drug resistance. We collected samples from 6 patients with locally advanced triple-negative breast cancer (ER-, PR-, HER2-negative, defined as HER2 immunohistochemistry 0, 1+ or 2+ but FISH-negative). We compared the cell subgroups and their gene expression in biopsy specimens before neoadjuvant chemotherapy with those in post-treatment specimens obtained during surgery, analyzing changes in cell composition in the tumor microenvironment before and after immunotherapy to identify specific cell types potentially contributing to the outcome of immunotherapy, particularly cell subtypes associated with T-cell clonal proliferation. We found that in the group with good neoadjuvant treatment response (Miller-Payne grade 4-5), B cells, CD4+ T cells, CD8+ T cells, and Tregs cells were all significantly downregulated, while endothelial cells and aSMA-positive fibroblast cells were significantly upregulated. By comparing changes in the immune microenvironment between patients with and without T-cell clonal proliferation before and after treatment, we revealed the differentiation patterns of various immune cells in immunotherapy and potential mechanisms of action. Citation Format: Yingkuan Shao, Kailun Xu. Single-cell genomics study before and after neoadjuvant therapy for triple-negative breast cancer [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 7607.

The Revolution in Breast Cancer Diagnostics: From Visual Inspection of Histopathology Slides to Using Desktop Tissue Analysers for Automated Nanomechanical Profiling of Tumours.

We aim to develop new portable desktop tissue analysers (DTAs) to provide fast, low-cost, and precise test results for fast nanomechanical profiling of tumours. This paper will explain the reasoning for choosing indentation-type atomic force microscopy (IT-AFM) to reveal the functional details of cancer. Determining the subtype, cancer stage, and prognosis will be possible, which aids in choosing the best treatment. DTAs are based on fast IT-AFM at the size of a small box that can be made for a low budget compared to other clinical imaging tools. The DTAs can work in remote areas and all parts of the world. There are a number of direct benefits: First, it is no longer needed to wait a week for the pathology report as the test will only take 10 min. Second, it avoids the complicated steps of making histopathology slides and saves costs of labour. Third, computers and robots are more consistent, more reliable, and more economical than human workers which may result in fewer diagnostic errors. Fourth, the IT-AFM analysis is capable of distinguishing between various cancer subtypes. Fifth, the IT-AFM analysis could reveal new insights about why immunotherapy fails. Sixth, IT-AFM may provide new insights into the neoadjuvant treatment response. Seventh, the healthcare system saves money by reducing diagnostic backlogs. Eighth, the results are stored on a central server and can be accessed to develop strategies to prevent cancer. To bring the IT-AFM technology from the bench to the operation theatre, a fast IT-AFM sensor needs to be developed and integrated into the DTAs.

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.