With the rising incidence of breast cancer among women, neoadjuvant chemotherapy (NAC) is becoming increasingly crucial as a preoperative treatment modality, enabling tumor downstaging and volume reduction. However, its efficacy varies significantly among patients, underscoring the importance of predicting pathological complete response (pCR) following NAC. Early research relied on statistical methods to integrate clinical data for predicting treatment outcomes. With the advent of artificial intelligence (AI), traditional machine learning approaches were subsequently employed for efficacy prediction. Deep learning emerged to dominate this field, and demonstrated the capability to automatically extract imaging features and integrate multimodal data for pCR prediction. This review comprehensively examined the applications and limitations of these three methodologies in predicting breast cancer pCR. Future efforts must prioritize the development of superior predictive models to achieve precise predictions, integrate them into clinical workflows, enhance patient care, and ultimately improve therapeutic outcomes and quality of life.
Humans ; Breast Neoplasms/pathology* ; Neoadjuvant Therapy ; Artificial Intelligence ; Female ; Machine Learning ; Deep Learning ; Chemotherapy, Adjuvant ; Treatment Outcome

OBJECTIVES

The influence of weight change on the response to neoadjuvant chemotherapy (NAC) among adult Filipino patients with breast cancer remains unclear. Currently, there has been increasing evidence that weight gain during NAC is associated with increased recurrence risk and decreased survival. This study aimed to investigate this relationship and identify significant predictors of pathologic complete response (pCR), overall survival (OS) and disease-free survival (DFS).

This is a retrospective study using data from 52 female patients who received NAC for stage II or III breast cancer and had complete records of weight before and after NAC. Significant predictors of pCR such as host factors and tumor characteristics and associations between weight change and pCR, OS and DFS were examined using univariate and multivariable logistic regression analyses.

The average weight of all patients before NAC was 57.0 kg while the average weight of all patients after NAC was 59.5 kg. The average BMI of all patients before NAC was 25.8 kg/m2. In total, 29 patients (55.8%) were classified in the overweight/obese (OW/OB) group, and the rest were classified in the normal weight/underweight (NW/UW) group. The pCR rate was 51.3% in the OW/OB group versus 48.7% in the NW/UW group (p = 0.11). Initial BMI was a significant factor for achieving pCR (hazard ratio, 3.85; 95% confidence interval [CI], 1.72-8.60, p = 0.001), suggesting that a higher initial BMI was associated with an increased likelihood of achieving pCR. Initial BMI was also an independent prognostic factor for OS (p = 0.0006) and DFS (p = 0.0005). On the other hand, no significant correlation was seen between pCR rates as well as OFS and DFS (p = 0.0551) among patients whose weight changed during the course of treatment.

These findings suggest that while initial weight may significantly predict pCR rates and affect DFS and OS, weight change during treatment may not be as influential. Further research is needed to validate these findings in more diverse and larger patient populations.

BACKGROUND: Neoadjuvant immunochemotherapy has emerged as an indispensable therapeutic modality for non-small cell lung cancer (NSCLC). However, its clinical application experience remains limited, and the associations between various clinical factors and treatment benefits remain undefined. This study aims to evaluate the efficacy and safety of neoadjuvant immunochemotherapy in patients with stage IB-IIIB NSCLC in a real-world setting, analyze survival outcomes among subgroups with diverse clinical characteristics, and identify potential clinical predictive factors for pathological response. METHODS: This study included patients with stage IB-IIIB NSCLC who underwent radical lung resection after 2-4 cycles of neoadjuvant immunochemotherapy at Peking University People's Hospital between August 2019 and March 2024. Medical records and follow-up information were collected to analyze therapeutic response, adverse events and survival outcomes. Logistic analysis was used to identify clinical predictors of pathological response. RESULTS: Among 183 enrolled patients, 116 (63.4%) were stage III. Grade 3-4 immune-related adverse events (irAEs) occurred in 39 (21.3%) patients. Radiographic complete response (CR) or partial response (PR) was achieved in 118 (64.5%) patients. R0 resection was achieved in 180 (98.4%) patients. Major pathologic response (MPR) was observed in 107 (58.5%) patients, with 78 (42.6%) achieving pathologic complete response (pCR). Squamous cell carcinoma and radiographic objective response were associated with pathological response (pCR/MPR). With a median follow-up of 22.1 [interquartile range (IQR): 18.3-32.2] months, the 2-year event-free survival (EFS) and overall survival (OS) rates were 82.5% and 90.4%, respectively. Achievement of pathological response (pCR/MPR) was correlated with prolonged survival outcomes. CONCLUSIONS Neoadjuvant immunochemotherapy is safe and effective for patients with stage IB-IIIB NSCLC. Patients achieving pCR or MPR exhibit significantly better survival benefits from neoadjuvant immunochemotherapy. Squamous cell carcinoma and radiographic objective response can serve as clinical predictors of pathological response.
Humans ; Carcinoma, Non-Small-Cell Lung/mortality* ; Male ; Lung Neoplasms/mortality* ; Female ; Middle Aged ; Neoadjuvant Therapy/adverse effects* ; Aged ; Neoplasm Staging ; Adult ; Immunotherapy/adverse effects* ; Treatment Outcome ; Retrospective Studies

BACKGROUND: The proportion of patients with non-small cell lung cancer (NSCLC) harboring epidermal growth factor receptor (EGFR) mutations is relatively high in China. However, these patients currently lack significant benefits from available neoadjuvant treatment options. This study aims to explore the potential application value of neoadjuvant targeted therapy by evaluating its efficacy and safety in patients with EGFR-mutant resectable lung adenocarcinoma. METHODS: A multicenter retrospective study was used to analyze the treatment effect of patients with stage IIA-IIIB EGFR-mutant lung adenocarcinoma who underwent surgical resection after receiving neoadjuvant targeted therapy from July 2019 to October 2024. RESULTS: A total of 24 patients with EGFR-mutant lung adenocarcinoma from three centers were included in this study. All patients successfully underwent surgery and achieved R0 resection of 100.0%. The objective response rate (ORR) was 83.3% (20/24) . The major pathologic response (MPR) rate was 37.5% (9/24), with 2 patients (8.3%) achieving pathological complete response (pCR). During neoadjuvant therapy, 13 out of 24 patients (54.2%) experienced adverse events of grade 1-2, with no occurrences of ≥ grade 3. The most common treatment-related adverse events were rash (n=4, 16.7%), mouth sores (n=2, 8.3%), and diarrhea (n=2, 8.3%). The median follow-up time was 33.0 months, no deaths occurred in all patients, and the overall survival (OS) rate was 100.0%. The 1-year disease-free survival (DFS) rate was 91.1%, and the 2-year DFS rate remained at 86.2%. CONCLUSIONS The application of neoadjuvant targeted therapy in patients with EGFR-mutant resectable lung adenocarcinoma is safe and feasible, and is expected to become a highly promising neoadjuvant treatment option for the patients with EGFR-mutant lung adenocarcinoma.
Humans ; ErbB Receptors/metabolism* ; Male ; Female ; Middle Aged ; Adenocarcinoma of Lung/surgery* ; Neoadjuvant Therapy ; Lung Neoplasms/surgery* ; Aged ; Retrospective Studies ; Mutation ; Adult

BACKGROUND: Neoadjuvant therapeutic strategies play a pivotal role in the comprehensive treatment of non-small cell lung cancer (NSCLC). However, lung squamous cell carcinoma (SCC) generally exhibits a more favorable response to neoadjuvant therapy compared with lung adenocarcinoma (ADC). The aim of this study is to elucidate how baseline cancer-associated fibroblasts (CAFs) and tumor-associated endothelial cells (TAECs) influence the differential therapeutic outcomes of neoadjuvant treatment in SCC versus ADC. METHODS: We retrospectively collected pretreatment biopsy samples from 104 patients with stage II-III NSCLC who underwent neoadjuvant chemotherapy (NAC) or neoadjuvant chemoimmunotherapy (NAIC) at Shandong Cancer Hospital between January 1, 2018 and December 31, 2023. Tissue microarrays were constructed using an automated arrayer, and multiplex immunofluorescence staining (α-SMA/CD31/CK/DAPI) was performed to identify CAFs (α-SMA+/CK-) and TAECs (CD31+/CK-). Quantitative analyses included CAFs and TAECs densities, the nearest neighbor distance (NND) between CAFs and TAECs, and their spatial proximity (30 μm). Differences in major pathological response (MPR) between groups, defined as residual viable tumor cells ≤10% in resected specimens after neoadjuvant therapy, were assessed using the χ² test. The Mann-Whitney U test was applied to analyze intergroup differences in quantitative indicators, and receiver operating characteristic (ROC) curve analysis was conducted to evaluate the predictive performance of immune-related markers for MPR in the NAIC cohort. RESULTS: Among the 104 NSCLC patients who received neoadjuvant therapy, 35 underwent NAIC and 69 received NAC. Overall, patients with SCC were more likely to achieve MPR compared with those with ADC (50.0% vs 22.4%, P=0.006). This trend persisted in the NAIC subgroup (72.7% vs 30.8%, P=0.038), whereas no significant difference in MPR rates was observed between SCC and ADC in the NAC subgroup. At baseline, prior to NAIC or NAC, programmed cell death ligand 1 (PD-L1)/programmed cell death 1 (PD-1) expression, CAFs and TAECs densities, CAFs-TAECs NND, and CAFs-TAECs proximity (30 μm) showed no significant differences between SCC and ADC. In patients with SCC receiving NAIC, baseline PD-L1/PD-1 expression, CAFs density, and TAECs density showed not significant differences between MPR and NMPR groups. However, the CAFs-TAECs distance was significantly greater in the MPR group (NND: 31.2 vs 24.7 μm, P=0.038), and the number of TAECs within 30 μm of CAFs was significantly lower (proximity: 1.1 vs 3.6, P=0.038). Univariate Cox regression analysis indicated that low TAECs density was associated with MPR following NAIC (OR=36.00, 95%CI: 2.68-1486.88, P=0.019). Furthermore, ROC analysis demonstrated that baseline CAFs-TAECs NND and proximity (30 μm) exhibited strong predictive performance for MPR in SCC patients treated with NAIC, with an area under the curve (AUC) of 0.893, sensitivity of 0.857, and specificity of 1.000. CONCLUSIONS CAFs are more spatially distant from TAECs and more prone to MPR after NAIC in SCC, which may be related to the reduced interaction of CAFs with TAECs and reduced tumor-associated angiogenesis.
Humans ; Lung Neoplasms/therapy* ; Neoadjuvant Therapy ; Male ; Female ; Middle Aged ; Retrospective Studies ; Endothelial Cells/drug effects* ; Aged ; Cancer-Associated Fibroblasts/drug effects* ; Immunotherapy ; Carcinoma, Squamous Cell/drug therapy* ; Carcinoma, Non-Small-Cell Lung/drug therapy* ; Adult

Rectal cancer is one of the most common malignant tumors in China, with more than half of patients diagnosed at the locally advanced stage. Currently, the standard treatment for locally advanced rectal cancer (LARC) primarily involves neoadjuvant chemoradiotherapy followed by radical surgery. The advent of immune checkpoint inhibitors has revolutionized the neoadjuvant treatment landscape for mismatch repair-deficient/microsatellite instability-high (dMMR/MSI-H) rectal cancer. However, most rectal cancer patients exhibit mismatch repair-proficient/microsatellite stable (pMMR/MSS) status and show poor responsiveness to immunotherapy. In recent years, multiple studies have demonstrated that neoadjuvant short-course radiotherapy followed by chemotherapy and immunotherapy can improve the pathological complete response rate in pMMR/MSS LARC patients. Nevertheless, controversies persist regarding patient selection, efficacy evaluation, adverse event management, postoperative adjuvant therapy, and follow-up strategies. Considering the Colorectal Surgery Group of the Surgery Branch of the Chinese Medical Association, in collaboration with the Colorectal and Anal Surgery Committee of the Chinese Research Hospital Association, the Chinese Colorectal Cancer Clinical Research Collaborative Group, and related experts, has developed this consensus document by referencing domestic and international research advancements. The aim is to provide standardized guidance for the clinical application of this treatment approach.
Humans ; Rectal Neoplasms/genetics* ; Neoadjuvant Therapy ; Immunotherapy ; DNA Mismatch Repair ; Microsatellite Instability ; Consensus ; Combined Modality Therapy

OBJECTIVE: To explore the effect of concurrent administration of goserelin for ovarian function protection on the pathological complete response (pCR) rate and objective response rate (ORR) of neoadjuvant chemotherapy (NAC) in young breast cancer patients. METHODS: The study enrolled breast cancer patients aged 18-45 with clinical stages ⅡA~ⅢC from January 2016 to May 2020. According to patients' willingness, they were divided into two groups: Those who chose to receive goserelin to protect ovarian function during NAC (goserelin group) and those who did not (chemotherapy group). The pCR rate and ORR were compared between the two groups, and subgroup analysis was conducted for patients with different molecular subtypes. RESULTS: A total of 93 patients were included in this study (31 in the goserelin group and 62 in the chemotherapy group). After propensity score weighting (PSW) adjustment, baseline data such as age, preoperative clinical stage, postoperative pathological stage, pa-thological type, hormone receptor status, human epidermal growth factor receptor 2 (HER2) and Ki-67 expression, molecular subtypes, and chemotherapy regimens were well-matched between the two groups. There was no significant difference in the pCR rate between the goserelin group and the chemotherapy group, with rates of 29.0% and 25.8%, respectively (P=0.741). Similarly, there was no significant difference in ORR between the two groups (90.3% vs. 87.1%, P=0.746). Subgroup analysis revealed that among the patients with hormone receptor-positive tumors, there were no significant differences in pCR rate (6.3% vs. 7.7%, P=0.852) or ORR (87.5% vs. 82.1%, P=0.839) between the goserelin and chemotherapy groups. Among the patients with hormone receptor-negative tumors, there were also no significant differences in pCR rate (53.3% vs. 56.5%, P=0.847) or ORR (93.3% vs. 95.7%, P=0.975) between the two groups. One year after the completion of chemotherapy, the incidence of chemotherapy-induced amenorrhea (CIA) was significantly lower in the goserelin group compared with the chemotherapy group (9.5% vs. 33.3%, P=0.036). CONCLUSION For young breast cancer patients with clinical stages of ⅡA~ⅢC, there was no statistical difference in pCR rate and ORR whether or not using goserelin during NAC. However, it is still necessary to expand the sample size and carry out a longer follow-up to evaluate the effect of goserelin on the long-term survival of young patients.
Humans ; Goserelin/administration & dosage* ; Female ; Breast Neoplasms/pathology* ; Neoadjuvant Therapy/methods* ; Adult ; Middle Aged ; Young Adult ; Adolescent ; Chemotherapy, Adjuvant ; Antineoplastic Combined Chemotherapy Protocols/therapeutic use* ; Antineoplastic Agents, Hormonal/therapeutic use* ; Treatment Outcome ; Receptor, ErbB-2

BACKGROUND: This study aims to compare the efficacy between neoadjuvant immune checkpoint inhibitors (ICIs) plus chemotherapy vs . chemotherapy, and neoadjuvant triplet vs . doublet chemotherapeutic regimens in locally advanced gastric/esophagogastric junction cancer (LAGC). METHODS: We included LAGC patients from 47 hospitals in China's National Cancer Information Database (NCID) from January 2019 to December 2022. Using propensity score matching (PSM), we retrospectively analyzed the efficacy between neoadjuvant ICIs plus chemotherapy vs . chemotherapy alone, and neoadjuvant triplet vs . doublet chemotherapeutic regimens. The primary study result was the pathologic complete response (pCR) rate. The secondary study results were disease-free survival (DFS) and overall survival (OS). RESULTS: A total of 1205 LAGC patients were included. After PSM, the ICIs plus chemotherapy and the chemotherapy cohorts had 184 patients each, while the doublet and triplet chemotherapy cohorts had 246 patients each. The pCR rate (14.13% vs . 7.61%, χ2 = 4.039, P = 0.044), and the 2-year (77.60% vs . 61.02%, HR = 0.67, 95% con-fidence interval [CI] 0.43-0.98, P = 0.048) and 3-year (70.55% vs . 61.02%, HR = 0.58, 95% CI 0.32-0.93, P = 0.048) DFS rates in the ICIs plus chemotherapy cohort were improved compared to those in the chemotherapy cohort. No significant increase was observed in the OS rates at both 1 year and 2 years. The pCR rates, DFS rates at 1-3 years, and OS rates at 1-2 years did not differ significantly between the doublet and triplet cohorts, respectively. No differences were observed in postoperative complications between any of the group comparisons. CONCLUSIONS Neoadjuvant ICIs plus chemotherapy improved the pCR rate and 2-3 years DFS rates of LAGC compared to chemotherapy alone, but whether short-term benefit could translate into long-term efficacy is unclear. The triplet regimen was not superior to the doublet regimen in terms of efficacy. The safety after surgery was similar between either ICIs plus chemotherapy and chemotherapy or the triplet and the doublet regimen.
Humans ; Stomach Neoplasms/metabolism* ; Female ; Neoadjuvant Therapy/methods* ; Immune Checkpoint Inhibitors/therapeutic use* ; Male ; Middle Aged ; Propensity Score ; Retrospective Studies ; Aged ; Receptor, ErbB-2/metabolism* ; Adult ; Antineoplastic Combined Chemotherapy Protocols/therapeutic use* ; Disease-Free Survival ; Cohort Studies

BACKGROUND: Neoadjuvant therapy enhances the possibility of achieving radical resection and improves the prognosis for locally advanced gastric cancer (GC). However, there is a lack of evidence regarding the optimal extent of resection for locally advanced proximal GC after neoadjuvant therapy. METHODS: In this study, 330 patients underwent resection in Peking University Cancer Hospital, with curative intent after neoadjuvant therapy for histologically confirmed proximal GC from January 2009 to December 2022. RESULTS: In this study, 45 patients underwent proximal gastrectomy (PG), while 285 underwent total gastrectomy (TG). After propensity-score matching, 110 patients (71 TG and 39 PG) were included in the analysis. No significant differences between PG and TG regarding short-term outcomes and long-term prognosis were found. Specifically, PG demonstrated comparable overall survival to TG ( P = 0.47). Subgroup analysis revealed that although not statistically significant, PG showed a potential advantage over TG in overall survival for patients with tumor-long diameters less than 4 cm ( P  = 0.31). However, for those with a long diameter larger than 4 cm, TG had a better survival probability ( P  = 0.81). No substantial differences were observed in baseline characteristics, surgical safety, postoperative recovery, and postoperative complications. CONCLUSION For locally advanced proximal GC with objective response to neoadjuvant therapy (long diameter <4 cm), PG is an alternative surgical procedure.
Humans ; Stomach Neoplasms/drug therapy* ; Gastrectomy/methods* ; Neoadjuvant Therapy/methods* ; Male ; Female ; Middle Aged ; Propensity Score ; Aged ; Adult ; Retrospective Studies

BACKGROUND: Neoadjuvant chemoradiotherapy followed by radical surgery has been a common practice for patients with locally advanced rectal cancer, but the response rate varies among patients. This study aimed to develop a ResNet-Vision Transformer based magnetic resonance imaging (MRI)-endoscopy fusion model to precisely predict treatment response and provide personalized treatment. METHODS: In this multicenter study, 366 eligible patients who had undergone neoadjuvant chemoradiotherapy followed by radical surgery at eight Chinese tertiary hospitals between January 2017 and June 2024 were recruited, with 2928 pretreatment colonic endoscopic images and 366 pelvic MRI images. An MRI-endoscopy fusion model was constructed based on the ResNet backbone and Transformer network using pretreatment MRI and endoscopic images. Treatment response was defined as good response or non-good response based on the tumor regression grade. The Delong test and the Hanley-McNeil test were utilized to compare prediction performance among different models and different subgroups, respectively. The predictive performance of the MRI-endoscopy fusion model was comprehensively validated in the test sets and was further compared to that of the single-modal MRI model and single-modal endoscopy model. RESULTS: The MRI-endoscopy fusion model demonstrated favorable prediction performance. In the internal validation set, the area under the curve (AUC) and accuracy were 0.852 (95% confidence interval [CI]: 0.744-0.940) and 0.737 (95% CI: 0.712-0.844), respectively. Moreover, the AUC and accuracy reached 0.769 (95% CI: 0.678-0.861) and 0.729 (95% CI: 0.628-0.821), respectively, in the external test set. In addition, the MRI-endoscopy fusion model outperformed the single-modal MRI model (AUC: 0.692 [95% CI: 0.609-0.783], accuracy: 0.659 [95% CI: 0.565-0.775]) and the single-modal endoscopy model (AUC: 0.720 [95% CI: 0.617-0.823], accuracy: 0.713 [95% CI: 0.612-0.809]) in the external test set. CONCLUSION The MRI-endoscopy fusion model based on ResNet-Vision Transformer achieved favorable performance in predicting treatment response to neoadjuvant chemoradiotherapy and holds tremendous potential for enabling personalized treatment regimens for locally advanced rectal cancer patients.
Humans ; Rectal Neoplasms/diagnostic imaging* ; Magnetic Resonance Imaging/methods* ; Male ; Female ; Middle Aged ; Neoadjuvant Therapy/methods* ; Aged ; Adult ; Chemoradiotherapy/methods* ; Endoscopy/methods* ; Treatment Outcome