Objective To explore the accuracy of contrast-enhanced magnetic resonance imaging (MRI) in predicting pathological complete remission (pCR) in breast cancer patients after neoadjuvant therapy (NAC). Methods The clinicopathological data of 245 patients with invasive breast cancer who had completed the surgical resection after NAC in the Affiliated Hospital of Southwest Medical University from March 2020 to April 2022 were collected retrospectively. According to the results of hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) detected by immunohistochemistry, all patients were divided into four subgroups: HR+/HER2–, HR+/HER2+, HR–/HER2+ and HR–/HER2–. The value of MRI in evaluating the efficacy of NAC was analyzed by comparing the postoperative pathological results as the gold standard with the residual tumor size assessed by preoperative MRI. Meanwhile, the sensitivity, specificity and positive predictive value (PPV) of pCR predicted by the evaluation results of enhanced MRI were analyzed, and further analyzed its predictive value for pCR of different subtypes of breast cancer. Results There were 88 cases (35.9%) achieved radiological complete response (rCR) and 106 cases (43.3%) achieved pCR in 245 patients. Enhanced MRI in assessing the size of residual tumors overestimated and underestimated 12.7% (31/245) and 9.8% (24/245) of patients, respectively. When setting rCR as the MRI assessment index the specificity, sensitivity and PPV were 84.2% (117/139), 62.3% (66/106) and 75.0% (66/88), respectively. When setting near-rCR as the MRI assessment index the specificity, sensitivity and PPV were 70.5% (98/139), 81.1% (86/106), and 67.7% (86/127), respectively. The positive predictive value of both MRI-rCR and MRI-near-rCR in evaluating pCR of each subtype subgroup of breast cancer was the highest in the HR–/HER2+ subgroup (91.7% and 83.3%, respectively). In each subgroup, compared with rCR, the specificity of near-rCR to predict pCR decreased to different degrees, while the sensitivity increased to different degrees. Conclusions Breast contrast-enhanced MRI can more accurately evaluate the efficacy of localized breast lesions after NAC, and can also more accurately predict the breast pCR after NAC. The HR–/HER2+ subgroup may be a potentially predictable population with pCR exemption from breast surgery. However, the accuracy of the evaluation of pCR by breast enhancement MRI in HR+/HER2– subgroup is low.
Objective To explore the predictive value of peripheral blood cells in the efficacy of neoadjuvant immunotherapy combined with chemotherapy for esophageal squamous cell carcinoma. Methods A retrospective study was conducted on patients with esophageal squamous cell carcinoma (clinical stages Ⅱ-Ⅳa) who underwent neoadjuvant immunotherapy combined with chemotherapy at the Department of Thoracic Surgery, Affiliated Hospital of North Sichuan Medical College from April 2020 to November 2023. According to whether the pathology was completely relieved after treatment, patients were divided into a pathological complete remission group and a pathological incomplete remission group. The College of American Pathologists criteria were used to evaluate the tumor pathological regression grade (TRG) after neoadjuvant therapy (TRG=0, 1 defined as a good efficacy group, TRG=2, 3 defined as a poor efficacy group). Results A total of 92 patients with esophageal squamous cell carcinoma were collected, including 72 males and 20 females. The average age was (65.86±7.66) years. The complete remission of pathology was closely related to the number of lymphocytes in the blood before treatment (P=0.019). The area under the curve (AUC) for predicting complete remission of esophageal squamous cell carcinoma after neoadjuvant immunotherapy combined with chemotherapy was 0.678, the maximum Youden index was 0.328, and the optimal cutoff value was 1.845. The incidence of postoperative pulmonary infection in the pathological incomplete remission group was higher than that in the pathological complete remission group (25.0% vs. 5.6%, P=0.030). Using the optimal cutoff value, there were statistically significant differences in pathological N stage and pathological TNM stage between patients with lymphocyte counts <1.845×109/L and ≥1.845×109/L (P<0.05). Treatment response (by TRG) was significantly associated with the pretreatment red blood cell count (P=0.009). The AUC for predicting a good TRG response was 0.669, with a maximum Youden index of 0.385 and an optimal cutoff value of 4.235. Between the good and poor response groups, there were statistically significant differences in postoperative pathological T stage (P<0.001), N stage (P=0.041), and TNM stage (P＜0.001). When stratified by the optimal cutoff value, there were statistically significant differences in age (P＜0.001) and the prevalence of hypertension (P=0.022) between patients with red blood cell counts <4.235×1012/L and ≥4.235×1012/L. Conclusion A pretreatment absolute lymphocyte count ≥1.845×109/L and a red blood cell count <4.235×1012/L are good predictors for pathological complete response and a good pathological response, respectively, following neoadjuvant immunotherapy combined with chemotherapy in patients with esophageal squamous cell carcinoma.
ObjectiveTo develop a multimodal prediction model integrating radiomics, deep learning (DL) and nomogram, and evaluate its performance in predicting pathologic complete response (pCR) after total neoadjuvant therapy (TNT) for locally advanced rectal cancer (LARC). MethodsPatients with LARC who underwent radical resection after TNT from January 2023 to December 2024 were prospectively enrolled and randomly divided into a training cohort and a test cohort at a ratio of 7∶3. In the training cohort, radiomic features were extracted from baseline T2-weighted imaging and diffusion-weighted imaging; The least absolute shrinkage and selection operator regression was adopted to screen the optimal feature subsets, based on which a radiomics score formula was constructed, and the radiomics score of each patient was subsequently calculated; A dual-channel DL model based on ResNet-50 architecture was constructed simultaneously; Univariate and multivariate logistic regression analyses were performed to screen independent predictive factors for the development of a nomogram model. A stacking ensemble strategy was adopted to integrate the above three base models into a final fusion model. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, Brier score, Hosmer-Lemeshow test, integrated discrimination improvement (IDI) index, net reclassification improvement (NRI) index, decision curve analysis (DCA), and subgroup analysis were applied to comprehensively evaluate the performance and clinical value of all models. ResultsA total of 196 patients were enrolled, among whom 58 patients achieved pCR, accounting for 29.6%. Among 196, 137 cases were assigned to the training cohort and 59 cases to the test cohort. Based on the training cohort data, five independent predictive factors were identified using multivariate logistic regression to develop a nomogram, including tumor distance from the anal verge, baseline carcinoembryonic antigen (CEA), neutrophil-to-lymphocyte ratio, ≥60% reduction in CEA at mid-chemotherapy (after 2 cycles), and interval from the end of radiotherapy to surgery. The DL model converged after 50 training epochs, radiomics score [M（P25, P75）] was 0.45 (–0.32, 1.58). A stacking ensemble fusion model was established by integrating three base models, namely the radiomics model, DL model, and nomogram. In the test cohort, the AUC of the fusion model was 0.893, which was higher than 0.801 for the radiomics model, 0.841 for the DL model, and 0.788 for the nomogram. All differences were statistically significant by the DeLong test (all P<0.05). The sensitivity, specificity, accuracy, and Brier score of the fusion model were 88.24%, 83.33%, 84.75%, and 0.112, respectively. The Hosmer-Lemeshow test suggested a good consistency between the predicted and actual probabilities (P=0.522). The IDI index of the fusion model vs. the DL model and vs. the nomogram was 0.128 and 0.156, respectively; the NRI index was 0.342 and 0.287 (all P<0.001), respectively. DCA demonstrated that the fusion model yielded the highest clinical net benefit within the threshold range of 10% to 60%. Subgroup analysis showed that the fusion model maintained favorable predictive performance across subgroups stratified by tumor location, clinical stage, baseline CEA level, age, gender, and interval from the end of radiotherapy to surgery, with AUC values ranging from 0.856 to 0.918. Particularly, the AUC reached 0.918 in patients with tumor distance from the anal verge <5 cm and 0.911 in those with interval from the end of radiotherapy to surgery ＞10 weeks. ConclusionsThe fusion model constructed by the stacking ensemble strategy integrates multi-phase magnetic resonance imaging radiomic features, dynamic biomarker changes, and clinicopathologic parameters. It exhibits excellent discriminative ability, calibration performance and clinical practicability, and maintains robust stability across different clinical subgroups. This model can accurately predict the status of pCR in LARC patients after TNT. Compared with single models, the fusion model achieves better predictive efficacy and higher clinical net benefit, and can provide references for individualized clinical treatment decisions.