Predicting Pathologic Complete Response in Locally Advanced Rectal Cancer with [68Ga]Ga-FAPI-04 PET, [18F]FDG PET, and Contrast-Enhanced MRI: Lesion-to-Lesion Comparison with Pathology.

Neoadjuvant therapy in patients with locally advanced rectal cancer (LARC) has achieved good pathologic complete response (pCR) rates, potentially eliminating the need for surgical intervention. This study investigated preoperative methods for predicting pCR after neoadjuvant short-course radiotherapy (SCRT) combined with immunochemotherapy. Methods: Treatment-naïve patients with histologically confirmed LARC were enrolled from February 2023 to July 2023. Before surgery, the patients received neoadjuvant SCRT followed by 2 cycles of capecitabine and oxaliplatin plus camrelizumab. 68Ga-labeled fibroblast activation protein inhibitor ([68Ga]Ga-FAPI-04) PET/MRI, [18F]FDG PET/CT, and contrast-enhanced MRI were performed before treatment initiation and before surgery in each patient. PET and MRI features and the size and number of lesions were also collected from each scan. Each parameter's sensitivity, specificity, and diagnostic cutoff were derived via receiver-operating-characteristic curve analysis. Results: Twenty eligible patients (13 men, 7 women; mean age, 60.2 y) were enrolled and completed the entire trial, and all patients had proficient mismatch repair or microsatellite-stable LARC. A postoperative pCR was achieved in 9 patients (45.0%). In the visual evaluation, both [68Ga]Ga-FAPI-04 PET/MRI and [18F]FDG PET/CT were limited to forecasting pCR. Contrast-enhanced MRI had a low sensitivity of 55.56% to predict pCR. In the quantitative evaluation, [68Ga]Ga-FAPI-04 change in SULpeak percentage, where SULpeak is SUVpeak standardized by lean body mass, had the largest area under the curve (0.929) with high specificity (sensitivity, 77.78%; specificity, 100.0%; cutoff, 63.92%). Conclusion: [68Ga]Ga-FAPI-04 PET/MRI is a promising imaging modality for predicting pCR after SCRT combined with immunochemotherapy. The SULpeak decrease exceeding 63.92% may provide valuable guidance in selecting patients who can forgo surgery after neoadjuvant therapy.

Validation of large language models for detecting pathologic complete response in breast cancer using population-based pathology reports.

AIMS: The primary goal of this study is to evaluate the capabilities of Large Language Models (LLMs) in understanding and processing complex medical documentation. We chose to focus on the identification of pathologic complete response (pCR) in narrative pathology reports. This approach aims to contribute to the advancement of comprehensive reporting, health research, and public health surveillance, thereby enhancing patient care and breast cancer management strategies. METHODS: The study utilized two analytical pipelines, developed with open-source LLMs within the healthcare system's computing environment. First, we extracted embeddings from pathology reports using 15 different transformer-based models and then employed logistic regression on these embeddings to classify the presence or absence of pCR. Secondly, we fine-tuned the Generative Pre-trained Transformer-2 (GPT-2) model by attaching a simple feed-forward neural network (FFNN) layer to improve the detection performance of pCR from pathology reports. RESULTS: In a cohort of 351 female breast cancer patients who underwent neoadjuvant chemotherapy (NAC) and subsequent surgery between 2010 and 2017 in Calgary, the optimized method displayed a sensitivity of 95.3% (95%CI: 84.0-100.0%), a positive predictive value of 90.9% (95%CI: 76.5-100.0%), and an F1 score of 93.0% (95%CI: 83.7-100.0%). The results, achieved through diverse LLM integration, surpassed traditional machine learning models, underscoring the potential of LLMs in clinical pathology information extraction. CONCLUSIONS: The study successfully demonstrates the efficacy of LLMs in interpreting and processing digital pathology data, particularly for determining pCR in breast cancer patients post-NAC. The superior performance of LLM-based pipelines over traditional models highlights their significant potential in extracting and analyzing key clinical data from narrative reports. While promising, these findings highlight the need for future external validation to confirm the reliability and broader applicability of these methods.

Comparison of radiomics-based machine-learning classifiers for the pretreatment prediction of pathologic complete response to neoadjuvant therapy in breast cancer.

Background: Machine learning classifiers are increasingly used to create predictive models for pathological complete response (pCR) in breast cancer after neoadjuvant therapy (NAT). Few studies have compared the effectiveness of different ML classifiers. This study evaluated radiomics models based on pre- and post-contrast first-phase T1 weighted images (T1WI) in predicting breast cancer pCR after NAT and compared the performance of ML classifiers. Methods: This retrospective study enrolled 281 patients undergoing NAT from the Duke-Breast-Cancer-MRI dataset. Radiomic features were extracted from pre- and post-contrast first-phase T1WI images. The Synthetic Minority Oversampling Technique (SMOTE) was applied, then the dataset was randomly divided into training and validation groups (7:3). The radiomics model was built using selected optimal features. Support vector machine (SVM), random forest (RF), decision tree (DT), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were classifiers. Receiver operating characteristic curves were used to assess predictive performance. Results: LightGBM performed best in predicting pCR [area under the curve (AUC): 0.823, 95% confidence interval (CI) [0.743-0.902], accuracy 74.0%, sensitivity 85.0%, specificity 67.2%]. During subgroup analysis, RF was most effective in pCR prediction in luminal breast cancers (AUC: 0.914, 95% CI [0.847-0.981], accuracy 87.0%, sensitivity 85.2%, specificity 88.1%). In triple-negative breast cancers, LightGBM performed best (AUC: 0.836, 95% CI [0.708-0.965], accuracy 78.6%, sensitivity 68.2%, specificity 90.0%). Conclusion: The LightGBM-based radiomics model performed best in predicting pCR in patients with breast cancer. RF and LightGBM showed promising results for luminal and triple-negative breast cancers, respectively.

Autologous transplant vs. CAR-T therapy in patients with DLBCL treated while in complete remission.

In patients with relapsed DLBCL in complete remission (CR), autologous hematopoietic cell transplantation (auto-HCT) and CAR-T therapy are both effective, but it is unknown which modality provides superior outcomes. We compared the efficacy of auto-HCT vs. CAR-T in patients with DLBCL in a CR. A retrospective observational study comparing auto-HCT (2015-2021) vs. CAR-T (2018-2021) using the Center for International Blood & Marrow Transplant Research registry. Median follow-up was 49.7 months for the auto-HCT and 24.7 months for the CAR-T cohort. Patients ages 18 and 75 with a diagnosis of DLBCL were included if they received auto-HCT (n = 281) or commercial CAR-T (n = 79) while in a CR. Patients undergoing auto-HCT with only one prior therapy line and CAR-T patients with a previous history of auto-HCT treatment were excluded. Endpoints included Progression-free survival (PFS), relapse rate, non-relapse mortality (NRM) and overall survival (OS). In univariate analysis, treatment with auto-HCT was associated with a higher rate of 2-year PFS (66.2% vs. 47.8%; p < 0.001), a lower 2-year cumulative incidence of relapse (27.8% vs. 48% ; p < 0.001), and a superior 2-year OS (78.9% vs. 65.6%; p = 0.037). In patients with early (within 12 months) treatment failure, auto-HCT was associated with a superior 2-year PFS (70.9% vs. 48.3% ; p < 0.001), lower 2-year cumulative incidence of relapse (22.8% vs. 45.9% ; p < 0.001) and trend for higher 2-year OS (82.4% vs. 66.1% ; p = 0.076). In the multivariable analysis, treatment with auto-HCT was associated with a superior PFS (hazard ratio 1.83; p = 0.0011) and lower incidence of relapse (hazard ratio 2.18; p < 0.0001) compared to CAR-T. In patients with relapsed LBCL who achieve a CR, treatment with auto-HCT is associated with improved clinical outcomes compared to CAR-T. These data support the consideration of auto-HCT in select patients with LBCL achieving a CR in the relapsed setting.

Initial MRI findings predictive of a pathological complete response to neoadjuvant treatments in HER2-positive breast cancers.

PURPOSE: This study aimed to determine if initial MRI findings could predict a pathological complete response (pCR) following neoadjuvant systemic therapy (NST) in HER2-positive breast cancers. METHODS: The study retrospectively included 111 patients (Center 1, training set) and 71 patients (Center 2, validation set) with HER2-positive cancer who underwent NST. Initial clinicopathological data and MRI findings were recorded. Continuous variables were analyzed using the Mann-Whitney and Student's t-tests, while categorical variables were analyzed using the χ2 or Fisher's exact test. Univariate analysis was conducted to determine the associations between these variables and pathological complete response (pCR), defined as the absence of invasive malignant cells in the breast and lymph nodes. Interobserver reproducibility was assessed for associated non-mass enhancement (NME) parameter by analyzing 50 MR studies (intraclass correlation coefficient). RESULTS: pCR was achieved in 67 patients, 51 (46 %) from Center 1 and 16 (23%) from Center 2 (p = 0.003), with significant differences between Centers 1 and 2 in tumor-infiltrating lymphocyte levels and lymphovascular invasion (p < 0.001). The initial presence of suspicious associated NME was the only significant parameter predictive of pCR (p < 0.001 for Center 1 and 0.04 for Center 2). The inter-observer reproducibility for this MRI feature was good, with an intraclass correlation coefficient of 0.872 (95 % CI: 0.73-1.00). CONCLUSION: The presence of suspicious associated NME in HER2-positive cancers on the initial MRI study was predictive of achieving pCR after NST. This significant preliminary finding warrants confirmation through prospective multicenter studies.

Correlative Analysis of ATM, RB1, ERCC2, and FANCC Mutations and Pathologic Complete Response After Neoadjuvant Chemotherapy in Patients with Muscle-invasive Bladder Cancer: Results from the SWOG S1314 Trial.

We previously reported that tumors harboring any one of four gene mutations (ATM, RB1, FANCC, or ERCC2) were likely to respond to neoadjuvant cisplatin-based chemotherapy (NAC), resulting in cancer-free surgical specimens at the time of cystectomy (pT0). Here, we report our validation of this finding. Using the CARIS 592 Gene Panel (Caris Life Sciences, Phoenix, AZ, USA), we analyzed 105 pre-NAC tumor specimens from a large multicenter trial (S1314) of either neoadjuvant gemcitabine and cisplatin (GC), or dose-dense methotrexate, vinblastine, Adriamycin, and cisplatin (DDMVAC). We found that a mutation in any one of these four genes predicted for pT0 at surgery (odds ratio = 5.36; 95% confidence interval [CI] 2.05, 14.02; two-sided p = 0.0006). The biomarker was better at predicting the presence of disease (negative predictive value for pT0 86%; 95% CI 73%, 94%) than the absence of disease (positive predictive value for pT0 48%; 95% CI 35%, 62%). There was no evidence of an interaction between the treatment arm (DDMVAC vs GC) and the genetic variant in terms of pT0. When combined with clinical assessment, these findings help inform patient selection for bladder preservation after cisplatin-based chemotherapy.