Background: The aim of this study was to assess whether multiparametric 18F-FDG PET/MRI-based radiomics analysis is able to predict pathological complete response in breast cancer patients and hence potentially enhance pretherapeutic patient stratification. Methods: A total of 73 female patients (mean age 49 years; range 27–77 years) with newly diagnosed, therapy-naive breast cancer underwent simultaneous 18F-FDG PET/MRI and were included in this retrospective study. All PET/MRI datasets were imported to dedicated software (ITK-SNAP v. 3.6.0) for lesion annotation using a semi-automated method. Pretreatment biopsy specimens were used to determine tumor histology, tumor and nuclear grades, and immunohistochemical status. Histopathological results from surgical tumor specimens were used as the reference standard to distinguish between complete pathological response (pCR) and noncomplete pathological response. An elastic net was employed to select the most important radiomic features prior to model development. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were calculated for each model. Results: The best results in terms of AUCs and NPV for predicting complete pathological response in the entire cohort were obtained by the combination of all MR sequences and PET (0.8 and 79.5%, respectively), and no significant differences from the other models were observed. In further subgroup analyses, combining all MR and PET data, the best AUC (0.94) for predicting complete pathologic response was obtained in the HR+/HER2− group. No difference between results with/without the inclusion of PET characteristics was observed in the TN/HER2+ group, each leading to an AUC of 0.92 for all MR and all MR + PET datasets. Conclusion: 18F-FDG PET/MRI enables comprehensive high-quality radiomics analysis for the prediction of pCR in breast cancer patients, especially in those with HR+/HER2− receptor status.
Purpose To compare CT, MRI, and [18F]-fluorodeoxyglucose positron emission tomography ([18F]-FDG PET/MRI) for nodal status, regarding quantity and location of metastatic locoregional lymph nodes in patients with newly diagnosed breast cancer. Materials and methods One hundred eighty-two patients (mean age 52.7 ± 11.9 years) were included in this prospective double-center study. Patients underwent dedicated contrast-enhanced chest/abdomen/pelvis computed tomography (CT) and whole-body ([18F]-FDG PET/) magnet resonance imaging (MRI). Thoracal datasets were evaluated separately regarding quantity, lymph node station (axillary levels I–III, supraclavicular, internal mammary chain), and lesion character (benign vs. malign). Histopathology served as reference standard for patient-based analysis. Patient-based and lesion-based analyses were compared by a McNemar test. Sensitivity, specificity, positive and negative predictive values, and accuracy were assessed for all three imaging modalities. Results On a patient-based analysis, PET/MRI correctly detected significantly more nodal positive patients than MRI (p < 0.0001) and CT (p < 0.0001). No statistically significant difference was seen between CT and MRI. PET/MRI detected 193 lesions in 75 patients (41.2%), while MRI detected 123 lesions in 56 patients (30.8%) and CT detected 104 lesions in 50 patients, respectively. Differences were statistically significant on a lesion-based analysis (PET/MRI vs. MRI, p < 0.0001; PET/MRI vs. CT, p < 0.0001; MRI vs. CT, p = 0.015). Subgroup analysis for different lymph node stations showed that PET/MRI detected significantly more lymph node metastases than MRI and CT in each location (axillary levels I–III, supraclavicular, mammary internal chain). MRI was superior to CT only in axillary level I (p = 0.0291). Conclusion [18F]-FDG PET/MRI outperforms CT or MRI in detecting nodal involvement on a patient-based analysis and on a lesion-based analysis. Furthermore, PET/MRI was superior to CT or MRI in detecting lymph node metastases in all lymph node stations. Of all the tested imaging modalities, PET/MRI showed the highest sensitivity, whereas CT showed the lowest sensitivity, but was most specific.
Purpose The aim of this study was to correlate prognostically relevant immunohistochemical parameters of breast cancer with simultaneously acquired SUVs and apparent diffusion coefficient (ADC) values derived from hybrid breast PET/MRI. Patients and Methods Fifty-six women with newly diagnosed, therapy-naive, histologically proven breast cancer (mean age, 54.1 ± 12.0 years) underwent dedicated prone 18F-FDG breast PET/MRI. Diffusion-weighted imaging (b-values: 0, 500, 1000 s/mm2) was performed simultaneously with the PET acquisition. A region of interest encompassing the entire primary tumor on each patient’s PET/MRI scan was used to determine the glucose metabolism represented by maximum and mean SUV as well as into corresponding ADC maps to assess tumor cellularity represented by mean and minimum ADC values. Histopathological tumor grading and prognostically relevant immunohistochemical markers, that is, Ki67, progesterone receptor, estrogen receptor, and human epidermal growth factor receptor 2 (HER2), were assessed. Pearson correlation coefficients were calculated to compare SUV and ADC values as well as the immunohistochemically markers and molecular subtype. For the comparison with the tumor grading, a Wilcoxon test was used. Results A significant inverse correlation between SUV and ADC values derived from breast PET/MRI (r = −0.49 for SUVmean vs ADCmean; r = −0.43 for SUVmax vs ADCmin; both P’s < 0.001) was found. Tumor grading and Ki67 both showed a positive correlation with SUVmean from breast PET/MRI (r = 0.37 and r = 0.32, P < 0.01). For immunohistochemical markers, HER2 showed an inverse correlation with ADC values from breast PET/MRI (r = −0.35, P < 0.01). Molecular subtypes significantly correlate with SUVmax and SUVmean (r = 0.52 and r = 0.42, both P’s < 0.05). In addition, estrogen receptor expression showed an inverse correlation with SUVmax and SUVmean from breast PET/MRI (r = −0.45 and r = −0.42, P < 0.001). Conclusions The present data show a correlation between increased glucose metabolism, cellularity, tumor grading, estrogen and HER2 expression, as well as molecular subtype of breast cancer primaries. Hence, simultaneous 18F-FDG PET and diffusion-weighted imaging from hybrid breast PET/MRI may serve as a predictive tool for identifying high-risk breast cancer patients in initial staging and guide-targeted therapy.
Background To assess the diagnostic value of an additional late-phase PET/CT scan after urination as part of 68 Ga-PSMA-11 PET/CT for the restaging of patients with biochemically recurrent prostate cancer (BCR). Methods This retrospective trial included patients with BCR following radical prostatectomy, who underwent standard whole-body early-phase PET/CT performed 105 ± 45 min and an additional late-phase PET/CT performed 159 ± 13 min after injection of 68 Ga-PSMA-11. Late-phase PET/CT covered a body volume from below the liver to the upper thighs and was conducted after patients had used the bathroom to empty their urinary bladder. Early- and late-phase images were evaluated regarding lesion count, type, localisation, and SUVmax. Reference standard was histopathology and/or follow-up imaging. Results Whole-body early-phase PET/CT detected 93 prostate cancer lesions in 33 patients. Late-phase PET/CT detected two additional lesions in two patients, both local recurrences. In total, there were 57 nodal, 28 bone, and 3 lung metastases, and 7 local recurrences. Between early- and late-phase PET/CT, lymph node metastases showed a significant increase of SUVmax from 14.5 ± 11.6 to 21.5 ± 17.6 (p = 0.00007), translating to a factor of + 1.6. Benign lymph nodes in the respective regions showed a significantly lower increase of SUVmax of 1.4 ± 0.5 to 1.7 ± 0.5 (p = 0.0014, factor of + 1.2). Local recurrences and bone metastases had a SUVmax on late-phase PET/CT that was + 1.7 and + 1.1 times higher than the SUVmax on early-phase PET/CT, respectively. Conclusion In patients with BCR following radical prostatectomy, an additional abdomino-pelvic late-phase 68 Ga-PSMA-11 PET/CT scan performed after emptying the urinary bladder may help to detect local recurrences missed on standard whole-body 68 Ga-PSMA-11 PET/CT. Lymph node metastases show a higher SUVmax and a stronger increase of SUVmax than benign lymph nodes on late-phase PET/CT, hence, biphasic 68 Ga-PSMA-11 PET/CT might help to distinguish between malignant and benign nodes. Bone metastases, and especially local recurrences, also demonstrate a metabolic increase over time.
Pancreatic cancer is a fatal malignancy with poor prognosis and limited treatment options. Early detection in primary and secondary locations is critical, but fraught with challenges. While digital pathology can assist with the classification of histopathological images, the training of such networks always relies on a ground truth, which is frequently compromised as tissue sections contain several types of tissue entities. Here we show that pancreatic cancer can be detected on hematoxylin and eosin (H&E) sections by convolutional neural networks using deep transfer learning. To improve the ground truth, we describe a preprocessing data clean-up process using two communicators that were generated through existing and new datasets. Specifically, the communicators moved image tiles containing adipose tissue and background to a new data class. Hence, the original dataset exhibited improved labeling and, consequently, a higher ground truth accuracy. Deep transfer learning of a ResNet18 network resulted in a five-class accuracy of about 94% on test data images. The network was validated with independent tissue sections composed of healthy pancreatic tissue, pancreatic ductal adenocarcinoma, and pancreatic cancer lymph node metastases. The screening of different models and hyperparameter fine tuning were performed to optimize the performance with the independent tissue sections. Taken together, we introduce a step of data preprocessing via communicators as a means of improving the ground truth during deep transfer learning and hyperparameter tuning to identify pancreatic ductal adenocarcinoma primary tumors and metastases in histological tissue sections.
Background: Survival after surgery for pancreatic ductal adenocarcinoma (PDAC) remains poor. Thus, novel therapeutic concepts focus on the development of targeted therapies. In this context, inhibitor of apoptosis protein (IAP) survivin is regarded as a promising oncotherapeutic target. However, its expression and prognostic value in different tumour compartments of PDAC have not been studied. Methods: Immunohistochemical analysis of survivin in different PDAC tumour compartments from 236 consecutive patients was correlated with clinicopathological variables and survival. Results: In comparison to healthy pancreatic tissue high nuclear (p < 0.001) and high cytoplasmic (p < 0.01) survivin expression became evident in the tumour centre, along the invasion front and in lymph node metastases. Cytoplasmic overexpression of survivin in tumour centres was related to the presence of distant metastasis (p = 0.016) and UICC III/IV stages (p = 0.009), while high cytoplasmic expression at the invasion front grouped with venous infiltration (p = 0.022). Increased nuclear survivin along the invasion front correlated with perineural invasion (p = 0.035). High nuclear survivin in tumour centres represented an independent prognostic factor for overall survival of pancreatic tail carcinomas (HR 13.5 95%CI (1.4–129.7)) and correlated with a limited disease-free survival in PDAC (HR 1.80 95%CI (1.04–3.12)). Conclusion: Survivin is associated with advanced disease stages and poor prognosis. Therefore, survivin will help to identify patients with aggressive tumour phenotypes that could benefit from the inclusion in clinical trials incorporating survivin inhibitors in PDAC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.