Preoperative Tumor Histology Research Articles

Development and Validation of a Deep Learning Radiomics Model Predicting Lymph Node Status in Operable Cervical Cancer.

Aim: To develop and validate a deep learning radiomics model, which could predict the lymph node metastases preoperatively in cervical cancer patients.Patients and methods: We included a cohort of 226 pathological proven operable cervical cancer patients in two academic medical institutions from December 2014 to November 2017. Then this dataset was split into training set (n = 176) and independent testing set (n = 50) randomly. Five radiomic features were selected and a radiomic signature was established. We then combined these five radiomic features with the preoperative tumor histology and grade of these patients together. Baseline logistic regression model (LRM) and support vector machine model (SVM) were established for the comparison. We then explored the performance of a deep neural network (DNN), which is a popular deep learning model nowadays. Finally, performance of this DNN was validated in another independent test set including 50 cases of operable cervical cancer patients.Results: One thousand forty-five radiomic features were extracted for each patient. Twenty-eight features were found to be significantly correlated with the lymph node status in these patients (P < 0.05). Five radiomic features were further selected for further study due to their higher predictive powers. Baseline LRM incorporating these five radiomic and two clinicopathological features was established, which had an area under receiver operating characteristic curve (ROC) of 0.7372 and an accuracy of 89.20%. The established DNN model had four neural layers, in which layer there were 10 neurons. Adagrad optimizer and 1,500 iterations were used in training. The trained DNN had an area under curve (AUC) of 0.99 and an accuracy of 97.16% in the internal validation. To exclude the overfitting, independent external validation was also performed. AUC and accuracy in test set could still retain 0.90 and 92.00% respectively.Conclusion: This study used deep learning method to provide a comprehensive predictive model using preoperative CT images, tumor histology, and grade in cervical cancer patients. This model showed an acceptable accuracy in the prediction of lymph node status in cervical cancer. Our model may help identifying those patients who could benefit a lot from radiation therapy rather than primary hysterectomy surgery if this model could resist strict testing of future randomized controlled trials (RCTs).

Multidisciplinary team meeting and EUSOMA quality indicators in breast cancer care: A French regional multicenter study

IntroductionWe evaluate breast cancer (BC) pathway at a regional level including public, private and university institutions. We assessed the quality of multidisciplinary team meetings (MTM) and compliance with a panel of European high-quality indicators (EUSOMA QIs). MethodsWe conducted a retrospective multicenter (n = 20) study in the largest health care region in France. Between January and April 2015, we included all patients discussed at an MTM after a diagnosis of BC (n = 619). We analyzed quality of MTM by assessing the quorum, the reliability of data transcription and the exhaustivity of pre-therapeutic MTM. We then analyzed the compliance with a selected panel of 16 EUSOMA QIs. ResultsDuring MTM discussion, data were more than 95% consistent with medical records for 9/11 items. Pre-operative tumor histology (90.6%) and post-operative resection margins (84.3%) were the least concordant between medical records and MTM. Minimum standards as defined by EUSOMA were reached for 11/16 QIs, but not reached for pathology reports in non-invasive BC (78.2%), proportion of exclusive sentinel lymph node biopsies in patients with clinically negative axilla (85.2%), performing adjuvant chemotherapy (76.6%), and proportion of patients discussed in pre-therapeutic and post-operative MTM (63.5%). ConclusionsIn this multicentric study evaluating the quality of BC care with a representative sample of institutions, compliance with EUSOMA indicators was satisfactory for all type of institutions. However, too few patients were discussed in pre-therapeutic MTM (especially in non-university hospitals 43.7% [39.4–48.1]) versus 88.7% for others [82.2–95.1]) and data transcription was likely responsible for up to 15% of discordance.