Volumetric imaging parameters are significant for predicting the pathological complete response of preoperative concurrent chemoradiotherapy in local advanced rectal cancer

Assessing the predictive value of clinical factors to pathological complete response for locally advanced rectal cancer: An analysis of 124 patients

Purpose

To investigate the clinical factors affecting pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC).

Methods

Clinical data of 124 LARC patients treated with nCRT and surgery in the fourth Hospital of Hebei Medical University from 2014 to 2019 were retrospectively analyzed. In this study, univariate analysis and logistic dichotomous multivariate regression analysis were used to study the clinical factors affecting pCR, and the receiver operator characteristic curve (ROC) analysis was used to further verify the accuracy of partial indexes in predicting pCR.

Results

Of the 124 enrolled patients, 19 patients (15.32%) achieved pCR. Univariate analysis showed that the number of cycles of consolidation chemotherapy, serum carcino-embryonic antigen (CEA) level before treatment, MRI longitudinal length of tumor, and extramural vascular invasion (EMVI) were statistically correlated with pCR. ROC analysis of the longitudinal length of tumor measured by MRI showed that the area under the curve (AUC) value, sensitivity and specificity were 0.735, 89.47% and 48.57% respectively, and the optimal cut-off value was 5.5cm. The ROC analysis showed that the AUC value, sensitivity and specificity of pCR prediction using CEA were 0.741, 63.16% and 90.48%, respectively, and the optimal cut-off value was 3.1ng/ml. Multivariate results showed that the number of cycles of consolidation chemotherapy, serum CEA level before treatment, and EMVI were independent predictors of pCR.

Conclusion

The number of cycles of consolidation chemotherapy, serum CEA level before treatment, and EMVI may be important determinants of LARC patients to reach pCR after nCRT.

Testing the Ability of Convolutional Neural Networks to Learn Radiomic Features

BACKGROUND AND OBJECTIVE

Radiomics and deep learning have emerged as two distinct approaches to medical image analysis. However, their relative expressive power remains largely unknown. Theoretically, hand-crafted radiomic features represent a mere subset of features that neural networks can approximate, thus making deep learning a more powerful approach. On the other hand, automated learning of hand-crafted features may require a prohibitively large number of training samples. Here we directly test the ability of convolutional neural networks (CNNs) to learn and predict the intensity, shape, and texture properties of tumors as defined by standardized radiomic features.

METHODS

Conventional 2D and 3D CNN architectures with an increasing number of convolutional layers were trained to predict the values of 16 standardized radiomic features from real and synthetic PET images of tumors, and tested. In addition, several ImageNet-pretrained advanced networks were tested. A total of 4000 images were used for training, 500 for validation, and 500 for testing.

RESULTS

Features quantifying size and intensity were predicted with high accuracy, while shape irregularity and heterogeneity features had very high prediction errors and generalized poorly. For example, mean normalized prediction error of tumor diameter with a 5-layer CNN was 4.23 ± 0.25, while the error for tumor sphericity was 15.64 ± 0.93. We additionally found that learning shape features required an order of magnitude more samples compared to intensity and size features.

CONCLUSIONS

Our findings imply that CNNs trained to perform various image-based clinical tasks may generally under-utilize the shape and texture information that is more easily captured by radiomics. We speculate that to improve the CNN performance, shape and texture features can be computed explicitly and added as auxiliary variables to the networks, or supplied as synthetic inputs.

Analysis of influencing factors of no/low response to preoperative concurrent chemoradiotherapy in locally advanced rectal cancer

The aim of this study is to investigate the influencing factors associated with no/low response to preoperative concurrent chemoradiotherapy (CCRT) for locally advanced rectal cancer (LARC) patients. A total of 79 patients were included in this prospective study. Fifteen factors that might affect the resistance to CCRT were included in this logistic regression analysis, these factors include the general clinical data of patients, the expression status of tumor stem cell marker CD44v6 and the volumetric imaging parameters of primary tumor lesions. We found that the no/low response status to preoperative CCRT was positively correlated with the real tumor volume (RTV), the total surface area of tumor (TSA), and CD44v6 expression, whereas negatively correlated with the tumor compactness (TC). According to the results of logistic regression analysis, two formulas that could predict whether or not no/low response to preoperative CCRT were established. The Area Under Curve (AUC) of the two formulas and those significant measurement data (RTV, TC, TSA) were 0.900, 0.858, 0.771, 0.754, 0.859, the sensitivity were 95.8%, 79.17%, 62.50%, 95.83%, 62.5%, the specificity were 70.9%, 74.55%, 83.64%,47.27%, 96.36%, the positive predictive values were 58.96%, 57.58%, 62.51%,44.23%, 88.23%, the negative predictive values were 97.48%, 89.13%, 83.64%, 96.29%, and 85.48%, respectively.