Texture analysis of apparent diffusion coefficient maps: can it identify nonresponse to neoadjuvant chemotherapy for additional radiation therapy in rectal cancer patients?

Background: Neoadjuvant chemotherapy (NCT) alone can achieve comparable treatment outcomes to chemoradiotherapy in locally advanced rectal cancer (LARC) patients. This study aimed to investigate the value of texture analysis (TA) in apparent diffusion coefficient (ADC) maps for identifying non-responders to NCT. Methods: This retrospective study included patients with LARC after NCT, and they were categorized into nonresponse group (pTRG 3) and response group (pTRG 0-2) based on pathological tumor regression grade (pTRG). Predictive texture features were extracted from pre- and post-treatment ADC maps to construct a TA model using RandomForest. The ADC model was developed by manually measuring pre- and post-treatment ADC values and calculating their changes. Simultaneously, subjective evaluations based on magnetic resonance imaging assessment of TRG were performed by two experienced radiologists. Model performance was compared using the area under the curve (AUC) and DeLong test. Results: A total of 299 patients from two centers were divided into three cohorts: the primary cohort (center A; n = 194, with 36 non-responders and 158 responders), the internal validation cohort (center A; n = 49, with 9 non-responders) and external validation cohort (center B; n = 56, with 33 non-responders). The TA model was constructed by post_mean, mean_change, post_skewness, post_entropy, and entropy_change, which outperformed both the ADC model and subjective evaluations with an impressive AUC of 0.997 (95% confidence interval [CI], 0.975-1.000) in the primary cohort. Robust performances were observed in internal and external validation cohorts, with AUCs of 0.919 (95% CI, 0.805-0.978) and 0.938 (95% CI, 0.840-0.985), respectively. Conclusions: The TA model has the potential to serve as an imaging biomarker for identifying nonresponse to NCT in LARC patients, providing a valuable reference for these patients considering additional radiation therapy.

A transformer-based multi-task deep learning model for simultaneous infiltrated brain area identification and segmentation of gliomas.

BACKGROUND: The anatomical infiltrated brain area and the boundaries of gliomas have a significant impact on clinical decision making and available treatment options. Identifying glioma-infiltrated brain areas and delineating the tumor manually is a laborious and time-intensive process. Previous deep learning-based studies have mainly been focused on automatic tumor segmentation or predicting genetic/histological features. However, few studies have specifically addressed the identification of infiltrated brain areas. To bridge this gap, we aim to develop a model that can simultaneously identify infiltrated brain areas and perform accurate segmentation of gliomas. METHODS: We have developed a transformer-based multi-task deep learning model that can perform two tasks simultaneously: identifying infiltrated brain areas segmentation of gliomas. The multi-task model leverages shaped location and boundary information to enhance the performance of both tasks. Our retrospective study involved 354 glioma patients (grades II-IV) with single or multiple brain area infiltrations, which were divided into training (N = 270), validation (N = 30), and independent test (N = 54) sets. We evaluated the predictive performance using the area under the receiver operating characteristic curve (AUC) and Dice scores. RESULTS: Our multi-task model achieved impressive results in the independent test set, with an AUC of 94.95% (95% CI, 91.78-97.58), a sensitivity of 87.67%, a specificity of 87.31%, and accuracy of 87.41%. Specifically, for grade II-IV glioma, the model achieved AUCs of 95.25% (95% CI, 91.09-98.23, 84.38% sensitivity, 89.04% specificity, 87.62% accuracy), 98.26% (95% CI, 95.22-100, 93.75% sensitivity, 98.15% specificity, 97.14% accuracy), and 93.83% (95%CI, 86.57-99.12, 92.00% sensitivity, 85.71% specificity, 87.37% accuracy) respectively for the identification of infiltrated brain areas. Moreover, our model achieved a mean Dice score of 87.60% for the whole tumor segmentation. CONCLUSIONS: Experimental results show that our multi-task model achieved superior performance and outperformed the state-of-the-art methods. The impressive performance demonstrates the potential of our work as an innovative solution for identifying tumor-infiltrated brain areas and suggests that it can be a practical tool for supporting clinical decision making.

Deep learning-based automatic segmentation of meningioma from multiparametric MRI for preoperative meningioma differentiation using radiomic features: a multicentre study.

OBJECTIVES: Develop and evaluate a deep learning-based automatic meningioma segmentation method for preoperative meningioma differentiation using radiomic features. METHODS: A retrospective multicentre inclusion of MR examinations (T1/T2-weighted and contrast-enhanced T1-weighted imaging) was conducted. Data from centre 1 were allocated to training (n = 307, age = 50.94 ± 11.51) and internal testing (n = 238, age = 50.70 ± 12.72) cohorts, and data from centre 2 external testing cohort (n = 64, age = 48.45 ± 13.59). A modified attention U-Net was trained for meningioma segmentation. Segmentation accuracy was evaluated by five quantitative metrics. The agreement between radiomic features from manual and automatic segmentations was assessed using intra class correlation coefficient (ICC). After univariate and minimum-redundancy-maximum-relevance feature selection, L1-regularized logistic regression models for differentiating between low-grade (I) and high-grade (II and III) meningiomas were separately constructed using manual and automatic segmentations; their performances were evaluated using ROC analysis. RESULTS: Dice of meningioma segmentation for the internal testing cohort were 0.94 ± 0.04 and 0.91 ± 0.05 for tumour volumes in contrast-enhanced T1-weighted and T2-weighted images, respectively; those for the external testing cohort were 0.90 ± 0.07 and 0.88 ± 0.07. Features extracted using manual and automatic segmentations agreed well, for both the internal (ICC = 0.94, interquartile range: 0.88-0.97) and external (ICC = 0.90, interquartile range: 0.78-70.96) testing cohorts. AUC of radiomic model with automatic segmentation was comparable with that of the model with manual segmentation for both the internal (0.95 vs. 0.93, p = 0.176) and external (0.88 vs. 0.91, p = 0.419) testing cohorts. CONCLUSIONS: The developed deep learning-based segmentation method enables automatic and accurate extraction of meningioma from multiparametric MR images and can help deploy radiomics for preoperative meningioma differentiation in clinical practice. KEY POINTS: • A deep learning-based method was developed for automatic segmentation of meningioma from multiparametric MR images. • The automatic segmentation method enabled accurate extraction of meningiomas and yielded radiomic features that were highly consistent with those that were obtained using manual segmentation. • High-grade meningiomas were preoperatively differentiated from low-grade meningiomas using a radiomic model constructed on features from automatic segmentation.

Predicting treatment response from longitudinal images using multi-task deep learning.

Radiographic imaging is routinely used to evaluate treatment response in solid tumors. Current imaging response metrics do not reliably predict the underlying biological response. Here, we present a multi-task deep learning approach that allows simultaneous tumor segmentation and response prediction. We design two Siamese subnetworks that are joined at multiple layers, which enables integration of multi-scale feature representations and in-depth comparison of pre-treatment and post-treatment images. The network is trained using 2568 magnetic resonance imaging scans of 321 rectal cancer patients for predicting pathologic complete response after neoadjuvant chemoradiotherapy. In multi-institution validation, the imaging-based model achieves AUC of 0.95 (95% confidence interval: 0.91-0.98) and 0.92 (0.87-0.96) in two independent cohorts of 160 and 141 patients, respectively. When combined with blood-based tumor markers, the integrated model further improves prediction accuracy with AUC 0.97 (0.93-0.99). Our approach to capturing dynamic information in longitudinal images may be broadly used for screening, treatment response evaluation, disease monitoring, and surveillance.

Radiomics-Based Preoperative Prediction of Lymph Node Status Following Neoadjuvant Therapy in Locally Advanced Rectal Cancer.

Background and Purpose: Lymph node status is a key factor for the recommendation of organ preservation for patients with locally advanced rectal cancer (LARC) following neoadjuvant therapy but generally confirmed post-operation. This study aimed to preoperatively predict the lymph node status following neoadjuvant therapy using multiparametric magnetic resonance imaging (MRI)-based radiomic signature. Materials and Methods: A total of 391 patients with LARC who underwent neoadjuvant therapy and TME were included, of which 261 and 130 patients were allocated to the primary cohort and the validation cohort, respectively. The tumor area, as determined by preoperative MRI, underwent radiomics analysis to build a radiomic signature related to lymph node status. Two radiologists reassessed the lymph node status on MRI. The radiomic signature and restaging results were included in a multivariate analysis to build a combined model for predicting the lymph node status. Stratified analyses were performed to test the predictive ability of the combined model in patients with post-therapeutic MRI T1-2 or T3-4 tumors, respectively. Results: The combined model was built in the primary cohort, and predicted lymph node metastasis (LNM+) with an area under the curve of 0.818 and a negative predictive value (NPV) of 93.7% were considered in the validation cohort. Stratified analyses indicated that the combined model could predict LNM+ with a NPV of 100 and 87.8% in the post-therapeutic MRI T1-2 and T3-4 subgroups, respectively. Conclusion: This study reveals the potential of radiomics as a predictor of lymph node status for patients with LARC following neoadjuvant therapy, especially for those with post-therapeutic MRI T1-2 tumors.

Radiomics-Based Pretherapeutic Prediction of Non-response to Neoadjuvant Therapy in Locally Advanced Rectal Cancer.

OBJECTIVE: The aim of this study was to investigate whether pretherapeutic, multiparametric magnetic resonance imaging (MRI) radiomic features can be used for predicting non-response to neoadjuvant therapy in patients with locally advanced rectal cancer (LARC). METHODS: We retrospectively enrolled 425 patients with LARC [allocated in a 3:1 ratio to a primary (n = 318) or validation (n = 107) cohort] who received neoadjuvant therapy before surgery. All patients underwent T1-weighted, T2-weighted, diffusion-weighted, and contrast-enhanced T1-weighted MRI scans before receiving neoadjuvant therapy. We extracted 2424 radiomic features from the pretherapeutic, multiparametric MR images of each patient. The Wilcoxon rank-sum test, Spearman correlation analysis, and least absolute shrinkage and selection operator regression were successively performed for feature selection, whereupon a multiparametric MRI-based radiomic model was established by means of multivariate logistic regression analysis. This feature selection and multivariate logistic regression analysis was also performed on all single-modality MRI data to establish four single-modality radiomic models. The performance of the five radiomic models was evaluated by receiver operating characteristic (ROC) curve analysis in both cohorts. RESULTS: The multiparametric, MRI-based radiomic model based on 16 features showed good predictive performance in both the primary (p < 0.01) and validation (p < 0.05) cohorts, and performed better than all single-modality models. The area under the ROC curve of this multiparametric MRI-based radiomic model achieved a score of 0.822 (95% CI 0.752-0.891). CONCLUSIONS: We demonstrated that pretherapeutic, multiparametric MRI radiomic features have potential in predicting non-response to neoadjuvant therapy in patients with LARC.

Role of microRNA221 in regulating normal mammary epithelial hierarchy and breast cancer stem-like cells.

Increasing evidence suggests that lineage specific subpopulations and stem-like cells exist in normal and malignant breast tissues. Epigenetic mechanisms maintaining this hierarchical homeostasis remain to be investigated. In this study, we found the level of microRNA221 (miR-221) was higher in stem-like and myoepithelial cells than in luminal cells isolated from normal and malignant breast tissue. In normal breast cells, over-expression of miR-221 generated more myoepithelial cells whereas knock-down of miR-221 increased luminal cells. Over-expression of miR-221 stimulated stem-like cells in luminal type of cancer and the miR-221 level was correlated with clinical outcome in breast cancer patients. Epithelial-mesenchymal transition (EMT) was induced by overexpression of miR-221 in normal and breast cancer cells. The EMT related gene ATXN1 was found to be a miR-221 target gene regulating breast cell hierarchy. In conclusion, we propose that miR-221 contributes to lineage homeostasis of normal and malignant breast epithelium.

[Development of transcutaneous jaundice predictor for the neonates].

Neonatal jaundice is a common neonatal disease. Severe jaundices lead to kernicterus that affects intellectual development of infants or even causes death. Timely and early prediction is vital to the treatment and prevention. This paper presents a jaundice predictor, which uses C8051F020 as the core of single-chip microcomputer (SCM) system with prediction algorithms proven by a large number of clinical trials. The jaundice predictor can reduce the incidence rate of jaundice, alleviate the condition of infants with jaundice, improve the quality of perinatal, with predicting pathologic neonatal jaundice effectively and calling attention to the prophylactic treatment. In addition, compared with the existing transcutaneous jaundice meters, the new predictor has a smaller size, a lighter weight, more user-friendly, and easier to use by hand-holding.