How does CBCT reconstruction algorithm impact on deformably mapped targets and accumulated dose distributions?

PURPOSE: We performed quantitative analysis of differences in deformable image registration (DIR) and deformable dose accumulation (DDA) computed on CBCT datasets reconstructed using the standard (Feldkamp-Davis-Kress: FDK_CBCT) and a novel iterative (iterative_CBCT) CBCT reconstruction algorithms. METHODS: Both FDK_CBCT and iterative_CBCT images were reconstructed for 323 fractions of treatment for 10 prostate cancer patients. Planning CT images were deformably registered to each CBCT image data set. After daily dose distributions were computed, they were mapped to planning CT to obtain deformed doses. Dosimetric and image registration results based CBCT images reconstructed by two algorithms were compared at three levels: (A) voxel doses over entire dose calculation volume, (B) clinical constraint results on targets and sensitive structures, and (C) contours propagated to CBCT images using DIR results based on three algorithms (SmartAdapt, Velocity, and Elastix) were compared with manually delineated contours as ground truth. RESULTS: (A) Average daily dose differences and average normalized DDA differences between FDK_CBCT and iterative_CBCT were ≤1 cGy. Maximum daily point dose differences increased from 0.22 ± 0.06 Gy (before the deformable dose mapping operation) to 1.33 ± 0.38 Gy after the deformable dose mapping. Maximum differences of normalized DDA per fraction were up to 0.80 Gy (0.42 ± 0.19 Gy). (B) Differences in target minimum doses were up to 8.31 Gy (-0.62 ± 4.60 Gy) and differences in critical structure doses were 0.70 ± 1.49 Gy. (C) For mapped prostate contours based on iterative_CBCT (relative to standard FDK_CBCT), dice similarity coefficient increased by 0.10 ± 0.09 (p < 0.0001), mass center distances decreased by 2.5 ± 3.0 mm (p < 0.00005), and Hausdorff distances decreased by 3.3 ± 4.4 mm (p < 0.00015). CONCLUSIONS: The new iterative CBCT reconstruction algorithm leads to different mapped volumes of interest, deformed and cumulative doses than results based on conventional FDK_CBCT.

A deep dive into understanding tumor foci classification using multiparametric MRI based on convolutional neural network.

PURPOSE: Deep learning models have had a great success in disease classifications using large data pools of skin cancer images or lung X-rays. However, data scarcity has been the roadblock of applying deep learning models directly on prostate multiparametric MRI (mpMRI). Although model interpretation has been heavily studied for natural images for the past few years, there has been a lack of interpretation of deep learning models trained on medical images. In this paper, an efficient convolutional neural network (CNN) was developed and the model interpretation at various convolutional layers was systematically analyzed to improve the understanding of how CNN interprets multimodality medical images and the predictive powers of features at each layer. The problem of small sample size was addressed by feeding the intermediate features into a traditional classification algorithm known as weighted extreme learning machine (wELM), with imbalanced distribution among output categories taken into consideration. METHODS: The training data collection used a retrospective set of prostate MR studies, from SPIE-AAPM-NCI PROSTATEx Challenges held in 2017. Three hundred twenty biopsy samples of lesions from 201 prostate cancer patients were diagnosed and identified as clinically significant (malignant) or not significant (benign). All studies included T2-weighted (T2W), proton density-weighted (PD-W), dynamic contrast enhanced (DCE) and diffusion-weighted (DW) imaging. After registration and lesion-based normalization, a CNN with four convolutional layers were developed and trained on tenfold cross validation. The features from intermediate layers were then extracted as input to wELM to test the discriminative power of each individual layer. The best performing model from the tenfolds was chosen to be tested on the holdout cohort from two sources. Feature maps after each convolutional layer were then visualized to monitor the trend, as the layer propagated. Scatter plotting was used to visualize the transformation of data distribution. Finally, a class activation map was generated to highlight the region of interest based on the model perspective. RESULTS: Experimental trials indicated that the best input for CNN was a modality combination of T2W, apparent diffusion coefficient (ADC) and DWIb50 . The convolutional features from CNN paired with a weighted extreme learning classifier showed substantial performance compared to a CNN end-to-end training model. The feature map visualization reveals similar findings on natural images where lower layers tend to learn lower level features such as edges, intensity changes, etc, while higher layers learn more abstract and task-related concept such as the lesion region. The generated saliency map revealed that the model was able to focus on the region of interest where the lesion resided and filter out background information, including prostate boundary, rectum, etc. CONCLUSIONS: This work designs a customized workflow for the small and imbalanced dataset of prostate mpMRI where features were extracted from a deep learning model and then analyzed by a traditional machine learning classifier. In addition, this work contributes to revealing how deep learning models interpret mpMRI for prostate cancer patient stratification.

Improvements in CBCT Image Quality Using a Novel Iterative Reconstruction Algorithm: A Clinical Evaluation.

PURPOSE: This study aimed to evaluate the clinical utility of a novel iterative cone beam computed tomography (CBCT) reconstruction algorithm for prostate and head and neck (HN) cancer. METHODS AND MATERIALS: A total of 10 patients with HN and 10 patients with prostate cancer were analyzed. For each patient, raw CBCT acquisition data were used to reconstruct images with a currently available algorithm (FDK_CBCT) and novel iterative algorithm (Iterative_CBCT). Quantitative contouring variation analysis was performed using structures delineated by several radiation oncologists. For prostate, observers contoured the prostate, proximal 2 cm seminal vesicles, bladder, and rectum. For HN, observers contoured the brain stem, spinal canal, right-left parotid glands, and right-left submandibular glands. Observer contours were combined to form a reference consensus contour using the simultaneous truth and performance level estimation method. All observer contours then were compared with the reference contour to calculate the Dice coefficient, Hausdorff distance, and mean contour distance (prostate contour only). Qualitative image quality analysis was performed using a 5-point scale ranging from 1 (much superior image quality for Iterative_CBCT) to 5 (much inferior image quality for Iterative_CBCT). RESULTS: The Iterative_CBCT data sets resulted in a prostate contour Dice coefficient improvement of approximately 2.4% (P = .029). The average prostate contour Dice coefficient for the Iterative_CBCT data sets was improved for all patients, with improvements up to approximately 10% for 1 patient. The mean contour distance results indicate an approximate 15% reduction in mean contouring error for all prostate regions. For the parotid contours, Iterative_CBCT data sets resulted in a Hausdorff distance improvement of approximately 2 mm (P < .01) and an approximate 2% improvement in Dice coefficient (P = .03). The Iterative_CBCT data sets were scored as equivalent or of better image quality for 97.3% (prostate) and 90.0% (HN) of the patient data sets. CONCLUSIONS: Observers noted an improvement in image uniformity, noise level, and overall image quality for Iterative_CBCT data sets. In addition, expert observers displayed an improved ability to consistently delineate soft tissue structures, such as the prostate and parotid glands. Thus, the novel iterative reconstruction algorithm analyzed in this study is capable of improving the visualization for prostate and HN cancer image guided radiation therapy.

The impact of adjuvant vaginal brachytherapy in women with Stage II uterine endometrioid carcinoma: Results of a National Cancer Database analysis.

PURPOSE: To report survival outcomes in women with Stage II uterine endometrioid carcinoma who received adjuvant radiation therapy (RT) without chemotherapy using the National Cancer Database. METHODS AND MATERIALS: The National Cancer Database was queried for women with International Federation of Gynecology and Obstetrics Stage II uterine endometrioid carcinoma who underwent hysterectomy followed by adjuvant RT without chemotherapy. The χ2 tests were performed to compare differences in outcome by type of adjuvant RT (external beam radiation therapy [EBRT] alone, vaginal brachytherapy [VBT] alone, or combination of EBRT and VBT). Overall survival (OS) was assessed by Kaplan-Meier and log-rank tests. Univariate and multivariate analyses were performed to identify predictors of OS. RESULTS: We identified 2681 women. Simple hysterectomy was performed on 2261 women (84%). Adjuvant EBRT, VBT, and combination RT were administered to 27%, 36%, and 37%, respectively. There was a statistically significant difference in OS by modality of adjuvant RT (p = 0.01) favoring women who received VBT alone or in combination with EBRT. The 5-year OS was 80%, 87%, and 83% for women who received EBRT, VBT, and combination RT, respectively (p = 0.001). On multivariate analysis, old age, African-American race, no or fewer number of examined lymph nodes, and higher tumor grade were independent predictors of worse OS. RT modality did not sustain its independent prognostic significance as a predictor of OS. CONCLUSIONS: In this nationwide hospital-based study of women with International Federation of Gynecology and Obstetrics Stage II uterine endometrioid carcinoma, adjuvant VBT alone provided excellent survival outcomes and may be a reasonable adjuvant RT modality for properly selected women with adequate lymph node dissection and low-grade tumors.

Survival outcomes and patterns of failure in women with stage IIIC2 endometrial carcinoma.

OBJECTIVES: Para-aortic lymph node involvement in women with endometrial carcinoma (EC) is a poor prognostic factor. Many studies have included women with stage IIIC2 in cohorts of patients with advanced stage disease. The aim of this study was to analyze survival outcomes and patterns of failure in women with solely stage IIIC2 EC. METHODS: We identified women with FIGO stage IIIC2 EC who underwent surgical staging at our institution. In addition to descriptive analyses of patient demographics, tumor characteristics, and adjuvant treatment received, univariate log-rank analyses and Cox regression multivariate analyses (MVA) were performed to identify predictors of recurrence-free (RFS), disease-specific (DSS) and overall survival (OS). RESULTS: A total of 72 women were included in this study cohort. The median follow-up time was 43 months. The median number of positive para-aortic lymph nodes was one. Of the 61 women (84.7%) who received adjuvant therapy, 40 women (65.6%) received chemotherapy and radiation therapy (CRT), 17 women (27.9%) received chemotherapy alone (CT), and only 4 women (6.6%) received radiation therapy alone. Thirty-seven women (51.4%) experienced disease recurrence. Distant metastasis was the most common pattern of failure (73%). Five-year RFS, DSS, and OS were 48%, 51%, and 48%, respectively. Due to small study size, our exploratory multivariate analysis demonstrated that histologic grade was the only significant prognostic factor for DSS (p=0.03) and OS (p=0.02). The type of adjuvant therapy did not sustain its independent predictive significance for RFS, DSS and OS. CONCLUSIONS: Our findings suggest that almost half of women with stage IIIC2 can be cured with surgical staging and adjuvant therapies. The most common pattern of failure was distant metastasis calling for further optimization of systemic therapy.

The Malaysian Clinical Guidance on the management of postmenopausal osteoporosis, 2012: a summary.

AIM: This Clinical Guidance is aimed to help practitioners assess, diagnose and manage their patients with osteoporosis (OP), using the best available evidence. METHODS: A literature search using PubMed (MEDLINE) and The Cochrane Library identified all relevant articles on OP and its assessment, diagnosis and treatment, from 2005, to update from the previous edition published in 2006. The studies were assessed and the level of evidence assigned; for each statement, studies with the highest level of evidence were used to frame the recommendation. RESULTS: This article summarizes the diagnostic and treatment pathways for OP, highlighting the new data that have changed the way we assess and treat OP. Instead of starting treatment based on bone mineral density alone, there has been a move to assessing 10-year fracture risk before treatment, using tools such as the Fracture Risk Assessment Tool (FRAX). There has been a re-evaluation on calcium supplementation and more emphasis on the importance of vitamin D. There has been concern about the potential adverse effects of the long-term usage of bisphosphonates, which we have discussed fully. New drugs that have been licensed since 2006 in Malaysia have been included. CONCLUSIONS: Adequate intake of calcium (1000 mg from both diet and supplements) and vitamin D (800 IU) daily remain important in the treatment of OP. However, in confirmed OP, pharmacological therapy with anti-resorptives is the mainstay of treatment. Patients need to be regularly assessed while on medication and treatment adjusted as required.