A review of segmentation and deformable registration methods applied to adaptive cervical cancer radiation therapy treatment planning

Exploring the therapeutic potential of tonic Chinese herbal medicine for gynecological disorders: An updated review

ETHNOPHARMACOLOGICAL RELEVANCE

Gynecological disorders have the characteristics of high incidence and recurrence rate, which sorely affects female's health. Since ancient times, traditional Chinese medicine (TCM), especially tonic medicine (TM), has been used to deal with gynecological disorders and has unique advantages in effectiveness and safety.

AIM OF THE REVIEW

In this article, we aim to summarize the research progress of TMs in-vivo and in-vitro, including their formulas, single herbs, and compounds, for gynecological disorders treatment in recent years, and to offer a reference for further research on the treatment of gynecological disorders and their clinical application in the treatment of TMs.

MATERIALS AND METHODS

Relevant information on the therapeutic potential of TMs against gynecological disorders was collected from several scientific databases including Web of Science, PubMed, CNKI, Google Scholar and other literature sources.

RESULTS

So far, there are 46 different formulas, 3 single herbs, and 24 compounds used in the treatment of various gynecological disorders such as premature ovarian failure, endometriosis breast cancer, and so on. Many experimental results have shown that TMs can regulate apoptosis, invasion, migration, oxidative stress, and the immune system. In addition, the effect of TMs in gynecological disorders treatment may be due to the regulation of VEGF, PI3K-AKT, MAPK, NF-κB, and other signaling pathways. Apparently, TMs play an active role in the treatment of gynecological disorders by regulating these signaling pathways.

CONCLUSION

TMs have a curative effect on the prevention and treatment of gynecological disorders. It could relieve and treat gynecological disorders through a variety of pathways. Therefore, the appropriate TM treatment program makes it more possible to treat gynecological disorders.

Automation and artificial intelligence in radiation therapy treatment planning

Automation and artificial intelligence (AI) is already possible for many radiation therapy planning and treatment processes with the aim of improving workflows and increasing efficiency in radiation oncology departments. Currently, AI technology is advancing at an exponential rate, as are its applications in radiation oncology. This commentary highlights the way AI has begun to impact radiation therapy treatment planning and looks ahead to potential future developments in this space. Historically, radiation therapist's (RT's) role has evolved alongside the adoption of new technology. In Australia, RTs have key clinical roles in both planning and treatment delivery and have been integral in the implementation of automated solutions for both areas. They will need to continue to be informed, to adapt and to transform with AI technologies implemented into clinical practice in radiation oncology departments. RTs will play an important role in how AI-based automation is implemented into practice in Australia, ensuring its application can truly enable personalised and higher-quality treatment for patients. To inform and optimise utilisation of AI, research should not only focus on clinical outcomes but also AI's impact on professional roles, responsibilities and service delivery. Increased efficiencies in the radiation therapy workflow and workforce need to maintain safe improvements in practice and should not come at the cost of creativity, innovation, oversight and safety.

Improving hybrid image and structure-based deformable image registration for large internal deformations

Objective.Deformable image registration (DIR) is a widely used technique in radiotherapy. Complex deformations, resulting from large anatomical changes, are a regular challenge. DIR algorithms generally seek a balance between capturing large deformations and preserving a smooth deformation vector field (DVF). We propose a novel structure-based term that can enhance the registration efficacy while ensuring a smooth DVF.Approach.The proposed novel similarity metric for controlling structures was introduced as a new term into a commercially available algorithm. Its performance was compared to the original algorithm using a dataset of 46 patients who received pelvic re-irradiation, many of which exhibited complex deformations.Main results.The mean Dice Similarity Coefficient (DSC) under the improved algorithm was 0.96, 0.94, 0.76, and 0.91 for bladder, rectum, colon, and bone respectively, compared to 0.69, 0.89, 0.62, and 0.88 for the original algorithm. The improvement was more pronounced for complex deformations.Significance.With this work, we have demonstrated that the proposed term is able to improve registration accuracy for complex cases while maintaining realistic deformations.

The research progress on radiation resistance of cervical cancer

Cervical carcinoma is the most prevalent gynecology malignant tumor and ranks as the fourth most common cancer worldwide, thus posing a significant threat to the lives and health of women. Advanced and early-stage cervical carcinoma patients with high-risk factors require adjuvant treatment following surgery, with radiotherapy being the primary approach. However, the tolerance of cervical cancer to radiotherapy has become a major obstacle in its treatment. Recent studies have demonstrated that radiation resistance in cervical cancer is closely associated with DNA damage repair pathways, the tumor microenvironment, tumor stem cells, hypoxia, cell cycle arrest, and epigenetic mechanisms, among other factors. The development of tumor radiation resistance involves complex interactions between multiple genes, pathways, and mechanisms, wherein each factor interacts through one or more signaling pathways. This paper provides an overview of research progress on an understanding of the mechanism underlying radiation resistance in cervical cancer.

QUIZ: An arbitrary volumetric point matching method for medical image registration

Rigid pre-registration involving local-global matching or other large deformation scenarios is crucial. Current popular methods rely on unsupervised learning based on grayscale similarity, but under circumstances where different poses lead to varying tissue structures, or where image quality is poor, these methods tend to exhibit instability and inaccuracies. In this study, we propose a novel method for medical image registration based on arbitrary voxel point of interest matching, called query point quizzer (QUIZ). QUIZ focuses on the correspondence between local-global matching points, specifically employing CNN for feature extraction and utilizing the Transformer architecture for global point matching queries, followed by applying average displacement for local image rigid transformation.We have validated this approach on a large deformation dataset of cervical cancer patients, with results indicating substantially smaller deviations compared to state-of-the-art methods. Remarkably, even for cross-modality subjects, it achieves results surpassing the current state-of-the-art.

Upregulation of TMEM40 is associated with the malignant behavior and promotes tumor progression in cervical cancer

OBJECTIVE

Recent studies indicated that transmembrane protein 40 (TMEM40) is associated with several types of cancers but is not clear in cervical cancer (CC). The study aimed to examine the role of TMEM40 in CC and related mechanisms.

METHODS

The expression of TMEM40 in CC tissues and cell lines was studied with western blot and real-time quantitative RT-PCR. The effect of TMEM40 on proliferation was evaluated by CCK-8, EdU and colony formation assay. The migration, invasion, cell cycle and apoptosis of CC cells were studied with wound healing, transwell assays and flow cytometry. Tumor growth was evaluated in vivo using a xenogenous subcutaneously implant model.

RESULTS

The results revealed that the TMEM40 elevation in CC tissues and cell lines was closely correlated with tumor size and lymph node metastasis in clinical patients. Upregulation of TMEM40 with OE-TMEM40 vector promoted the invasion, migration and proliferation, inhibited the apoptosis and led to distinct S cell cycle arrest in CC cell lines. Silencing TMEM40 with shRNA inhibited the invasion, migration and proliferation, promoted apoptosis and led to a G0/G1 cell cycle arrest in CC cell lines. Silence of TMEM40 downregulated the expression of c-MYC, Cyclin D1, matrix metalloproteinase-1 (MMP-1) and matrix metalloproteinase-9 (MMP-9), but in contrast, activated p53 and several apoptosis related proteins such as p53, Caspase-3, Caspase-9 and PARP1. In addition, TMEM40 silencing dramatically decreased tumor growth in mice models.

CONCLUSION

The present study demonstrates that TMEM40 upregulation can be a potential prognostic biomarker and contribute to CC development.

Excitement and Concerns of Young Radiation Oncologists over Automatic Segmentation: A French Perspective

Introduction: Segmentation of organs at risk (OARs) and target volumes need time and precision but are highly repetitive tasks. Radiation oncology has known tremendous technological advances in recent years, the latest being brought by artificial intelligence (AI). Despite the advantages brought by AI for segmentation, some concerns were raised by academics regarding the impact on young radiation oncologists’ training. A survey was thus conducted on young french radiation oncologists (ROs) by the SFjRO (Société Française des jeunes Radiothérapeutes Oncologues). Methodology: The SFjRO organizes regular webinars focusing on anatomical localization, discussing either segmentation or dosimetry. Completion of the survey was mandatory for registration to a dosimetry webinar dedicated to head and neck (H & N) cancers. The survey was generated in accordance with the CHERRIES guidelines. Quantitative data (e.g., time savings and correction needs) were not measured but determined among the propositions. Results: 117 young ROs from 35 different and mostly academic centers participated. Most centers were either already equipped with such solutions or planning to be equipped in the next two years. AI segmentation software was mostly useful for H & N cases. While for the definition of OARs, participants experienced a significant time gain using AI-proposed delineations, with almost 35% of the participants saving between 50–100% of the segmentation time, time gained for target volumes was significantly lower, with only 8.6% experiencing a 50–100% gain. Contours still needed to be thoroughly checked, especially target volumes for some, and edited. The majority of participants suggested that these tools should be integrated into the training so that future radiation oncologists do not neglect the importance of radioanatomy. Fully aware of this risk, up to one-third of them even suggested that AI tools should be reserved for senior physicians only. Conclusions: We believe this survey on automatic segmentation to be the first to focus on the perception of young radiation oncologists. Software developers should focus on enhancing the quality of proposed segmentations, while young radiation oncologists should become more acquainted with these tools.

Segmentation of Clinical Target Volume From CT Images for Cervical Cancer Using Deep Learning

Introduction: Segmentation of clinical target volume (CTV) from CT images is critical for cervical cancer brachytherapy, but this task is time-consuming, laborious, and not reproducible. In this work, we aim to propose an end-to-end model to segment CTV for cervical cancer brachytherapy accurately. Methods: In this paper, an improved M-Net model (Mnet_IM) is proposed to segment CTV of cervical cancer from CT images. An input and an output branch are both proposed to attach to the bottom layer to deal with CTV locating challenges due to its lower contrast than surrounding organs and tissues. A progressive fusion approach is then proposed to recover the prediction results layer by layer to enhance the smoothness of segmentation results. A loss function is defined on each of the multiscale outputs to form a deep supervision mechanism. Numbers of feature map channels that are directly connected to inputs are finally homogenized for each image resolution to reduce feature redundancy and computational burden. Result: Experimental results of the proposed model and some representative models on 5438 image slices from 53 cervical cancer patients demonstrate advantages of the proposed model in terms of segmentation accuracy, such as average surface distance, 95% Hausdorff distance, surface overlap, surface dice, and volumetric dice. Conclusion: A better agreement between the predicted CTV from the proposed model Mnet_IM and manually labeled ground truth is obtained compared to some representative state-of-the-art models.

3D-US and CBCT Dual-guided Radiotherapy for Postoperative Uterine Malignancy: A Primary Workflow Set-up

Introduction: The consistency of clinical target volume is essential to guiding radiotherapy with precision for postoperative uterine malignancy patients. By introducing a three-dimensional ultrasound system (3D-US) into image-guided radiation therapy (IGRT), this study was designed to investigate the initial workflow set-up, the therapeutic potential, and the adverse events of 3D-US and cone-beam computed tomography (CBCT) dual-guided radiotherapy in postoperative uterine malignancy treatment. Methods: From April 2021 to December 2021, postoperative uterine malignancy patients were instructed to follow the previously standard protocol of daily radiation treatment, particularly a 3D-US (Clarity system) guiding was involved before CBCT. Soft-tissue-based displacements resulting from the additional US-IGRT were acquired in the LT (left)/RT (right), ANT (anterior)/POST (posterior), and SUP (superior)/INF(inferior) directions of the patient before fractional treatment. Displacement distributions before and after treatment either from 3D-US or from CBCT were also estimated and compared subsequently, and the urinary and rectal toxicity was further evaluated. Results: All the patients completed radiation treatment as planned. The assessment of 170 scans resulted in a mean displacement of (0.17 ± 0.24) cm, (0.19 ± 0.23) cm, (0.22 ± 0.26) cm for bladder in LT/RT, ANT/POST, and SUP/INF directions. A mean deviation of (0.26 ± 0.22) cm, (0.58 ± 0.5) cm, and (0.3 ± 0.23) cm was also observed for the bladder centroid between the CBCT and computed tomography -simulation images in three directions. Paired comparison between these two guidance shows that the variations from 3D-US are much smaller than those from CBCT in three directions, especially in ANT/POST and SUP/INF directions with significance (P = 0.000, 0.001, respectively). During treatment, and 0, 3, 6, 9, and 12 months after treatment, there was no severe urinary and rectal toxicity happened. Conclusion: A primary workflow of 3D-US and CBCT dual-guided radiotherapy has been established, which showed great therapeutic potential with mild to moderate urinary and rectal toxicity for postoperative uterine malignancy patients. But the clinical outcomes of this non-invasive technique need to be investigated further.

Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network

PURPOSE

Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft-tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning-based method to segment CTV from MR images.

METHODS

Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior-inferior CTV span is then detected using an Attention U-Net. A CTV-specific region of interest (ROI) is determined, and three-dimensional (3-D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3-D U-Net from the extracted 3-D blocks.

RESULTS

We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state-of-the-art methods significantly (p-value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed.

CONCLUSIONS

Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer.

Deep Learning for Automated Contouring of Gross Tumor Volumes in Esophageal Cancer

Purpose

The aim of this study was to propose and evaluate a novel three-dimensional (3D) V-Net and two-dimensional (2D) U-Net mixed (VUMix-Net) architecture for a fully automatic and accurate gross tumor volume (GTV) in esophageal cancer (EC)–delineated contours.

Methods

We collected the computed tomography (CT) scans of 215 EC patients. 3D V-Net, 2D U-Net, and VUMix-Net were developed and further applied simultaneously to delineate GTVs. The Dice similarity coefficient (DSC) and 95th-percentile Hausdorff distance (95HD) were used as quantitative metrics to evaluate the performance of the three models in ECs from different segments. The CT data of 20 patients were randomly selected as the ground truth (GT) masks, and the corresponding delineation results were generated by artificial intelligence (AI). Score differences between the two groups (GT versus AI) and the evaluation consistency were compared.

Results

In all patients, there was a significant difference in the 2D DSCs from U-Net, V-Net, and VUMix-Net (p=0.01). In addition, VUMix-Net showed achieved better 3D-DSC and 95HD values. There was a significant difference among the 3D-DSC (mean ± STD) and 95HD values for upper-, middle-, and lower-segment EC (p<0.001), and the middle EC values were the best. In middle-segment EC, VUMix-Net achieved the highest 2D-DSC values (p<0.001) and lowest 95HD values (p=0.044).

Conclusion

The new model (VUMix-Net) showed certain advantages in delineating the GTVs of EC. Additionally, it can generate the GTVs of EC that meet clinical requirements and have the same quality as human-generated contours. The system demonstrated the best performance for the ECs of the middle segment.

Tanshinone I inhibits metastasis of cervical cancer cells by inducing BNIP3/NIX-mediated mitophagy and reprogramming mitochondrial metabolism

BACKGROUND

Cervical cancer is the most common malignancy of the female lower genital tract. Tanshinone I (Tan I) is one of the crucial lipid-soluble components of red sage (Salvia miltiorrhiza). While its mode of action against cervical cancer is unclear.

PURPOSE

Our study aimed to explore the role of Tan I on cervical cancer in vitro.

STUDY DESIGN AND METHODS

Effects of Tan I on cervical cancer cells viability, migration and mitochondrial function were investigated by Cell Counting Kit-8, Transwell and Fluorescence laser confocal microscope assays respectively. The potential mechanism of Tan I was uncovered by an integrative approach combining RNA profiling and hydrogen nuclear magnetic resonance-based metabolic analysis, molecular docking and Western blot.

RESULTS

Tan I significantly inhibited the growth and colony formation of HeLa and SiHa cells. It induced apoptosis and cell cycle S phase arrest at low (12.5-25 μM) but not high (50 μM) concentrations. It also altered the HeLa cell ultrastructure, decreased the membrane potential and increased the total mitochondrial content. Further, Tan I induced autophagic flux and the colocalization of mitochondria with lysosomes, led to decreased adhesion, invasion, and migration of cervical cancer cells. Transcriptomic analysis revealed that Tan I altered the RNA profile and signal processing in HeLa cells. Tan I significantly impacted "central carbon metabolism in cancer" and "mitophagy-animal" processes. A global metabolic analysis identified 25 metabolites affected by Tan I treatment in HeLa cells. Changes in the metabolic profile indicated that Tan I affected such processes as protein digestion and absorption, central carbon metabolism in cancer, and aminoacyl-tRNA biosynthesis in cervical cancer cells. Furthermore, Tan I significantly induced the expression of mitophagy-related proteins BNIP3, NIX and Optineurin and the conversion from LC3-I to LC3-II, inhibited the NDP52 and P62 level in a concentration-dependent manner. While CQ further increased the conversion of LC3-I to LC3-II and the expression of P62. Moreover, Tan I interacted with BNIP3 and NIX through hydrogen bond. Tan I induce mitophagy could be prevented by BNIP3 and NIX siRNA transfection.

CONCLUSION

Tan I induced the BNIP3/NIX-mediated mitophagy, and reprogrammed the mitochondrial metabolism in cervical cancer cells, thus inhibiting metastasis.

Studierfenster: an Open Science Cloud-Based Medical Imaging Analysis Platform

Imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI) are widely used in diagnostics, clinical studies, and treatment planning. Automatic algorithms for image analysis have thus become an invaluable tool in medicine. Examples of this are two- and three-dimensional visualizations, image segmentation, and the registration of all anatomical structure and pathology types. In this context, we introduce Studierfenster (www.studierfenster.at): a free, non-commercial open science client-server framework for (bio-)medical image analysis. Studierfenster offers a wide range of capabilities, including the visualization of medical data (CT, MRI, etc.) in two-dimensional (2D) and three-dimensional (3D) space in common web browsers, such as Google Chrome, Mozilla Firefox, Safari, or Microsoft Edge. Other functionalities are the calculation of medical metrics (dice score and Hausdorff distance), manual slice-by-slice outlining of structures in medical images, manual placing of (anatomical) landmarks in medical imaging data, visualization of medical data in virtual reality (VR), and a facial reconstruction and registration of medical data for augmented reality (AR). More sophisticated features include the automatic cranial implant design with a convolutional neural network (CNN), the inpainting of aortic dissections with a generative adversarial network, and a CNN for automatic aortic landmark detection in CT angiography images. A user study with medical and non-medical experts in medical image analysis was performed, to evaluate the usability and the manual functionalities of Studierfenster. When participants were asked about their overall impression of Studierfenster in an ISO standard (ISO-Norm) questionnaire, a mean of 6.3 out of 7.0 possible points were achieved. The evaluation also provided insights into the results achievable with Studierfenster in practice, by comparing these with two ground truth segmentations performed by a physician of the Medical University of Graz in Austria. In this contribution, we presented an online environment for (bio-)medical image analysis. In doing so, we established a client-server-based architecture, which is able to process medical data, especially 3D volumes. Our online environment is not limited to medical applications for humans. Rather, its underlying concept could be interesting for researchers from other fields, in applying the already existing functionalities or future additional implementations of further image processing applications. An example could be the processing of medical acquisitions like CT or MRI from animals [Clinical Pharmacology & Therapeutics, 84(4):448–456, 68], which get more and more common, as veterinary clinics and centers get more and more equipped with such imaging devices. Furthermore, applications in entirely non-medical research in which images/volumes need to be processed are also thinkable, such as those in optical measuring techniques, astronomy, or archaeology.

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

Purpose

To propose a novel deep-learning-based auto-segmentation model for CTV delineation in cervical cancer and to evaluate whether it can perform comparably well to manual delineation by a three-stage multicenter evaluation framework.

Methods

An adversarial deep-learning-based auto-segmentation model was trained and configured for cervical cancer CTV contouring using CT data from 237 patients. Then CT scans of additional 20 consecutive patients with locally advanced cervical cancer were collected to perform a three-stage multicenter randomized controlled evaluation involving nine oncologists from six medical centers. This evaluation system is a combination of objective performance metrics, radiation oncologist assessment, and finally the head-to-head Turing imitation test. Accuracy and effectiveness were evaluated step by step. The intra-observer consistency of each oncologist was also tested.

Results

In stage-1 evaluation, the mean DSC and the 95HD value of the proposed model were 0.88 and 3.46 mm, respectively. In stage-2, the oncologist grading evaluation showed the majority of AI contours were comparable to the GT contours. The average CTV scores for AI and GT were 2.68 vs. 2.71 in week 0 (P = .206), and 2.62 vs. 2.63 in week 2 (P = .552), with no significant statistical differences. In stage-3, the Turing imitation test showed that the percentage of AI contours, which were judged to be better than GT contours by ≥5 oncologists, was 60.0% in week 0 and 42.5% in week 2. Most oncologists demonstrated good consistency between the 2 weeks (P > 0.05).

Conclusions

The tested AI model was demonstrated to be accurate and comparable to the manual CTV segmentation in cervical cancer patients when assessed by our three-stage evaluation framework.

Therapeutic effects and prognostic factors of 125I brachytherapy for pelvic recurrence after early cervical cancer surgery

To investigate the efficacy of ¹²⁵I seed implantation in the treatment regimen of pelvic recurrence after early cervical cancer surgery and to analyse prognostic factors. To evaluate efficacy and analyse prognostic factors of ¹²⁵I seed implantation for pelvic recurrence after early cervical cancer surgery. A prospective study was conducted on 62 patients who experienced pelvic recurrence after early cervical cancer surgery between August 2005 and September 2015. The 62 patients were treated and assessed in 2 groups (n = 30). All 62 patients were randomized into two groups that received two different treatment regimens: the treatment group (n = 30), which received ¹²⁵I particle implantation therapy, and the control group (n = 32), which received whole-pelvic irradiation using the anteroposterior/posteroanterior field and cisplatin-based concurrent chemoradiation therapy. The efficacy/efficiency of ¹²⁵I seed implantation and prognostic factors were analysed by logistic regression. Overall survival was determined by Kaplan-Meier analysis. Multivariate analysis results were obtained by the Cox proportional hazards regression model. The effective control rates at 1, 3, 6 and 12 months were 76.7%, 80.0%, 83.3%, and 86.7% in the ¹²⁵I particle implantation group. The total effective control rates at 1, 3, 6 and 12 months were 65.6%, 65.5%, 62.5%, and 71.9% in the chemoradiotherapy group. Significant differences were observed between the two groups. The overall survival rates at 1, 2, 3, 4, and 5 years and the median overall were 96.7%, 93.3%, 86.7%, 71.9%, 65.6% and 4.34 years, respectively, in the ¹²⁵I seed implantation group and 81.3%, 71.9%, 62.5%, 56.3%, 53.1% and 3.59 years, respectively, in the control group. There were statistically significant differences in survival rates depending on the diameter of the largest recurrent pelvic tumour (χ² = 6.611, P = 0.010). The multivariate analysis showed that the survival rates were related to the diameter of the largest recurrent pelvic tumour (χ² = 4.538, P = 0.033). ¹²⁵I implantation is an effective, safe, and promising method for the treatment of pelvic recurrence after early cervical cancer surgery. The diameter of the recurrent pelvic tumour was identified as a significant independent prognostic factor in patients who received ¹²⁵I implantation.

Quality Assurance in Modern Gynecological HDR-Brachytherapy (Interventional Radiotherapy): Clinical Considerations and Comments

Simple Summary

This is a focused review discussing quality assurance during interventional brachytherapy in gynecological cancers. This topic is very large and is usually addressed from the technical and physical sides, therefore, we decided to select “hot-spots” under this large title and discuss them from the point of view of clinicians. We hope that this concise and focused review will help clinicians in improving their quality assurance protocols and draw attention to the discussed issues.

Abstract

The use of brachytherapy (interventional radiotherapy) in the treatment of gynecological cancers is a crucial element in both definitive and adjuvant settings. The recent developments in high-dose rate remote afterloaders, modern applicators, treatment-planning software, image guidance, and dose monitoring systems have led to improvement in the local control rates and in some cases improved the survival rates. The development of these highly advanced and complicated treatment modalities has been accompanied by challenges, which have made the existence of quality assurance protocols a must to ensure the integrity of the treatment process. Quality assurance aims at standardizing the technical and clinical procedures involved in the treatment of patients, which could eventually decrease the source of uncertainties whether technical (source/equipment related) or clinical. This commentary review sheds light (from a clinical point of view) on some potential sources of uncertainties associated with the use of modern brachytherapy in the treatment of gynecological cancers.

Semi-automatic sigmoid colon segmentation in CT for radiation therapy treatment planning via an iterative 2.5-D deep learning approach

Automatic sigmoid colon segmentation in CT for radiotherapy treatment planning is challenging due to complex organ shape, close distances to other organs, and large variations in size, shape, and filling status. The patient bowel is often not evacuated, and CT contrast enhancement is not used, which further increase problem difficulty. Deep learning (DL) has demonstrated its power in many segmentation problems. However, standard 2-D approaches cannot handle the sigmoid segmentation problem due to incomplete geometry information and 3-D approaches often encounters the challenge of a limited training data size. Motivated by human's behavior that segments the sigmoid slice by slice while considering connectivity between adjacent slices, we proposed an iterative 2.5-D DL approach to solve this problem. We constructed a network that took an axial CT slice, the sigmoid mask in this slice, and an adjacent CT slice to segment as input and output the predicted mask on the adjacent slice. We also considered other organ masks as prior information. We trained the iterative network with 50 patient cases using five-fold cross validation. The trained network was repeatedly applied to generate masks slice by slice. The method achieved average Dice similarity coefficients of 0.82 0.06 and 0.88 0.02 in 10 test cases without and with using prior information.

Exploiting proteases for cancer theranostic through molecular imaging and drug delivery

The measurement of biological processes at a molecular and cellular level serves as a basis for molecular imaging. As compared with traditional imaging approaches, molecular imaging functions to probe molecular anomalies that are the basis of a disease rather than the evaluation of end results of these molecular changes. Proteases play central role in tumor invasion, angiogenesis and metastasis thus can be exploited as a target for imaging probes in early diagnosis and treatment of tumors. Molecular imaging of protease has undergone tremendous breakthroughs in the field of diagnosis. It allows the clinicians not only to see the tumor location but also provides an insight into the expression and activity of different types of markers associated with the tumor microenvironment. These imaging techniques are expected to have a huge impact on early cancer detection and personalized cancer treatment. Effective development of protease imaging probes with the highest in vivo biocompatibility, stability and most appropriate pharmacokinetics for clinical translation will upsurge the success level of early cancer detection and treatment.

Investigating conditional GAN performance with different generator architectures, an ensemble model, and different MR scanners for MR-sCT conversion

Recent developments in magnetic resonance (MR) to synthetic computed tomography (sCT) conversion have shown that treatment planning is possible without an initial planning CT. Promising conversion results have been demonstrated recently using conditional generative adversarial networks (cGANs). However, the performance is generally only tested on images from one MR scanner, which neglects the potential of neural networks to find general high-level abstract features. In this study, we explored the generalizability of the generator models, trained on a single field strength scanner, to data acquired with higher field strengths. T2-weighted 0.35T MRIs and CTs from 51 patients treated for prostate (40) and cervical cancer (11) were included. 25 of them were used to train four different generators (SE-ResNet, DenseNet, U-Net, and Embedded Net). Further, an ensemble model was created from the four network outputs. The models were validated on 16 patients from a 0.35T MR scanner. Further, the trained models were tested on the Gold Atlas dataset, containing T2-weighted MR scans of different field strengths; 1.5T(7) and 3T(12), and 10 patients from the 0.35T scanner. The sCTs were dosimetrically compared using clinical VMAT plans for all test patients. For the same scanner (0.35T), the results from the different models were comparable on the test set, with only minor differences in the mean absolute error (MAE) (35-51HU body). Similar results were obtained for conversions of 3T GE Signa and the 3T GE Discovery images (40-62HU MAE) for three of the models. However, larger differences were observed for the 1.5T images (48-65HU MAE). The overall best model was found to be the ensemble model. All dose differences were below 1%. This study shows that it is possible to generalize models trained on images of one scanner to other scanners and different field strengths. The best metric results were achieved by the combination of all networks.

The Stacked-Ellipse Algorithm: An Ultrasound-Based 3-D Uterine Segmentation Tool for Enabling Adaptive Radiotherapy for Uterine Cervix Cancer

The stacked-ellipse (SE) algorithm was developed to rapidly segment the uterus on 3-D ultrasound (US) for the purpose of enabling US-guided adaptive radiotherapy (RT) for uterine cervix cancer patients. The algorithm was initialised manually on a single sagittal slice to provide a series of elliptical initialisation contours in semi-axial planes along the uterus. The elliptical initialisation contours were deformed according to US features such that they conformed to the uterine boundary. The uterus of 15 patients was scanned with 3-D US using the Clarity System (Elekta Ltd.) at multiple days during RT and manually contoured (n = 49 images and corresponding contours). The median (interquartile range) Dice similarity coefficient and mean surface-to-surface-distance between the SE algorithm and manual contours were 0.80 (0.03) and 3.3 (0.2) mm, respectively, which are within the ranges of reported inter-observer contouring variabilities. The SE algorithm could be implemented in adaptive RT to precisely segment the uterus on 3-D US.

Inhibition of Uncoupling Protein 2 Enhances the Radiosensitivity of Cervical Cancer Cells by Promoting the Production of Reactive Oxygen Species

Objective

The mechanism of enhanced radiosensitivity induced by mitochondrial uncoupling protein UCP2 was investigated in HeLa cells to provide a theoretical basis as a novel target for cervical cancer treatment.

Methods

HeLa cells were irradiated with 4 Gy X-radiation at 1.0 Gy/min. The expression of UCP2 mRNA and protein was assayed by real-time quantitative polymerase chain reaction and western blotting. UCP2 siRNA and negative control siRNA fragments were constructed and transfected into HeLa cells 24 h after irradiation. The effect of UCP2 silencing and irradiation on HeLa cells was determined by colony formation, CCK-8 cell viability, γH2AX immunofluorescence assay of DNA damage, Annexin V-FITC/PI apoptosis assay, and propidium iodide cell cycle assay. The effects on mitochondrial structure and function were investigated with fluorescent probes including dichlorodihydrofluorescein diacetate (DCFH-DA) assay of reactive oxygen species (ROS), rhodamine 123, and MitoTracker Green assay of mitochondrial structure and function.

Results

Irradiation upregulated UCP2 expression, and UCP2 knockdown decreased the survival of irradiated HeLa cells. UCP2 silencing sensitized HeLa cells to irradiation-induced DNA damage and led to increased apoptosis, cell cycle arrest in G2/M, and increased mitochondrial ROS. Increased radiosensitivity was associated with an activation of P53, decreased Bcl-2, Bcl-xl, cyclin B, CDC2, Ku70, and Rad51 expression, and increased Apaf-1, cytochrome c, caspase-3, and caspase-9 expression.

Conclusions

UCP2 inhibition augmented the radiosensitivity of cervical cancer cells, and it may be a potential target of radiotherapy of advanced cervical cancer.

Evaluation of parametrial infiltration in cervical cancer with voxel-based segmentation of integrated 18F-FDG PET/MRI images: A preliminary study

PURPOSE

To identify parametrial infiltration (PMI) in cervical cancer with voxel-based segmentation of integrated PET/MRI images.

METHOD

This retrospective study enrolled 79 cervical cancer patients confirmed by pathology (FIGO stage IB to IIB) who underwent ¹⁸F-FDG PET/MRI prior to surgery. Region of interest (ROI) at the largest tumor level was delineated on the T2W-MR image, and the ROI was applied to PET image of the corresponding layer. Then, these images were postprocessed with segmentation and gray level calculations in the parauterine area.

RESULTS

In total, 37 patients (46.8%) had postoperative pathology-confirmed PMI, and 42 patients (53.2%) showed no PMI. There was a moderate correlation between pathological results and the gray level values of each region (rs > 0.5, P < 0.001). According to FIGO stage, as the cervical lesions became more malignant, the gray level values gradually increased. The diagnostic results of MRI and PET/MRI were in good agreement (kappa = 0.693, P < 0.001); the accuracy (78.5%), sensitivity (64.9%) and NPV (74.5%) of PET/MRI were slightly higher than those of MRI (74.7%,59.5%,71.2%, respectively), with no statistically significant difference (P = 1.000). The diagnostic results of MRI and PET/MRI+gray level values were generally consistent (kappa = 0.475, P < 0.001); the accuracy (87.3%), sensitivity(83.8%) and NPV(86.4%) of PET/MRI+gray level values were higher than those of MRI, with statistically significant differences (all P values < 0.05).

CONCLUSIONS

It is feasible to evaluate PMI based on PET/T2W-MRI voxel segmentation and to obtain quantitative and visual indicators. PET/MRI and gray level values considered together can also improve the accuracy, sensitivity and NPV of PMI diagnosis.

MR-based treatment planning in radiation therapy using a deep learning approach

Purpose

To develop and evaluate the feasibility of deep learning approaches for MR‐based treatment planning (deepMTP) in brain tumor radiation therapy.

Methods and materials

A treatment planning pipeline was constructed using a deep learning approach to generate continuously valued pseudo CT images from MR images. A deep convolutional neural network was designed to identify tissue features in volumetric head MR images training with co‐registered kVCT images. A set of 40 retrospective 3D T1‐weighted head images was utilized to train the model, and evaluated in 10 clinical cases with brain metastases by comparing treatment plans using deep learning generated pseudo CT and using an acquired planning kVCT. Paired‐sample Wilcoxon signed rank sum tests were used for statistical analysis to compare dosimetric parameters of plans made with pseudo CT images generated from deepMTP to those made with kVCT‐based clinical treatment plan (CTTP).

Results

deepMTP provides an accurate pseudo CT with Dice coefficients for air: 0.95 ± 0.01, soft tissue: 0.94 ± 0.02, and bone: 0.85 ± 0.02 and a mean absolute error of 75 ± 23 HU compared with acquired kVCTs. The absolute percentage differences of dosimetric parameters between deepMTP and CTTP was 0.24% ± 0.46% for planning target volume (PTV) volume, 1.39% ± 1.31% for maximum dose and 0.27% ± 0.79% for the PTV receiving 95% of the prescribed dose (V95). Furthermore, no significant difference was found for PTV volume (P = 0.50), the maximum dose (P = 0.83) and V95 (P = 0.19) between deepMTP and CTTP.

Conclusions

We have developed an automated approach (deepMTP) that allows generation of a continuously valued pseudo CT from a single high‐resolution 3D MR image and evaluated it in partial brain tumor treatment planning. The deepMTP provided dose distribution with no significant difference relative to a kVCT‐based standard volumetric modulated arc therapy plans.

Deformable image registration for radiation therapy: principle, methods, applications and evaluation

Background: Deformable image registration (DIR) is increasingly used in the field of radiation therapy (RT) to account for anatomical deformations. The aims of this paper are to describe the main applications of DIR in RT and discuss current DIR evaluation methods. Methods: Articles on DIR published from January 2000 to October 2018 were extracted from PubMed and Science Direct. Our search was restricted to articles that report data obtained from humans, were written in English, and address DIR methods for RT. A total of 207 articles were selected from among 2506 identified in the search process. Results: At planning, DIR is used for organ delineation using atlas-based segmentation, deformation-based planning target volume definition, functional planning and magnetic resonance imaging-based dose calculation. In image-guided RT, DIR is used for contour propagation and dose calculation on per-treatment imaging. DIR is also used to determine the accumulated dose from fraction to fraction in external beam RT and brachytherapy, both for dose reporting and adaptive RT. In the case of re-irradiation, DIR can be used to estimate the cumulated dose of the two irradiations. Finally, DIR can be used to predict toxicity in voxel-wise population analysis. However, the evaluation of DIR remains an open issue, especially when dealing with complex cases such as the disappearance of matter. To quantify DIR uncertainties, most evaluation methods are limited to geometry-based metrics. Software companies have now integrated DIR tools into treatment planning systems for clinical use, such as contour propagation and fraction dose accumulation. Conclusions: DIR is increasingly important in RT applications, from planning to toxicity prediction. DIR is routinely used to reduce the workload of contour propagation. However, its use for complex dosimetric applications must be carefully evaluated by combining quantitative and qualitative analyses.

Radiotherapy Immobilization Mask Molding Through the Use of 3D-Printed Head Models

PURPOSE

To evaluate the feasibility of a workflow free of a simulation appointment using three-dimensional-printed heads and custom immobilization devices.

MATERIALS AND METHODS

Simulation computed tomography scans of 11 patients who received radiotherapy for brain tumors were used to create three-dimensional printable models of the patients' heads and neck rests. The models were three-dimensional-printed using fused deposition modeling and reassembled. Then, thermoplastic immobilization masks were molded onto them. These setups were then computed tomography-scanned and compared against the volumes from the original patient computed tomography-scans. Following translational +/- rotational coregistrations of the volumes from three-dimensional-printed models and the patients, the similarities and accuracies of the setups were evaluated using Dice similarity coefficients, Hausdorff distances, differences in centroid positions, and angular deviations. Potential dosimetric differences secondary to inaccuracies in the rotational positioning of patients were calculated.

RESULTS

Mean angular deviation of the 3D-printout from the original volume for the Pitch, Yaw, and Roll were 1.1° (standard deviation = 0.77°), 0.59° (standard deviation = 0.41°), and 0.79° (standard deviation = 0.86°), respectively. Following translational + rotational shifts, the mean Dice similarity coefficients of the three-dimensional-printed and original volumes was 0.985 (standard deviation = 0.002) while the mean Hausdorff distance was 0.9 mm (standard error of the mean: 0.1 mm). The mean centroid vector displacement was 0.5 mm (standard deviation: 0.3 mm). Compared to plans that were coregistered using translational + rotational shifts, the D₉₅ of the brain from three-dimensional-printed heads adjusted for TR shifts only differed by -0.1% (standard deviation = 0.2%).

CONCLUSIONS

Patient head volumes and positions at simulation computed tomography scans can be accurately reproduced using three-dimensional-printed models, which can be used to mold radiotherapy immobilization masks onto. This strategy, if applied on diagnostic computed tomography scans, may allow symptomatic and frail patients to avoid a computed tomography-simulation and mask molding session in preparation for palliative whole brain radiotherapy.

Current State of Image Guidance in Radiation Oncology: Implications for PTV Margin Expansion and Adaptive Therapy

Image guidance technology has evolved and seen widespread application in the past several decades. Advancements in the diagnostic imaging field have found new applications in radiation oncology and promoted the development of therapeutic devices with advanced imaging capabilities. A recent example is the development of linear accelerators that offer magnetic resonance imaging for real-time imaging and online adaptive planning. Volumetric imaging, in particular, offers more precise localization of soft tissue targets and critical organs which reduces setup uncertainty and permit the use of smaller setup margins. We present a review of the status of current imaging modalities available for radiation oncology and its impact on target margins and use for adaptive therapy.

Error analysis of applicator position for combined internal/external radiation therapy in cervical cancer

The aim of this study was to analyze the error variation in the applicator placement during the first and second radiotherapy session for cervical cancer. We recruited 22 patients with cervical cancer treated with radiotherapy. According to the image output in the first and second CT-Sim inspection, we conducted comparative analysis of image fusion to accurately measure the errors in applicator position in the horizontal (X-), longitudinal (Y-) and vertical (Z)-axes. The calibration processing was implemented in accordance with the data error measured and the location parameters, such as the angle and depth of the applicator. Electronic portal imaging technology (EPID) was used to calibrate posture change amplitude for the extracorporeal irradiation of patients, and dynamic measurement with applicator position was used to describe the error of the parameters. Finally, the data from two measurements in CT-Sim, digital reconstruction radiography (DRR) and EPID were compared. After calibration, the mean value of error of the applicator were significantly smaller. Image registration planning for error parameter calibration of applicator position can effectively reduce the applied horizontal spatial position error in radiotherapy treatment, and improve the accuracy and effectiveness during treatment.

LEFMIS: locally-oriented evaluation framework for medical image segmentation algorithms

This article proposes a novel framework for the locally-oriented evaluation of segmentation algorithms (LEFMIS). The presented approach is robust and takes into account local inter/intra-observer variability and the anisotropy of medical images. What is more, the framework makes it possible to distinguish types of error locally. These features are crucial in the context of cancer image data. The proposed framework is based on use of the signed anisotropic Euclidean distance transform and the distance projection. It can be used easily in many different applications with or without additional expert outlines (both inter- and intra-observer variability). The performance of the proposed framework is depicted using both artificial and kidney cancer CT data with experts' manual outlines. In the article, in the case of artificial data, it is presented that the manual outlines dispersion is symmetric in relation to the truth border. The effectiveness of the selected segmentation algorithm was analysed in the context of kidney cancer using computed tomography data. For the calculated local inter-observer variability, 80.11% of the surface points generated by the kidney segmentation algorithm are within one expert outline standard deviation and 97.96% are within five. An error distribution shift in the direction of type I error equivalent was also observed. Finally, the significance of the local estimation of error type differences is presented. The article shows the greater usefulness and flexibility of the proposed framework in comparison to the state-of-the-art methods. The exemplary usage of the LEFMIS with or without inter-/intra-observer variability is also presented.

Current Applications and Future Impact of Machine Learning in Radiology

Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed.

Biological imaging for individualized therapy in radiation oncology: part I physical and technical aspects

Recently, there has been an increase in the imaging modalities available for radiotherapy planning and radiotherapy prognostic outcome: dual energy computed tomography (CT), dynamic contrast enhanced CT, dynamic contrast enhanced magnetic resonance imaging (MRI), diffusion-weighted MRI, positron emission tomography-CT, dynamic contrast enhanced ultrasound, MR spectroscopy and positron emission tomography-MR. These techniques enable more precise gross tumor volume definition than CT alone and moreover allow subvolumes within the gross tumor volume to be defined which may be given a boost dose or an individual voxelized dose prescription may be derived. With increased plan complexity care must be taken to immobilize the patient in an accurate and reproducible manner. Moreover the physical and technical limitations of the entire treatment planning chain need to be well characterized and understood, interdisciplinary collaboration ameliorated (physicians and physicists within nuclear medicine, radiology and radiotherapy) and image protocols standardized.

Improving oncoplastic breast tumor bed localization for radiotherapy planning using image registration algorithms

Knowledge about tumor bed localization and its shape analysis is a crucial factor for preventing irradiation of healthy tissues during supportive radiotherapy and as a result, cancer recurrence. The localization process is especially hard for tumors placed nearby soft tissues, which undergo complex, nonrigid deformations. Among them, breast cancer can be considered as the most representative example. A natural approach to improving tumor bed localization is the use of image registration algorithms. However, this involves two unusual aspects which are not common in typical medical image registration: the real deformation field is discontinuous, and there is no direct correspondence between the cancer and its bed in the source and the target 3D images respectively. The tumor no longer exists during radiotherapy planning. Therefore, a traditional evaluation approach based on known, smooth deformations and target registration error are not directly applicable. In this work, we propose alternative artificial deformations which model the tumor bed creation process. We perform a comprehensive evaluation of the most commonly used deformable registration algorithms: B-Splines free form deformations (B-Splines FFD), different variants of the Demons and TV-L¹ optical flow. The evaluation procedure includes quantitative assessment of the dedicated artificial deformations, target registration error calculation, 3D contour propagation and medical experts visual judgment. The results demonstrate that the currently, practically applied image registration (rigid registration and B-Splines FFD) are not able to correctly reconstruct discontinuous deformation fields. We show that the symmetric Demons provide the most accurate soft tissues alignment in terms of the ability to reconstruct the deformation field, target registration error and relative tumor volume change, while B-Splines FFD and TV-L¹ optical flow are not an appropriate choice for the breast tumor bed localization problem, even though the visual alignment seems to be better than for the Demons algorithm. However, no algorithm could recover the deformation field with sufficient accuracy in terms of vector length and rotation angle differences.

Autodelineation of cervical cancers using multiparametric magnetic resonance imaging and machine learning

BACKGROUND

Tumour delineation is a challenging, time-consuming and complex part of radiotherapy planning. In this study, an automatic method for delineating locally advanced cervical cancers was developed using a machine learning approach.

MATERIALS AND METHODS

A method for tumour segmentation based on image voxel classification using Fisher?s Linear Discriminant Analysis (LDA) was developed. This was applied to magnetic resonance (MR) images of 78 patients with locally advanced cervical cancer. The segmentation was based on multiparametric MRI consisting of T2- weighted (T2w), T1-weighted (T1w) and dynamic contrast-enhanced (DCE) sequences, and included intensity and spatial information from the images. The model was trained and assessed using delineations made by two radiologists.

RESULTS

Segmentation based on T2w or T1w images resulted in mean sensitivity and specificity of 94% and 52%, respectively. Including DCE-MR images improved the segmentation model?s performance significantly, giving mean sensitivity and specificity of 85?93%. Comparisons with radiologists? tumour delineations gave Dice similarity coefficients of up to 0.44.

CONCLUSION

Voxel classification using a machine learning approach is a flexible and fully automatic method for tumour delineation. Combining all relevant MR image series resulted in high sensitivity and specificity. Moreover, the presented method can be extended to include additional imaging modalities.

Dimethylfumarate induces cell cycle arrest and apoptosis via regulating intracellular redox systems in HeLa cells

Dimethylfumarate (DMF) is cytotoxic to several kinds of cells and serves as an anti-tumor drug. This study was designed to investigate the effects and underlying mechanism of DMF on cervical cancer cells. HeLa cells were cultured and treated with 0, 50, 100, 150, and 200 μM DMF, respectively. After 24 h, cell growth was evaluated using Cell Counting Kit-8 (CCK-8) assay and the cell cycle was examined using flow cytometry. In addition, cell apoptosis was detected by Annexin V/propidium iodide (PI) staining and the expressions of caspase-3 and poly-ADP-ribose polymerase (PARP) were detected using western blotting. The redox-related factors were then assessed. Furthermore, all of the indicators were detected in HeLa cells after combined treatment of DMF and N-acetyl-L-cysteine (NAC, an oxygen-free radical scavenger). The cell number and cell growth of HeLa were obviously inhibited by DMF in a dose-dependent manner, as the cell cycle was arrested at G0/G1 phase (P < 0.05). The apoptotic HeLa cells were markedly increased, and the expression levels of caspase-3 and PARP were significantly increased in a DMF concentration-dependent way (P < 0.05). Meanwhile, loss of △Ψm, increase in reactive oxygen species and O₂^·-, and the decrease in catalase activity and glutathione (GSH) level were found after DMF treatment (P < 0.05). All these changes were significantly attenuated and even completely disappeared by adding NAC (P < 0.05). In conclusion, the cytotoxicity of DMF on cell proliferation and apoptosis of HeLa cells was mainly related to the intracellular redox systems by depletion of intracellular GSH.