Automated deep learning-based segmentation of COVID-19 lesions from chest computed tomography images.

Purpose: The novel coronavirus COVID-19, which spread globally in late December 2019, is a global health crisis. Chest computed tomography (CT) has played a pivotal role in providing useful information for clinicians to detect COVID-19. However, segmenting COVID-19-infected regions from chest CT results is challenging. Therefore, it is desirable to develop an efficient tool for automated segmentation of COVID-19 lesions using chest CT. Hence, we aimed to propose 2D deep-learning algorithms to automatically segment COVID-19-infected regions from chest CT slices and evaluate their performance. Material and methods: Herein, 3 known deep learning networks: U-Net, U-Net++, and Res-Unet, were trained from scratch for automated segmenting of COVID-19 lesions using chest CT images. The dataset consists of 20 labelled COVID-19 chest CT volumes. A total of 2112 images were used. The dataset was split into 80% for training and validation and 20% for testing the proposed models. Segmentation performance was assessed using Dice similarity coefficient, average symmetric surface distance (ASSD), mean absolute error (MAE), sensitivity, specificity, and precision. Results: All proposed models achieved good performance for COVID-19 lesion segmentation. Compared with Res-Unet, the U-Net and U-Net++ models provided better results, with a mean Dice value of 85.0%. Compared with all models, U-Net gained the highest segmentation performance, with 86.0% sensitivity and 2.22 mm ASSD. The U-Net model obtained 1%, 2%, and 0.66 mm improvement over the Res-Unet model in the Dice, sensitivity, and ASSD, respectively. Compared with Res-Unet, U-Net++ achieved 1%, 2%, 0.1 mm, and 0.23 mm improvement in the Dice, sensitivity, ASSD, and MAE, respectively. Conclusions: Our data indicated that the proposed models achieve an average Dice value greater than 84.0%. Two-dimensional deep learning models were able to accurately segment COVID-19 lesions from chest CT images, assisting the radiologists in faster screening and quantification of the lesion regions for further treatment. Nevertheless, further studies will be required to evaluate the clinical performance and robustness of the proposed models for COVID-19 semantic segmentation.

A historical literature review on the role of posterior axillary boost field in the axillary lymph node coverage and development of lymphedema following regional nodal irradiation in breast cancer.

To elucidate whether (1) a posterior axillary boost (PAB) field is an optimal method to target axillary lymph nodes (LNs); and (2) the addition of a PAB increases the incidence of lymphedema, a systematic review was undertaken. A literature search was performed in the PubMed database. A total of 16 studies were evaluated. There were no randomized studies. Seven articles have investigated dosimetric aspects of a PAB. The remaining 9 articles have determined the effect of a PAB field on the risk of lymphedema. Only 2 of 9 articles have prospectively reported the impact of a PAB on the risk of lymphedema development. There are conflicting reports on the necessity of a PAB. The PAB field provides a good coverage of level I/II axillary LNs because these nodes are usually at a greater depth. The main concern regarding a PAB is that it produces a hot spot in the anterior region of the axilla. Planning studies optimized a traditional PAB field. Prospective studies and the vast majority of retrospective studies have reported the use of a PAB field does not result in increasing the risk of lymphedema development over supraclavicular-only field. The controversies in the incidence of lymphedema suggest that field design may be more important than field arrangement. A key factor regarding the use of a PAB is the depth of axillary LNs. The PAB field should not be used unless there is an absolute indication for its application. Clinicians should weigh lymphedema risk in individual patients against the limited benefit of a PAB, in particular after axillary dissection. The testing of the inclusion of upper arm lymphatics in the regional LN irradiation target volume, and universal methodology measuring lymphedema are all areas for possible future studies.

Effectiveness of rectal displacement devices during prostate external-beam radiation therapy: A review.

Dose-escalated prostate radiotherapy (RT) can improve treatment outcomes, but rectal toxicity is the main limiting factor for introducing dose-escalated RT. Pushing rectal wall away from the prostate reduces the volume of the rectum in high-dose region, which can decrease both short- and long-term rectal toxicities after RT. This review focuses on the literature using different rectal displacement devices such as endorectal balloons, tissue spacers, rectal retractor, and ProSpare during prostate External beam radiotherapy, with regard to dosimetric effects, clinical benefits, prostate motion, and postoperative RT setting.

Rectal wall sparing effect of a rectal retractor in prostate intensity-modulated radiotherapy.

PURPOSE: The objective of the study was to evaluate the effectiveness of a rectal retractor (RR) designed to protect rectal tissue in intensity-modulated radiotherapy (IMRT) by pushing rectal wall (RW) away from the prostate. MATERIALS AND METHODS: Twelve patients with localized prostate cancer were enrolled into this study. Patients underwent two computed tomography (CT) scans without and with RR. A prescription of 80 Gy in 40 fractions was planned on CT scans with and without RR. This study evaluates the ability of the RR in RW dose reduction, in particular reduction of the RW V70Gy≥ 25% in comparison with the plan without RR dose-volume histograms were generated with and without RR. The patient's tolerance was assessed by patient-reported outcomes. RESULTS: The planning target volume coverage was equal for both without and with RR (P = 0.155). The mean dose to the RW was statistically significantly lower for the plan with RR than that for the plan without RR, a mean reduction of 5.8 Gy (P = 0.003). Significant relative reductions in rectal dose-volume parameters whether in absolute volume (cc) or as a percentage of contoured RW were detected. A relative reduction more than 25% in RW V70Gy(%) in 100% of patients was achieved. The rectal retraction resulted in a significant increase in the prostate to the rectum space at the prostate midgland level, an absolute increase of 2.7 mm. The retraction of the rectum induced a mean (±standard deviation) pain score of 2.7 (±1.3) according to the visual analog score. CONCLUSION: The application of a RR showed a remarkable rectal sparing effect during prostate IMRT. This may lead to reduced acute and late rectal toxicities in prostate IMRT.

A comparison of skin dose estimation between thermoluminescent dosimeter and treatment planning system in prostatic cancer: A brachytherapy technique.

Aims: This study aimed to compare the skin dose calculated by treatment planning system (TPS) and measured with thermoluminescent dosimeters (TLDs) in brachytherapy of prostatic cancer to show the skin TLD dosimetry as an appropriate quality assurance procedure for TPS dose calculations. Methods: The skin dose of 15 patients with prostatic cancer treated by high dose rate brachytherapy technique was assessed by two types of TLD dosimeters (GR-200 and TLD-100). The TLDs were placed on the patient's skin at three different points (anterior, left, and right) using five TLDs for each point. The dose values of TLDs and TPS were compared using paired t-test and the percentages of difference were reported. Results: There was a good agreement between TPS calculations and TLDs measurements for both of the GR-200 and TLD-100 dosimeters. The mean skin dose values for anterior, left, and right points were 65.06±21.88, 13.88±4.1, and 10.05±4.39 cGy, respectively, for TPS. These values were 65.70±23.2, 14.51±4.3, and 10.54±5 cGy for GR-200, and 64.22±23.5, 13.43±4.4, and 9.99±4.1 cGy for TLD-100, respectively. Conclusion: The TPS skin dose calculations in brachytherapy of prostatic cancer had a good agreement with the TLD-100 and GR-200 measurements at the three different points on patients' skin. TLD-100 had lower differences with TPS calculations compared to GR-200. Relevance for Patients: The outcome of this research shows that for people with prostatic cancer, TPS can estimate accurately the skin dose of different points including anterior, left, and right in brachytherapy technique.

Evaluation of lung heterogeneity effects on dosimetric parameters in small photon fields using MAGIC polymer gel, Gafchromic film, and Monte Carlo simulation.

In this work, the performance of MAGIC polymer gel in measuring dosimetric parameters beyond lung heterogeneity in small fields was investigated. All data were obtained using MAGIC, EBT2, and MC in four small field sizes. The maximum local differences between MAGIC and MC were less than 5.1, 3.9, 3.1, and 2.6% for PDD values behind lung heterogeneity at 5, 10, 20, and 30 mm field sizes, respectively. The findings showed that MAGIC is a suitable tool for dosimetry behind low-density heterogeneity.

Different Dosimeters/Detectors Used in Small-Field Dosimetry: Pros and Cons.

With the advent of complex and precise radiation therapy techniques, the use of relatively small fields is needed. Using such field sizes can cause uncertainty in dosimetry; therefore, special attention is required both in dose calculations and measurements. There are several challenges in small-field dosimetry such as the steep gradient of the radiation field, volume averaging effect, lack of charged particle equilibrium, partial occlusion of radiation source, beam alignment, and unable to use a reference dosimeter. Due to these challenges, special dosimeters are needed for small-field dosimetry, and this review article discusses this topic.

Design of a slab phantom for breast dosimetry applications.

BACKGROUND: Design of phantoms for use in radiotherapy should consider the complex geometry of breast tissue and inhomogeneity. The aim of this study is design of a slab phantom for breast dosimetry applications. MATERIALS AND METHODS: In this study, an anatomical slab phantom was designed with cork lung inhomogeneity and plexi colored heart part, also describes the different size of breast and chest wall phantom that have been designed and constructed for dosimetry. Three size different phantoms have been manufactured that installed in one trunk, as "small," "medium," and "large," two breast size fixed and one size was movable on a chest wall phantom. Two different dosimeters selected to dosimetry in this phantom, film was chosen for this dosimetry since it provides good spatial resolution and suitable for two-dimensional dosimetry also measure dose distribution used a point dosimetry with thermoluminescent dosimeter (TLD). RESULTS: The results were shown near date due to either software or phantom calculation. CONCLUSION: Application include assessment dose in the junction region between the tangential fields and the supraclavicular fossa field, as well as assess dose in inhomogeneities, the phantom were formed from a variety of tissue substitute materials.