Review of Deep Learning Based Autosegmentation for Clinical Target Volume: Current Status and Future Directions.

Purpose: Manual contour work for radiation treatment planning takes significant time to ensure volumes are accurately delineated. The use of artificial intelligence with deep learning based autosegmentation (DLAS) models has made itself known in recent years to alleviate this workload. It is used for organs at risk contouring with significant consistency in performance and time saving. The purpose of this study was to evaluate the performance of present published data for DLAS of clinical target volume (CTV) contours, identify areas of improvement, and discuss future directions. Methods and Materials: A literature review was performed by using the key words "deep learning" AND ("segmentation" or "delineation") AND "clinical target volume" in an indexed search into PubMed. A total of 154 articles based on the search criteria were reviewed. The review considered the DLAS model used, disease site, targets contoured, guidelines used, and the overall performance. Results: Of the 53 articles investigating DLAS of CTV, only 6 were published before 2020. Publications have increased in recent years, with 46 articles published between 2020 and 2023. The cervix (n = 19) and the prostate (n = 12) were studied most frequently. Most studies (n = 43) involved a single institution. Median sample size was 130 patients (range, 5-1052). The most common metrics used to measure DLAS performance were Dice similarity coefficient followed by Hausdorff distance. Dosimetric performance was seldom reported (n = 11). There was also variability in specific guidelines used (Radiation Therapy Oncology Group (RTOG), European Society for Therapeutic Radiology and Oncology (ESTRO), and others). DLAS models had good overall performance for contouring CTV volumes for multiple disease sites, with most studies showing Dice similarity coefficient values >0.7. DLAS models also delineated CTV volumes faster compared with manual contouring. However, some DLAS model contours still required at least minor edits, and future studies investigating DLAS of CTV volumes require improvement. Conclusions: DLAS demonstrates capability of completing CTV contour plans with increased efficiency and accuracy. However, most models are developed and validated by single institutions using guidelines followed by the developing institutions. Publications about DLAS of the CTV have increased in recent years. Future studies and DLAS models need to include larger data sets with different patient demographics, disease stages, validation in multi-institutional settings, and inclusion of dosimetric performance.

Survival benefit of local consolidative therapy for patients with single-organ metastatic pancreatic cancer: a propensity score-matched cross-sectional study based on 17 registries.

Background: The continuous exploration of oligometastatic disease has led to the remarkable achievements of local consolidative therapy (LCT) and favorable outcomes for this disease. Thus, this study investigated the potential benefits of LCT in patients with single-organ metastatic pancreatic ductal adenocarcinoma (PDAC). Methods: Patients with single-organ metastatic PDAC diagnosed between 2010 - 2019 were identified from the Surveillance, Epidemiology, and End Results (SEER) database. Propensity score matching (PSM) was performed to minimize selection bias. Factors affecting survival were assessed by Cox regression analysis and Kaplan-Meier estimates. Results: A total of 12900 patients were identified from the database, including 635 patients who received chemotherapy combined with LCT with a 1:1 PSM with patients who received only chemotherapy. Patients with single-organ metastatic PDAC who received chemotherapy in combination with LCT demonstrated extended median overall survival (OS) by approximately 57%, more than those who underwent chemotherapy alone (11 vs. 7 months, p < 0.001). Furthermore, the multivariate Cox regression analysis revealed that patients that received LCT, younger age (< 65 years), smaller tumor size (< 50 mm), and lung metastasis (reference: liver) were favorable prognostic factors for patients with single-organ metastatic PDAC. Conclusion: The OS of patients with single-organ metastatic pancreatic cancer who received LCT may be prolonged compared to those who received only chemotherapy. Nevertheless, additional prospective randomized clinical trials are required to support these findings.

Review of cone beam computed tomography based online adaptive radiotherapy: current trend and future direction.

Adaptive radiotherapy (ART) was introduced in the late 1990s to improve the accuracy and efficiency of therapy and minimize radiation-induced toxicities. ART combines multiple tools for imaging, assessing the need for adaptation, treatment planning, quality assurance, and has been utilized to monitor inter- or intra-fraction anatomical variations of the target and organs-at-risk (OARs). Ethos™ (Varian Medical Systems, Palo Alto, CA), a cone beam computed tomography (CBCT) based radiotherapy treatment system that uses artificial intelligence (AI) and machine learning to perform ART, was introduced in 2020. Since then, numerous studies have been done to examine the potential benefits of Ethos™ CBCT-guided ART compared to non-adaptive radiotherapy. This review will explore the current trends of Ethos™, including improved CBCT image quality, a feasible clinical workflow, daily automated contouring and treatment planning, and motion management. Nevertheless, evidence of clinical improvements with the use of Ethos™ are limited and is currently under investigation via clinical trials.

Improvement in plan quality after Implementation of clinical goals in a large network of cancer centers.

Clinical Goals (CG) is a tool available in the Varian Eclipse planning system to objectively and visually evaluate the quality of treatment plans based upon user-defined dose-volume parameters. We defined a set of CG for Stereotactic Radiosurgery (SRS) and Intensity-Modulated Radiotherapy (IMRT) based on published data and guidelines and implemented this in a network of cancer centers in India (American Institute of Oncology). A dosimetric study was performed to compare brain SRS and breast IMRT plan quality before and after CG implementation.The CG defined for SRS plans were target V100% ≥ 98%, dose gradient measure (GM) ≤ 0.5 cm, conformity index (CI) 1.0 to 1.2. For breast IMRT plans, CG defined target V100% ≥ 97%, V95% ≥ 95%, V107% ≤ 2%, V105% ≤ 10%, and Dmax ≤ 2.4 Gy. Dose limits to organs-at-risk (OAR) were summarize in supplemental materials. Twenty brain SRS and 10 breast IMRT treatment plans that were previously delivered on patients were selected and re-planned using CG. The pre and postoptimized plan parameters were compared using student t-tests.For brain SRS plans, the V100, GM, and CI for the pre- and post-Clinical-Goals plans were 93.22% ± 7.2% vs 97.96% ± 0.29% (p = 0.009), 0.63 ± 0.16 vs 0.42 ± 0.05 (p < 0.001) and 1.07 ± 0.18 vs 1.06 ± 0.06 (p = 0.79), respectively. There were no differences in max dose to OARs. In breast IMRT plans, the target V107% for pre and postimplemented plans were 16.50% ± 10.98% vs 0.32% ± 0.32%, respectively (p = 0.001). The average target V105% were 44.00% ± 15.72% and 8.69% ± 4.53%, respectively (p < 0.001). No differences were found in the average target V100% (p = 0.128) and V95% (p = 0.205). The average target Dmax were 112.28% ± 1.59% and 109.14% ± 0.73%, respectively (p < 0.001). There were only minor differences in doses to OARs.The implementation of CG in Varian Eclipse significantly improved SRS and IMRT plan quality with enhanced coverage, dose GM, and CI without increased dose to OARs.

RapidPlan hippocampal sparing whole brain model version 2-how far can we reduce the dose?

Whole-brain radiotherapy has been the standard palliative treatment for patients with brain metastases due to its effectiveness, availability, and ease of administration. Recent clinical trials have shown that limiting radiation dose to the hippocampus is associated with decreased cognitive toxicity. In this study, we updated an existing Knowledge Based Planning model to further reduce dose to the hippocampus and improve other dosimetric plan quality characteristics. Forty-two clinical cases were contoured according to guidelines. A new dosimetric scorecard was created as an objective measure for plan quality. The new Hippocampal Sparing Whole Brain Version 2 (HSWBv2) model adopted a complex recursive training process and was validated with five additional cases. HSWBv2 treatment plans were generated on the Varian HalcyonTM and TrueBeamTM systems and compared against plans generated from the existing (HSWBv1) model released in 2016. On the HalcyonTM platform, 42 cases were re-planned. Hippocampal D100% from HSWBv2 and HSWBv1 models had an average dose of 5.75 Gy and 6.46 Gy, respectively (p < 0.001). HSWBv2 model also achieved a hippocampal Dmean of 7.49 Gy, vs 8.10 Gy in HSWBv1 model (p < 0.001). Hippocampal D0.03CC from HSWBv2 model was 9.86 Gy, in contrast to 10.57 Gy in HSWBv1 (p < 0.001). For PTV_3000, D98% and D2% from HSWBv2 model were 28.27 Gy and 31.81 Gy, respectively, compared to 28.08 Gy (p = 0.020) and 32.66 Gy from HSWBv1 (p < 0.001). Among several other dosimetric quality improvements, there was a significant reduction in PTV_3000 V105% from 35.35% (HSWBv1) to 6.44% (HSWBv2) (p < 0.001). On 5 additional validation cases, dosimetric improvements were also observed on TrueBeamTM. In comparison to published data, the HSWBv2 model achieved higher quality hippocampal avoidance whole brain radiation therapy treatment plans through further reductions in hippocampal dose while improving target coverage and dose conformity/homogeneity. HSWBv2 model is shared publicly.

Placenta Percreta Complications.

Placenta percreta is the most severe form of placenta accreta and is characterized by placental invasion through the entirety of the myometrium and possibly into extrauterine tissues. It is associated with prior cesarean deliveries and placenta previa. Herein, we present the case of a patient who developed placenta percreta and experienced massive blood loss of 27 liters. She developed many complications over the next 11 months, including deep vein thrombosis, pulmonary embolism, preeclampsia after pregnancy, hematoma, blood clots in the bladder, lactation failure, ileus, vesicovaginal fistula, excessive scar tissue requiring surgery, loss of an ovary, and recurrent bladder perforation. We analyze the mechanisms of these complications and the most common complications associated with placenta percreta.

Retrohepatic Mass: A Case of Human Herpesvirus-8 Negative Multicentric Castleman's Disease.

Multicentric Castleman's disease (MCD) is a rare lymphoproliferative disorder with aggressive systemic presentation and poor prognosis. Here, we present a case of MCD in a 37-year-old Asian American woman with a past medical history of the polycystic ovarian syndrome (PCOS), human papilloma virus (HPV), herpes simplex virus-1 (HSV-1), iron deficiency, and vitamin B12 deficiency-related anemia. The patient underwent surgical resection with good recovery. Hemoglobin and erythrocyte sedimentation rate (ESR) normalized after surgical resection. Although the influence of risk factors such as human immunodeficiency virus (HIV) or human herpesvirus-8 (HHV-8) infections on MCD relapse are not well understood, patient education on MCD risk factors is important, as they may place the patient at greater risk for recurrence. MCD should be considered in patients with chronic inflammation and a mass on imaging.

A Tantalum Disulfide Charge-Density-Wave Stochastic Artificial Neuron for Emulating Neural Statistical Properties.

Artificial neuronal devices that functionally resemble biological neurons are important toward realizing advanced brain emulation and for building bioinspired electronic systems. In this Communication, the stochastic behaviors of a neuronal oscillator based on the charge-density-wave (CDW) phase transition of a 1T-TaS2 thin film are reported, and the capability of this neuronal oscillator to generate spike trains with statistical features closely matching those of biological neurons is demonstrated. The stochastic behaviors of the neuronal device result from the melt-quench-induced reconfiguration of CDW domains during each oscillation cycle. Owing to the stochasticity, numerous key features of the Hodgkin-Huxley description of neurons can be realized in this compact two-terminal neuronal oscillator. A statistical analysis of the spike train generated by the artificial neuron indicates that it resembles the neurons in the superior olivary complex of a mammalian nervous system, in terms of its interspike interval distribution, the time-correlation of spiking behavior, and its response to acoustic stimuli.

Assessing efficacy and safety of stereotactic body radiation therapy for oligometastatic non-small cell lung cancer with epidermal growth factor receptor (EGFR) wild type.

BACKGROUND: Stereotactic body radiation therapy (SBRT) is an emerging therapy for oligometastatic cancer. The aim of this study was to investigate the efficacy and safety of high-dose radiotherapy for primary and oligometastatic lesions in epidermal growth factor receptor (EGFR) wild-type non-small cell lung cancer (NSCLC). METHODS: A total of 40 EGFR wild-type oligometastatic NSCLC patients (defined as ≤5 metastases) treated with SBRT in our department between 2009 and 2016 were analyzed retrospectively. SBRT was delivered to the lesions with a median biologically effective dose at alpha/beta 10 (BED10) value of 102.7 Gy (range, 94.5-113.5 Gy). Primary endpoints including progression-free survival (PFS) and overall survival (OS) were estimated with the Kaplan-Meier method. Factors potentially affecting OS and PFS were evaluated by univariate and multivariate Cox-regression analyses. RESULTS: After a median follow-up of 39 months, the median OS observed in this study was 40 months (95% CI: 32.562-47.438 months). One-, 2-, and 3-year OS rates were 100.0%, 72.5%, and 62.5% respectively. Twenty-nine patients (72.5%) succumbed to tumor burden and median PFS was 13 months (range, 10.687-15.313 months). One-, 2-, and 3-year PFS rates were 65.0%, 10.0%, and 0% respectively. Multivariate analysis suggested Eastern Cooperative Oncology Group performance status (ECOG PS) <2 and high-dose radiation regimens were independent prognostic factors of longer OS (P<0.001 and 0.049, respectively), and patients receiving radiotherapy with BED10 ≥100 Gy showed a better PFS than those undergoing low dose (P=0.047). There were no patients of CTCAE v 5.0 grade 4-5 toxicity or treatment-related deaths. Grade 3 toxicity occurred in 2 (5.0%) patients and 36 (90.0%) patients experienced grade 1-2 adverse reactions. CONCLUSIONS: The current study suggested systemic chemotherapy combined with SBRT for pulmonary and metastatic lesions was feasible and tolerable to improve outcomes of EGFR wild-type oligometastatic NSCLC patients.

Fluoroscopy-Guided Percutaneous Sacroplasty for Painful Metastases at the Sacral Ala.

OBJECTIVE: Percutaneous sacroplasty (PSP) is widely used in the clinic for osteoporotic sacral insufficiency fractures; however, few reports have described the safety and effectiveness of PSP for painful sacral metastases at the sacral ala under fluoroscopy alone. We aimed to evaluate the safety and efficacy of fluoroscopy-guided PSP for painful metastases at the sacral ala. PATIENTS AND METHODS: Thirty-five consecutive patients (median age, 60.74 ± 12.74 years), with a total of 41 metastatic lesions at the sacral ala, were treated with PSP. The patients were followed up for periods ranging from 1 month to 30 months (average, 8.23 ± 6.75 months). The visual analog scale (VAS), Oswestry Disability Index (ODI), and Karnofsky Performance Scale (KPS) were used to evaluate pain, mobility, and quality of life before the procedure and at 3 days and 1, 3, 6, 12, and 18 months after the procedure. RESULTS: Technical success was achieved in all patients. The minimum follow-up duration was 1 month. The mean VAS scores declined significantly from 7.20 ± 0.93 before the procedure to 3.43 ± 1.38 by day 3 after the procedure, and was 3.13 ± 1.07 at 1 month, 3.17 ± 1.15 at 3 months, 2.91± 1.38 at 6 months, and 2.57 ± 1.51 at 12 months after the procedure (P < 0.001). After PSP, analgesic drug administration had been discontinued in 31 of 35 patients (88.57%). The ODI and KPS also changed after PSP, with significant differences between the baseline scores and those at each follow-up examination (P < 0.001). Extraosseous cement leakage occurred in 12 cases without any major clinical complications. CONCLUSION: PSP is a safe and effective technique for the palliative treatment of painful metastases involving the sacral ala under fluoroscopic guidance alone. It can relieve pain, reduce disability, and improve function, and is associated with minimal complications.

Application of Percutaneous Osteoplasty in Treating Pelvic Bone Metastases: Efficacy and Safety.

BACKGROUND: Percutaneous vertebroplasty has been a good option to treat vertebral metastases. The pelvic bone is a common site of spread for many cancers. Using follow-up data for 126 patients, we evaluated the safety and efficacy of percutaneous osteoplasty (POP) to treat pelvic bone metastases. MATERIALS AND METHODS: In this retrospective study, 126 patients (mean age 57.45 ± 11.46 years old) with 178 lesions were treated using POP. The visual analog scale (VAS), Oswestry Disability Index (ODI), and the changes in the patient's use of painkillers were used to evaluate pain and quality of life before the procedure, and at 3 days and 1, 3, 6, 9, and 12 months after the procedure. RESULTS: Technical success was achieved in all patients. The mean VAS scores decreased significantly from 6.87 ± 1.33 before the procedure to 3.33 ± 1.94 by day 3 after the procedure (P < 0.05), 2.26 ± 1.59 at 1 month (P < 0.05), 1.89 ± 1.53 at 3 months (P < 0.05), 1.87 ± 1.46 at 6 months (P < 0.05), 1.90 ± 1.47 at 9 months (P < 0.05), and 1.49 ± 1.17 at 12 months (P < 0.05). The ODI also changed after the procedure, with significant differences between baseline scores and at each follow-up examination (P < 0.05). Pain relief was achieved in 118 patients (93.65%); however, pain relief was not obvious in seven patients (5.56%), and pain was aggravated in one patient (0.79%). Extraosseous cement leakage occurred in 35 patients (27.78%) without causing any clinical complications. CONCLUSION: Percutaneous osteoplasty is a safe and effective choice for patients with painful osteolytic pelvic bone metastases. It can relieve pain, reduce disability, and improve function. LEVEL OF EVIDENCE: Level 3b, retrospective study.