Multi-modal trained artificial intelligence solution to triage chest X-ray for COVID-19 using pristine ground-truth, versus radiologists.

The front-line imaging modalities computed tomography (CT) and X-ray play important roles for triaging COVID patients. Thoracic CT has been accepted to have higher sensitivity than a chest X-ray for COVID diagnosis. Considering the limited access to resources (both hardware and trained personnel) and issues related to decontamination, CT may not be ideal for triaging suspected subjects. Artificial intelligence (AI) assisted X-ray based application for triaging and monitoring require experienced radiologists to identify COVID patients in a timely manner with the additional ability to delineate and quantify the disease region is seen as a promising solution for widespread clinical use. Our proposed solution differs from existing solutions presented by industry and academic communities. We demonstrate a functional AI model to triage by classifying and segmenting a single chest X-ray image, while the AI model is trained using both X-ray and CT data. We report on how such a multi-modal training process improves the solution compared to single modality (X-ray only) training. The multi-modal solution increases the AUC (area under the receiver operating characteristic curve) from 0.89 to 0.93 for a binary classification between COVID-19 and non-COVID-19 cases. It also positively impacts the Dice coefficient (0.59 to 0.62) for localizing the COVID-19 pathology. To compare the performance of experienced readers to the AI model, a reader study is also conducted. The AI model showed good consistency with respect to radiologists. The DICE score between two radiologists on the COVID group was 0.53 while the AI had a DICE value of 0.52 and 0.55 when compared to the segmentation done by the two radiologists separately. From a classification perspective, the AUCs of two readers was 0.87 and 0.81 while the AUC of the AI is 0.93 based on the reader study dataset. We also conducted a generalization study by comparing our method to the-state-art methods on independent datasets. The results show better performance from the proposed method. Leveraging multi-modal information for the development benefits the single-modal inferencing.

Individually selected teletherapy technique for accelerated partial breast irradiation.

BACKGROUND: The aim of the study was to individualize accelerated partial breast irradiation based on optimal dose distribution, protect risk organ and predict most advantageous technique. MATERIALS AND METHODS: 138 breast cancer patients receiving postoperative APBI were enrolled. APBI plans were generated using 3D-conformal (3D-CRT), sliding window intensity-modulated radiotherapy (IMRT) and volumetric-modulated arc therapy (VMAT). In the case of superficial tumours, additional plans were developed by adding electron beam. To planning target volume (PTV) 37.5 Gy/10 fractions, 1 fraction/day was prescribed. A novel plan quality index (PQI) served as the basis for comparisons. RESULTS: IMRT was the most advantageous technique regarding homogeneity. VMAT provided best conformity, 3D-CR T - the lowest lung and heart exposure. PQI was the best in 45 (32.61%) VMAT, 13 (9.42%) IMRT, 9 (6.52%) 3D-CRT plans. In 71 cases (51.45%) no difference was detected. In patients with large PTV, 3D-CRT was the most favourable. Additional electron beam improved PQI of 3D-CRT plans but had no meaningful effect on IMRT or VMAT. IMRT was superior to VMAT if the tumour was superficial (p < 0.001), situated in the medial (p = 0.032) or upper quadrant (p = 0.046). CONCLUSIONS: In half of all cases, individually selected teletherapy techniques provide superior results over others; relevance of a certain technique may be predicted by volume and PTV localization.

Adaptive Radiotherapy for Glioblastoma Multiforme - The Impact on Disease Outcome.

BACKGROUND/AIM: To study the changes of glioblastoma multiforme during chemoradiotherapy (CRT) and to evaluate the impact of changes on dosimetry and clinical outcomes. PATIENTS AND METHODS: Forty-three patients underwent volumetric imaging-based replanning. Prognostic factors and gross tumor volume changes in relation to overall survival and the effect of adaptive replanning were statistically analyzed. RESULTS: Patients with total tumor removal, with shorter time to CRT (<27 days), with methylated O-6 methylguanine DNA methyltransferase and good performance status (>60%) had better survival. Tumor shrinkage in 24 patients resulted in improved survival compared to 19 in whom tumor was unchanged or progressed (25.3 vs. 11.1 months, p=0.04). Adapted planning target volume allowed a reduction in irradiated volume, while increasing survival (12.06 vs. 28.98 months, p=0.026). CONCLUSION: Tumor response during CRT has significant impact on the outcome. Adaptation of the planning target volume to the tumor changes proved to be beneficial and warrants further investigation.

Low Fraction Size Re-irradiation for Large Volume Recurrence of Glial Tumours.

The aim of the present study was to evaluate the efficacy of re-irradiation (re-RT) in patients with advanced local relapses of glial tumours and to define the factors influencing the result of the hyper-fractionated external beam therapy on progression after primary management. We have analysed the data of 55 patients with brain tumours (GBM: 28) on progression, who were re-irradiated between January 2007 and December 2018. The mean volume of the recurrent tumour was 118 cm3, and the mean planning target volume (PTV) was 316 cm3, to which 32 Gy was delivered in 20 fractions at least 7.7 months after the first radiotherapy, using 3D conformal radiotherapy (CRT) or intensity modulated radiotherapy (IMRT). The median overall survival (mOS) from the re-RT was 8.4 months, and the 6-month and the 12-month OS rate was 64% and 31%, respectively. The most important factors by univariate analysis, which significantly improved the outcome of re-RT were the longer time interval between the diagnosis and second radiotherapy (p = 0.029), the lower histology grade (p = 0.034), volume of the recurrent tumour (p = 0.006) and Karnofsky performance status (KPS) (p = 0.009) at the re-irradiation. Our low fraction size re-irradiation ≥ 8 months after the first radiotherapy proved to be safe and beneficial for patients with large volume recurrent glial tumours.

Subventricular zone volumetric and dosimetric changes during postoperative brain tumor irradiation and its impact on overall survival.

PURPOSE: The aim of this retrospective study was to investigate the relationship between the dose to the subventricular zone (SVZ) and overall survival (OS) of 41 patients with glioblastoma multiforme (GBM), who were treated with an adaptive approach involving repeated topometric CT and replanning at two-thirds (40 Gy) of their course of postoperative radiotherapy for planning of a 20 Gy boost. METHODS: We examined changes in the ipsilateral lateral ventricle (LV) and SVZ (iLV and iSVZ), as well as in the contralateral LV and SVZ (cLV and cSVZ). We evaluated the volumetric changes on both planning CT scans (primary CT1 and secondary CT2). The survival of the GBM patients was analyzed using the Kaplan-Meier method; the multivariate Cox regression was also performed. RESULTS: Median follow-up and OS were 34.5 months and 17.6 months, respectively. LV and SVZ structures exhibited significant volumetric changes on CT2, resulting in an increase of dose coverage. At a cut-off point of 58 Gy, a significant correlation was detected between the iSVZ2 mean dose and OS (27.8 vs 15.6 months, p = 0.048). In a multivariate analysis, GBM patients with a shorter time to postoperative chemoradiotherapy (<3.8 weeks), with good performance status (≥70%) and higher mean dose (≥58 Gy) to the iSVZ2 had significantly better OS. CONCLUSIONS: Significant anatomical and dose distribution changes to the brain structures were observed, which have a relevant impact on the dose-effect relationship for GBM; therefore, involving the iSVZ in the target volume should be considered and adapted to the changes.

A simple clinical method for predicting the benefit of prone vs. supine positioning in reducing heart exposure during left breast radiotherapy.

BACKGROUND AND PURPOSE: The benefit of reduced radiation heart exposure in the prone vs. supine position individually differs. In this prospective cohort study, the goal was to develop a simple method for the operation of a validated model for the prediction of preferable treatment position during left breast radiotherapy. MATERIAL AND METHODS: In 100 cases, a single CT slice was utilized for the collection of the needed patient-specific data (in addition to body mass index, the distance of the LAD from the chest wall and the area of the heart included in the radiation fields at the middle of the heart in the supine position). Outcome was analyzed in relation to the full CT series acquired in both positions and dosimetric data. RESULTS: Great consistency was found between the tested and original method regarding sensitivity and specificity. The prioritization of LAD dose, and the use of heart dose and position-specific dose constraints as safety measures ensure sensitivity and specificity values of 82.8% and 87.3%, respectively. In an additional "routine clinical practice" series of 60 patients the new method seemed feasible in routine clinical practice. External testing on a 28-case series indicated similar accuracy. CONCLUSION: We consider this simple clinical tool appropriate for assisting individual positioning aiming at maximum heart protection during left breast irradiation.

Daily Setup Accuracy, Side-effects and Quality of Life During and After Prone Positioned Prostate Radiotherapy.

BACKGROUND/AIM: Exposure of organs at risk with prostate radiotherapy (RT) is lower in the prone position. This study is a prospective evaluation of setup accuracy, side-effects, and quality of life (QOL) during and after prone positioned RT. PATIENTS AND METHODS: Image-guided (IG) intensity-modulated (IM) RT was administered in prone position on belly-board to 55 high-risk prostate cancer (PC) patients. Rectum diameters were measured in two areas of the symphysis at the beginning of RT and during it. Side-effects, QOL, and prostate specific symptoms (PSS) were evaluated. RESULTS: Setup accuracy was similar to that reported in the literature. In the upper area of symphysis rectal diameters were significantly changed during treatment, but in the prostate region, no difference was detected. No change was detected in patients' QOL and PSS during treatment, but after RT, they improved. CONCLUSION: Prone positioned IG-IMRT is feasible with tolerable side-effects for high-risk PC patients. Changes in QOL and PSS are insignificant during RT, while improvement after RT suggests a rapid recovery.