Automated segmentation in pelvic radiotherapy: A comprehensive evaluation of ATLAS-, machine learning-, and deep learning-based models.

Artificial intelligence can standardize and automatize highly demanding procedures, such as manual segmentation, especially in an anatomical site as common as the pelvis. This study investigated four automated segmentation tools on computed tomography (CT) images in female and male pelvic radiotherapy (RT) starting from simpler and well-known atlas-based methods to the most recent neural networks-based algorithms. The evaluation included quantitative, qualitative and time efficiency assessments. A mono-institutional consecutive series of 40 cervical cancer and 40 prostate cancer structure sets were retrospectively selected. After a preparatory phase, the remaining 20 testing sets per each site were auto-segmented by the atlas-based model STAPLE, a Random Forest-based model, and two Deep Learning-based tools (DL), MVision and LimbusAI. Setting manual segmentation as the Ground Truth, 200 structure sets were compared in terms of Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and Distance-to-Agreement Portion (DAP). Automated segmentation and manual correction durations were recorded. Expert clinicians performed a qualitative evaluation. In cervical cancer CTs, DL outperformed the other tools with higher quantitative metrics, qualitative scores, and shorter correction times. On the other hand, in prostate cancer CTs, the performance across all the analyzed tools was comparable in terms of both quantitative and qualitative metrics. Such discrepancy in performance outcome could be explained by the wide range of anatomical variability in cervical cancer with respect to the strict bladder and rectum filling preparation in prostate Stereotactic Body Radiation Therapy (SBRT). Decreasing segmentation times can reduce the burden of pelvic radiation therapy routine in an automated workflow.

Lung optimized treatment with CyberKnife® in inoperable lung cancer patients: feasibility analysis of a mono-institutional 115 patient series.

CyberKnife® Lung Optimized Treatment (LOT) allows the treatment of lung cancer without invasive fiducial implantation. The aim of this retrospective analysis was to evaluate the feasibility, toxicity and clinical outcome. One hundred fifteen patients (124 lesions) were treated with CyberKnife® using LOT. The median age was 72.6 years (range 31.8-90.3). From 124 treated lesions, 52 were with histopathological confirmation (41 primitive pulmonary cancers, 8 pulmonary metastases) and 72 as untyped tumors. For 5 patients (6 lesions) treatment was an in-field re-irradiation. Concomitant therapy was administered in 7 patients. Zero-View tracking was applied in 69 patients, 1-View in 33 patients, 2-View in 22 patients. The median total dose was 45 Gy (range 18-54), median dose/fraction was 15 Gy (range 4-18) with a median prescription isodose of 80% (range 68-85). The median planning target volume (PTV) was 25 cm3 (range 3-195). The median follow-up was 20 months (range 7-47). Thirty-seven patients (32%) were alive with no evidence of disease, 39 patients (34%) were alive with clinically evident disease, and 38 patients (33%) died of the disease. The 1- and 2-year overall survival (OS) rate was 83% and 61%. The median time to progression was 19 months (95% confidence interval: 11-19 months), 1- and 2-year progression-free survival (PFS) rates were 62% and 41%, respectively. Smaller PTV was significantly associated with better OS, PFS and in-field PFS in univariate and multivariate analyses. Acute toxicity was observed in 36 patients (41%). Late toxicity was registered in 25 patients (29%). G3 late toxicity was observed in one patient (1.1%). Our data suggest that fiducial less-stereotactic body radiation therapy (SBRT) is a feasible, well-tolerated and potentially effective treatment with high compliance in the setting of inoperable patients due to concomitant disease or previous treatments.

Insuficiência cardiorrespiratória aguda por choque elétrico: estudo hemodinâmico invasivo / Acute cardiorespiratory insufficiency due to electric injury: invasive hemodynamic study

Case report on right branch block, acute pulmonary oedema and enteritis caused by electric shock in a boy. The invasive hemodynamic study showed primary pulmonary hypertension, cardiogenic shock, and acute respiratory failure. The outcome was good, with total and progressive recovery of all lesions. The literature review revealed the rarity of pulmonary oedema and enteritis after an electric shock. The invasive haemodynamic data suggest physiopathological explanations for findings in the case and indicate therapeutic measures for similar situations.

[Acute cardiorespiratory insufficiency due to electric injury: invasive hemodynamic study]. / Insuficiência cardiorrespiratória aguda por choque elétrico: estudo hemodinâmico invasivo.

Case report on right branch block, acute pulmonary oedema and enteritis caused by electric shock in a boy. The invasive hemodynamic study showed primary pulmonary hypertension, cardiogenic shock, and acute respiratory failure. The outcome was good, with total and progressive recovery of all lesions. The literature review revealed the rarity of pulmonary oedema and enteritis after an electric shock. The invasive haemodynamic data suggest physiopathological explanations for findings in the case and indicate therapeutic measures for similar situations.