Artificial Intelligence (AI)-based auto-contouring for treatment planning in radiotherapy needs extensive clinical validation, including the impact of editing after automatic segmentation. The aims of this study were to assess the performance of a commercial system for Clinical Target Volumes (CTVs) (prostate/seminal vesicles) and selected Organs at Risk (OARs) (rectum/bladder/femoral heads + femurs), evaluating also inter-observer variability (manual vs automatic + editing) and the reduction of contouring time. Two expert observers contoured CTVs/OARs of 20 patients in our Treatment Planning System (TPS). Computed Tomography (CT) images were sent to the automatic contouring workstation: automatic contours were generated and sent back to TPS, where observers could edit them if necessary. Inter- and intra-observer consistency was estimated using Dice Similarity Coefficients (DSC). Radiation oncologists were also asked to score the quality of automatic contours, ranging from 1 (complete re-contouring) to 5 (no editing). Contouring times (manual vs automatic + edit) were compared. DSCs (manual vs automatic only) were consistent with inter-observer variability (between 0.65 for seminal vesicles and 0.94 for bladder); editing further improved performances (range: 0.76–0.94). The median clinical score was 4 (little editing) and it was <4 in 3/2 patients for the two observers respectively. Inter-observer variability of automatic + editing contours improved significantly, being lower than manual contouring (e.g.: seminal vesicles: 0.83vs0.73; prostate: 0.86vs0.83; rectum: 0.96vs0.81). Oncologist contouring time reduced from 17 to 24 min of manual contouring time to 3–7 min of editing time for the two observers (p < 0.01). Automatic contouring with a commercial AI-based system followed by editing can replace manual contouring, resulting in significantly reduced time for segmentation and better consistency between operators.

Purpose: We investigated the dose enhancement and internalization of gold nanoparticles (AuNPs) used as a radiosensitizer agent for rotational radiotherapy of breast cancer using a kilovoltage (kV) X‐ray beam.Methods: Human breast cancer cells MDA‐MB‐231 were incubated with or without 100 μg/mL (4.87 nM) or 200 μg/mL (9.74 nM) 15 nm AuNPs and irradiated with 100 kV, 190 kV, or 6 MV X‐rays. To assess the toxicity of the AuNPs, we performed a Sulforhodamine B assay. Using atomic absorption spectroscopy, scanning electron microscopy, transmission electron microscopy, and time‐lapse optical microscopy (rate of 2 frames per minute), we carried out a quantitative assessment of the amount of gold internalized by MDA‐MB‐231 cells and a characterization of the static and dynamical aspects of this internalization process.Results: No effect of AuNPs alone was shown on cell viability. Time‐lapse optical microscopy showed for the first time AuNPs cellular uptake and the dynamics of AuNPs internalization. Electron microscopy demonstrated AuNPs localization in endosomal vesicles, preferentially in the perinuclear region. After irradiation at doses up to 2 Gy, cell survival fraction curves showed increased mortality with AuNPs, with respect to irradiation without AuNPs. The highest effect of radioenhancement by AuNPs (at 9.74 nM AuNPs concentration) was observed at 190 kV showing a dose enhancement factor of 1.33 ± 0.06 (1.34 ± 0.02 at 100 kV), while at 6 MV it was 1.14 ± 0.06.Conclusions: The observed radio‐sensitization effect is promising for future radio‐enhanced kV radiotherapy of breast cancer and quantitatively in the order of previous observations for 15 nm AuNPs. These results of a significant dose enhancement were obtained at 15 nm AuNPs concentration as low as several nanomolar units, at dose levels typical of a single dose fraction in a radiotherapy session. Dynamical behavior of the 3D spatial distribution of 15 nm AuNPs outside the nucleus of single breast cancer cell was observed, with possible implications for future models of AuNPs sensitization.

We report molecular subtype impact on 1325 early breast cancer (BCa) patients treated with whole breast hypofractionated (WBH) adjuvant forward-planned intensity modulated radiotherapy (F-IMRT) without boost. From 02/2009-05/2017 1325 patients with pTis-pT3, pNx-N1aM0 BCa who underwent breast conservation surgery were treated with WBHF-IMRT in our institute, to a total dose of 40 Gy/15 fractions, without boost. Median age: 62 (interquartile range-IQR-:51.14–70.53) years. Histology: 8% in situ carcinoma (ISC), 92% invasive tumors. Molecular subtypes (invasive tumors): 49.9% Luminal A, 33.1% Luminal B Her2 negative (−), 6.2% Luminal B Her2 positive (+), 3.6% Hormone Receptor (HR)- Her2+, 7.1% Triple negative (TNBC), and 0.2% HR+. Chemotherapy (CT) was prescribed in 28% of patients, hormonal therapy in 80.3%, monoclonal antibodies (MAb) in 86.8% of Luminal B Her2+ and 97.7% of HR- Her2+ patients. Median follow up was 72.43 (IQR: 44.63–104.13) months. The 5-year Kaplan-Meier estimates of local relapse-free survival (LRFS) was 97.8%, regional-(RRFS) 98.6%, loco-regional- (LRRFS) 96.9%, distant- (DRFS) 96.6%, disease-free survival (DFS) 94.8% and overall survival (OS) 95.5%. Considering molecular subtypes, 5-year LRFS was: 99.8% for Luminal A, 96.7% for Luminal B Her2-, 94.1% for Luminal B Her2+, 87.9% for HR- Her2+, 95.1% for TNBC and 99.1% for in situ carcinoma. While the overall estimated probability of LR within 5 years after WBHF-IMRT without boost is good (2.2%), molecular subtypes have a strong impact, despite MAb therapy in Her2+ patients, and CT for TNBC patients, and could be used as a parameter in deciding the boost prescription.

Tomotherapy may deliver high-quality whole breast irradiation at static angles. The aim of this study was to implement Knowledge-Based (KB) automatic planning for left-sided whole breast using this modality. Virtual volumetric plans were associated to the dose distributions of 69 Tomotherapy (TT) clinical plans of previously treated patients, aiming to train a KB-model using a commercial tool completely implemented in our treatment planning system. An individually optimized template based on the resulting KB-model was generated for automatic plan optimization. Thirty patients of the training set and ten new patients were considered for internal/external validation. Fully-automatic plans (KB-TT) were generated and compared using the same geometry/number of fields of the corresponding clinical plans. KB-TT plans were successfully generated in 26/30 and 10/10 patients of the internal/external validation sets; for 4 patients whose original plans used only two fields, the manual insertion of one/two fields before running the automatic template was sufficient to obtain acceptable plans. Concerning internal validation, planning target volume V_95%/D_1%/dose distribution standard deviation improved by 0.9%/0.4Gy/0.2Gy (p < 0.05) against clinical plans; Organs at risk mean doses were also slightly improved (p < 0.05) by 0.07/0.4/0.2/0.01 Gy for left lung/heart/right breast/right lung respectively. Similarly satisfactory results were replicated in the external validation set. The resulting treatment duration was 8 ± 1 min, consistent with our clinical experience. The active planner time per patient was 5–10 minutes. Automatic TT left-sided breast KB-plans are comparable to or slightly better than clinical plans and can be obtained with limited planner time. The approach is currently under clinical implementation.