MATERIALS AND METHODS: This was a retrospective study utilizing CT scans from three hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm. In the lesion detection phase, 2147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area-under-the-curve (AUC) analysis. In the path planning phase, Bayesian optimization was utilized to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared against actual biopsy path trajectories from intraoperative CT scans in 150 patients, with a match defined as angular deviation of <5 degrees between the two.
RESULTS: The model achieved an overall AUC of 97.4% (95%CI=96.3-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. 85.3% of software-proposed needle trajectories were feasible, with 82% matching actual paths, and similar performance between supine and prone/oblique patient orientations (p=0.311). Average angular deviation between matching trajectories was 2.30±1.22o; average path deviation was 2.94±1.60mm.
CONCLUSIONS: Segmentation, lesion detection and path-planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way towards fully automated biopsy procedures.
METHODS: Patients with schizophrenia from Japan, South Korea, Malaysia, and Taiwan were randomly assigned to 6 weeks of double-blind treatment with 40 or 80 mg/d of lurasidone or placebo. The primary efficacy measure was change from baseline to week 6 on the Positive and Negative Syndrome Scale (PANSS) total score. Efficacy was evaluated using a mixed-model repeated-measures (MMRM) analysis in the modified intention-to-treat (mITT) population.
RESULTS: On the basis of the analysis for the mITT population, the estimated difference score for lurasidone 40 and 80 mg/d vs placebo was -4.8 (P = 0.050) and -4.2 (P = 0.080). For the full intention-to-treat (ITT) population, the difference score for lurasidone 40 and 80 mg/d vs placebo was -5.8 (P = 0.017) and -4.2 (P = 0.043). The most frequent adverse events in the lurasidone 40 and 80 mg/d and placebo groups, respectively, were akathisia (7.3%, 10.4%, 3.3%), somnolence (6.0%, 2.6%, 0.7%), and vomiting (6.0%, 5.8%, 2.0%). The proportion of patients experiencing clinically significant weight gain (≥7%) was 5.3% for lurasidone 40 mg/d, 1.3% for 80 mg/d, and 1.4% for placebo. End point changes in metabolic parameters and prolactin were comparable for both lurasidone groups and placebo.
CONCLUSIONS: In the ITT (but not the mITT) population, treatment with lurasidone was associated with significant improvement in the PANSS total score in patients with schizophrenia. Lurasidone was generally well tolerated with minimal impact on weight and metabolic parameters.
METHODS: This double-blind, multicenter, phase 3 study consisted of a 1-week observation period during which patients were treated with two patches of placebo, followed by a 6-week double-blind period where patients were randomized (1:1:1) to receive once-daily blonanserin 40 mg, blonanserin 80 mg, or placebo patches. The primary endpoint was the change from baseline in the total Positive and Negative Symptom Scale (PANSS) score. Safety assessments included treatment-emergent adverse events (TEAEs).
RESULTS: Between December 2014 and October 2018, patients were recruited and randomly assigned to blonanserin 40 mg (n = 196), blonanserin 80 mg (n = 194), or placebo (n = 190); of these, 77.2% completed the study. Compared with placebo, blonanserin significantly improved PANSS total scores at 6 weeks (least square mean [LSM] difference vs placebo: -5.6 with blonanserin 40 mg; 95% confidence interval [CI] -9.6, -1.6; adjusted p = 0.007, and - 10.4 with blonanserin 80 mg; 95% CI -14.4, -6.4; adjusted p