MATERIALS AND METHODS: Ninety-seven ROs were randomly assigned to either manual or AI-assisted contouring of eight OARs for two head-and-neck cancer cases with an in-between teaching session on contouring guidelines. Thereby, the effect of teaching (yes/no) and AI-assisted contouring (yes/no) was quantified. Second, ROs completed short-term and long-term follow-up cases all using AI assistance. Contour quality was quantified with Dice Similarity Coefficient (DSC) between ROs' contours and expert consensus contours. Groups were compared using absolute differences in medians with 95% CIs.
RESULTS: AI-assisted contouring without previous teaching increased absolute DSC for optic nerve (by 0.05 [0.01; 0.10]), oral cavity (0.10 [0.06; 0.13]), parotid (0.07 [0.05; 0.12]), spinal cord (0.04 [0.01; 0.06]), and mandible (0.02 [0.01; 0.03]). Contouring time decreased for brain stem (-1.41 [-2.44; -0.25]), mandible (-6.60 [-8.09; -3.35]), optic nerve (-0.19 [-0.47; -0.02]), parotid (-1.80 [-2.66; -0.32]), and thyroid (-1.03 [-2.18; -0.05]). Without AI-assisted contouring, teaching increased DSC for oral cavity (0.05 [0.01; 0.09]) and thyroid (0.04 [0.02; 0.07]), and contouring time increased for mandible (2.36 [-0.51; 5.14]), oral cavity (1.42 [-0.08; 4.14]), and thyroid (1.60 [-0.04; 2.22]).
CONCLUSION: The study suggested that AI-assisted contouring is safe and beneficial to ROs working in LMICs. Prospective clinical trials on AI-assisted contouring should, however, be conducted upon clinical implementation to confirm the effects.
METHODS: Twenty-nine children in each group, matched for age, sex and ethnicity, were assessed using the Glasgow outcome Scale (GOS), Weschler Intelligence Scale for Children (WISC-III), Movement Assessment Battery for Children (Movement ABC), Wide Range Assessment of Learning and Memory (WRAML) and a standardised neurological examination 6 months post-injury. Parental reporting of pre- and post-injury behaviour was documented using the Child Behaviour Checklist (CBCL).
RESULTS: Seven (24.1%) children with sCHI and three (10.3%) orthopaedic controls had residual motor deficits. Three (10.3%) children with sCHI and none in the other groups faced problems with independent ambulation. Twenty-seven (93.1%) of those with sCHI and all children in the other groups had GOS scores of good recovery or moderate disability. Twenty-two (81.5%) sCHI, five (18.5%) mCHI and one (3.7%) orthopaedic control reported a deterioration in school performance. MANOVAS identified a significant injury group effect for performance skills (P = 0.007), verbal skills (P = 0.002), memory and learning (P = 0.001) and motor skills (P = 0.001). Repeated measures ANOVA for pre- and post-injury CBCL scores showed significant differences related to somatic complaints (P = 0.004), problems of socialising (P = 0.003), delinquency (P = 0.004), aggressiveness (P = 0.010), thought (P < 0.001) and attention (P < 0.001). Post-hoc univariate analysis showed the significant differences were between that of the sCHI children and the other two groups.
CONCLUSION: Although most sCHI children seemed to have made good physical recovery, there were cognitive, motor, memory and learning difficulties and behavioural problems concomitant with a deterioration in school performance compared with those with lesser or no head injury. This highlights the need for better integrated rehabilitation services to enable a gradual return into mainstream school.
METHODOLOGY: A retrospective study of 865 patients was performed at Netherlands Cancer Institute-Antoni Van Leeuwenhoek Hospital to investigate the feasibility of selective ND (SND). All patients with squamous cell carcinoma of the pharynx and larynx who received primary radiation and underwent salvage ND were included in the study.
RESULT: A total of 29 NDs were analyzed. In 17 neck sides, viable metastases were found (58%), whereas in the other 12 specimens there were no viable metastases. In 16 of the 17 necks (94%), the metastases were located either in level II, III, or IV or in a combination of these 3 levels. Level V was involved in only 1 case (6%).
CONCLUSION: It is well justified to perform a salvage SND (levels II, III, and IV) for pharyngeal and laryngeal carcinoma after primary radiation. In carefully selected cases of supraglottic and oropharyngeal carcinoma, a superselective ND also appears as an efficient option.