Background And Purpose: 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.

Materials And Methods: 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.

Results: 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).

Conclusion: 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.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10618761PMC
http://dx.doi.org/10.1016/j.phro.2023.100501DOI Listing

Publication Analysis

Top Keywords

computed tomography
8
treatment planning
8
inter-observer variability
8
automatic contours
8
automatic
5
real-world validation
4
validation artificial
4
artificial intelligence-based
4
intelligence-based computed
4
tomography auto-contouring
4

Similar Publications

Associations of fat, bone, and muscle indices with disease severity in patients with obstructive sleep apnea hypopnea syndrome.

Sleep Breath

January 2025

Department of Pulmonary and Critical Care Medicine, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, No.1 Da Hua Road, Dong Dan, Dongcheng District, Beijing, 100730, PR China.

Purpose: To investigate the relationship between obstructive sleep apnea hypopnea syndrome (OSAHS) severity and fat, bone, and muscle indices.

Methods: This study included 102 patients with OSAHS and retrospectively reviewed their physical examination data. All patients underwent polysomnography, body composition analysis, dual-energy X-ray absorptiometry, computed tomography (CT) and blood test.

View Article and Find Full Text PDF

Objectives: To assess the effect of patient positioning and general anesthesia on the condylar position in orthognathic surgery.

Materials And Methods: This prospective study included patients undergoing orthognathic surgery between 2019 and 2020. Four weeks prior to surgery (T0) cone-beam computed tomography (CBCT) scans and intra-oral scans (IOS) were acquired in an upright position.

View Article and Find Full Text PDF

Reducing Healing Period with DDM/rhBMP-2 Grafting for Early Loading in Dental Implant Surgery.

Tissue Eng Regen Med

January 2025

Department of Oral and Maxillofacial Surgery, Section of Dentistry, Seoul National University Bundang Hospital, 172 Dolma-ro, Bundang-gu, Seongnam-si, Gyeonggi-do, 13620, Republic of Korea.

Background: Traditionally, dental implants require a healing period of 4 to 9 months for osseointegration, with longer recovery times considered when bone grafting is needed. This retrospective study evaluates the clinical efficacy of demineralized dentin matrix (DDM) combined with recombinant human bone morphogenetic protein-2 (rhBMP-2) during dental implant placement to expedite the osseointegration period for early loading.

Methods: Thirty patients (17 male, 13 female; mean age 55.

View Article and Find Full Text PDF

Background: To provide improved treatment for hallux valgus (HV), we sought to understand more about the pathophysiologic connection between flatfoot deformity and HV by comparing coronal plane alignment of the medial column of the foot for patients with isolated HV, isolated flatfoot, and combined HV-flatfoot vs controls.

Methods: This study retrospectively assessed a consecutive series of 33 patients with combined symptomatic and radiographic HV and flatfoot, 33 isolated symptomatic HV, 33 isolated symptomatic flatfoot, and 33 controls. The medial column alignment was assessed in the coronal plane using 3-dimensional weightbearing computed tomography (WBCT); rotation was measured for the navicular, medial cuneiform, and first metatarsal (M1).

View Article and Find Full Text PDF

Background: Advanced pancreatic ductal adenocarcinoma (aPDAC) is often accompanied by significant muscle mass loss, contributing to poor prognosis. SarcAPACaP, an ancillary study of the GERCOR-APACaP phase III trial, evaluated the role of adapted physical activity (APA) in aPDAC Western patients receiving first-line chemotherapy. The study aimed to assess (1) the potential impact of computed tomography (CT)-quantified muscle mass before and during treatments on health-related quality of life (HRQoL) and overall survival (OS) and (2) the role of APA in mitigating muscle mass loss.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!