Division of General Surgery, Department of Surgery, Tri‐Service General Hospital Songshan Branch National Defense Medical University Taipei Taiwan (ROC)
Auto-generated profile, based on publicly available information
Chien‐Yi Yang
Division of General Surgery, Department of Surgery, Tri‐Service General Hospital Songshan Branch National Defense Medical University Taipei Taiwan (ROC)
Aim: Most previous research on AI‐based image diagnosis of acute cholecystitis (AC) has utilized ultrasound images. While these studies have shown promising outcomes, the results were based on still images captured by physicians, introducing inevitable selection bias. This study aims to develop a fully automated system for precise gallbladder detection among various abdominal structures, aiding clinicians in the rapid assessment of AC requiring cholecystectomy. Methods: The dataset comprised images from 250 AC patients and 270 control participants. The VGG‐16 architecture was employed for gallbladder recognition. Post‐processing techniques such as the flood fill algorithm and centroid calculation were integrated into the model. U‐Net was utilized for segmentation and features extraction. All models were combined to develop a fully automated AC detection system. Results: The gallbladder identification accuracy among various abdominal organs was 95.3%, with the model effectively filtering out CT images lacking a gallbladder. In diagnosing AC, the model was tested on 120 cases, achieving an accuracy of 92.5%, sensitivity of 90.4%, and specificity of 94.1%. After integrating all components, the ensemble model achieved an overall accuracy of 86.7%. The automated process required 0.029 seconds of computation time per CT slice and 3.59 seconds per complete CT set. Conclusions: The proposed system achieves promising performance in the automatic detection and diagnosis of gallbladder conditions in patients requiring cholecystectomy, with robust accuracy and computational efficiency. With further clinical validation, this computer‐assisted system could serve as an auxiliary tool in identifying patients requiring emergency surgery.
4 September 2024 in European Archives of Oto-Rhino-Laryngology
Objectives: Organ preservation strategies are increasingly adopted for hypopharyngeal carcinoma, but functional outcomes may be suboptimal. Posttreatment tracheostomy dependence significantly increases morbidity and reduces quality of life. This study evaluated airway outcomes and oncologic results in patients treated with primary chemoradiotherapy (CRT) or upfront surgery. Methods: This retrospective study included 165 patients, with data collected on demographics, treatment type, tracheostomy status, and oncologic outcomes. The primary endpoint was long‐term tracheostomy dependence. Oncologic outcomes, including local control, disease‐free survival (DFS), and overall survival (OS), were analyzed. Results: Among the 165 patients included, 139 had advanced‐stage disease; 54 received CRT and 85 underwent upfront surgery. The 5‐year OS rate was significantly higher with surgery (40.0%) than CRT (18.4%). Patients who underwent total laryngectomy (TL) had higher 5‐year OS (35.5% vs. 28.6%) and 3‐year DFS (41.9% vs. 27.3%) compared to those managed with organ preservation. When stratified by airway status, 5‐year OS was 58.8% in patients with preserved airways, 29.3% after TL, and 6.7% in those with long‐term tracheostomy dependence. Notably, emergency tracheostomy ( n = 41) was associated with significantly poorer OS (12.2%), and none of these patients retained their native airway. Overall, 75.54% (105/139) of advanced‐stage patients ultimately lost their native airway, including 55.84% (43/77) of those who initially pursued an organ preservation strategy. Conclusions: Patients with long‐term tracheostomy dependence exhibited the poorest prognosis and highest recurrence rates. Emergency tracheostomy was a strong predictor of long‐term dependence. Upfront surgery may be more appropriate for patients with impaired baseline laryngeal function. Level of Evidence: 3.