The clinical application of binocular endoscope relies primarily on the visual system of physicians to create a three-dimensional effect, but it cannot provide accurate depth information. The utilization of 3D reconstruction technology in binocular endoscopy can facilitate the recovery of image depth information, and the application of deep learning-based 3D reconstruction technology can significantly improve the accuracy and real-time performance of reconstruction results, making it widely applicable in the realm of minimally invasive surgery. This paper aims to explore the key technologies and implementation methods of deep learning based 3D reconstruction for binocular endoscopic images, and seeks to outline strategies for enhancing the quality of 3D reconstruction in endoscopic images, providing guidance for sustainable development of binocular endoscopic image reconstruction technology in clinical settings. This will assist in the application of minimally invasive surgery and contribute to meeting the demands of precision medicine.
Deep Learning ; Imaging, Three-Dimensional/methods* ; Humans ; Endoscopy/methods* ; Image Processing, Computer-Assisted/methods* ; Minimally Invasive Surgical Procedures

Objective To observe the effect of Tongyang-Kuanxiong guanule combined with conventional western medicine for the stable angina pectoris (SAP) with qi and phlegm and blood stasis syndrome. Methods Eighty-six SAP patients who met the inclusion criteria were randomly divided into two groups according to the digital table method, with 43 cases in each group. The control group was treated with routine Western medical therapy. The observation group was given Tongyang-Kuanxiong guanule on the basis of the control group. Both groups were treated for 28 days. The TCM syndromes and angina pectoris scores were evaluated before and after treatment. The treadmill exercise test was used to observe the duration of exercise, the metabolic equivalent, the maximum value of ST segment depression, the heart rate at maximum load, the duration of ST segment depression. And the adverse reactions were recorded. Results The total effective rate was 88.4％ (38/43) in the observation group and 67.4％ (29/43) in the control group. The difference between the two groups was statistically significant (χ2=5.549, P=0.018). After treatment, the duration of exercise (9.5 ± 1.2 min vs. 8.6 ± 1.2 min, t=3.371), metabolic equivalent (10.8 ± 2.5 METs vs. 9.2 ± 2.4 METs, t=3.084) in the observation group were significantly higher than those in the control group (P<0.01 or P<0.05). The largest degree of ST segment changes (1.2 ± 0.6 mV vs. 1.9 ± 0.6 mV, t=5.484), and the duration of ST segment descent (125.0 ± 94.5 s vs. 162.4 ± 96.9 s, t=1.795) in the observation group were significantly lower than those in the control group (P<0.01 or P<0.05). Thefrequency of angina attacks (9.7 ± 1.6 times per week vs. 17.3 ± 2.1 times per week, t=18.778), duration of attacks (3.2 ± 1.4 min vs. 6.4 ± 1.5 min, t=10.146) consumption of nitroglycerin (1.3 ± 0.8 mg vs. 2.5 ± 0.8 mg, t=7.624) and Symptom score (8.3 ± 2.8 vs. 12.5 ± 3.1, t=6.593) in the observation group were significantly lower than the control group (P<0.01). Conclusions The Tongyang-Kuanxiong guanule can significantly improve the exercise tolerance of SAP patients with qi and phlegm and blood stasis, reduce myocardial oxygen consumption, improve angina pectoris and reduce the number of angina attacks.