Leukemia is a common, multiple and dangerous blood disease, whose early diagnosis and treatment are very important. At present, the diagnosis of leukemia heavily relies on morphological examination of blood cell images by pathologists, which is tedious and time-consuming. Meanwhile, the diagnostic results are highly subjective, which may lead to misdiagnosis and missed diagnosis. To address the gap above, we proposed an improved Vision Transformer model for blood cell recognition. First, a faster R-CNN network was used to locate and extract individual blood cell slices from original images. Then, we split the single-cell image into multiple image patches and put them into the encoder layer for feature extraction. Based on the self-attention mechanism of the Transformer, we proposed a sparse attention module which could focus on the discriminative parts of blood cell images and improve the fine-grained feature representation ability of the model. Finally, a contrastive loss function was adopted to further increase the inter-class difference and intra-class consistency of the extracted features. Experimental results showed that the proposed module outperformed the other approaches and significantly improved the accuracy to 91.96% on the Munich single-cell morphological dataset of leukocytes, which is expected to provide a reference for physicians’ clinical diagnosis.
ObjectiveTo summarize the experience of robot-assisted lung basal segmentectomy, and analyze the clinical application value of intersegmental tunneling and pulmonary ligament approach for S9 and/or S10 segmentectomy. MethodsThe clinical data of 78 patients who underwent robotic lung basal segmentectomy in our hospital between January 2020 to May 2022 were retrospectively reviewed. There were 32 males and 46 females with a median age of 50 (33-72) years. The patients who underwent S9 and/or S10 segmentectomy were divided into a single-direction group (pulmonary ligament approach, n=19) and a bi-direction group (intersegmental tunneling, n=19) according to different approaches, and the perioperative outcomes between the two groups were compared. ResultsAll patients successfully completed the operation, without conversion to thoracotomy and lobectomy, serious complications, or perioperative death. The median operation time was 100 (40-185) min, the blood loss was 50 (10-210) mL, and the median number of dissected lymph nodes was 3 (1-14). There were 4 (5.1%) patients with postoperative air leakage, and 4 (5.1%) patients with hydropneumothorax. No patient showed localized atelectasis or lung congestion at 6 months after the operation. Further analysis showed that there was no significant difference in the operation time, blood loss, thoracic drainage time, complications or postoperative hospital stay between the single-direction and bi-direction groups (P>0.05). However, the number of dissected lymph nodes of the bi-direction group was more than that of the single-direction group [6 (1-13) vs. 5 (1-9), P=0.040]. ConclusionThe robotic lung basal segmentectomy for pulmonary nodules is safe and effective. The perioperative results of robotic S9 and/or S10 complex segmentectomy using intersegmental tunneling and pulmonary ligament approach are similar.
ObjectiveTo evaluate the localization accuracy and perioperative safety of three-dimensional (3D)-printed guide plate localization based on digital lung models in minimally invasive surgery for pulmonary nodules, and to provide an optimized strategy for precise localization of early-stage lung cancer. MethodsPatients with pulmonary nodules who underwent minimally invasive sublobar resection between January 2025 and January 2026 were enrolled. They were randomly allocated to a CT-guided group, a territory analysis group, and an intelligent guide plate group in a 1:1:1 ratio using a computer-generated random sequence. The intelligent guide plate group utilized dual-phase CT data to construct individualized digital lung models and design 3D-printed puncture guide plates for preoperative localization. The three groups were then compared in terms of localization accuracy (evaluated by 3D spatial linear distance grading for the CT-guided and intelligent guide plate groups, and by resection margin distance concordance grading for the territory analysis group), perioperative indicators, and complications. ResultsA total of 75 patients were enrolled, including 26 males and 49 females, with a median age of 56 years (range, 24-81 years). There were 26 patients in the CT-guided group, 26 in the territory analysis group, and 23 in the intelligent guide plate group. The high-precision rate was 60.87% (14/23) in the intelligent guide plate group and 61.54% (16/26) in the CT-guided group, with no statistically significant difference (P=0.944). In the territory analysis group, the resection margin distance concordance was graded as high in 17 patients (65.38%), moderate in 6 (23.08%), low in 2 (7.69%), and absent in 1 (3.85%). Defining high/moderate precision for the CT-guided and intelligent guide plate groups and high/moderate concordance for the territory analysis group as the ideal localization criteria, the qualification rates were 92.31% (24/26), 91.30% (21/23), and 88.46% (23/26), respectively, with no statistically significant difference among the three groups (P=0.886). There were no statistically significant differences in operative time, blood loss, drainage volume, pain score, or postoperative hospitalization costs among the three groups (all P>0.05). The overall complication rate also did not differ significantly among the three groups (P=0.847), and the complications were predominantly mild, including pulmonary air leakage, intermuscular venous thrombosis, pulmonary infection, hepatic insufficiency, etc. All patients improved after symptomatic treatment, with no severe complications encountered. After a median follow-up of 7 months, there were no patients of recurrence, metastasis, or death. Conclusion3D-printed guide plate localization based on digital lung models can effectively restore pulmonary physiological motion and eliminate the "displacement error" of traditional guide plates. It is comparable to CT-guided and territory analysis localization in terms of accuracy and safety, representing a safe and feasible novel precise localization strategy for minimally invasive surgery of early-stage lung cancer.