Background
Neoadjuvant chemotherapy (NAC) has been recognized as an effective therapeutic option for locally advanced gastric cancer as it is expected to reduce tumor size, increase the resection ...rate, and improve overall survival. However, for patients who are not responsive to NAC, the best operation timing may be missed together with suffering from side effects. Therefore, it is paramount to differentiate potential respondents from non-respondents. Histopathological images contain rich and complex data that can be exploited to study cancers. We assessed the ability of a novel deep learning (DL)-based biomarker to predict pathological responses from images of hematoxylin and eosin (H&E)-stained tissue.
Methods
In this multicentre observational study, H&E-stained biopsy sections of patients with gastric cancer were collected from four hospitals. All patients underwent NAC followed by gastrectomy. The Becker tumor regression grading (TRG) system was used to evaluate the pathologic chemotherapy response. Based on H&E-stained slides of biopsies, DL methods (Inception-V3, Xception, EfficientNet-B5, and ensemble CRSNet models) were employed to predict the pathological response by scoring the tumor tissue to obtain a histopathological biomarker, the chemotherapy response score (CRS). The predictive performance of the CRSNet was evaluated.
Results
69,564 patches from 230 whole-slide images of 213 patients with gastric cancer were obtained in this study. Based on the F1 score and area under the curve (AUC), an optimal model was finally chosen, named the CRSNet model. Using the ensemble CRSNet model, the response score derived from H&E staining images reached an AUC of 0.936 in the internal test cohort and 0.923 in the external validation cohort for predicting pathological response. The CRS of major responders was significantly higher than that of minor responders in both internal and external test cohorts (both
p
< 0.001).
Conclusion
In this study, the proposed DL-based biomarker (CRSNet model) derived from histopathological images of the biopsy showed potential as a clinical aid for predicting the response to NAC in patients with locally advanced GC. Therefore, the CRSNet model provides a novel tool for the individualized management of locally advanced gastric cancer.
In recent years, natural orifice specimen extraction surgery (NOSES) has become a field of special interest for colorectal surgeons. Some researchers have reported transanal specimen extraction in ...the laparoscopic anterior rectal resection, including intersphincteric resection (ISR) and rectal eversion-resection. However, these surgical procedures have certain limitations. Based on the proven expertise in laparoscopic surgery, our center has developed a modified technique of transanal specimen extraction. The aim of this study was to investigate the safety and feasibility of a modified technique of transanal specimen extraction in the laparoscopic anterior rectal resection.
From January 2011 to January 2014, the patients with upper rectal or lower sigmoid colon cancer who had undergone laparoscopic anterior rectal resection with specimen extraction by a modified transanal technique were enrolled in the observation group, and the patients who had undergone laparoscopic anterior rectal resection with specimen extraction via an abdominal incision by the same surgeons during the same period were enrolled in the control group.
A total of 36 patients were included in the observation group and 128 patients were included in the control group. There were no significant differences (P > 0.05) between the two groups in terms of the mean operative time 144 ± 10 min vs. 141 ± 11 min, mean intraoperative blood loss 63 ± 6 ml vs. 61 ± 7 ml, and the mean time to anal exhaust 67 ± 7 h vs. 65 ± 8 h. However, there were significant differences (P < 0.05) between the two groups in terms of the mean postoperative Visual Analogue Scale (VAS) pain scores 3.4 ± 1.1 vs. 4.5 ± 1.2, mean postoperative hospital stay 6.0 ± 1.1 days ± vs. 7.2 ± 1.2 days, and incidence of postoperative complications (4/36 vs. 15/128). Long-term follow-up results showed that there was no significant difference (P > 0.05) between the two groups in terms of the 3- or 5-year overall survival.
The modified technique of transanal specimen extraction in the laparoscopic anterior rectal resection fulfilled the principle of no-neoplasm touch technique, with advantages, such as minimal trauma, rapid recovery, and fewer complications. Long-term follow-up results also showed satisfactory oncological outcomes.
Laparoscopic total mesorectal excision combined with intersphincteric resection is technically safe and feasible for the treatment of ultra‐low rectal cancer. The curative effect is encouraging, but ...surgical indications should be determined.
Background
Quite a few studies on anal functions after open total mesorectal excision combined with transanal intersphincteric resection (ISR) have been reported, but there is little literature on anal function after laparoscopic total mesorectal excision (LTME) combined with transanal ISR. The aim of this study was to explore the post‐operative anorectal dynamic changes in ultra‐low rectal cancer patients undergoing LTME combined with transanal ISR.
Methods
The data of 26 ultra‐low rectal cancer patients undergoing LTME + transanal ISR were analysed. A total of 30 patients undergoing laparoscopic low anterior resection by the same surgeons during the same period were randomly enrolled into the control group.
Results
There were no differences in the preoperative anorectal manometry data and Wexner anal function scores between the observation group and the control group (P > 0.05). There were no significant differences in the mean operation time, the mean amount of bleeding and the mean post‐operative hospital stay between the two groups (P > 0.05). The mean follow‐up time was 16 months. No recurrence and metastasis were found in all cases. At 3 and 6 months after the operation, there were significant differences in the anorectal manometry data and Wexner anal function scores between the two groups (P < 0.05). However, at 1 year after the operation, there were no significant differences in the anorectal manometry data and Wexner anal function scores between the two groups (P > 0.05).
Conclusion
Laparoscopic ISR for ultra‐low rectal cancer is technically feasible, but the surgical indications should be strictly defined.