Examination of Surgical Specimens of the Esophagus

A YOLOv5-based network for the detection of a diffuse reflectance spectroscopy probe to aid surgical guidance in gastrointestinal cancer surgery

PURPOSE

A positive circumferential resection margin (CRM) for oesophageal and gastric carcinoma is associated with local recurrence and poorer long-term survival. Diffuse reflectance spectroscopy (DRS) is a non-invasive technology able to distinguish tissue type based on spectral data. The aim of this study was to develop a deep learning-based method for DRS probe detection and tracking to aid classification of tumour and non-tumour gastrointestinal (GI) tissue in real time.

METHODS

Data collected from both ex vivo human tissue specimen and sold tissue phantoms were used for the training and retrospective validation of the developed neural network framework. Specifically, a neural network based on the You Only Look Once (YOLO) v5 network was developed to accurately detect and track the tip of the DRS probe on video data acquired during an ex vivo clinical study.

RESULTS

Different metrics were used to analyse the performance of the proposed probe detection and tracking framework, such as precision, recall, mAP 0.5, and Euclidean distance. Overall, the developed framework achieved a 93% precision at 23 FPS for probe detection, while the average Euclidean distance error was 4.90 pixels.

CONCLUSION

The use of a deep learning approach for markerless DRS probe detection and tracking system could pave the way for real-time classification of GI tissue to aid margin assessment in cancer resection surgery and has potential to be applied in routine surgical practice.

Real-time Tracking and Classification of Tumor and Nontumor Tissue in Upper Gastrointestinal Cancers Using Diffuse Reflectance Spectroscopy for Resection Margin Assessment

Importance

Cancers of the upper gastrointestinal tract remain a major contributor to the global cancer burden. The accurate mapping of tumor margins is of particular importance for curative cancer resection and improvement in overall survival. Current mapping techniques preclude a full resection margin assessment in real time.

Objective

To evaluate whether diffuse reflectance spectroscopy (DRS) on gastric and esophageal cancer specimens can differentiate tissue types and provide real-time feedback to the operator.

Design, Setting, and Participants

This was a prospective ex vivo validation study. Patients undergoing esophageal or gastric cancer resection were prospectively recruited into the study between July 2020 and July 2021 at Hammersmith Hospital in London, United Kingdom. Tissue specimens were included for patients undergoing elective surgery for either esophageal carcinoma (adenocarcinoma or squamous cell carcinoma) or gastric adenocarcinoma.

Exposures

A handheld DRS probe and tracking system was used on freshly resected ex vivo tissue to obtain spectral data. Binary classification, following histopathological validation, was performed using 4 supervised machine learning classifiers.

Main Outcomes and Measures

Data were divided into training and testing sets using a stratified 5-fold cross-validation method. Machine learning classifiers were evaluated in terms of sensitivity, specificity, overall accuracy, and the area under the curve.

Results

Of 34 included patients, 22 (65%) were male, and the median (range) age was 68 (35-89) years. A total of 14 097 mean spectra for normal and cancerous tissue were collected. For normal vs cancer tissue, the machine learning classifier achieved a mean (SD) overall diagnostic accuracy of 93.86% (0.66) for stomach tissue and 96.22% (0.50) for esophageal tissue and achieved a mean (SD) sensitivity and specificity of 91.31% (1.5) and 95.13% (0.8), respectively, for stomach tissue and of 94.60% (0.9) and 97.28% (0.6) for esophagus tissue. Real-time tissue tracking and classification was achieved and presented live on screen.

Conclusions and Relevance

This study provides ex vivo validation of the DRS technology for real-time differentiation of gastric and esophageal cancer from healthy tissue using machine learning with high accuracy. As such, it is a step toward the development of a real-time in vivo tumor mapping tool for esophageal and gastric cancers that can aid decision-making of resection margins intraoperatively.

Impact of radial margins after esophagectomy for esophageal cancer

INTRODUCTION

The prognostic significance of radial margin (RM) involvement in esophagectomy cancer specimens is unclear. Our study investigated survival and recurrence rates between different depths of RM involvement.

MATERIALS AND METHODS

We retrospectively analyzed 1103 esophagectomies at our institution from 2005 to 2019. Patients were grouped by three-tier stratification: negative RM > 1 mm away, direct RM involvement at 0 mm, and close RM between 0 mm and 1 mm. Survival, loco-regional and distant recurrences were analyzed.

RESULTS

1103 esophageal cancer patients were analyzed. 389 patients had recurrence (35.3%). Median survival (13.2 months) and recurrence rates (71%) were worst with direct RM (p < 0.001) as compared to negative RM (median survival not achieved within 5-years from surgery and 30%). Without nodal involvement, RM involvement of <1 mm was associated with decreased overall survival, and overall, loco-regional and distant recurrence-free survival compared to negative RM (log rank p-value <0.05). In those with persistent nodal disease, only direct RM was associated with decreased overall and loco-regional recurrence-free survival as compared to negative margins (p < 0.05). Direct RM tended to do worse compared to close RM in terms of median survival and trended worse for recurrence. Direct RM (baseline negative RM), but not close RM, was an independent RF in a multivariable Cox model for worse overall survival (HR 2.74; p < 0.001), recurrence-free survival (HR 1.96; p = 0.019), and loco-regional recurrence-free survival (HR 3.19; p = 0.011).

CONCLUSION

RM involvement affects survival and recurrence. Tumor at 0 mm remained an independent RF for worse survival and overall and loco-regional recurrence.

Optimizing histopathologic evaluation of EMR specimens of Barrett's esophagus-related neoplasia: a randomized study of 3 specimen handling methods

BACKGROUND AND AIMS

Endoscopic resection is the cornerstone of treatment of Barrett's esophagus (BE)-related neoplasia. However, accurate histopathologic evaluation of endoscopic resection specimens can be challenging, and the preferred specimen handling method remains unknown. Therefore, the aim of our study was to compare 3 different specimen handling methods for assessment of all clinically relevant histopathologic parameters and time required for specimen handling.

METHODS

In this multicenter, randomized study EMR specimens of BE-related neoplasia with no suspicion of submucosal invasion during endoscopy were randomized to 3 specimen handling methods: pinning on paraffin using needles, direct fixation in formalin without prior tissue handling, and the cassette technique (small box for enclosing specimens). The histopathologic evaluation scores were assessed by 2 dedicated GI pathologists blinded to the handling method.

RESULTS

Of the 126 randomized EMR specimens, 45 were assigned to pinning on paraffin, 41 to direct fixation in formalin, and 40 to the cassette technique. The percentages of specimens with overall optimal histopathologic evaluation scores were similar for the pinning method (98%; 95% confidence interval [CI], 88.0-99.9) and for no handling (90%; 95% CI, 76.9-97.3) but were significantly lower (64%; 95% CI, 47.2-78.8) for the cassette technique (P < .001). Time required for specimen handling was shortest when no handling method was used (P < .001 vs pinning and cassette).

CONCLUSIONS

Both pinning on paraffin and direct fixation in formalin resulted in optimal histopathologic evaluation scores in a high proportion of specimens, whereas the cassette technique performs significantly worse, and its use in clinical daily practice should be discouraged. Given the significantly shorter handling time, direct fixation in formalin appears to be the preferred method over pinning on paraffin. However, the latter needs to be confirmed in larger studies with inclusion of all EMR specimens. (Clinical trial registration number: ISRCTN50525266.).

Staging of T1 esophageal adenocarcinoma with volumetric laser endomicroscopy: a feasibility study

Background and study aims  Precise staging in T1 esophageal adenocarcinoma (EAC) is critical in determining candidacy for curative endoscopic resection. High-frequency endoscopic ultrasound (EUS) has demonstrated suboptimal accuracy in T1 EAC staging due to insufficient spatial resolution. Volumetric laser endomicroscopy (VLE) allows for high-resolution wide-field visualization of the esophageal microstructure. We aimed to investigate the role of VLE in staging T1 EAC. Patients and methods  Patients undergoing endoscopic mucosal resection (EMR) were prospectively enrolled and only T1 EAC cases were included. EMR specimens were imaged using second-generation VLE immediately after resection. VLE images were analyzed for signal intensity by depth and signal attenuation (dB/mm) in both cross-sectional and en-face orientation. A decision tree model was constructed to combine measured VLE parameters and delineate diagnostic thresholds. Results  Thirty EMR scans were obtained - 15 T1a specimens from 9 patients and 15 T1b specimens from 11 patients. T1b specimen VLE scans exhibited higher signal intensity ( P  < 0.0001) and higher signal attenuation compared to T1a specimens ( P  = 0.03). A combination of signal attenuation and signal intensity at 150 µm depth yielded optimal diagnostic thresholds and an area under the curve (AUC) of 0.77. VLE signal attenuation was significantly associated with grade of differentiation, irrespective of EAC stage. Conclusions  VLE signal intensity and signal attenuation are quantitatively distinct in T1a and T1b EAC and associated with grade of differentiation. This is the first study examining the role of VLE for staging of T1 EAC and demonstrates promising diagnostic performance. With further in vivo validation, VLE may serve a role in staging superficial EAC.

Preoperative endoscopic titanium clip placement facilitates intraoperative localization of early-stage esophageal cancer or severe dysplasia

Background

Accurate intraoperative localization of esophageal lesions is essential for successful surgical resection. We tested whether preoperative endoscopic placement of titanium clips could facilitate intraoperative localization of early-stage esophageal cancer or severe dysplasia.

Methods

A prospective randomized clinical trial was performed between May 2012 and July 2014. All enrolled patients received preoperative endoscopy and esophageal endoscopic ultrasound, as well as pathological study on the biopsy specimen, to confirm early stage esophageal cancer or severe dysplasia. One day before the surgical operation, patients in the experimental group received the preoperative endoscopic titanium labeling of esophageal lesions. Then, during the surgical operation, palpitation of titanium clips was used to localize the lesions in these patients. In patients in the control group, palpitation of nodules or esophageal wall mucosal thickening, together with the consideration of the results from preoperative endoscopic and ultrasound studies, was applied to estimate the location of the esophageal lesions. Study outcomes included the proportions of patients having successful intraoperative pre-resection lesion localization, post-esophagectomy lesion visualization, negative upper surgical margin, change of surgical approaches, and positive postoperative pathological diagnosis.

Results

A total of 27 patients were enrolled into the study, with 14 in the experimental group and 13 in the control group. Compared to the patients in the control group, a higher proportion of patients in the experimental group had statistically significant successful intraoperative esophageal lesion localization (100 versus 15.3% in the experimental versus control group).

Conclusions

Preoperative endoscopic titanium clip placement could facilitate intraoperative localization of early-stage esophageal cancer or severe dysplasia.

Trial registration

Current study was registered in Chinese Clinical Trial Registry and World Health Organization International Clinical Trials Registry Platform, ChiCTR-INR-17010949. Registered 22 March 2017, retrospectively registered.

Handling and Pathology Reporting of Gastrointestinal Endoscopic Mucosal Resection

Endoscopic mucosal resection (EMR) is a non-invasive alternative to surgery that is now frequently used for resection of early lesions in both upper and lower parts of the gastrointestinal (GI) tract. One of the main advantages of these techniques is providing tissue for histopathological examination. Pathological examination of endoscopically resected specimens of GI tract is a crucial component of these procedures and is useful for prediction of both the risk of metastasis and lymph node involvement.

As the first step, it is very important for the pathologist to handle the EMR gross specimen in the correct way: it should be oriented, and then the margins should be labeled and inked accurately before fixation.

In the second step, the EMR pathological report should include all the detailed information about the diagnosis, grading, depth of invasion (mucosa only or submucosal involvement), status of the margins, and the presence or absence of lymphovascular invasion.

The current literature (PubMed and Google Scholar) was searched for the words "endoscopic mucosal resection" to find all relevant publications about this technique with emphasis on the pathologist responsibilities.