Machine Learning-Based Prediction of Responsiveness to Neoadjuvant Chemoradiotheapy in Locally Advanced Rectal Cancer Patients from Endomicroscopy.

The protocol for treating locally advanced rectal cancer consists of the application of chemoradiotherapy (neoCRT) followed by surgical intervention. One issue for clinical oncologists is predicting the efficacy of neoCRT in order to adjust the dosage and avoid treatment toxicity in cases when surgery should be conducted promptly. Biomarkers may be used for this purpose along with in vivo cell-level images of the colorectal mucosa obtained by probe-based confocal laser endomicroscopy (pCLE) during colonoscopy. The aim of this article is to report our experience with Motiro, a computational framework that we developed for machine learning (ML) based analysis of pCLE videos for predicting neoCRT response in locally advanced rectal cancer patients. pCLE videos were collected from 47 patients who were diagnosed with locally advanced rectal cancer (T3/T4, or N+). The patients received neoCRT. Response to treatment by all patients was assessed by endoscopy along with biopsy and magnetic resonance imaging (MRI). Thirty-seven patients were classified as non-responsive to neoCRT because they presented a visible macroscopic neoplastic lesion, as confirmed by pCLE examination. Ten remaining patients were considered responsive to neoCRT because they presented lesions as a scar or small ulcer with negative biopsy, at post-treatment follow-up. Motiro was used for batch mode analysis of pCLE videos. It automatically characterized the tumoral region and its surroundings. That enabled classifying a patient as responsive or non-responsive to neoCRT based on pre-neoCRT pCLE videos. Motiro classified patients as responsive or non-responsive to neoCRT with an accuracy of ~ 0.62 when using images of the tumor. When using images of regions surrounding the tumor, it reached an accuracy of ~ 0.70. Feature analysis showed that spatial heterogeneity in fluorescence distribution within regions surrounding the tumor was the main contributor to predicting response to neoCRT. We developed a computational framework to predict response to neoCRT by locally advanced rectal cancer patients based on pCLE images acquired pre-neoCRT. We demonstrate that the analysis of the mucosa of the region surrounding the tumor provides stronger predictive power.

Pretreatment colostomy in patients with anal squamous cell carcinoma: Risk factors for a permanent stoma.

BACKGROUND: The current standard of care for anal squamous cell carcinoma (SCC) is concurrent chemoradiation (CRT), which enables tumor eradication while preserving the anal sphincter. Patients with locally advanced tumors, however, may experience complications that preclude treatment before stoma creation. OBJECTIVE: To evaluate the reversal rate of pretreatment stomas and the risk factors associated with nonreversal. METHODS: This single-institution retrospective cohort study using a prospective database included patients diagnosed with anal SCC from January 2008 to December 2020 who required a stoma before curative CRT. RESULTS: In total, 651 patients were identified; 65 required a stoma before chemoradiation due to obstruction (43.1%), rectovaginal fistula (20%), and perianal sepsis (36.9%). The stoma was reversed in nine patients after a mean follow-up of 35.8 months. Risk factors associated with a permanent stoma were perianal sepsis (p = 0.010), interruptions during radiotherapy for more than 7 days (p = 0.010), male sex (p = 0.013), poor performance status (Eastern Cooperative Oncology Group [ECOG] ≥ 2) (p = 0.023), large tumors (p = 0.045), and cisplatin-based chemotherapy (p = 0.047). CONCLUSIONS: Pretreatment stomas are unlikely to be reversed, and risk factors for a permanent stoma are perianal sepsis, interruptions during radiotherapy for more than 7 days, male sex, poor performance status (ECOG ≥ 2), large tumors, and cisplatin-based chemotherapy.

Two-step ESD: an option for en-bloc resection of extensive colorectal laterally spreading tumors.

Background and study aims Endoscopic submucosal dissection (ESD) is considered feasible and safe for treatment of colorectal laterally spreading tumors (LST), However it remains a challenge in case of extensive lesions even for experts. This study aimed to describe a new method to facilitate ESD of extensive colorectal LSTs. Between July 2010 and January 2018, 140 patients underwent ESD for colorectal LSTs. Four of them were submitted to two-step ESD and were included in this retrospective study. The submucosal dissection of lesions larger than 12 cm started and continued until the medical team decided to pause the procedure and continue it in a second step. The second procedure was performed 2 days after to finish the en-bloc resection.Three patients were male, with mean age of 67.2y (±â€Š2.2). All lesions were located in the rectum, with a mean size of 153.7 mm (±â€Š33.8). En-bloc and curative resection were successfully achieved in all cases. Mean duration of the first step of the procedure was 255 minutes (±â€Š61.8), and mean duration of the second step was 205 minutes (±â€Š205). Overall mean duration of both steps was 460 minutes (±â€Š168). Mean dissected area in the first step of the procedure was approximately 55 % of the lesion. No adverse events were observed. In conclusion, our results suggest that performing ESD in two steps could be a feasible and safe option for exceptional cases in which is not possible to finish the procedure in one step, avoiding the morbidity of surgical treatment.

Role of Magnification Chromoendoscopy in the Management of Colorectal Neoplastic Lesions Suspicious for Submucosal Invasion.

BACKGROUND: Correctly predicting the depth of tumor invasion in the colorectal wall is crucial for successful endoscopic resection of superficial colorectal neoplasms. OBJECTIVE: The aim of this study was to assess the accuracy of magnifying chromoendoscopy in a Western medical center to predict the depth of invasion by the pit pattern classification in patients with colorectal neoplasms with a high risk of submucosal invasion. DESIGN: This single-center retrospective study, from a prospectively collected database, was conducted between April 2009 and June 2015. SETTINGS: The study was conducted at a single academic center. PATIENTS: Consecutive patients with colorectal neoplasms with high risk of submucosal invasion were included. These tumors were defined by large (≥20 mm) sessile polyps (nonpedunculated), laterally spreading tumors, or depressed lesions of any size. INTERVENTIONS: Patients underwent magnifying chromoendoscopy and were classified according to the Kudo pit pattern. The therapeutic decision, endoscopic or surgery, was defined by the magnification assessment. MAIN OUTCOME MEASURES: Sensitivity, specificity, and positive and negative predictive values of magnifying chromoendoscopy for assessment of these lesions were determined. RESULTS: A total of 123 lesions were included, with a mean size of 54.0 ± 37.1 mm. Preoperative magnifying chromoendoscopy with pit pattern classification had 73.3% sensitivity, 100% specificity, 100% positive predictive value, 96.4% negative predictive value, and 96.7% accuracy to predict depth of invasion and consequently to guide the appropriate treatment. Thirty-three rectal lesions were also examined by MRI, and 31 were diagnosed as T2 lesions. Twenty two (70.1%) of these lesions were diagnosed as noninvasive by magnifying colonoscopy, were treated by endoscopic resection, and met the curative criteria. LIMITATIONS: This was a single-center retrospective study with a single expert endoscopist experience. CONCLUSIONS: Magnifying chromoendoscopy is highly accurate for assessing colorectal neoplasms suspicious for submucosal invasion and can help to select the most appropriate treatment. See Video Abstract at http://links.lww.com/DCR/A920.

Screening anal dysplasia in HIV-infected patients: is there an agreement between anal pap smear and high-resolution anoscopy-guided biopsy?

PURPOSE: The purpose of this study was to analyze the agreement between anal Pap smear and high-resolution anoscopy-guided biopsy in diagnosing anal dysplasia in HIV-infected patients. METHODS: We conducted cross-sectional analysis of HIV-infected patients receiving anal dysplasia screening as part of routine care. Agreement between measures was estimated by weighted kappa statistics, using a three-tiered cytologic and histologic grading system (normal, low-grade dysplasia, and high-grade dysplasia). Estimates of sensitivity, specificity, and predictive values were calculated using a two-tiered cytologic and histologic grading system ("without dysplasia" and "with dysplasia of any grade"). Estimates were also calculated for the detection of high-grade dysplasia. RESULTS: During a one-year period, 222 patients underwent 330 anal Pap smears followed by high-resolution anoscopy-guided biopsies. There were 311 satisfactory Pap smears with concurrent biopsies. Considering histology the standard, the frequency of anal dysplasia was 46%. Kappa agreement between anal Pap smear and biopsy was 0.20. For detection of anal dysplasia of any grade, anal Pap smear showed sensitivity of 61%, specificity of 60%, positive predictive value of 56%, and negative predictive value of 64%. For high-grade dysplasia, anal Pap smear showed sensitivity of 16% and specificity of 97%. CONCLUSION: Anal Pap smears alone were not sensitive enough to rule out anal dysplasia. We recommend that high-resolution anoscopy-guided biopsy be incorporated as a complementary screening test for anal dysplasia in high-risk patients. Following baseline high-resolution anoscopy, these individuals could be followed with serial anal cytology to dictate the need for future high-resolution anoscopy-guided biopsies.

Fatal pulmonary thromboembolism in gastrectomy intraoperative procedures by gastric adenocarcinoma: case report

Relata-se um caso de paciente com adenocarcinoma gastrico com indicacao de gastrectomia. O ato operatorio transcorreu sem anormalidades. Foi realizada gastrectomia subtotal paliativa, pois encontrou-se linfonodos para-aorticos comprometidos pela neoplasia, confirmado pelo exame anatomo-patologico de congelacao realizado no decorrer da intervencao. Ao fim da confeccao da gastroentero-anastomose o paciente passou a apresentar bradicardia intensa: 38 batimentos por minuto (bpm), hipotensao arterial, alteracoes do tracado do eletrocardiograma (Supra-desnivelamento do segmento ST) e parada cardiaca. Realizadas as manobras de ressucitacao com sucesso temporario, ja que a seguir o paciente apresentou novo colapso circulatorio, sendo novamente recuperado, finalmente a terceira parada cardiaca foi irreversivel e constatou-se o obito intra-operatorio