Artificial intelligence and high-resolution anoscopy: automatic identification of anal squamous cell carcinoma precursors using a convolutional neural network.

BACKGROUND: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell cancer (ASCC) precursors. Although it is superior to other diagnostic methods, particularly cytology, the visual identification of areas suspected of having high-grade squamous intraepithelial lesions remains difficult. Convolutional neural networks (CNNs) have shown great potential for assessing endoscopic images. The aim of the present study was to develop a CNN-based system for automatic detection and differentiation of HSIL versus LSIL in HRA images. METHODS: A CNN was developed based on 78 HRA exams from a total of 71 patients who underwent HRA at a single high-volume center (GH Paris Saint-Joseph, Paris, France) between January 2021 and January 2022. A total of 5026 images were included, 1517 images containing HSIL and 3509 LSIL. A training dataset comprising 90% of the total pool of images was defined for the development of the network. The performance of the CNN was evaluated using an independent testing dataset comprising the remaining 10%. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve (AUC) were calculated. RESULTS: The algorithm was optimized for the automatic detection of HSIL and its differentiation from LSIL. Our model had an overall accuracy of 90.3%. The CNN had sensitivity, specificity, positive and negative predictive values of 91.4%, 89.7%, 80.9%, and 95.6%, respectively. The area under the curve was 0.97. CONCLUSIONS: The CNN architecture for application to HRA accurately detected precursors of squamous anal cancer. Further development and implementation of these tools in clinical practice may significantly modify the management of these patients.

Extensive suppuration and being overweight are factors associated with the failure of laser treatment for pilonidal disease: lessons from the first French retrospective cohort.

BACKGROUND: The aim of our study was to assess the efficacy of sinus laser therapy (SiLaT) for the treatment of pilonidal disease. METHODS: All adult patients treated with SiLaT in our department between June 1, 2018, and August 23, 2019, were included in the study. Success was defined as the closure of cutaneous orifices and the absence of discharge or abscesses. RESULTS: We included 29 consecutive patients (22 males) with a median age of 32.5 ± 10.5 years. Eight patients had already undergone prior surgery for pilonidal disease. The procedure was performed under spinal (55%) or general (45%) anesthesia. The mean follow-up was 370.3 days (± 165.8 days). We observed 2 primary failures (6.9%) and 7 recurrences (24.1%). Ultimately, 20 patients were considered to have been cured (69%). The mean time to healing was 25 days (± 8.1 days). No serious complications were reported. Usual activities were resumed within a mean of 4.9 days (± 7.2), and 86% of patients reported being "very satisfied" with the treatment. The body mass index was lower for patients who were cured (24.0 ± 3.6) than for those who experienced treatment failure (27.6 ± 3.4; p = 0.018). The cured patients were less likely to have one or more secondary openings (35.0 versus 88.9%, p = 0.014). CONCLUSIONS: Almost 70% of our patients were cured by SiLaT. Complications were rare and mild. The technique appeared to be less effective for overweight patients and those with one or more secondary openings associated with pilonidal pits.

Hemorrhoidal surgery in patients with IBD: caution is the parent of safety.

BACKGROUND: The aim of this study was to evaluate the outcome of hemorrhoidal surgery in patients with inflammatory bowel disease (IBD) undergoing surgery at our center. METHODS: All adult patients with IBD undergoing hemorrhoidal surgery in our department between November 1, 2013 and July 7, 2020 were included in the study. At the time of surgery, the patients' IBD was in clinical, biological and endoscopic remission, and none of the patients had specific primary anoperineal lesions. RESULTS: We included 25 patients (48% female) with a mean age 48 years (± 13.1 years). There were 13 cases of CD (52%) and 12 of ulcerative colitis (UC). Pharmacological and instrumental hemorrhoidal treatment had failed in all patients. The CD lesions were exclusively ileal (77%) or ileocolic (23%). The surgical procedures performed for CD were mono-hemorrhoidectomy in three patients (21.4%), tripedicular hemorrhoidectomy in six patients (42.9%), and artery ligations with mucopexy in five patients (35.7%). UC was rectal (16.7%), rectosigmoid (66.7%), or pancolic (16.6%). The surgical procedures performed for UC were a tripedicular hemorrhoidectomy in ten patients (83.3%) and artery ligations with mucopexy in two patients (16.7%). The mean duration of postoperative follow-up was 15.1 months. None of the patients was lost to follow-up. The mean time to wound healing after resection was 71.1 days (± 21 days) for patients with CD and 56.9 days (± 6.7 days) for patients with UC (p = 0.05). Postoperative complications were reported for four patients with CD (28.8%) and two patients with UC (16.7%). There was no suppuration, stenosis, or anal incontinence sequelae. CONCLUSIONS: Hemorrhoidal surgery resulted in a non-negligible frequency of complications in our series of IBD patients, especially in those with CD. Caution is, therefore, still necessary in this patient population.

Patients with atherosclerotic peripheral arterial disease have a high risk of lung cancer: Systematic review and meta-analysis of literature.

PURPOSE: Lung cancer and atherosclerosis share common risk factors. Literature data suggest that the prevalence of lung malignancy in patients with peripheral arterial disease (PAD) is higher than in the general population. Our goal was to determine, through a systematic literature review, the prevalence of lung cancer in patients with PAD. METHODS: We consulted available publications in the Cochrane library, MEDLINE, PUBMED, EMBASE, and ClinicalTrials.gov. We included all articles, written in English or French, published between 1990 and 2020 reporting the prevalence of lung cancer in patients with PAD (atherosclerotic aortic aneurysm or peripheral occlusive diseases). Patients with coronary artery disease, cardiac valvulopathy or carotid stenosis were not included. We did not include case reports. We performed a critical analysis of each article. Data were collected from two independent readers. A fixed effect model meta-analysis allowed to estimate a summary prevalence rate. RESULTS: We identified 303 articles, and selected 19 articles according to selection criteria. A total of 16849 patients were included (mean age 68.3 years, 75.1% of males). Aortic aneurysms were found in 29% of patients and atherosclerotic occlusive disease in 66% of patients. Lung cancer was identified in 538 patients, representing a prevalence of 3%. DISCUSSION: Lung cancer is found in 3% of patients with atherosclerotic PAD. This prevalence is higher than that found in lung cancer screening programs performed in the general population of smokers and former smokers. These patients should be screened for lung cancer. Their selection may dramatically increase the benefit of lung cancer screening.

Secondary bleeding following proctological surgery: Rare but potentially severe.

PURPOSE: Haemorrhage following proctological surgery is one of the complications with the greatest potential for severity. The aim of this work was to assess the frequency and risk factors of haemorrhage requiring hospitalization during 30-days postoperatively. METHODS: A retrospective cohort review of all surgeries performed in a Parisian department of medico-surgical proctology between January 2016 and June 2018 was performed. Demographic and surgical data were collected for patients who were hospitalized for postoperative haemorrhage. Their analysis was conducted as a single analysis followed by multivariate analysis. RESULTS: A total of 7533 surgeries were performed on 6727 patients. The mean patient age was 42.6 (±14.3) years and 67.2% were males. Postoperative haemorrhage occurred in 111 patients (1.5%) with a total of 123 haemorrhagic episodes (12 relapses) within a mean of 6 (±5.5) days. In therapeutic terms, 28.5% of haemorrhages required transfusion, 37.4% required haemostasis in the operating theatre and 14.6% required haemostasis under local anaesthesia. Using multivariate analysis, haemorrhage was more frequent after haemorrhoid surgery and in the case of anticoagulant treatment, particularly direct oral anticoagulants, and if the ASA score was equal to 3. Active smoking was associated with a decreased risk of haemorrhage. CONCLUSION: Haemorrhage requiring hospitalization occurred in 1.5% of cases following proctological surgery, 52.8% were severe and recurred in 10.8% of cases. The study also specified certain risk factors for haemorrhage and demonstrated the protective effect of active smoking.

Is quantitative sensory testing helpful in the management of oxaliplatin neuropathy? a two-year clinical study.

PURPOSE: To better understand how quantitative sensory testing could help the clinician in the management of oxaliplatin-induced peripheral neuropathy in terms of earlier and more reliable detection, we conducted a two-year prospective study. METHODS: Thermal sensory assessment, tactile sensory assessment, neuropathic pain assessment and adverse events gradation (NCI-CTC) were performed during treatment and 6 months after treatment completion. RESULTS: 35 patients were enrolled and followed-up during one year. Cold and Warm Detection Thresholds were higher 6 months after treatment completion than at enrollment. Mechanical detection thresholds didn't change significantly. Neurotoxicity was mostly grade-1, only 18% grade-2 and no grade-3. Grade-2 patients received lower oxaliplatin cumulative dose than grade-1, which reveals effective dose adaptation and grade-2 patients were more likely to develop painful neuropathy. CONCLUSION: Thermal thresholds impairment emerges too late to help the clinician in the prophylaxis of neuropathy. Management of OXA-treatment based on NCI-CTC, as currently recommended, remains the best way to detect neuropathy and ensure treatment adaptation.

Evaluation of operator radioprotection using a new injection device during vertebroplasty.

This study aimed to evaluate the protection granted by a simple device (X'TENS(®), Thiebaud, France) and to provide operators with information on the performance of this new device, which has not yet been assessed. Our assumption is that this device efficiently reduces the radiation dose to the operator. In a prospective clinical study, the radiation dose the operator's hand receives has been assessed using a specific sensor (UNFOR Instrument). Each patient included in the study was to receive at least two injections of cement during the procedure. Exposure was measured with and without the range extender. The data collected were then processed using a Wilcoxon matched pairs test. During 14 interventions, 20 vertebrae were treated with both procedures. Eleven women and three men were included. Seven patients underwent vertebroplasty for metastatic lesions and seven for osteoporotic lesions, bone fractures or vertebral compressions. The average injection time was 1.35 minutes with the device and 1.20 without (p=0.75). The dose to the hand per ml injected was 111.37 vs. 166.91 (p<0.05). Theoretically, the protection granted by the range extender depends on the length of the device. Our results are consistent with the inverse-square law. However, the variations in our results indicate that a proper and rigorous use is mandatory for the device to be effective. Given that radioprotection during fluoroscopy procedures is a frequently raised issue, the need for information for a safer practice increases likewise.