Abstract
Background
Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence ...(AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs).
Methods
Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations PIVI-1 threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines.
Results
Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %–93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %–98.9 %) and 92.6 % (95 %CI 90.0 %–95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %–87.3 %) than for experts (91.9 %, 95 %CI 88.5 %–94.5 %); however, nonexperts quickly approached the performance levels of experts over time.
Conclusion
AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopistsʼ high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.
Abstract Background and study aims Artificial Intelligence (AI) systems could make the optical diagnosis (OD) of diminutive colorectal polyps (DCPs) more reliable and objective. This study was aimed ...at prospectively evaluating feasibility and diagnostic performance of AI-standalone and AI-assisted OD of DCPs in a real-life setting by using a white light-based system (GI Genius, Medtronic Co, Minneapolis, Minnesota, United States). Patients and methods Consecutive colonoscopy outpatients with at least one DCP were evaluated by 11 endoscopists (5 experts and 6 non-experts in OD). DCPs were classified in real time by AI (AI-standalone OD) and by the endoscopist with the assistance of AI (AI-assisted OD), with histopathology as the reference standard. Results Of the 480 DCPs, AI provided the outcome “adenoma” or “non-adenoma” in 81.4% (95% confidence interval CI: 77.5–84.6). Sensitivity, specificity, positive and negative predictive value, and accuracy of AI-standalone OD were 97.0% (95% CI 94.0–98.6), 38.1% (95% CI 28.9–48.1), 80.1% (95% CI 75.2–84.2), 83.3% (95% CI 69.2–92.0), and 80.5% (95% CI 68.7–82.8%), respectively. Compared with AI-standalone, the specificity of AI-assisted OD was significantly higher (58.9%, 95% CI 49.7–67.5) and a trend toward an increase was observed for other diagnostic performance measures. Overall accuracy and negative predictive value of AI-assisted OD for experts and non-experts were 85.8% (95% CI 80.0–90.4) vs. 80.1% (95% CI 73.6–85.6) and 89.1% (95% CI 75.6–95.9) vs. 80.0% (95% CI 63.9–90.4), respectively. Conclusions Standalone AI is able to provide an OD of adenoma/non-adenoma in more than 80% of DCPs, with a high sensitivity but low specificity. The human-machine interaction improved diagnostic performance, especially when experts were involved.
A 63-year-old woman was admitted because of sudden ischemic hemyplegia promptly cleared up by intravenous (IV) recombinant tissue plasminogen activator. On subsequent 2-dimensional echocardiogram, we ...observed an extremely mobile homogeneous mass attached by a short stalk to ventricular insertion of anterolateral papillary muscle chordae tendineae. The mass was surgically removed. Gross anatomy showed a mass with a gelatinoids appearance formed on histology by a lining of hyperplastic endocardial cells covering a hypocellular stroma consistent with papillary fibroelastoma. Given the prompt clinical improvement with IV thrombolytic therapy, we postulate that cerebral artery occlusion was at least in part because of thrombotic material.
Glucocorticoid treatment is the standard initial therapy for patients with immune thrombocytopenia (ITP). Despite a rate of 60–80% of initial remissions, only 30 to 50% of adults have a sustained ...response after discontinuation. Second line options are splenectomy, thrombopoietin-receptor agonists (TPO-RAs), rituximab and intravenous immunoglobulin. Third line treatments include a mix of immunosuppressive drugs (e.g. azathioprine, ciclosporin, etc.). Recently international guidelines have proposed a treatment algorithm formalizing TPO-RAs and splenectomy as second and third line respectively, confirming splenectomy as second line choice only in emergency. Here we present a single center observational retrospective study of eltrombopag as second line treatment. We evaluated 48 adult primary chronic ITP patients since 2003. Forty-four out of 48 patients received a first line treatment with glucocorticoids. Twenty-two (61%) patients needed a second line treatment: 18 received eltrombopag, 3 a second course of steroid and one patient underwent splenectomy. Every patient before starting eltrombopag or receiving splenectomy underwent bone marrow examination. Overall response rate to eltrombopag was 94% with a CR rate of 76% and a PR of 23%; only one patient was non responder, underwent splenectomy and received subsequent treatment with rituximab, romiplostim and cyclosporin obtaining CR. One patient developed an autoimmune pancytopenia about a month after starting TPO-RA and in addition to eltrombopag received steroid and rituximab with blood count improvement. After a median follow up of 21,1 months (range 0,4–64,7 months) 16 patients (89%) are still on therapy maintaining response. As regards safety, gastrointestinal side effects were rare and low grade; only one patient discontinued eltrombopag after few weeks, because of dizziness. One patient had a relapse of deep venous thrombosis while no major bleeding complications were observed. Our real-life single center experience confirms efficacy and safety of eltrombopag as second line treatment in chronic ITP patients.
Myeloid sarcomas (MS) are rare extramedullary hematological tumors which generally occur during the natural course of acute myeloid leukemia or chronic myeloid leukemia. Rarely, their onset precedes ...peripheral blood and bone marrow manifestations of disease. Common sites of involvement are skin, bone, soft tissue, lymph nodes, reproductive or digestive organs, and central nervous system.Herein, we report the case of a 72-year-old man affected by JAK2 V617F mutated myeloproliferative neoplasm who developed MS involving collecting system of both kidneys. MS and MS-related obstructive nephropathy were the first signs of the acute evolution of a known chronic hematological malignancy, preceding by some weeks the onset of leukocytosis.
As shown by genomic studies, colorectal cancer (CRC) is a highly heterogeneous disease, where copy number alterations (CNAs) may greatly vary among different patients. To explore whether CNAs may be ...present also in histologically normal tissues from patients affected by CRC, we performed CGH + SNP Microarray on 15 paired tumoral and normal samples. Here, we report for the first time the occurrence of CNAs as a common feature of the histologically normal tissue from CRC patients, particularly CNAs affecting different oncogenes and tumor-suppressor genes, including some not previously reported in CRC and others known as being involved in tumor progression. Moreover, from the comparison of normal vs paired tumoral tissue, we were able to identify three groups: samples with an increased number of CNAs in tumoral vs normal tissue, samples with a similar number of CNAs in both tissues, and samples with a decrease of CNAs in tumoral vs normal tissue, which may be likely due to a selection of the cell population within the tumor. In conclusion, our approach allowed us to uncover for the first time an unexpected frequency of genetic alteration in normal tissue, suggesting that tumorigenic genetic lesions are already present in histologically normal colonic tissue and that the use in array comparative genomic hybridization (CGH) studies of normal samples as reference for the paired tumors can lead to misrepresented genomic data, which may be incomplete or limited, especially if used for the research of target molecules for personalized therapy and for the possible correlation with clinical outcome.