Improving Ki67 assessment concordance by the use of an artificial intelligence-empowered microscope: a multi-institutional ring study.

AIMS: The nuclear proliferation biomarker Ki67 plays potential prognostic and predictive roles in breast cancer treatment. However, the lack of interpathologist consistency in Ki67 assessment limits the clinical use of Ki67. The aim of this article was to report a solution utilising an artificial intelligence (AI)-empowered microscope to improve Ki67 scoring concordance. METHODS AND RESULTS: We developed an AI-empowered microscope in which the conventional microscope was equipped with AI algorithms, and AI results were provided to pathologists in real time through augmented reality. We recruited 30 pathologists with various experience levels from five institutes to assess the Ki67 labelling index on 100 Ki67-stained slides from invasive breast cancer patients. In the first round, pathologists conducted visual assessment on a conventional microscope; in the second round, they were assisted with reference cards; and in the third round, they were assisted with an AI-empowered microscope. Experienced pathologists had better reproducibility and accuracy [intraclass correlation coefficient (ICC) = 0.864, mean error = 8.25%] than inexperienced pathologists (ICC = 0.807, mean error = 11.0%) in visual assessment. Moreover, with reference cards, inexperienced pathologists (ICC = 0.836, mean error = 10.7%) and experienced pathologists (ICC = 0.875, mean error = 7.56%) improved their reproducibility and accuracy. Finally, both experienced pathologists (ICC = 0.937, mean error = 4.36%) and inexperienced pathologists (ICC = 0.923, mean error = 4.71%) improved the reproducibility and accuracy significantly with the AI-empowered microscope. CONCLUSION: The AI-empowered microscope allows seamless integration of the AI solution into the clinical workflow, and helps pathologists to obtain higher consistency and accuracy for Ki67 assessment.

Comparison of the efficacy of Nutritional Risk Screening 2002 and Mini Nutritional Assessment Short Form in recognizing sarcopenia and predicting its mortality.

OBJECTIVE: This study aimed to examine the efficacy of Nutritional Risk Screening 2002 (NRS2002) and Mini Nutritional Assessment Short Form (MNA-SF) in recognizing sarcopenia and predicting its mortality in Chinese geriatric hospitalized patients. METHODS: A prospective analysis was performed in 430 hospitalized geriatric patients. Nutrition status was assessed using the NRS2002 and MNA-SF scales. Anthropometric measures and biochemical parameters were carried out for each patient. Sarcopenia was defined according to the revised consensus definition of the European Working Group on Sarcopenia in Older People (EWGSOP2). Patients were follow-up for up to 26 months. RESULTS: The overall prevalence of sarcopenia was 35.3% in this population. In the sarcopenic patients, 53 (34.9%) were malnutrition/nutritional risk according to NRS2002 assessment and 101 (66.4%) patients were malnutrition/nutritional risk according to MNA-SF assessment. NRS2002 vs MNA-SF showed moderate agreement (κ = 0.460, P < 0.001). Receiver operating characteristic analysis showed that the area under the curve of MNA-SF was larger than NRS2002 in recognizing sarcopenia (0.763 vs 0.649, P = 0.001). During a median follow-up time of 20.22 months, 48 (31.6%) sarcopenic patients died. The Kaplan-Meier curve demonstrated that malnutrition/nutritional risk patients according to whether NRS2002 or MNA-SF assessment had a higher risk of death than the normal nutrition patients (χ2 = 15.728, P < 0.001; χ2 = 7.039, P = 0.008, respectively). Age, serum albumin levels, and NRS2002 score were independent factors influencing the mortality. CONCLUSION: MNA-SF score may be better than the NRS2002 score to recognize sarcopenia in Chinese geriatric population. Both NRS2002 and MNA-SF scores could predict mortality, but NRS2002 score was the independent predict factor.

Assessment of T staging and mesorectal fascia status using high-resolution MRI in rectal cancer with rectal distention.

AIM: To determine the accuracy of high-resolution magnetic resonance imaging (MRI) using phased-array coil for preoperative assessment of T staging and mesorectal fascia infiltration in rectal cancer with rectal distention. METHODS: In a prospective study of 67 patients with primary rectal cancer, high-resolution magnetic resonance imaging (in-plane resolution, 0.66 multiply 0.56) with phased-array coil were performed for T-staging and measurement of distance between the tumor and the mesorectal fascia. The assessment of MRI was compared with postoperative histopathologic findings. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were evaluated. RESULTS: The overall magnetic resonance accuracy was 85.1% for T staging and 88% for predicting mesorectal fascia involvement. Magnetic resonance sensitivity, specificity, accuracy, positive predictive value, and negative predictive value was 70%, 97.9%, 89.6%, 93.3% and 88.5% for