PAIP 2020: Microsatellite instability prediction in colorectal cancer.

Microsatellite instability (MSI) refers to alterations in the length of simple repetitive genomic sequences. MSI status serves as a prognostic and predictive factor in colorectal cancer. The MSI-high status is a good prognostic factor in stage II/III cancer, and predicts a lack of benefit to adjuvant fluorouracil chemotherapy in stage II cancer but a good response to immunotherapy in stage IV cancer. Therefore, determining MSI status in patients with colorectal cancer is important for identifying the appropriate treatment protocol. In the Pathology Artificial Intelligence Platform (PAIP) 2020 challenge, artificial intelligence researchers were invited to predict MSI status based on colorectal cancer slide images. Participants were required to perform two tasks. The primary task was to classify a given slide image as belonging to either the MSI-high or the microsatellite-stable group. The second task was tumor area segmentation to avoid ties with the main task. A total of 210 of the 495 participants enrolled in the challenge downloaded the images, and 23 teams submitted their final results. Seven teams from the top 10 participants agreed to disclose their algorithms, most of which were convolutional neural network-based deep learning models, such as EfficientNet and UNet. The top-ranked system achieved the highest F1 score (0.9231). This paper summarizes the various methods used in the PAIP 2020 challenge. This paper supports the effectiveness of digital pathology for identifying the relationship between colorectal cancer and the MSI characteristics.

Diagnostic Algorithm Based on Machine Learning to Predict Complicated Appendicitis in Children Using CT, Laboratory, and Clinical Features.

To establish a diagnostic algorithm for predicting complicated appendicitis in children based on CT and clinical features. METHODS: This retrospective study included 315 children (<18 years old) who were diagnosed with acute appendicitis and underwent appendectomy between January 2014 and December 2018. A decision tree algorithm was used to identify important features associated with the condition and to develop a diagnostic algorithm for predicting complicated appendicitis, including CT and clinical findings in the development cohort (n = 198). Complicated appendicitis was defined as gangrenous or perforated appendicitis. The diagnostic algorithm was validated using a temporal cohort (n = 117). The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) from the receiver operating characteristic curve analysis were calculated to evaluate the diagnostic performance of the algorithm. RESULTS: All patients with periappendiceal abscesses, periappendiceal inflammatory masses, and free air on CT were diagnosed with complicated appendicitis. In addition, intraluminal air, transverse diameter of the appendix, and ascites were identified as important CT findings for predicting complicated appendicitis. C-reactive protein (CRP) level, white blood cell (WBC) count, erythrocyte sedimentation rate (ESR), and body temperature also showed important associations with complicated appendicitis. The AUC, sensitivity, and specificity of the diagnostic algorithm comprising features were 0.91 (95% CI, 0.86-0.95), 91.8% (84.5-96.4), and 90.0% (82.4-95.1) in the development cohort, and 0.7 (0.63-0.84), 85.9% (75.0-93.4), and 58.5% (44.1-71.9) in test cohort, respectively. CONCLUSION: We propose a diagnostic algorithm based on a decision tree model using CT and clinical findings. This algorithm can be used to differentiate between complicated and noncomplicated appendicitis and to provide an appropriate treatment plan for children with acute appendicitis.

Utilization of a Machine Learning Algorithm for the Application of Ancillary Features to LI-RADS Categories LR3 and LR4 on Gadoxetate Disodium-Enhanced MRI.

BACKGROUND: This study aimed to identify the important ancillary features (AFs) and determine the utilization of a machine-learning-based strategy for applying AFs for LI-RADS LR3/4 observations on gadoxetate disodium-enhanced MRI. METHODS: We retrospectively analyzed MRI features of LR3/4 determined with only major features. Uni- and multivariate analyses and random forest analysis were performed to identify AFs associated with HCC. A decision tree algorithm of applying AFs for LR3/4 was compared with other alternative strategies using McNemar's test. RESULTS: We evaluated 246 observations from 165 patients. In multivariate analysis, restricted diffusion and mild-moderate T2 hyperintensity showed independent associations with HCC (odds ratios: 12.4 [p < 0.001] and 2.5 [p = 0.02]). In random forest analysis, restricted diffusion is the most important feature for HCC. Our decision tree algorithm showed higher AUC, sensitivity, and accuracy (0.84, 92.0%, and 84.5%) than the criteria of usage of restricted diffusion (0.78, 64.5%, and 76.4%; all p < 0.05); however, our decision tree algorithm showed lower specificity than the criterion of usage of restricted diffusion (71.1% vs. 91.3%; p < 0.001). CONCLUSION: Our decision tree algorithm of applying AFs for LR3/4 shows significantly increased AUC, sensitivity, and accuracy but reduced specificity. These appear to be more appropriate in certain circumstances in which there is an emphasis on the early detection of HCC.

Prediction of insufficient hepatic enhancement during the Hepatobiliary phase of Gd-EOB DTPA-enhanced MRI using machine learning classifier and feature selection algorithms.

PURPOSE: The purpose of this study was to reveal the usefulness of machine learning classifier and feature selection algorithms for prediction of insufficient hepatic enhancement in the HBP. METHODS: We retrospectively assessed 214 patients with chronic liver disease or liver cirrhosis who underwent MRI enhanced with Gd-EOB-DTPA. Various liver function tests, Child-Pugh score (CPS) and Model for End-stage Liver Disease Sodium (MELD-Na) score were collected as candidate predictors for insufficient hepatic enhancement. Insufficient hepatic enhancement was assessed using liver-to-portal vein signal intensity ratio and 5-level visual grading. The clinico-laboratory findings were compared using Student's t-test and Mann-Whitney U test. Relationships between the laboratory tests and insufficient hepatic enhancement were assessed using Pearson's and Spearman's rank correlation coefficient. Feature importance was assessed by Random UnderSampling boosting algorithms. The predictive models were constructed using decision tree(DT), k-nearest neighbor(KNN), random forest(RF), and support-vector machine(SVM) classifier algorithms. The performances of the prediction models were analyzed by calculating the area under the receiver operating characteristic curve(AUC). RESULTS: Among four machine learning classifier algorithms using various feature combinations, SVM using total bilirubin(TB) and albumin(Alb) showed excellent predictive ability for insufficient hepatic enhancement(AUC = 0.93, [95% CI: 0.93-0.94]) and higher AUC value than conventional logistic regression(LR) model (AUC = 0.92, [95% CI; 0.92-0.93], predictive models using the MELD-Na (AUC = 0.90 [95% CI: 0.89-0.91]) and CPS (AUC = 0.89 [95% CI: 0.88-0.90]). CONCLUSION: Machine learning-based classifier (i.e. SVM) and feature selection algorithms can be used to predict insufficient hepatic enhancement in the HBP before performing MRI.

Development and operation of a digital platform for sharing pathology image data.

BACKGROUND: Artificial intelligence (AI) research is highly dependent on the nature of the data available. With the steady increase of AI applications in the medical field, the demand for quality medical data is increasing significantly. We here describe the development of a platform for providing and sharing digital pathology data to AI researchers, and highlight challenges to overcome in operating a sustainable platform in conjunction with pathologists. METHODS: Over 3000 pathological slides from five organs (liver, colon, prostate, pancreas and biliary tract, and kidney) in histologically confirmed tumor cases by pathology departments at three hospitals were selected for the dataset. After digitalizing the slides, tumor areas were annotated and overlaid onto the images by pathologists as the ground truth for AI training. To reduce the pathologists' workload, AI-assisted annotation was established in collaboration with university AI teams. RESULTS: A web-based data sharing platform was developed to share massive pathological image data in 2019. This platform includes 3100 images, and 5 pre-processing algorithms for AI researchers to easily load images into their learning models. DISCUSSION: Due to different regulations among countries for privacy protection, when releasing internationally shared learning platforms, it is considered to be most prudent to obtain consent from patients during data acquisition. CONCLUSIONS: Despite limitations encountered during platform development and model training, the present medical image sharing platform can steadily fulfill the high demand of AI developers for quality data. This study is expected to help other researchers intending to generate similar platforms that are more effective and accessible in the future.

PAIP 2019: Liver cancer segmentation challenge.

Pathology Artificial Intelligence Platform (PAIP) is a free research platform in support of pathological artificial intelligence (AI). The main goal of the platform is to construct a high-quality pathology learning data set that will allow greater accessibility. The PAIP Liver Cancer Segmentation Challenge, organized in conjunction with the Medical Image Computing and Computer Assisted Intervention Society (MICCAI 2019), is the first image analysis challenge to apply PAIP datasets. The goal of the challenge was to evaluate new and existing algorithms for automated detection of liver cancer in whole-slide images (WSIs). Additionally, the PAIP of this year attempted to address potential future problems of AI applicability in clinical settings. In the challenge, participants were asked to use analytical data and statistical metrics to evaluate the performance of automated algorithms in two different tasks. The participants were given the two different tasks: Task 1 involved investigating Liver Cancer Segmentation and Task 2 involved investigating Viable Tumor Burden Estimation. There was a strong correlation between high performance of teams on both tasks, in which teams that performed well on Task 1 also performed well on Task 2. After evaluation, we summarized the top 11 team's algorithms. We then gave pathological implications on the easily predicted images for cancer segmentation and the challenging images for viable tumor burden estimation. Out of the 231 participants of the PAIP challenge datasets, a total of 64 were submitted from 28 team participants. The submitted algorithms predicted the automatic segmentation on the liver cancer with WSIs to an accuracy of a score estimation of 0.78. The PAIP challenge was created in an effort to combat the lack of research that has been done to address Liver cancer using digital pathology. It remains unclear of how the applicability of AI algorithms created during the challenge can affect clinical diagnoses. However, the results of this dataset and evaluation metric provided has the potential to aid the development and benchmarking of cancer diagnosis and segmentation.

Seasonal variation in hemoglobin a1c in korean patients with type 2 diabetes mellitus.

A seasonal variation of glucose homeostasis in humans has been reported in various geographic regions. In this study, we examined seasonal variations in hemoglobin A1c (HbA1c) in patients with type 2 diabetes living in Korea. We analyzed 57,970 HbA1c values from 4,191 patients and the association of these values with ambient temperature for 3.5 yr. Overall, HbA1c exhibited its highest values from February to March and its lowest values from September to October (coefficient for cos t = -0.0743, P = 0.058) and the difference between the peak and nadir in a year was 0.16%-0.25%. A statistically significant seasonal variation was observed in the patients who were taking oral anti-diabetic drugs (OADs) without insulin treatment (coefficient for cos t = -0.0949, P < 0.05). The Spearman correlation coefficient between daily HbA1c values and the corresponding 3-month moving average ambient temperature was -0.2154 (95% confidence interval [CI]: -0.2711, -0.1580; P < 0.05). In conclusion, HbA1c values exhibited a seasonal variation in Korean patients with type 2 diabetes, with the highest values during the cold season, particularly in those who were treated with OADs, which should be taken into account in clinical practice for stable glucose control during the cold season.

Lead and cadmium concentrations in shorebirds from the Yeongjong Island, Korea.

This study presents concentration levels of pollutants (lead, and cadmium) in tissues (livers, kidneys, muscles, and bones) of shorebirds (Kentish Plovers (n = 5), Mongolian Plovers (n = 2), Dunlins (n = 6), Great Knots (n = 10), Terek Sandpipers (n = 10)) from Yeongjong Island, Korea in the East Asian-Australian migration flyways during the autumn migration in 1994-1995. Lead concentrations in livers, in kidneys, in muscles, and in bones were significantly different among shorebird species. Lead concentrations in livers of Kentish Plovers (4.76 +/- 2.72 microg/wet g), Mongolian Plovers (2.05 microg/wet g), Dunlins (3.77 +/- 1.07 microg/wet g), and Great Knots (4.27 +/- 3.19 microg/wet g) were less than the toxic level, and lead concentrations in livers of Terek Sandpipers (1.20 +/- 0.94 microg/wet g) were at the background level. Cadmium concentrations in livers, in kidneys, in muscles, and in bones did not vary among shorebirds, and concentrations of cadmium in livers and in kidneys were at background level (respectively, approximate 1 mug/wet g, approximate 2.67 microg/wet g) in all shorebird species. We suggest that interspecific differences of lead and cadmium concentrations were attributed to differences in exposure time and differences of diet, microhabitats in wintering ground. In livers and kidney of shorebirds from Yeongjong Island, lead and cadmium concentrations were higher than other locations previously reported.

Trace elements and pollutants concentrations in shorebirds from Yeongjong Island, Korea in the East Asian-Australian migration flyways.

This study presents concentration levels of trace metals and pollutants (zinc, manganese, copper, lead, and cadmium) in tissues (livers, kidneys, muscles, and bones) of shorebirds from Yeongjong Island, Korea, in the East Asian-Australian migration flyways. Essential trace elements, zinc concentrations in kidneys, and copper concentrations in muscles significantly differed among shorebirds, but manganese concentrations did not differ in each tissue. We suggest that essential elements are within normal range and are maintained there by normal homeostatic mechanism. Lead concentrations in livers, kidneys, muscles, and bones were significantly different among shorebird species. Lead concentrations in livers of Kentish Plovers, Mongolian Plovers, Dunlins, and Great Knots were less than the toxic level, and lead concentrations in livers of Terek Sandpipers were at the background level. Cadmium concentrations in livers, kidneys, muscles, and bones did not vary among shorebirds, and concentrations of cadmium in livers and kidneys were at background level in all shorebirds. In livers of Dunlins from Yeongjong Island, lead and cadmium concentrations were higher than other locations previously reported.

Spontaneous intracerebral haemorrhage caused by extra-adrenal phaeochromocytoma.

We report an 18-year-old man who presented with a sudden onset of headache followed by left hemianopia. A brain CT scan showed intracerebral haemorrhage in the left frontoparietal area, but a cerebral angiogram and MRI revealed no vascular anomaly. The patient was managed conservatively and his headache and visual loss improved over time. Hypertension in the form of paroxysmal attacks led us to suspect phaeochromocytoma. Subsequently, the patient was diagnosed with an extra-adrenal phaeochromocytoma in the left para-aortic area following endocrinological evaluation, abdominal CT scan and (131)I-meta-iodobenzylguanidine (MIBG) scintigraphy. The patient presented here illustrates the importance of a careful search for a remediable cause of hypertension in children and young adults with spontaneous intracerebral haemorrhage.