Digital Hepatic Iron Content: An Artificial Intelligence Model for Spatially Resolved Histologic Iron Quantitative Analysis in Liver Samples.

Currently, the precise evaluation of tissue hepatic iron content (HIC) requires laboratory testing using tissue-destructive methods based on colorimetry or spectrophotometry. To maximize the use of routine histologic stains in this context, we developed an artificial intelligence (AI) model for the recognition and spatially resolved measurement of iron in liver samples. Our AI model was developed using a cloud-based, supervised deep learning platform (Aiforia Technologies). Using digitized Pearl Prussian blue iron stain whole slide images representing the full spectrum of changes seen in hepatic iron overload, our training set consisted of 59 cases, and our validation set consisted of 19 cases. The study group consisted of 98 liver samples from 5 different laboratories, for which tissue quantitative analysis using inductively coupled plasma mass spectrometry was available, collected between 2012 and 2022. The correlation between the AI model % iron area and HIC was Rs = 0.93 for needle core biopsy samples (n = 73) and Rs = 0.86 for all samples (n = 98). The digital hepatic iron index (HII) was highly correlated with HII > 1 (area under the curve [AUC] = 0.93) and HII > 1.9 (AUC = 0.94). The percentage area of iron within hepatocytes (vs Kupffer cells and portal tract iron) identified patients with any hereditary hemochromatosis-related mutations (either homozygous or heterozygous) (AUC = 0.65, P = .01) with at least similar accuracy than HIC, HII, and any histologic iron score. The correlation between the Deugnier and Turlin score and the AI model % iron area for all patients was Rs = 0.87 for total score, Rs = 0.82 for hepatocyte iron score, and Rs = 0.84 for Kupffer cell iron score. Iron quantitative analysis using our AI model was highly correlated with both detailed histologic scoring systems and tissue quantitative analysis using inductively coupled plasma mass spectrometry and offers advantages (related to the spatial resolution of iron analysis and the nontissue-destructive nature of the test) over standard quantitative methods.

Performance of an Artificial Intelligence Model for Recognition and Quantitation of Histologic Features of Eosinophilic Esophagitis on Biopsy Samples.

We have developed an artificial intelligence (AI)-based digital pathology model for the evaluation of histologic features related to eosinophilic esophagitis (EoE). In this study, we evaluated the performance of our AI model in a cohort of pediatric and adult patients for histologic features included in the Eosinophilic Esophagitis Histologic Scoring System (EoEHSS). We collected a total of 203 esophageal biopsy samples from patients with mucosal eosinophilia of any degree (91 adult and 112 pediatric patients) and 10 normal controls from a prospectively maintained database. All cases were assessed by a specialized gastrointestinal (GI) pathologist for features in the EoEHSS at the time of original diagnosis and rescored by a central GI pathologist (R.K.M.). We subsequently analyzed whole-slide image digital slides using a supervised AI model operating in a cloud-based, deep learning AI platform (Aiforia Technologies) for peak eosinophil count (PEC) and several histopathologic features in the EoEHSS. The correlation and interobserver agreement between the AI model and pathologists (Pearson correlation coefficient [rs] = 0.89 and intraclass correlation coefficient [ICC] = 0.87 vs original pathologist; rs = 0.91 and ICC = 0.83 vs central pathologist) were similar to the correlation and interobserver agreement between pathologists for PEC (rs = 0.88 and ICC = 0.91) and broadly similar to those for most other histologic features in the EoEHSS. The AI model also accurately identified PEC of >15 eosinophils/high-power field by the original pathologist (area under the curve [AUC] = 0.98) and central pathologist (AUC = 0.98) and had similar AUCs for the presence of EoE-related endoscopic features to pathologists' assessment. Average eosinophils per epithelial unit area had similar performance compared to AI high-power field-based analysis. Our newly developed AI model can accurately identify, quantify, and score several of the main histopathologic features in the EoE spectrum, with agreement regarding EoEHSS scoring which was similar to that seen among GI pathologists.

Artificial intelligence-based reticulin proportionate area - a novel histological outcome predictor in hepatocellular carcinoma.

AIMS: Reticulin stain is used routinely in the histological evaluation of hepatocellular carcinoma (HCC). The goal of this study was to assess whether the histological reticulin proportionate area (RPA) in HCCs predicts tumour-related outcomes. METHODS AND RESULTS: We developed and validated a supervised artificial intelligence (AI) model that utilises a cloud-based, deep-learning AI platform (Aiforia Technologies, Helsinki, Finland) to specifically recognise and quantify the reticulin framework in normal livers and HCCs using routine reticulin staining. We applied this reticulin AI model to a cohort of consecutive HCC cases from patients undergoing curative resection between 2005 and 2015. A total of 101 HCC resections were included (median age = 68 years, 64 males, median follow-up time = 49.9 months). AI model RPA reduction of > 50% (compared to normal liver tissue) was predictive of metastasis [hazard ratio (HR) = 3.76, P = 0.004, disease-free survival (DFS, HR = 2.48, P < 0.001) and overall survival (OS), HR = 2.80, P = 0.001]. In a Cox regression model, which included clinical and pathological variables, RPA decrease was an independent predictor of DFS and OS and the only independent predictor of metastasis. Similar results were found in the moderately differentiated HCC subgroup (WHO grade 2), in which reticulin quantitative analysis was an independent predictor of metastasis, DFS and OS. CONCLUSION: Our data indicate that decreased RPA is a strong predictor of various HCC-related outcomes, including within the moderately differentiated subgroup. Reticulin, therefore, may represent a novel and important prognostic HCC marker, to be further explored and validated.

Studying Early Decision Making with Progressive Bar Charts.

We conduct a user study to quantify and compare user performance for a value comparison task using four bar chart designs, where the bars show the mean values of data loaded progressively and updated every second (progressive bar charts). Progressive visualization divides different stages of the visualization pipeline-data loading, processing, and visualization-into iterative animated steps to limit the latency when loading large amounts of data. An animated visualization appearing quickly, unfolding, and getting more accurate with time, enables users to make early decisions. However, intermediate mean estimates are computed only on partial data and may not have time to converge to the true means, potentially misleading users and resulting in incorrect decisions. To address this issue, we propose two new designs visualizing the history of values in progressive bar charts, in addition to the use of confidence intervals. We comparatively study four progressive bar chart designs: with/without confidence intervals, and using near-history representation with/without confidence intervals, on three realistic data distributions. We evaluate user performance based on the percentage of correct answers (accuracy), response time, and user confidence. Our results show that, overall, users can make early and accurate decisions with 92% accuracy using only 18% of the data, regardless of the design. We find that our proposed bar chart design with only near-history is comparable to bar charts with only confidence intervals in performance, and the qualitative feedback we received indicates a preference for designs with history.

Development and technical validation of an artificial intelligence model for quantitative analysis of histopathologic features of eosinophilic esophagitis.

Background: In an attempt to provide quantitative, reproducible, and standardized analyses in cases of eosinophilic esophagitis (EoE), we have developed an artificial intelligence (AI) digital pathology model for the evaluation of histologic features in the EoE/esophageal eosinophilia spectrum. Here, we describe the development and technical validation of this novel AI tool. Methods: A total of 10 726 objects and 56.2 mm2 of semantic segmentation areas were annotated on whole-slide images, utilizing a cloud-based, deep learning artificial intelligence platform (Aiforia Technologies, Helsinki, Finland). Our training set consisted of 40 carefully selected digitized esophageal biopsy slides which contained the full spectrum of changes typically seen in the setting of esophageal eosinophilia, ranging from normal mucosa to severe abnormalities with regard to each specific features included in our model. A subset of cases was reserved as independent "test sets" in order to assess the validity of the AI model outside the training set. Five specialized experienced gastrointestinal pathologists scored each feature blindly and independently of each other and of AI model results. Results: The performance of the AI model for all cell type features was similar/non-inferior to that of our group of GI pathologists (F1-scores: 94.5-94.8 for AI vs human and 92.6-96.0 for human vs human). Segmentation area features were rated for accuracy using the following scale: 1. "perfect or nearly perfect" (95%-100%, no significant errors), 2. "very good" (80%-95%, only minor errors), 3. "good" (70%-80%, significant errors but still captures the feature well), 4. "insufficient" (less than 70%, significant errors compromising feature recognition). Rating scores for tissue (1.01), spongiosis (1.15), basal layer (1.05), surface layer (1.04), lamina propria (1.15), and collagen (1.11) were in the "very good" to "perfect or nearly perfect" range, while degranulation (2.23) was rated between "good" and "very good". Conclusion: Our newly developed AI-based tool showed an excellent performance (non-inferior to a group of experienced GI pathologists) for the recognition of various histologic features in the EoE/esophageal mucosal eosinophilia spectrum. This tool represents an important step in creating an accurate and reproducible method for semi-automated quantitative analysis to be used in the evaluation of esophageal biopsies in this clinical context.

Unique interstitial miRNA signature drives fibrosis in a murine model of autosomal dominant polycystic kidney disease.

AIM: To delineate changes in miRNA expression localized to the peri-cystic local microenvironment (PLM) in an orthologous mouse model of autosomal dominant polycystic kidney disease (ADPKD) (mcwPkd1(nl/nl) ). METHODS: We profiled miRNA expression in the whole kidney and laser captured microdissection (LCM) samples from PLM in mcwPkd1(nl/nl) kidneys with Qiagen miScript 384 HC miRNA PCR arrays. The three times points used are: (1) post-natal (PN) day 21, before the development of trichrome-positive areas; (2) PN28, the earliest sign of trichrome staining; and (3) PN42 following the development of progressive fibrosis. PN21 served as appropriate controls and as the reference time point for comparison of miRNA expression profiles. RESULTS: LCM samples revealed three temporally upregulated miRNAs [2 to 2.75-fold at PN28 and 2.5 to 4-fold (P ≤ 0.05) at PN42] and four temporally downregulated miRNAs [2 to 2.75 fold at PN28 and 2.75 to 5-fold (P ≤ 0.05) at PN42]. Expression of twenty-six miRNAs showed no change until PN42 [six decreased (2.25 to 3.5-fold) (P ≤ 0.05) and 20 increased (2 to 4-fold) (P ≤ 0.05)]. Many critical miRNA changes seen in the LCM samples from PLM were not seen in the contralateral whole kidney. CONCLUSION: Precise sampling with LCM identifies miRNA changes that occur with the initiation and progression of renal interstitial fibrosis (RIF). Identification of the target proteins regulated by these miRNAs will provide new insight into the process of fibrosis and identify unique therapeutic targets to prevent or slow the development and progression of RIF in ADPKD.

Semi-automated quantification of retinal IS/OS damage in en-face OCT image.

A variety of vision ailments are indicated by structural changes in the retinal substructures of the posterior segment of the eye. In particular, integrity of the inner-segment/outer-segment (IS/OS) junction directly relates to the visual acuity. In the en-face optical coherence tomography (OCT) image, IS/OS damage manifests as a dark spot in the foveal region, and its quantification, usually performed by experts, assumes diagnostic significance. In this context, in view of the general scarcity of experts, it becomes imperative to develop algorithmic methods to reduce expert time and effort. Accordingly, we propose a semi-automated method based on level sets. As the energy function, we adopt mutual information which exploits the difference in statistical properties of the lesion and its surroundings. On a dataset of 27 en-face OCT images, segmentation obtained by the proposed algorithm exhibits close visual agreement with that obtained manually. Importantly, our results also match manual results in various statistical criteria. In particular, we achieve a mean Dice coefficient of 85.69%, desirably close to the corresponding observer repeatability index of 89.45%. Finally, we quantify algorithmic accuracy in terms of two quotient measures, defined relative to observer repeatability, which could be used as bases for comparison with future algorithms, even if the latter are tested on disparate datasets.