littlEye AI

About

littlEye AI grew from a simple idea: the microscopic world gives meaning to the macroscopic one. It is built for forensic pathologists and pathologists in practice, but above all for medical students as an educational companion to histology and pathology — and for every enthusiast for whom a look through the eyepiece opens an understanding of the whole. Teach your own AI model to recognize histology slides — right on your iPhone, iPad or Mac, offline, without a single pixel leaving your device. TRAIN YOUR OWN MODELS • H&E slide dataset covering 27 organs and tissues — from brain, lung and heart to thyroid, breast and colon • Colleague slide review with an audit trail — majority vote sets the final diagnosis • On-device Core ML training: held-out test set, confusion matrix, per-class sensitivity and precision • Mark the finding with a crop; magnifications from 4× to 1000× and a stain field (H&E, PAS, trichrome, silver, elastic…) • Learning from corrections: fix a wrong result and add the image to your dataset in one tap — the next training round learns from it • Portable .le3AI models and .le3set slide datasets with metrics and audit trail — encrypted, shared via AirDrop or mail CASE WORKFLOW • Scanner slides attached to a case number, viewing with zoom • Case history, autopsy conclusion and toxicology as inputs • Tissue check: the organ-recognition model flags a possible slide mix-up • Concise summary with a "slides only" and a "with case data" conclusion — one tap to clipboard (Word) • Archiving and full backup to an external drive KNOWLEDGE BASE • Atlas of ~40 diagnoses with microscopic descriptions, key features and suggested conclusions • Image evaluation with a preliminary diagnosis and report draft; a field-of-view crop matches the image scale to the training • Education module: "what next after H&E" guide, special stains (Van Gieson, trichrome, reticulin, Perls…), IHC markers (CD68, fibronectin, β-APP, C5b-9…), cellular elements and pigments • Descriptions draw on referenced literature (Robbins & Cotran, Knight, Bancroft, Dabbs) — the source list is in the app • Fully bilingual SK/EN, professional and lay terminology ABOUT THE PROJECT littlEye AI is developed in collaboration by specialists from three departments of the Faculty of Medicine, Comenius University in Bratislava: the Institute of Histology and Embryology, the Institute of Pathological Anatomy, and the Institute of Forensic Medicine and Forensic Toxicology. The content is developed by Paulína Gálfiová, MD, PhD, Richard Hokša, MD, Ján Šikuta, MD, PhD, and other members of these institutes, building on the experience from the apps 4n6 Tools and Colorime3ka. PRIVACY The app makes no network connections. Images, cases and models remain exclusively on your device. The transfer files .le3AI and .le3set are encrypted — only littlEye AI can open them. littlEye AI is a research and decision-support tool for qualified professionals. It is not a medical device and does not provide diagnoses — the final assessment always belongs to the pathologist or forensic physician.