---
type: "post"
id: "a-habr-author-described-a-research-prototype-for-8261b9"
slug: "a-habr-author-described-a-research-prototype-for-8261b9"
title: "A Habr author described a research prototype for flagging possible hemorrhages in head CT slices"
description: "A Habr author described a research prototype for flagging possible hemorrhages in head CT slices."
retrieval_nugget: "A Habr author described a research prototype for flagging possible hemorrhages in head CT slices."
published_at: "2026-10-24"
updated_at: "2026-10-24"
record_date: "2026-10-24"
date_kind: "published_at"
topics: ["google"]
entities: ["Google Colab","Tesla T4","EfficientNet-B0","Kaggle","Habr"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Новый исследовательский прототип выявляет кровоизлияния на КТ головы; на небольшой выборке полная кросс-валидация дала AUC 0,931, но клинической проверки нет."
prior_refs: []
source_url: "https://habr.com/ru/articles/1098766?amp%3Butm_medium=rss&amp%3Butm_source=habrahabr"
source_urls: ["https://habr.com/ru/articles/1098766?amp%3Butm_medium=rss&amp%3Butm_source=habrahabr"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:a-habr-author-described-a-research-prototype-for-8261b9"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/a-habr-author-described-a-research-prototype-for-8261b9/","markdown":"https://newruntime.com/posts/a-habr-author-described-a-research-prototype-for-8261b9.md","json":"https://newruntime.com/posts/a-habr-author-described-a-research-prototype-for-8261b9.json"}
---

# A Habr author described a research prototype for flagging possible hemorrhages in head CT slices

## Retrieval answer

A Habr author described a research prototype for flagging possible hemorrhages in head CT slices.

A Habr author described a research prototype for flagging possible hemorrhages in head CT slices. The model was trained in Google Colab on a free Tesla T4 using 82 patients, 2,501 slices, and 318 hemorrhage-positive slices from an open Kaggle dataset. It used EfficientNet-B0 with 320x320 inputs and five patient-grouped validation folds.

The full input, combining brain and bone windows with a contrast-stretched brain channel, reached slice-level AUC 0.931 and patient-level AUC 0.914. An initial fold had reported AUC 0.963, but the full cross-validation result was lower. A bone-window-only model reached AUC 0.861; the author tested fractures and slice position as possible confounders but did not identify the source of that signal.

Adding a segmentation decoder left AUC nearly unchanged, at 0.932, while average precision rose from 0.699 to 0.795. At a target 95% slice-level sensitivity, specificity was 0.70 to 0.75; patient-level targets were not sustained, with two to three missed patients among 36 positive cases. The source does not establish clinical validity, diagnostic suitability, or regulatory clearance.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)