PPSW–SHAP: Towards Interpretable Cell Classification Using Tree-Based SHAP Image Decomposition and Restoration for High-Throughput Bright-Field Imaging

计算机科学 可解释性 人工智能 启发式 吞吐量 领域(数学) 聚类分析 机器学习 树(集合论) 模式识别(心理学) 无线 数学 电信 数学分析 纯数学
作者
Polat Göktaş,Ricardo Simón Carbajo
出处
期刊:Cells [Multidisciplinary Digital Publishing Institute]
卷期号:12 (10): 1384-1384 被引量:8
标识
DOI:10.3390/cells12101384
摘要

Advancements in high−throughput microscopy imaging have transformed cell analytics, enabling functionally relevant, rapid, and in−depth bioanalytics with Artificial Intelligence (AI) as a powerful driving force in cell therapy (CT) manufacturing. High−content microscopy screening often suffers from systematic noise, such as uneven illumination or vignetting artifacts, which can result in false−negative findings in AI models. Traditionally, AI models have been expected to learn to deal with these artifacts, but success in an inductive framework depends on sufficient training examples. To address this challenge, we propose a two−fold approach: (1) reducing noise through an image decomposition and restoration technique called the Periodic Plus Smooth Wavelet transform (PPSW) and (2) developing an interpretable machine learning (ML) platform using tree−based Shapley Additive exPlanations (SHAP) to enhance end−user understanding. By correcting artifacts during pre−processing, we lower the inductive learning load on the AI and improve end−user acceptance through a more interpretable heuristic approach to problem solving. Using a dataset of human Mesenchymal Stem Cells (MSCs) cultured under diverse density and media environment conditions, we demonstrate supervised clustering with mean SHAP values, derived from the ‘DFT Modulus’ applied to the decomposition of bright−field images, in the trained tree−based ML model. Our innovative ML framework offers end-to-end interpretability, leading to improved precision in cell characterization during CT manufacturing.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
3秒前
戴先森发布了新的文献求助10
6秒前
7秒前
钙离子发布了新的文献求助10
9秒前
卡卡完成签到,获得积分10
11秒前
khc发布了新的文献求助10
11秒前
xx完成签到,获得积分10
13秒前
15秒前
ab发布了新的文献求助10
15秒前
16秒前
英俊的铭应助khc采纳,获得10
17秒前
21秒前
MrRen发布了新的文献求助10
21秒前
壮观的擎发布了新的文献求助10
21秒前
风清扬发布了新的文献求助10
21秒前
ab完成签到,获得积分10
24秒前
善学以致用应助w_sea采纳,获得10
25秒前
Qo日不落o完成签到,获得积分10
27秒前
MchemG应助科研通管家采纳,获得10
28秒前
李爱国应助科研通管家采纳,获得10
28秒前
orixero应助科研通管家采纳,获得10
28秒前
CodeCraft应助科研通管家采纳,获得10
28秒前
MchemG应助科研通管家采纳,获得10
28秒前
不懈奋进应助阔达幻丝采纳,获得30
28秒前
深情安青应助科研通管家采纳,获得10
28秒前
我是老大应助科研通管家采纳,获得10
28秒前
fangjie应助科研通管家采纳,获得10
28秒前
学术达人应助科研通管家采纳,获得20
28秒前
思源应助科研通管家采纳,获得10
28秒前
Ava应助科研通管家采纳,获得10
28秒前
28秒前
28秒前
28秒前
爆米花应助科研通管家采纳,获得10
28秒前
28秒前
无花果应助苹果巧蕊采纳,获得30
30秒前
32秒前
32秒前
32秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 1370
Secondary Ion Mass Spectrometry: Basic Concepts, Instrumental Aspects, Applications and Trends 1000
Comparison of adverse drug reactions of heparin and its derivates in the European Economic Area based on data from EudraVigilance between 2017 and 2021 500
[Relativity of the 5-year follow-up period as a criterion for cured cancer] 500
Statistical Analysis of fMRI Data, second edition (Mit Press) 2nd ed 500
Sellars and Davidson in Dialogue 500
Huang‘s catheter ablation of cardiac arrthymias 5th edtion 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3943024
求助须知:如何正确求助?哪些是违规求助? 3488034
关于积分的说明 11046786
捐赠科研通 3218664
什么是DOI,文献DOI怎么找? 1779086
邀请新用户注册赠送积分活动 864519
科研通“疑难数据库(出版商)”最低求助积分说明 799562