TA模型性能指标
包含非小细胞肺癌CT图像分类模型的性能指标，采用知识蒸馏和可解释AI技术。
基本信息
资源简介
TA模型性能指标
【一句话概览】
本数据集是 figshare 公开的影像数据集，收录 1 个文件、合计 5.63 KB，主题涵盖 web application designed、training time applicable、recently captured images、obtaining shapley values、models achieved 90，可用于医学图像分割、检测与分类模型的训练与评测，CC BY 4.0 许可开放获取。
【数据集背景】
本数据集源站标题为《TA model’s performance metrics.》。源站首次发布：2024-11-06。
【数据内容】
源站原始描述：Non-small cell lung cancer (NSCLC) exhibits a comparatively slower rate of metastasis in contrast to small cell lung cancer, contributing to approximately 85% of the global patient population. In this work, leveraging CT scan images, we deploy a knowledge distillation technique within teaching assistant (TA) and student frameworks for NSCLC classification. We employed various deep learning models, CNN, VGG19, ResNet152v2, Swin, CCT, and ViT, and assigned roles as teacher, teaching assistant and…
【数据结构与技术规格】
文件数 1 个，合计 5.63 KB。Table 9.xls：application/vnd.ms-excel，5.63 KB。数据集 DOI：10.1371/journal.pone.0306441.t009。
【主题与分类】
源站学科分类：Medicine、Biotechnology、Biological Sciences not elsewhere classified、Cancer、Science Policy。主题标签：web application designed、training time applicable、recently captured images、obtaining shapley values、models achieved 90、knowledge distillation approach、global patient population、comparatively slower rate、classify lung types、class &# 8217。
【适用方向】
影像类数据可用于医学图像分析模型（检测、分割、分类）的训练与评测，也可用于标注质量与成像参数相关性的研究。
【获取与许可】
源站页面：https://plos.figshare.com/articles/dataset/TA_model_s_performance_metrics_/27624500
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Pavel, Mahir Afser; Islam, Rafiul; Bin Babor, Shoyeb; Mehadi, Riaz; Khan, Riasat (2024). TA model’s performance metrics.. PLOS ONE. Dataset
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取（Figshare）
- 源站标题：TA model’s performance metrics.
- DOI：10.1371/journal.pone.0306441.t009
- 发布日期：2024-11-06
- 文件数：1 个
- 文件总体积：5.63 KB
- 源站页面：https://plos.figshare.com/articles/dataset/TA_model_s_performance_metrics_/27624500
命令行下载
curl -L -o "Table 9.xls" "https://ndownloader.figshare.com/files/50272292"
文件清单
Table 9.xls（5.63 KB）
文件总体积 5.63 KB（源站 API 实测）。
数据说明
Non-small cell lung cancer (NSCLC) exhibits a comparatively slower rate of metastasis in contrast to small cell lung cancer, contributing to approximately 85% of the global patient population. In this work, leveraging CT scan images, we deploy a knowledge distillation technique within teaching assistant (TA) and student frameworks for NSCLC classification. We employed various deep learning models, CNN, VGG19, ResNet152v2, Swin, CCT, and ViT, and assigned roles as teacher, teaching assistant and student. Evaluation underscores exceptional model performance in performance metrics achieved via cost-sensitive learning and precise hyperparameter (alpha and temperature) fine-tuning, highlighting the model’s efficiency in lung cancer tumor prediction and classification. The applied TA (ResNet152) and student (CNN) models achieved 90.99% and 94.53% test accuracies, respectively, with optimal hyperparameters (alpha = 0.7 and temperature = 7). The implementation of the TA framework improves the overall performance of the student model. After obtaining Shapley values, explainable AI is applied with a partition explainer to check each class’s contribution, further enhancing the transparency of the implemented deep learning techniques. Finally, a web application designed to make it user-friendly and classify lung types in recently captured images. The execution of the three-stage knowledge distillation technique proved efficient with significantly reduced trainable parameters and training time applicable for memory-constrained edge devices.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.1371/journal.pone.0306441.t009（source: https://plos.figshare.com/articles/dataset/TA_model_s_performance_metrics_/27624500）。
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
