{"id":18466229,"url":"https://github.com/rainoffallingstar/kidneycarundemon","last_synced_at":"2026-06-25T03:31:08.727Z","repository":{"id":54686147,"uuid":"334007865","full_name":"rainoffallingstar/kidneycaRunDemon","owner":"rainoffallingstar","description":"fork from  https://github.com/cena001plus/inception","archived":false,"fork":false,"pushed_at":"2021-04-10T13:22:25.000Z","size":39418,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-31T23:54:59.970Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rainoffallingstar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-01-29T01:51:48.000Z","updated_at":"2021-03-07T11:13:52.000Z","dependencies_parsed_at":"2022-08-14T00:00:45.513Z","dependency_job_id":null,"html_url":"https://github.com/rainoffallingstar/kidneycaRunDemon","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rainoffallingstar/kidneycaRunDemon","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rainoffallingstar%2FkidneycaRunDemon","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rainoffallingstar%2FkidneycaRunDemon/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rainoffallingstar%2FkidneycaRunDemon/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rainoffallingstar%2FkidneycaRunDemon/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rainoffallingstar","download_url":"https://codeload.github.com/rainoffallingstar/kidneycaRunDemon/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rainoffallingstar%2FkidneycaRunDemon/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34758773,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-25T02:00:05.521Z","response_time":101,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-06T09:15:48.057Z","updated_at":"2026-06-25T03:31:08.702Z","avatar_url":"https://github.com/rainoffallingstar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"### kidneyca classification\n\n\n这是一个图像识别项目，基于 tensorflow，fork自原项目four_flouwers,现有的 CNN 网络可以识别两种肾肿瘤2dCT图像。适合新手对使用 tensorflow 进行一个完整的图像识别过程有一个大致轮廓。项目包括对数据集的处理，从硬盘读取数据，CNN 网络的定义，训练过程，还实现了一个 GUI 界面用于使用训练好的网络。\n\n#### 原始数据集及图片处理、扩增方法\n原始数据集包括RCC100张，Papillary100张，其他非肿瘤图像100张。肿瘤数据来源于TCIA官网。\n\n数据2D图片由Itksnap3.6软件读取导出。Itksnap（最新3.8）下载地址是：http://www.itksnap.org/pmwiki/pmwiki.php?n=Downloads.SNAP3\n\nItksnap进行影像数据处理的压箱绝技（？）详见B站番组[itksnap step1]:\n\n1. EP0:itksnap从入门到获取region of interest.[https://www.bilibili.com/video/BV1Xy4y1177d/]\n2. EP1：从水平切面导出病灶.[https://www.bilibili.com/video/BV1Py4y127mQ]\n3. EP2：itksanp解剖涂色书：图像分割.[https://www.bilibili.com/video/BV1Sv4y1f7FR]\n4. ......\n\n图像扩增工具包括传统扩增工具（basicaug/）和GAN数据生成器（GANaug/），在使用basicaug时需要手动安装opencv：pip3 install opencv-python\n\nGAN工具需要在数据量较大时进行测试，通过basicaug可实现原始数据24倍扩增，内含resize工具批量修改数据集图片大小。\n\n\n\n#### 可选网络构架\n1. 简单CNN及加一倍层数的v2\n2. googlenetV1-4\n3. resnet\n4. densenet （untested）\n\n#### Require\n\n1. 安装 Anaconda\n\n2. 导入环境 environment.yaml  \n   `conda env update -f=environment.yaml`\n   \n3. 如不想运行以上步骤则： pip3 install -r environment_cpu.txt  #cpu用户\n                       pip3 install -r environment_gpu.txt  #gpu用户\n#### Quick start\n\n1. git clone 这个项目\n2. 解压 input_data.rar 到你喜欢的目录。\n3. 修改 train.py、input_data.py、test.py等文件 中\n\n```\ntrain_dir = 'D:/DL/kidneyca/inputdata'  # 训练样本的读入路径\n\nlogs_train_dir = 'D:/DL/kidneyca/save'  # logs存储路径\n```\n\n为你本机的目录。\n\n4. 运行dataaugrcc16.py等文件获得数据增强24倍增益。\n5. 运行 train.py 开始训练。运行tensorboard：tensorboard --logdir=[写你的train_dir]\n6. 训练完成后，修改 test.py 中的`logs_train_dir = 'D:/DL/kidneyca/save/'`为你的目录。\n7. 运行 test.py 或者 gui.py 查看结果。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frainoffallingstar%2Fkidneycarundemon","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frainoffallingstar%2Fkidneycarundemon","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frainoffallingstar%2Fkidneycarundemon/lists"}