Closed ASmallWhit closed 1 year ago
Hi, thank you for your interest to our work! To segment abdominal CT images with multiple class (e.g., spleen, kidney, liver, ...etc), we define the number of classes (out_classes) that we want to segment. For instance, FLARE dataset have four organs labeled, so the number of classes will be 5 (number of organs + background).
For calculating the Dice score, we have leveraged a built-in function in MONAI (dice_metric) to compute the dice score across all categories. However, if you want to output the dice score of each category, you may need to use the dice_metric function for each prediction channel. You can first obtain the one-hot prediction of each channel and evaluation the overlapping region with the ground truth (also in one-hot setting). If you are still not familiar with it, I can send you my own dice score function.
Hi, thank you for your interest to our work! To segment abdominal CT images with multiple class (e.g., spleen, kidney, liver, ...etc), we define the number of classes (out_classes) that we want to segment. For instance, FLARE dataset have four organs labeled, so the number of classes will be 5 (number of organs + background).
For calculating the Dice score, we have leveraged a built-in function in MONAI (dice_metric) to compute the dice score across all categories. However, if you want to output the dice score of each category, you may need to use the dice_metric function for each prediction channel. You can first obtain the one-hot prediction of each channel and evaluation the overlapping region with the ground truth (also in one-hot setting). If you are still not familiar with it, I can send you my own dice score function.
Thank you very much for your reply. I am a math major, but my programming ability is not enough to realize this idea by myself. If you can, I am looking forward to sending me a copy of the output of multi-category dice scores. Thank you very much.
Got it. Do you mind to give me your email? I can send a .py file to you and let you see how I compute the dice score for each category.
Ok, thank you very much for your reply. My email is: @.*** , looking forward to your reply.
------------------ 原始邮件 ------------------ 发件人: "MASILab/3DUX-Net" @.>; 发送时间: 2023年3月2日(星期四) 凌晨1:03 @.>; @.**@.>; 主题: Re: [MASILab/3DUX-Net] Output Category Issues (Issue #13)
Got it. Do you mind to give me your email? I can send a .py file to you and let you see how I compute the dice score for each category.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
I don't think that I can see your email. Here is my email: ho.hin.lee@vanderbilt.edu, feel free to reach out!
Hello, I didn't respond to the email I sent to you two days ago. If possible, could you send the code to the following email: @.*** Thank you very much.
------------------ 原始邮件 ------------------ 发件人: "MASILab/3DUX-Net" @.>; 发送时间: 2023年3月4日(星期六) 下午3:02 @.>; @.**@.>; 主题: Re: [MASILab/3DUX-Net] Output Category Issues (Issue #13)
I don't think that I can see your email. Here is my email: @.***, feel free to reach out!
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Got it. Do you mind to give me your email? I can send a .py file to you and let you see how I compute the dice score for each category.
Hi @leeh43 can you please send me the .py file too? My email is 1226656132xb@gmail.com. I am so interested in your work.Thanks!
Hi @leeh43 can you please send me the .py file too? My email is [xiaosenforai@gmail.com]. I am so interested in your work.Thanks!
Hello, thank you for your work. I want to ask how to segment abdominal CT images with multiple categories, and how to output the dice score of each category at the same time? I don't think this is reflected in your code. Thank you very much