# AI/ML General Championship — Data

来源：https://www.kaggle.com/competitions/aiml-general-championship/data

采集时间：2026-10-19T07:11:40Z

#**Input Data**


The input data are dermoscopic lesion images in JPEG format.

All lesion images are named using the scheme ISIC_ .jpg , where  is a 7-digit unique identifier. EXIF tags in the images have been removed; any remaining EXIF tags should not be relied upon to provide accurate metadata.

The lesion images come from the HAM10000 Dataset, and were acquired with a variety of dermatoscope types, from all anatomic sites (excluding mucosa and nails), from a historical sample of patients presented for skin cancer screening, from several different institutions. Images were collected with approval of the Ethics Review Committee of University of Queensland (Protocol-No. 2017001223) and Medical University of Vienna (Protocol-No. 1804/2017).

The distribution of disease states represent a modified "real world" setting whereby there are more benign lesions than malignant lesions, but an over-representation of malignancies.


#**Ground Truth Provenance**


As detailed in the HAM10000 Dataset description, diagnosis ground truth were established by one of the following methods:

* Histopathology
* Reflectance confocal microscopy
* Lesion did not change during digital dermatoscopic follow up over two years with at least three images
* Consensus of at least three expert dermatologists from a single image
* In all cases of malignancy, disease diagnoses were histopathologically confirmed.



#**Supporting papers**

(1) Robust Asymmetric Loss for Multi-Label Long-Tailed Learning ([Paper](https://arxiv.org/abs/2308.05542) / [Code](https://github.com/kalelpark/RAL))
(2) Focal Loss for Dense Object Detection ([Paper](https://arxiv.org/abs/1708.02002v2) / [Code]https://github.com/unsky/focal-loss))
(3) Asymmetric Loss For Multi-Label Classification ([Paper](https://arxiv.org/abs/2009.14119) / [Code](https://github.com/Alibaba-MIIL/ASL))
(4) Simple and Robust Loss Design for Multi-Label Learning with Missing Labels ([Paper](https://arxiv.org/abs/2112.07368) / [Code](https://github.com/xinyu1205/robust-loss-mlml))



## Files

*   **Training Images** - The training images are stored in "KCDH2024_Training_Input_10K" folder. All of the images are of .jpg type.
*   **KCDH2024_Training_GroundTruth.xlsx** - The spreadsheet containing the ground truth of the training images, it has 8 columns with the first being the image name in the "KCDH2024_Training_Input_10K" folder and the corresponding Boolean values, with a "1" means that the image belongs to the category of that particular column.
*   **sample_submission.csv** - a sample submission file in the correct format
*   **KCDH2024_Training_LesionGroupings.xlsx** - It is an additional information about the training images. You may or may not use it for building your model.

## Columns

*   `id` - The ID or name of the Image as corresponded in the **KCDH2024_Training_GroundTruth.xlsx**
*   `prediction` - The predicted class of the image.