Skip to content

Our manuscript, "Interpretation of the Outputs of Deep Learning Model Trained with Skin Cancer Dataset" was published as a letter article in the Journal of Investigative Dermatology today (https://www.jidonline.org/article/S0022-202X(18)31992-4/fulltext).

When we train a CNN model, we somtimes get a disappointing Top-1 accuracy. I also suffered this problem and I did not understand exactly what was wrong at that time. When my early version of the 12DX paper was reviewed in JAMA dermatology 2 years ago, the biggest reason for rejection was the low Top-1 accuracy.


However, unlike general object recognition studies, it is very difficult to determine medical research results with Top-1 accuracy, and it is important that the AUC can be high even with a low Top-1 accuracy. If you look carefully, most of medical AI researches have used AUC rather than Top-(n) accuracy.

Because of small and imbalanced training data in medical researches, the analysis of each class as Top-(n) accuracy is inadequate (but the mean Top-(n) of all classes is meaningful). Top-(n) accuracy of each classes vary whenever we repeat the training of CNN with imbalanced dataset. Therefore, we should see the corrected value while using thresholds of each classes, that is ROC curve.

With the AUC results, we published "Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm" (https://www.jidonline.org/article/S0022-202X(18)30111-8/fulltext)

There was a debate that my 12DX algorithm is not sensitive (low top-1 accuracy) with the ISIC dataset (Automated Dermatological Diagnosis: Hype or Reality?; https://www.jidonline.org/article/S0022-202X(18)31991-2/fulltext).

 

There was an additional problem as well as the Top accuracy problem.

When we analyze a clinical image, "the problem of judging whether it is melanoma or not" is easier than "the problem of matching the type of cancer".

Analyzing the output of the AI ​​(CNN) model is equivalent to "the problem of matching the type of cancer", and analyzing the ratio of output is proper if we want to analyze the problem of judging "whether cancer or not".

We interpreted the ratio of melanoma output and nevus output rather than using melanoma output alone.

RATIO (Melanoma Index) = melanoma output / (melanoma output + nevus output).

The clinical image of skin cancer consists of a nodular lesion and a background. If you want to concentrate on only the lesion, we need to analyze it with RATIO as above to get more accurate results.

In the attached photograph, (b) is "matching what cancer is" and (a) is judging "whether it is cancer or not".

We made web-DEMO (http://dx.medicalphoto.org), and we have made it possible to show what conclusions are coming up depending on the Top-5 output and how it is interpreted.

 



번호 제목 글쓴이 날짜 조회 수
1716 모든 연구 자료를 정리. 이것으로 마무리 짓기로. WHRIA 2024.03.03 11
1715 다시 이곳으로... WHRIA 2024.03.02 4
1714 MDR - PL WHRIA 2023.05.12 68
1713 언어 , 국가 WHRIA 2023.04.15 66
1712 cloudfront WHRIA 2023.04.09 49
1711 원격 진료 WHRIA 2023.03.23 61
1710 AI papers [6] WHRIA 2023.03.02 66
1709 gpt2 WHRIA 2023.02.21 385
1708 rsynccp WHRIA 2023.02.20 48
1707 disk error WHRIA 2023.02.16 46
1706 정량화 논문들 WHRIA 2023.02.16 58
1705 chat GPT WHRIA 2023.02.16 60
1704 Google vs Microsoft: The good, bad, and ugly of the AI arms race WHRIA 2023.02.14 125
1703 insync WHRIA 2023.02.09 46
1702 indexeddb [2] WHRIA 2021.02.07 105

Powered by Xpress Engine / Designed by Sketchbook

sketchbook5, 스케치북5

sketchbook5, 스케치북5

나눔글꼴 설치 안내


이 PC에는 나눔글꼴이 설치되어 있지 않습니다.

이 사이트를 나눔글꼴로 보기 위해서는
나눔글꼴을 설치해야 합니다.

설치 취소