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
1654 넘 바쁘고 장난 아니다. 으..죽겠다. 2000.12.25 2066
1653 *^^* 구름 2001.01.02 2238
1652 RE:119번 이야기 구름 2001.01.02 2082
1651 나양 2001.01.09 2161
1650 `4월이야기`와 `8월의 크리스마스`의 공통점은? soma 2001.01.09 2312
1649 우와~감탄의 연발~! 1004 2001.01.17 2417
1648 지나가는길에... 임연경 2001.01.24 2225
1647 넘 멋쪄요!!! 송혜린 2001.01.26 2065
1646 Re: 우와~감탄의 연발~! 한승석 2001.01.27 2072
1645 Re: 지나가는길에... 한승석 2001.01.27 2057
1644 Re: 넘 멋쪄요!!! 한승석 2001.01.27 2060
1643 Re: `4월이야기`와 `8월의 크리스마스`의 공통점은? 한승석 2001.01.27 2057
1642 order 서권 2001.02.11 3245
1641 여기는 신촌 최평균 2001.02.11 2063
1640 이오더 말이지... 윤재원 2001.02.13 2823

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