Skin Cancer Classifier: Unable to find normal skin images












1















Summary:



I'm working with TensorFlow to build skin cancer classifier I have found many images for skin cancer with labels. My problem is I haven't found any images for normal skin or false skin cancer. I noticed all blogs referred to some skin cancer dataset but never normal skin images.



Questions:



How can the network know what is and what is not skin cancer?



If a network is trained only with types of cancer and i give a normal skin image will it predict one of the skin cancer types?



Thank you



One of the blogs:



https://medium.com/intech-conseil-expertise/detect-mole-cancer-with-your-smartphone-using-deep-learning-8afad1efde8a



PS:New to deep learning










share|improve this question



























    1















    Summary:



    I'm working with TensorFlow to build skin cancer classifier I have found many images for skin cancer with labels. My problem is I haven't found any images for normal skin or false skin cancer. I noticed all blogs referred to some skin cancer dataset but never normal skin images.



    Questions:



    How can the network know what is and what is not skin cancer?



    If a network is trained only with types of cancer and i give a normal skin image will it predict one of the skin cancer types?



    Thank you



    One of the blogs:



    https://medium.com/intech-conseil-expertise/detect-mole-cancer-with-your-smartphone-using-deep-learning-8afad1efde8a



    PS:New to deep learning










    share|improve this question

























      1












      1








      1








      Summary:



      I'm working with TensorFlow to build skin cancer classifier I have found many images for skin cancer with labels. My problem is I haven't found any images for normal skin or false skin cancer. I noticed all blogs referred to some skin cancer dataset but never normal skin images.



      Questions:



      How can the network know what is and what is not skin cancer?



      If a network is trained only with types of cancer and i give a normal skin image will it predict one of the skin cancer types?



      Thank you



      One of the blogs:



      https://medium.com/intech-conseil-expertise/detect-mole-cancer-with-your-smartphone-using-deep-learning-8afad1efde8a



      PS:New to deep learning










      share|improve this question














      Summary:



      I'm working with TensorFlow to build skin cancer classifier I have found many images for skin cancer with labels. My problem is I haven't found any images for normal skin or false skin cancer. I noticed all blogs referred to some skin cancer dataset but never normal skin images.



      Questions:



      How can the network know what is and what is not skin cancer?



      If a network is trained only with types of cancer and i give a normal skin image will it predict one of the skin cancer types?



      Thank you



      One of the blogs:



      https://medium.com/intech-conseil-expertise/detect-mole-cancer-with-your-smartphone-using-deep-learning-8afad1efde8a



      PS:New to deep learning







      neural-network deep-learning dataset conv-neural-network






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 24 '18 at 23:44









      HeRoXLeGenD1HeRoXLeGenD1

      104




      104
























          1 Answer
          1






          active

          oldest

          votes


















          0














          That problem should be quite easy to resolve by pics of lots of healthy people pics!



          You can't perform supervised learning without a database of control images. You could redefine the question against the images that you have.



          If you can't do either you are stuck with unsupervised learning and your positive images will serve only to verify your unsupervised learning conclusions. You are hoping your unsupervised learning will yield two groups and if correct one of the group should map against your positive images. Then its solved without the control data set.



          If you can successfully map your positive images onto your output then the remainder becomes your control set for supervised learning, i.e. they become your training set.






          share|improve this answer



















          • 1





            Now I get the point of unsupervised learning. Thank you !

            – HeRoXLeGenD1
            Nov 25 '18 at 0:55











          Your Answer






          StackExchange.ifUsing("editor", function () {
          StackExchange.using("externalEditor", function () {
          StackExchange.using("snippets", function () {
          StackExchange.snippets.init();
          });
          });
          }, "code-snippets");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "1"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53463397%2fskin-cancer-classifier-unable-to-find-normal-skin-images%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          1 Answer
          1






          active

          oldest

          votes








          1 Answer
          1






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes









          0














          That problem should be quite easy to resolve by pics of lots of healthy people pics!



          You can't perform supervised learning without a database of control images. You could redefine the question against the images that you have.



          If you can't do either you are stuck with unsupervised learning and your positive images will serve only to verify your unsupervised learning conclusions. You are hoping your unsupervised learning will yield two groups and if correct one of the group should map against your positive images. Then its solved without the control data set.



          If you can successfully map your positive images onto your output then the remainder becomes your control set for supervised learning, i.e. they become your training set.






          share|improve this answer



















          • 1





            Now I get the point of unsupervised learning. Thank you !

            – HeRoXLeGenD1
            Nov 25 '18 at 0:55
















          0














          That problem should be quite easy to resolve by pics of lots of healthy people pics!



          You can't perform supervised learning without a database of control images. You could redefine the question against the images that you have.



          If you can't do either you are stuck with unsupervised learning and your positive images will serve only to verify your unsupervised learning conclusions. You are hoping your unsupervised learning will yield two groups and if correct one of the group should map against your positive images. Then its solved without the control data set.



          If you can successfully map your positive images onto your output then the remainder becomes your control set for supervised learning, i.e. they become your training set.






          share|improve this answer



















          • 1





            Now I get the point of unsupervised learning. Thank you !

            – HeRoXLeGenD1
            Nov 25 '18 at 0:55














          0












          0








          0







          That problem should be quite easy to resolve by pics of lots of healthy people pics!



          You can't perform supervised learning without a database of control images. You could redefine the question against the images that you have.



          If you can't do either you are stuck with unsupervised learning and your positive images will serve only to verify your unsupervised learning conclusions. You are hoping your unsupervised learning will yield two groups and if correct one of the group should map against your positive images. Then its solved without the control data set.



          If you can successfully map your positive images onto your output then the remainder becomes your control set for supervised learning, i.e. they become your training set.






          share|improve this answer













          That problem should be quite easy to resolve by pics of lots of healthy people pics!



          You can't perform supervised learning without a database of control images. You could redefine the question against the images that you have.



          If you can't do either you are stuck with unsupervised learning and your positive images will serve only to verify your unsupervised learning conclusions. You are hoping your unsupervised learning will yield two groups and if correct one of the group should map against your positive images. Then its solved without the control data set.



          If you can successfully map your positive images onto your output then the remainder becomes your control set for supervised learning, i.e. they become your training set.







          share|improve this answer












          share|improve this answer



          share|improve this answer










          answered Nov 25 '18 at 0:37









          Michael G.Michael G.

          2231316




          2231316








          • 1





            Now I get the point of unsupervised learning. Thank you !

            – HeRoXLeGenD1
            Nov 25 '18 at 0:55














          • 1





            Now I get the point of unsupervised learning. Thank you !

            – HeRoXLeGenD1
            Nov 25 '18 at 0:55








          1




          1





          Now I get the point of unsupervised learning. Thank you !

          – HeRoXLeGenD1
          Nov 25 '18 at 0:55





          Now I get the point of unsupervised learning. Thank you !

          – HeRoXLeGenD1
          Nov 25 '18 at 0:55




















          draft saved

          draft discarded




















































          Thanks for contributing an answer to Stack Overflow!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53463397%2fskin-cancer-classifier-unable-to-find-normal-skin-images%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          404 Error Contact Form 7 ajax form submitting

          How to know if a Active Directory user can login interactively

          TypeError: fit_transform() missing 1 required positional argument: 'X'