[et_pb_section fb_built=”1″ _builder_version=”4.5.1″ _module_preset=”default” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/01/landing-95-6.png” custom_padding=”60px||43px|||” animation_style=”slide” animation_direction=”top” background_last_edited=”on|phone” background_color_gradient_end_tablet=”rgba(0,42,71,0.44)” background_color_gradient_end_phone=”rgba(0,42,71,0.44)” background_color_gradient_overlays_image_tablet=”off” background_color_gradient_overlays_image_phone=”off” locked=”off”][et_pb_row use_custom_gutter=”on” gutter_width=”2″ make_equal=”on” module_class=”service-ti-sub” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” width_tablet=”90%” width_phone=”90%” width_last_edited=”on|tablet” max_width=”1210px” max_width_tablet=”90%” max_width_phone=”90%” max_width_last_edited=”on|desktop” custom_padding=”0px||0px||true|”][et_pb_column type=”4_4″ _builder_version=”4.7.7″ _module_preset=”default”][et_pb_text _builder_version=”4.5.1″ _module_preset=”default” header_font=”Josefin Sans|700|||||||” header_text_align=”center” header_text_color=”#ffffff” header_font_size=”60px” header_line_height=”0.9em” header_2_font=”Alata|700|||||||” header_2_text_align=”center” header_2_text_color=”#ffffff” header_2_font_size=”40px” header_2_line_height=”1.5em” header_3_font=”Alata|600|||||||” header_3_text_align=”center” header_3_text_color=”#000000″ header_3_font_size=”54px” header_3_letter_spacing=”-1px” custom_margin=”30px||||false|false” header_3_font_size_tablet=”” header_3_font_size_phone=”35px” header_3_font_size_last_edited=”on|phone”]
Skin Disorder Identification
[/et_pb_text][et_pb_text _builder_version=”4.5.1″ text_font=”Josefin Sans||||||||” text_text_color=”#ffffff” text_font_size=”20px” text_line_height=”1.5em” text_orientation=”center” text_font_size_tablet=”” text_font_size_phone=”20px” text_font_size_last_edited=”on|phone”]How Sigma’s AI platform can help identify skin diseases.[/et_pb_text][/et_pb_column][/et_pb_row][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.5.1″ _module_preset=”default” locked=”off”][et_pb_row column_structure=”1_2,1_2″ use_custom_gutter=”on” gutter_width=”1″ make_equal=”on” module_class=”ser-img-text” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” max_width=”1170px” max_width_tablet=”90%” max_width_phone=”” max_width_last_edited=”on|phone” custom_padding=”0px||0px||true|false” locked=”off” width__hover_enabled=”on|desktop”][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/02/D-7-Skin2.jpg” background_position=”top_right” animation_style=”slide” animation_direction=”left”][et_pb_divider _builder_version=”4.5.1″ _module_preset=”default” height_tablet=”300px” height_phone=”300px” height_last_edited=”on|tablet” locked=”off”][/et_pb_divider][/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.7.4″ _module_preset=”default” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/01/landing-95-6.png” custom_padding=”60px|60px|60px|60px|true|true” custom_padding_tablet=”” custom_padding_phone=”30px|30px|30px|30px|true|true” custom_padding_last_edited=”on|phone” animation_style=”slide” animation_direction=”right”][et_pb_text _builder_version=”4.5.1″ _module_preset=”default” header_2_font=”Josefin Sans|700|||||||” header_2_text_align=”center” header_2_text_color=”#ffffff” header_2_font_size=”25px” header_3_font=”Livvic|700|||||||” header_3_text_align=”center” header_3_text_color=”#ffffff” header_3_font_size=”36px” header_3_line_height=”1.3em” module_alignment=”center” custom_margin=”||21px|-31px|false|false” custom_margin_tablet=”-10px||||false|false” custom_margin_phone=”-10px||||false|false” custom_margin_last_edited=”on|phone”]
The Challenge
[/et_pb_text][et_pb_text _builder_version=”4.5.1″ text_font=”Josefin Sans||||||||” text_text_color=”#ffffff” text_font_size=”18px” text_line_height=”1.5em” text_orientation=”center” hover_enabled=”0″ text_font_size_tablet=”” text_font_size_phone=”20px” text_font_size_last_edited=”on|phone”]
The dermatology department of an important hospital wanted to improve efficiency in the diagnosis of skin diseases, so as to be able to do a first automatic filtering of patient’s skin photos. The main goal of this project was to detect and identify 8 skin diseases: Melanoma, Melanocytic Nevus, Actinic Keratosis, Benign Keratosis, Basal Cell Carcinoma, Dermatofibroma, Squamous Cell Carcinoma, and Vascular Lesion.
Sigma’s Computer Vision technology can recognize patterns with a very high accuracy, which makes it ideal for this use case.
[/et_pb_text][/et_pb_column][/et_pb_row][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.5.1″ _module_preset=”default” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/03/D-3-SALES-1.jpg” parallax=”on” parallax_method=”off” custom_margin_tablet=”40px||||false|false” custom_margin_phone=”40px||||false|false” custom_margin_last_edited=”on|phone” custom_padding=”50px||50px||true|false” top_divider_color=”#ffffff” top_divider_height=”40px” top_divider_flip=”vertical” top_divider_height_tablet=”” top_divider_height_phone=”20px” top_divider_height_last_edited=”on|phone” locked=”off”][et_pb_row column_structure=”1_2,1_2″ use_custom_gutter=”on” gutter_width=”2″ make_equal=”on” module_class=”ser-text-img” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” width_tablet=”90%” width_phone=”90%” width_last_edited=”on|tablet” max_width=”1210px” max_width_tablet=”90%” max_width_phone=”90%” max_width_last_edited=”on|desktop” custom_margin=”|auto|33px|auto||” custom_padding=”0px||0px|||” locked=”off”][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_color=”#ffffff” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)”][et_pb_blurb title=”The Solution” url=”#” content_max_width=”100%” _builder_version=”4.5.1″ _module_preset=”default” header_font=”Josefin Sans|700|||||||” header_text_align=”center” header_text_color=”#00223f” header_font_size=”20px” header_line_height=”1.5em” body_font=”Josefin Sans||||||||” body_text_align=”left” body_text_color=”#00223f” body_font_size=”18px” body_line_height=”1.5em” module_alignment=”center” animation=”off” border_width_right_image=”8px” border_color_right_image=”rgba(0,0,0,0)” header_text_color__hover_enabled=”on|desktop” header_text_color__hover=”#1273EB”]
The dermatology clinic had a large data base of annotated skin images, which allowed to adapt Sigma’s Computer Vision technology to the detection and identification of skin diseases very quickly and easily. Sigma’s team preprocessed the images to reduce variability and optimize the result of the machine learning process and fine tuned the technology parameters for this type of images.
Sigma also developed a user interface to visualize the results in a way that the dermatologist could rapidly confirm the diagnosis of the disease.
[/et_pb_blurb][/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_enable_color=”off” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/02/D-7-Skin1.jpg” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)”][et_pb_divider show_divider=”off” _builder_version=”4.5.1″ _module_preset=”default” height_tablet=”200px” height_phone=”200px” height_last_edited=”on|phone” locked=”off”][/et_pb_divider][/et_pb_column][/et_pb_row][et_pb_row column_structure=”1_2,1_2″ use_custom_gutter=”on” gutter_width=”2″ make_equal=”on” module_class=”ser-img-text” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” width_tablet=”90%” width_phone=”90%” width_last_edited=”on|tablet” max_width=”1210px” max_width_tablet=”90%” max_width_phone=”90%” max_width_last_edited=”on|desktop” custom_padding=”0px||0px|||” hover_enabled=”0″ locked=”off”][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_enable_color=”off” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/04/piel.jpg” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” hover_enabled=”0″ border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)” title_text=”piel”][et_pb_divider show_divider=”off” _builder_version=”4.5.1″ _module_preset=”default” height_tablet=”200px” height_phone=”200px” height_last_edited=”on|phone” locked=”off”][/et_pb_divider][/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_color=”#ffffff” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)”][et_pb_blurb title=”The Outcome” url=”#” content_max_width=”100%” _builder_version=”4.5.1″ _module_preset=”default” header_font=”Josefin Sans|700|||||||” header_text_align=”center” header_text_color=”#00223f” header_font_size=”20px” header_line_height=”1.5em” body_font=”Josefin Sans||||||||” body_text_align=”left” body_text_color=”#00223f” body_font_size=”18px” body_line_height=”1.5em” module_alignment=”center” animation=”off” border_width_right_image=”8px” border_color_right_image=”rgba(0,0,0,0)” header_text_color__hover_enabled=”on|desktop” header_text_color__hover=”#1273EB”]
The first version of the tool has the following accuracies: Melanoma, 80%; Melanocytic Nevus: 94.3%; Actinic Keratosis: 67.1%; Benign Keratosis: 78.3%; Basal Cell Carcinoma: 85.1%; Dermatofibroma: 78.7%; Squamous Cell Carcinoma: 74.4% and Vascular Lesion: 86%.
The best results correspond to the diseases for which there were more images in the data base, so more images are being collected to obtain higher accuracies.
[/et_pb_blurb][/et_pb_column][/et_pb_row][/et_pb_section]