AUTOMATIC LESION DETECTION SYSTEM (ALDS) FOR SKIN CANCER CLASSIFICATION USING DEEP LEARNING
Technology aided platforms provide very reliable tools in almost every field these days. These tools being supported by computational power are significant for applications that need sensitive and precise data analysis. One such important application in the medical field is Automatic Lesion Detectio
2025-06-28 16:30:27 - Adil Khan
AUTOMATIC LESION DETECTION SYSTEM (ALDS) FOR SKIN CANCER CLASSIFICATION USING DEEP LEARNING
Project Area of Specialization Artificial IntelligenceProject SummaryTechnology aided platforms provide very reliable tools in almost every field these days. These tools being supported by computational power are significant for applications that need sensitive and precise data analysis. One such important application in the medical field is Automatic Lesion Detection System (ALDS) for Skin Cancer Classification. Computer aided diagnosis helps physicians and dermatologists to obtain a “second opinion” for proper analysis and treatment of skin cancer. Precise segmentation of the cancerous mole along with surrounding area is essential for proper analysis and diagnosis. This project is focused in the development of improved ALDS based deep learning approach and utilizes active contours and watershed for segmenting out the mole. After lesion segmentation, the necessary features are classified to calculate that whether the desired case is melanoma, non-melanoma or its likelihood of becoming melanoma. The approach is tested for different datasets is performed that reflects the effectiveness of the proposed system.
Project ObjectivesIf we talk about the functionality of our project Fast and effective detection of skin cancer is paramount importance. If detected at an early stage, skin has one of the highest cure rates, and the most cases, the treatment is quite simple and involves excision of the lesion. The ultimate goal is to ease the doctor's role in the recognition of skin cancer mentioned above by providing better and more reliable results, so that more patients can be diagnosed.
Project Implementation MethodStep1. Image preprocessing: in this process acquiring the image of the required data. Image are refined by applying the sharping filter and remove the hair on the image using bull razor has been applied.
Step2. Segmentation: this phase is an important phase in this we use two technique for segmentation active contour and watershed. Active contours model is help to learn the point distribution and watershed is help to identify the close contour. Then merge the both result,
.
Step3. Feature extraction: this is also the part of algorithm compute the feature related to shape, texture and color from the segment mole.
Step4. In this step we classify the mole by Support Vector Machines(SVM) and deep neural network.
Step5. In the last phase is to classify the mole is this melanoma or non-melanoma using SVN (binary classification) and deep neural network.
%20FOR%20SKIN%20CANCER%20CLASSIFICATION%20USING%20DEEP%20LEARNING%20_1582916377.png)
The targets of this project are:
- Computer aided diagnosis helps physicians and dermatologists to obtain a “second opinion” for proper analysis and treatment of skin cancer
- To build up a model of skin cancer growth identification framework for analyze melanoma in beginning periods.
- To execute image processing to make a framework that can identify skin cancer growth symptoms.
- To assist patients with preventing the melanoma in beginning period.
- If we address this problem then it’s easy for doctor and patient to identify the cancer at the early stage without going through the time consuming test.
- Due to this technology workload decreases.
%20FOR%20SKIN%20CANCER%20CLASSIFICATION%20USING%20DEEP%20LEARNING%20_1582916378.png)
%20FOR%20SKIN%20CANCER%20CLASSIFICATION%20USING%20DEEP%20LEARNING%20_1582916380.png)
User interface is defined as the design of the user interfaces for machines and software’s such as computer, mobile devices and the other electronic devices with the focus on maximizing usability and the user experience. The user interface design of this project includes a embedded system to detect the skin cancers. Its melanoma or not for the doctor.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 69549 | |||
| MSI GeForce GTX 1070 Founders Edition | Equipment | 1 | 49850 | 49850 |
| Raspberry Pi 3 Model B+ 1.4Ghz | Equipment | 1 | 7600 | 7600 |
| Raspberry Pi Camera Module | Equipment | 1 | 5500 | 5500 |
| Raspberry Pi LCD screen | Equipment | 1 | 5499 | 5499 |
| Memory Card (16 GB) | Equipment | 1 | 1100 | 1100 |