A Comparative Study of Different Pre-Trained Deep Learning Models and Custom CNN for Pancreatic Tumor Detection
Bibliographic record
Abstract
Artificial Intelligence and its sub-branches like Machine Learning (ML) and Deep Learning (DL) applications have the potential to have positive effects that can directly affect human life. Medical imaging is briefly making the internal structure of the human body visible with various methods. With deep learning models, cancer detection, which is one of the most lethal diseases in the world, can be made possible with high accuracy. Pancreatic Tumor detection, which is one of the cancer types with the highest fatality rate, is one of the main targets of this project, together with the data set of Computed Tomography images, which is one of the medical imaging techniques and has an effective structure in Pancreatic Cancer imaging. In the field of image classification, which is a computer vision task, the transfer learning technique, which has gained popularity in recent years, has been applied quite frequently. Using pre-trained models were previously trained on a fairly large dataset and using them on medical images is common nowadays. The main objective of this article is to use this method, which is very popular in the medical imaging field, in the detection of PDAC, one of the deadliest types of pancreatic cancer, and to investigate how it per- forms compared to the custom model created and trained from scratch. The pre-trained models which are used in this project are VGG-16 and ResNet, which are popular Convolutional Neutral Network models, for Pancreatic Tumor Detection task. With the use of these models, early diagnosis of pancreatic cancer, which progresses insidiously and therefore does not spread to neighboring tissues and organs when the treatment process is started, may be possible. Due to the abundance of medical images reviewed by medical professionals, which is one of the main causes for heavy workload of healthcare systems, this application can assist radiologists and other specialists in Pancreatic Tumor detection by providing faster and more accurate method
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".