Early Detection of Pancreatic Cancer Using Jaundiced Eye Images

Pancreatic cancer is one of the deadliest cancers, with less than 9% survival rates. Pancreatic Ductal Adeno Carcinoma (PDAC) is common with the general public affecting most people older than 45. Early detection of PDAC is often challenging because cancer symptoms will progress only at later stages (advanced stage). One of the earlier symptoms of PDAC is Jaundice. Patients with diabetes, obesity, and alcohol consumption are also at higher risk of having pancreatic cancer. A decision support system is developed to detect pancreatic cancer at an earlier stage to address this challenge. Features such as Mean Hue, Mean Saturation, Mean Value, and Mean Standard Deviation are computed after color space conversion from RGB to HSV. Fuzzy k-Nearest Neighbor (F-kNN) is designed for classification. The system proposed is trained and tested using features extracted from jaundiced eye images. The proposed system results indicate that this model can predict pancreatic cancer as earlier as possible, helping clinicians make better decisions for surgical planning.     

糖尿病活体胰腺体积测量的临床应用

应用ＮＡＩ－２００医用数字图象处理系统对２４例国人糖尿病的胰腺ＣＴ影象进行了前瞻性研究，首次得出了精确的活体胰腺体积为１２．７９±２．２８ｃｍ３／ｍ２．正常人为１６．４４±４．１４ｃｍ３／ｍ２．经ｔ检验后具有明显的差异性Ｐ＜０．０１．提示国人糖尿病对叶伴有明显的胰腺体积缩小。