Computer-aided detection of prostate cancer on tissue sections

Abstract

We report an automated computer technique for detection of prostate cancer in prostate tissue sections processed with immunohistochemistry. Two sets of color optical images were acquired from prostate tissue sections stained with a double-chromogen triple-antibody cocktail combining alpha-methylacyl-CoA racemase, p63, and high-molecular-weight cytokeratin. The first set of images consisted of 20 training images (10 malignant) used for developing the computer technique and 15 test images (7 malignant) used for testing and optimizing the technique. The second set of images consisted of 299 images (114 malignant) used for evaluation of the performance of the computer technique. The computer technique identified image segments of alpha-methylacyl-CoA racemase-labeled malignant epithelial cells (red), p63, and high-molecular-weight cytokeratin-labeled benign basal cells (brown), and secretory and stromal cells (blue) for identifying prostate cancer automatically. The sensitivity and specificity of the computer technique were 94% (16/17) and 94% (17/18), respectively, on the first (training and test) set of images, and 88% (79/90) and 97% (136/140), respectively, on the second (validation) set of images. If high-grade prostatic intraepithelial neoplasia, which is a precursor of cancer, and atypical cases were included, the sensitivity and specificity were 85% (97/114) and 89% (165/185), respectively. These results show that the novel automated computer technique can accurately identify prostatic adenocarcinoma in the triple-antibody cocktail-stained prostate sections.

Figure 1

An image of prostate tissue processed with the triple-antibody-cocktail staining. Arrows indicate a number of small malignant glands with alpha-methylacyl-CoA-racemase (AMACR) staining in the secretory cell cytoplasm (red). Near the bottom of the image, arrowheads indicate a clearly visible basal-cell layer stained by p63 and high-molecular-weight cytokeratin (HMWCK) in two benign glands (brown). Stromal and secretory cell nuclei are stained by hematoxylin (blue).

Figure 2

Flowchart that illustrates the computer-segmentation technique. Rounded rectangles with shadows represent single images (the dashed-line rectangle represents three separate images), which can be the original input color image, individual color channels, binary images after thresholding, or the output image. Other rectangles represent operations applied to the images. Two different thresholding methods were applied. See text for details.

Figure 3

Examples of the computer image analysis in a malignant (top) and a benign (bottom) case. The results of the malignant case show (A) a section containing glands of prostatic adenocarcinoma; (B) computer results showing the segmentation of cytoplasm positive for alpha-methylacyl-CoA-racemase (AMACR) staining; (C) computer results showing the segmentation of basal cells positive for p63/HMWCK staining; and (D) final computer result showing the segmentation of malignant epithelial components. The results of the benign case show (E) a section containing benign glands; (F) computer results showing the segmentation of cytoplasm positive for AMACR staining; (G) computer results showing the segmentation of basal cells positive for p63/HMWCK staining; and (H) final computer result showing no malignant glands.

Figure 4

Illustration of a possible scenario for future clinical application of computer-aided diagnosis of prostate cancer. With automation, computer image analysis can provide additional information to assist the pathologist in making a cancer diagnosis. The present work addresses computer image analysis of one type of IHC images (shown in the right-hand column); work on computer image analysis of H&E images is currently ongoing (denoted in grey in the left-hand column).

Figure 5

An example of infiltrative malignant glands. Left, the original image. Right, the computer-identified malignant glands.

Figure 6

An example of a single small cancerous gland identified by the computer. Left, the original image. Right, the computer reports the identification of cancer.

Figure 7

A false-negative case of (left) original image and (right) computer segmentation result. The arrow indicates a focus of malignant glands. In the right image, dark regions correspond to the “brown” color and gray regions correspond to the “red” color of the original (left) image. The malignant glands were missed in this case because the computer over-estimated the “brown” color regions near the focus of malignant glands, incorrectly indicating the presence of a basal-cell layer.

Figure 8

A false-positive case of (left) original image and (right) computer segmentation result. The arrow indicates a tissue fragment with alpha-methylacyl-CoA-racemase (AMACR) staining isolated from the gland. The computer mistakenly identified the isolated tissue fragment as malignant based on color analysis.