Hiroyuki Ogihara

Use of hyperspectral imaging technology to develop a diagnostic support system for gastric cancer

Abstract. Hyperspectral imaging (HSI) is a new technology that obtains spectroscopic information and renders it in image form. This study examined the difference in the spectral reflectance (SR) of gastric tumors and normal mucosa recorded with a hyperspectral camera equipped with HSI technology and attempted to determine the specific wavelength that is useful for the diagnosis of gastric cancer. A total of 104 gastric tumors removed by endoscopic submucosal dissection from 96 patients at Yamaguchi University Hospital were recorded using a hyperspectral camera. We determined the optimal wavelength and the cut-off value for differentiating tumors from normal mucosa to establish a diagnostic algorithm. We also attempted to highlight tumors by image processing using the hyperspectral camera’s analysis software. A wavelength of 770 nm and a cut-off value of 1/4 the corrected SR were selected as the respective optimal wavelength and cut-off values. The rates of sensitivity, specificity, and accuracy of the algorithm’s diagnostic capability were 71%, 98%, and 85%, respectively. It was possible to enhance tumors by image processing at the 770-nm wavelength. HSI can be used to measure the SR in gastric tumors and to differentiate between tumorous and normal mucosa.

An accurate prognostic staging system for hepatocellular carcinoma patients after curative hepatectomy

The aim of this study was to develop an accurate predictive system for prognosis of hepatocellular carcinoma (HCC) patients after hepatectomy. We pooled data of clinicopathological features of 234 HCC patients who underwent curative hepatectomy. On the basis of the pooled data, we established a simple predictive staging system (PS score) scored by the mathematical product of tumor number and size, and degree of liver function. We compared the prognostic abilities of the PS score (score 0–3) with those of six well-known clinical staging systems. Then, we found that there were significant differences (P<0.05) in both disease-free survival (DFS) and overall survival (OS) between patients with different PS scores (PS score 0 vs. 1; PS score 1 vs. 2), and there was a significant difference in DFS, but not OS, between patients with PS score 2 and those with PS score 3. Moreover, the PS score had smaller values of the Akaike information criterion for both DFS and OS than any of the six well-known clinical staging systems. These results suggest that the PS score serves as a simple, accurate predictor for the prognosis of HCC patients after hepatectomy.

Metastatic ability and the epithelial‐mesenchymal transition in induced cancer stem‐like hepatoma cells

Cancer stem cells (CSCs) are thought to play important roles in cancer malignancy. Previously, we successfully induced sphere cancer stem‐like cells (CSLCs) from several cell lines and observed the property of chemoresistance. In the present study, we examined the metastatic potential of these induced CSLCs. Sphere cancer stem‐like cells were induced from a human hepatoma cell line (SK‐HEP‐1) in a unique medium containing neural survival factor‐1. Splenic injection of cells into immune‐deficient mice was used to assess hematogenous liver metastasis. Transcriptomic strand‐specific RNA‐sequencing analysis, quantitative real‐time PCR, and flow cytometry were carried out to examine the expression of epithelial‐mesenchymal transition (EMT)‐related genes. Splenic injection of CSLCs resulted in a significantly increased frequency of liver metastasis compared to parental cancer cells (P < .05). In CSLCs, a mesenchymal marker, Vimentin, and EMT‐promoting transcription factors, Snail and Twist1, were upregulated compared to parental cells. Correspondingly, significant enrichment of the molecular signature of the EMT in CSLCs relative to parental cancer cells was shown (q < 0.01) by RNA‐sequencing analysis. This analysis also revealed differential expression of CD44 isoforms between CSLCs and parental cancer cells. Increasing CD44 isoforms containing an extra exon were observed, and the standard CD44 isoform decreased in CSLCs compared to parental cells. Interestingly, another CD44 variant isoform encoding a short cytoplasmic tail was also upregulated in CSLCs (11.7‐fold). Our induced CSLCs possess an increased liver metastatic potential in which promotion of the EMT and upregulation of CD44 variant isoforms, especially short‐tail, were observed.

A new prognostic model for hepatocellular carcinoma recurrence after curative hepatectomy

We previously reported the effectiveness of the product of tumor number and size (NxS factor) for the prognosis of hepatocellular carcinoma (HCC) in patients following hepatectomy. The present study aimed to propose a new score based on the NxS factor to predict HCC recurrence following hepatectomy. A total of 406 patients who underwent hepatectomy for HCC at Osaka University Graduate School of Medicine were retrospectively analyzed to develop the new score. Among clinicopathological factors, including the NxS factor, the marker subset that achieved the best performance for prediction of early recurrence was assessed, and a prognostic model for HCC recurrence after curative hepatectomy (REACH) was developed. As the validation set, 425 patients who underwent hepatectomy for HCC at Yamaguchi University Graduate School of Medicine and Shimonoseki Medical Center were analyzed, and the prognostic ability of the REACH score was compared with that of well-known staging systems. Following analysis, the REACH score was constructed using six covariates (NxS factor, microscopic hepatic vein invasion, differentiation, serum albumin, platelet count and indocyanine green retention rate at 15 min). In the validation set, the REACH score predicted early recurrence in 73 of 81 samples, with a sensitivity of 89% and a specificity of 58%. The area under the curve (AUC) of the receiver operating characteristic curve of the REACH score was 0.78 and 0.74, respectively, for 1- and 2-year recurrence after hepatectomy; each AUC was higher than that of any of the other staging systems. Survival analysis indicated the REACH score had the best predictive value in disease-free and overall survival. The present findings demonstrated that the REACH score may be used to classify patients with HCC into high- and low-risk of recurrence, and to predict subsequent survival following hepatic resection.

Lymph node metastasis can be determined by just tumor depth and lymphovascular invasion in early gastric cancer patients after endoscopic submucosal dissection

Purpose Endoscopic submucosal dissection (ESD) is a minimally invasive treatment for early gastric cancer (EGC) with negligible risk of lymph node metastasis (LNM). When a patient is determined to have noncurative resection after ESD, additional surgical resection with lymph node dissection is recommended. Previous studies report that LNM is found in about 10% of these patients. It may be possible to avoid unnecessary surgical resection by selecting patients properly. We aimed to clarify the risk factors associated with LNM in EGC patients who underwent ESD and to develop a highly accurate diagnostic algorithm for LNM. Patients and methods Among 1005 patients with EGC who underwent ESD, 423 patients who could be followed up for more than 3 years after treatment or who underwent additional surgical resection were examined. We used the leave-one-out method to explore the combination of predictive factors of LNM and differentiated LNM by a unique classifier. Results Curative resection was achieved in 322 patients, whereas noncurative resection was achieved in 101 patients. In the noncurative resection group, LNM occurred in eight patients with additional surgical resection and one patient during follow-up. The combination of depth of invasion, lymphatic, and venous invasion showed the highest diagnostic performance and could differentiate LNM with 100% sensitivity, 86% specificity, and 86% diagnostic accuracy. Conclusion More than 500 &mgr;m submucosal invasion and lymphatic and venous invasion will be useful in assessing LNM after ESD for patients with EGC. When these three factors are not observed, follow-up alone might be appropriate and it may be possible to reduce unnecessary surgical resection.

Development of a Gastric Cancer Diagnostic Support System with a Pattern Recognition Method Using a Hyperspectral Camera

Gastric cancer is a completely curable cancer when it can be detected at its early stage. Thus, because early detection of gastric cancer is important, cancer screening by gastroscopy is performed. Recently, the hyperspectral camera (HSC), which can observe gastric cancer at a variety of wavelengths, has received attention as a gastroscope. HSC permits the discerning of the slight color variations of gastric cancer, and we considered its applicability to a gastric cancer diagnostic support system. In this paper, after correcting reflectance to absorb the individual variations in the reflectance of the HSC, a gastric cancer diagnostic support system was designed using the corrected reflectance. In system design, the problems of selecting the optimum wavelength and optimizing the cutoff value of a classifier are solved as a pattern recognition problem by the use of training samples alone. Using the hold-out method with 104 cases of gastric cancer as samples, design and evaluation of the system were independently repeated 30 times. After analyzing the performance in 30 trials, the mean sensitivity was 72.2% and the mean specificity was 98.8%. The results showed that the proposed system was effective in supporting gastric cancer screening.

Image quality of a novel light-emitting diode (LED)-illuminated colonoscope

BACKGROUND AND STUDY AIMS Light-emitting diodes (LEDs) are used widely for their high luminous efficiency and durability. We developed a novel prototype high definition endoscope with white LEDs and evaluated the image quality it produced against a commercial endoscope with conventional light source. PATIENTS AND METHODS The specifications of both colonoscopes were identical, except for the LED light source at the tip of the prototype. We examined 20 patients with rectal or sigmoid colon lesions and the image quality was evaluated in 40 images (one image from the LED colonoscope and one from the conventional colonoscope for each lesion) by three endoscopists. We additionally evaluated the 17 videos recorded with the LED colonoscope that were available. Image quality, mucosal and vascular color, and luminous distribution and intensity were scored on a 5-point scale. RESULTS The mean score for vascular color given by one evaluator was significantly higher using the LED colonoscope than using the conventional colonoscope. The mean scores for mucosal color and luminous intensity from another evaluator were significantly lower with the LED colonoscope than with the conventional colonoscope. There were no significant differences in the luminous distribution scores for any of the evaluators. The image quality of the videos was evaluated as being similar with both colonoscopes. CONCLUSIONS Image quality from the LED and conventional colonoscopes were similar, although the luminous intensity of the LEDs is inferior to that of the conventional light source at the present time.

Prediction of Early Recurrence of Liver Cancer by a Novel Discrete Bayes Decision Rule for Personalized Medicine

We discuss a novel diagnostic method for predicting the early recurrence of liver cancer with high accuracy for personalized medicine. The difficulty with cancer treatment is that even if the types of cancer are the same, the cancers vary depending on the patient. Thus, remarkable attention has been paid to personalized medicine. Unfortunately, although the Tokyo Score, the Modified JIS, and the TNM classification have been proposed as liver scoring systems, none of these scoring systems have met the needs of clinical practice. In this paper, we convert continuous and discrete data to categorical data and keep the natively categorical data as is. Then, we propose a discrete Bayes decision rule that can deal with the categorical data. This may lead to its use with various types of laboratory data. Experimental results show that the proposed method produced a sensitivity of 0.86 and a specificity of 0.49 for the test samples. This suggests that our method may be superior to the well-known Tokyo Score, the Modified JIS, and the TNM classification in terms of sensitivity. Additional comparative study shows that if the numbers of test samples in two classes are the same, this method works well in terms of the F1 measure compared to the existing scoring methods.

Classification Based on Boolean Algebra and Its Application to the Prediction of Recurrence of Liver Cancer

Liver cancer has a high likelihood of recurrence despite complete surgical resection and is thus known as an intractable cancer. If postoperative recurrence of cancer is correctly predicted for each patient as a form of personalized medicine, effective treatment can be carried out. The purpose of this paper is to investigate prediction of recurrence of liver cancer by use of blood test data only in patients who underwent complete surgical resection of liver cancer. For this purpose, we propose a classifier based on Boolean algebra using a binary pattern consisting of a combination of clinical and genomic data by which we can predict recurrence of liver cancer. We perform a predictive experiment using data from patients with recurrence and non-recurrence and discuss the effectiveness of the proposed method from the experimental results.

Objective Assessment of the Utility of Chromoendoscopy with a Support Vector Machine

PurposeThe utility of chromoendoscopy for early gastric cancer (GC) was determined by machine learning using data of color differences.MethodsEighteen histopathologically confirmed early GC lesions were examined. We prepared images from white light endoscopy (WL), indigo carmine (Indigo), and acetic acid-indigo carmine chromoendoscopy (AIM). A border between cancerous and non-cancerous areas on endoscopic images was established from post-treatment pathological findings, and 2000 pixels with equivalent luminance values were randomly extracted from each image of cancerous and non-cancerous areas. Each pixel was represented as a three-dimensional vector with RGB values and defined as a sample. We evaluated the Mahalanobis distance using RGB values, indicative of color differences between cancerous and non-cancerous areas. We then conducted diagnosis test using a support vector machine (SVM) for each image. SVM was trained using the 100 training samples per class and determined which area each of 1900 test samples per class came from.ResultsThe means of the Mahalanobis distances for WL, Indigo, and AIM were 1.52, 1.32, and 2.53, respectively and there were no significant differences in the three modalities. Diagnosability per endoscopy technique was assessed using the F1 measure. The means of F1 measures for WL, Indigo, and AIM were 0.636, 0.618, and 0.687, respectively. AIM images were better than WL and Indigo images for the diagnosis of GC.ConclusionObjective assessment by SVM found AIM to be suitable for diagnosis of early GC based on color differences.