Search

In this work, a custom deep learning method is proposed to develop a detection of visual fields defects which are the markers for serious optic pathway disease. Convolutional Neural Networks (CNN) is a deep learning method that is mostly used in images processing. Therefore, a custom 10 layers of CNN algorithm is built to detect the visual field defect. In this work, 1200 visual field defect images acquired from the Humphrey Field Analyzer 24–2 collected from Google Image have been used to classify 6 types of visual field defect. The defect patterns are including defects at central scotoma, right/left/upper/lower quadratopia, right/left hemianopia, vision tunnel, superior/inferior field defect and normal as baseline. The custom designed CNN is trained to discriminate between defect patterns in visual field images. In the proposed method, a mechanism of pre-processing is included to improve the classification of visual field defects. Then, the 6 visual field defect patterns are detected using a convolutional neural network. The dataset is evaluated using 5-fold cross-validation. The results of this work have shown that the proposed algorithm achieved a high classification rate with 96%. As comparison, traditional machine learning Support Vector Machine (SVM) and Classical Neural Network (NN) is chose and obtained classification rate at 74.54% and 90.72%.

An application specific integrated processor designed for ATM cell processing applications is described in this paper. A new dedicated architecture consisting of a custom-made CPU core, a pipeline input cell buffer and a content addressable memory (CAM) is employed to realize both high performance data processing and functional re-configurability. The chip has been implemented on 0.5 /spl mu/m CMOS. It consumes 2400 mW power under 3.3 V supply at 52 MHz clock frequency for a 155 Mbps high speed cell data stream. Programs for several different applications have been developed and are running on this chip. As a result of evaluation, each application program satisfies a required performance.

Background The prognosis of gastric cancer with peritoneal metastasis is extremely poor. Neither systemic chemotherapy nor surgery alone prolongs survival of patients significantly. Methods Patients diagnosed with advanced gastric cancer underwent staging laparoscopy and received chemotherapy when peritoneal dissemination and/or cancer cells on peritoneal cytology were confirmed. The chemotherapy regimen consisted of S-1, weekly intravenous and intraperitoneal paclitaxel, which was verified in our phase II trial (Ann Oncol 2009). S-1 was administered at 80 mg/m2/day for 14 consecutive days, followed by 7 days rest. Paclitaxel was administered intravenously at 50 mg/m2 and intraperitoneally at 20 mg/m2 on days 1 and 8. Clinical response of chemotherapy was assessed by computed tomography, gastroendoscopy, peritoneal cytology and second-look laparoscopy. Radical gastrectomy was carried out when macroscopic curative resection was made achievable by chemotherapy. Chemotherapy was restarted after operation as soon as possible. Overall survival, relapse free survival, morbidity and mortality of gastrectomy were evaluated. Results Out of 100 patients with peritoneal metastasis who received chemotherapy, 60 patients underwent gastrectomy after response to chemotherapy, including 54 with macroscopic metastasis and 6 with positive peritoneal cytology only. A median of three courses were administered preoperatively (range 1–16). Total or distal gastrectomy with lymphnode dissection was carried out in 54 or 6 patients, respectively. The median survival time was 34.5 months. The median relapse-free survival was 16.7 months. The first site of relapse was the peritoneum in 24 patients and the other organ site in 17 patients. Postoperative complications included anastomotic leakage and pancreatic fistula in two patients each, which were healed conservatively. There were no treatment-related deaths. Conclusions Gastrectomy combined with S-1, intravenous and intraperitoneal paclitaxel is safe and active for gastric cancer patients with peritoneal metastasis.

Background Since salvage surgery after failure of cheomradiotherapy (CRT) for esophageal cancer (EC) is associated with high morbidity and mortality, the development of curative and safety salvage treatment options has been needed to improve the patients' survival. Aim We conducted a phase I/II study to establish the recommended dose (RD) of laser irradiation and to evaluate safety and efficacy of Taraporfin sodium-based photodynamic therapy (PDT) as a salvage treatment after CRT (UMIN000003970). Patients and methods We recruited patients with residual or recurrent EC at primary site and who were treated with more than 50 Gy of (chemo)radiotherapy. To determine the dose-limiting toxicity (DLT) according to the energy of the diode laser, dose escalation was set at three energy levels (50, 75 and 100 J/cm2). The primary end point of phase I and II study were RD of laser irradiation and the complete response (CR) rate, respectively. Results In the phase I study, 9 patients were recruited and were treated using up to the third energy level in groups of three individuals. Since none of the patients experienced DLT at all energy levels, the recommended laser dose was 100 J/m2. In the phase II study, 10 patients were recruited and a complete response of the patients treated by RD was achieved in 6 of 13 patients (46%), which included the patients in level 3 of phase I. There was no patient with PDT-related adverse events. Conclusion Taraporfin sodium-based PDT could be a safe and effective treatment option for the local failure after CRT for EC.

4021 Background: JCOG9912, a randomized phase III trial of advanced gastric cancer (AGC), revealed significant non-inferiority of S-1 to 5-FU (P

We reviewed 16 trochanteric and 21 femoral neck fractures in last two years. Out of them 10 cases, which were 4 trochanteric and 6 neck fractures, were operated with a compression hip screw. All of trochanteric fracture united satisfactorily. Two of 6 neck fractures were secondary treated by prosthetic replacement from re-fracture by falling from the bed and technical failure.We paid special attention to the following points;1) varus dislocation of the fractured head is undesirable for use of the screw.2) A tip of the screw must be correctly installed in the center of the femoral head and is apart about 1cm from the surface of the head.

The cause of persistent symptoms after menisectomy has been assessed clinically, radiologically, arthrographically, and arthroscopically in 20 cases.We report two cases by lesion of subluxations of patella and one case by the chondropathy of patella and one case by synovial involvement.

Distal elongation of the Hamstrings was performed for contracture due to neurogenic disorders in forty-three patients. A follow-up study on twenty-eight of the patients with cerebral palsy is reported here. The success of the operation was judged by functional evaluation including joint measurement and gait analysis with T-V recorder. The disadvantages of this operation especially about genu recuirvatum and the need for prolonged aftercare are discussed.In the thirty-two knees, the spastic knee-flexion deformity was corrected, gait was improved, and a longer in eleven knees. It seemed that pre-operative ability for knee extension and ankle dorsi-flexion and age at operation were concerned to genu recuirvatum. In the five knees, recuirvatum was improved by fixed-ankle below-the-knee orthoses.