Radiation therapy alone in the treatment of carcinoma of the uterine cervix: review of experience at Tokyo Women's Medical College (1969-1983).

Three hundred thirteen patients presented with squamous cell carcinoma of the uterine cervix at Tokyo Women's Medical College from 1969 to 1983. The results are presented here. All of the patients were treated by radiotherapy with curative intent with a combination of intracavitary cesium by low-dose rate, using T.A.O. afterloading applicators, which was made of flexible tubes to adapt to the physique of Japanese women by Tazaki, E., Arai, T. and Oryu, S. and external irradiation. One hundred and sixty patients (51.1%) presented with FIGO Stage III disease, 23 patients (7.3%) presented with Stage I disease, and 75 (24.0%) with Stage II. The 5-year cumulative survival rate was 81.7% for Stage I, 76.8% for Stage II, 53.3% for Stage III, 29.2% for Stage IVa, and 10.5% for Stage IVb, respectively. The overall 5-year survival rate was 55.8%. The local regional recurrence rate according to stage was 13.6% in Stage I, 22.4% in Stage II, 41.3% in Stage IIII, and 46.7% in Stage IVa. The incidence of locoregional recurrence rate was 35.6% and distant metastasis 37.8%. The incidence of complications involving bleeding and pain which required hospitalization, was 12.2% in all patients. Only four required surgery to manage serious complications.

Medical diagnostic system using Fuzzy Coloured Petri Nets under uncertainty.

We propose a medical diagnostic system using Fuzzy Coloured Petri Nets (FCPN) in this paper. For complex real-world knowledge Fuzzy Petri Net (FPN) models have been proposed to perform fuzzy reasoning automatically. However, in the Petri Net we have to represent all kinds of processes by separate subnets even though the process has the same behavior of other one. Real-world knowledge often contains many parts which are similar, but not identical. This means that the total PTN becomes very large. The kind of problems may be annoying for a small system, and it may be catastrophic for the description of large-scale system. To avoid this kind of problems we propose a learning and reasoning method using FCPNs under uncertainty. On the other hand to correct the rules of knowledge-based system hand-built classifier and empirical learning method both based on domain theory have been proposed as machine learning methods, where there is a significant gap between the knowledge-intensive approach in the former and the virtually knowledge-free approach in the later. To resolve such problems simultaneously we propose a hybrid learning method which is built on the top of knowledge-based FCPN and Genetic Algorithms (GA). To verify the validity and the effectiveness of the proposed system, we have successfully applied it to the diagnosis of intervertebral diseases.

Extraction of fuzzy rules using neural networks with structure level adaptation--verification to the diagnosis of hepatobiliary disorders.

This paper presents the reasoning and learning method for fuzzy rules using structure level adaptation of neural networks. In a usual neural network mechanism, we can observe some behaviors during the learning process. Based on such behaviors of neuron activity, we can generate or annihilate the specified neurons respectively in hidden layer to achieve an overall good system. In the method that we have proposed, we have used a procedure to derive the neuron generation/annihilation automatically, and applied such a procedure to the learning system where the experimental data related to hepatobiliary disorders were used. After learning by using randomly chosen data, the proposed system correctly diagnosed over 70% of cases. According to these results, we can find that fuzzy rules have some relationship with the degree of the input weight vector. As a result, we can assume that fuzzy rules for hepatobiliary disorders are extracted from this learned network.

Extraction of fuzzy rules using neural networks with structure level adaptation and its application to diagnosis for hepatobiliary disorders.

First, this paper presents the reasoning and the learning method for fuzzy rules using structure level adaptation of neural networks. In a usual neural network's mechanism, during learning process of rules, we can observe the following two behaviors: Case 1: If a neural network does not have enough neurons to be satisfied to infer, then the input weight vector will have a tendency to fluctuate greatly, even after a certain long period the learning process. In this case, the network needs to generate a new neuron as its parent's attribute is inherited. Case 2: If a neural network has enough neurons to infer, and even if the input weight vector of each neuron will converge to a certain value, then we shall be able to turn out unnecessary neurons from the network in the calculation. In this case, because it is necessary to delete a redundant neuron to the calculation, the neuron is annihilated without affecting the performance of the network. By observing such behaviors, we can generate or annihilate the specified neuron respectively to achieve an overall good system. In the proposed method, we described a procedure to derive the neuron generation/annihilation automatically and applied the procedure to learning system. Next, we apply such procedure to the learning system in which the experimental data related to hepatobiliary disorders is used. We use a real medical database containing the results of ten biochemical terms test for four hepatobiliary disorders. We have 536 case data, including some errors. After the learning, by using 179 data chosen randomly from database, the proposed system converged to a certain small value and this constructed network has the optimal structure for these teaching data. In addition, we get that the fuzzy rules have some meanings related to the degree of the input weight vector, and the fuzzy rules for hepatobiliary disorders are extracted from the learned network with respect to the degree of input weight vector. Moreover, to verify the validity of the diagnosis of the proposed method, the feed-forward calculation was implemented using extracted fuzzy rules for all databases. As a result, the proposed system correctly diagnosed more than 70%.

[Reliability and limitation of various diagnostic methods including nuclear medicine in myocardial disease (author's transl)].

Electrocardiography (ECG), echocardiography, nuclear method, cardiac catheterization, left ventriculography (LVG) and endomyocardial biopsy (biopsy) were performed in 40 cases of cardiomyopathy (CM), 9 of endocardial fibroelastosis (EFE) and 19 of specific heart muscle disease (SHMD), and the usefulness and limitation of each method was comparatively estimated. In CM, various methods including biopsy were performed. The 40 patients were classified into 3 groups, i.e., 1) hypertrophic (17), 2) dilated (20) and 3) non-hypertrophic . non-dilated (3) on the basis of left ventricular ejection fraction (LVEF) and hypertrophy of the ventricular wall assessed by LVG and/or echocardiography. The hypertrophic group was divided into 4 subgroups: 9 septal, 4 apical, 2 posterior and 2 anterior. M-mode scan was useful for detecting hypertrophy at the site of the ventricular septum and posterior wall, but not at the site of the anterior wall and apex. The hypertrophy was detected in 18 out of 20 cases using nuclear method. The posterior wall was hypertrophic but the septum was normal in 2 cases. In 2 of 3 non-hypertrophic . non-dilated cases, the left ventricle was oval in shape by LVG, echocardiography was normal, but significant pathological changes were seen in the biopsy, and there were abnormal ECG findings. There was no correlation between the ECG findings and the site of ventricular hypertrophy. Left ventricular ejection fraction measured by LVG (Kasser) had a closer correlation to LVEF obtained by nuclear method (multigated blood pool scan; r = 0.97) than LVEF by echocardiography (Teichholz; r = 0.79), although LVEF obtained by nuclear method was slightly higher than LVEF obtained by LVG. Myocardial perfusion defect was found in 10 of 20 cases of dilated cardiomyopathy (DCM) and the site of relative hypokinesis coincided with the site of the defect in 6 of 7 cases. A semi-quantitative myocardial perfusion defect index (PDI) and histo pathological contractility failure index (HCFI) obtained by the biopsy were devised. HCFI is the score of myocardial degeneration, fragmentation and fibrosis. The PDI plus HCFI had a close correlation with LVEF (r = -0.898). In 9 cases of DCM, LVEF was more reduced than right ventricular ejection fraction. The perfusion defect was also found in 4 cases of EFE and 4 cases of SHMD, i.e., sarcoidosis, postmyocarditis, Kugelberg-Welander disease and cardiac tumor. We conclude that the nuclear study is useful in assessing the site of the abnormal ventricular thickening, perfusion defect and ventricular function. Echocardiography is most useful in detecting ASH. The biopsy gives the sole diagnostic clue, especially in non-hypertrophic . non-dilated cardiomyopathy. ECG is useful in all cases but correlation with the site of disproportional hypertrophy was not obtained.