Search

In the rapidly evolving field of medical image analysis utilizing artificial intelligence (AI), the selection of appropriate computational models is critical for accurate diagnosis and patient care. This literature review provides a comprehensive comparison of vision transformers (ViTs) and convolutional neural networks (CNNs), the two leading techniques in the field of deep learning in medical imaging. We conducted a survey systematically. Particular attention was given to the robustness, computational efficiency, scalability, and accuracy of these models in handling complex medical datasets. The review incorporates findings from 36 studies and indicates a collective trend that transformer-based models, particularly ViTs, exhibit significant potential in diverse medical imaging tasks, showcasing superior performance when contrasted with conventional CNN models. Additionally, it is evident that pre-training is important for transformer applications. We expect this work to help researchers and practitioners select the most appropriate model for specific medical image analysis tasks, accounting for the current state of the art and future trends in the field., (© 2024. The Author(s).)

Background: In an extensive genomic analysis of lung adenocarcinomas (LUADs), driver mutations have been recognized as potential targets for molecular therapy. However, there remain cases where target genes are not identified. Super-enhancers and structural variants are frequently identified in several hundred loci per case. Despite this, most cancer research has approached the analysis of these data sets separately, without merging and comparing the data, and there are no examples of integrated analysis in LUAD., Methods: We performed an integrated analysis of super-enhancers and structural variants in a cohort of 174 LUAD cases that lacked clinically actionable genetic alterations. To achieve this, we conducted both WGS and H3K27Ac ChIP-seq analyses using samples with driver gene mutations and those without, allowing for a comprehensive investigation of the potential roles of super-enhancer in LUAD cases., Results: We demonstrate that most genes situated in these overlapped regions were associated with known and previously unknown driver genes and aberrant expression resulting from the formation of super-enhancers accompanied by genomic structural abnormalities. Hi-C and long-read sequencing data further corroborated this insight. When we employed CRISPR-Cas9 to induce structural abnormalities that mimicked cases with outlier ERBB2 gene expression, we observed an elevation in ERBB2 expression. These abnormalities are associated with a higher risk of recurrence after surgery, irrespective of the presence or absence of driver mutations., Conclusions: Our findings suggest that aberrant gene expression linked to structural polymorphisms can significantly impact personalized cancer treatment by facilitating the identification of driver mutations and prognostic factors, contributing to a more comprehensive understanding of LUAD pathogenesis., (© 2024. The Author(s).)

DNA methylation is an epigenetic modification that results in dynamic changes during ontogenesis and cell differentiation. DNA methylation patterns regulate gene expression and have been widely researched. While tools for DNA methylation analysis have been developed, most of them have focused on intergroup comparative analysis within a dataset; therefore, it is difficult to conduct cross-dataset studies, such as rare disease studies or cross-institutional studies. This study describes a novel method for DNA methylation analysis, namely, methPLIER, which enables interdataset comparative analyses. methPLIER combines Pathway Level Information Extractor (PLIER), which is a non-negative matrix factorization (NMF) method, with regularization by a knowledge matrix and transfer learning. methPLIER can be used to perform intersample and interdataset comparative analysis based on latent feature matrices, which are obtained via matrix factorization of large-scale data, and factor-loading matrices, which are obtained through matrix factorization of the data to be analyzed. We used methPLIER to analyze a lung cancer dataset and confirmed that the data decomposition reflected sample characteristics for recurrence-free survival. Moreover, methPLIER can analyze data obtained via different preprocessing methods, thereby reducing distributional bias among datasets due to preprocessing. Furthermore, methPLIER can be employed for comparative analyses of methylation data obtained from different platforms, thereby reducing bias in data distribution due to platform differences. methPLIER is expected to facilitate cross-sectional DNA methylation data analysis and enhance DNA methylation data resources., (© 2024. The Author(s).)

The volume of medical images stored in hospitals is rapidly increasing; however, the utilization of these accumulated medical images remains limited. Existing content-based medical image retrieval (CBMIR) systems typically require example images, leading to practical limitations, such as the lack of customizable, fine-grained image retrieval, the inability to search without example images, and difficulty in retrieving rare cases. In this paper, we introduce a sketch-based medical image retrieval (SBMIR) system that enables users to find images of interest without the need for example images. The key concept is feature decomposition of medical images, which allows the entire feature of a medical image to be decomposed into and reconstructed from normal and abnormal features. Building on this concept, our SBMIR system provides an easy-to-use two-step graphical user interface: users first select a template image to specify a normal feature and then draw a semantic sketch of the disease on the template image to represent an abnormal feature. The system integrates both types of input to construct a query vector and retrieves reference images. For evaluation, ten healthcare professionals participated in a user test using two datasets. Consequently, our SBMIR system enabled users to overcome previous challenges, including image retrieval based on fine-grained image characteristics, image retrieval without example images, and image retrieval for rare cases. Our SBMIR system provides on-demand, customizable medical image retrieval, thereby expanding the utility of medical image databases., Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Kazuma Kobayashi reports financial support was provided by Fujifilm Corporation. Ryuji Hamamoto reports financial support was provided by Fujifilm Corporation. Kazuma Kobayashi has patent #PCT/JP2022/018956 pending to National Cancer Center and Fujifilm Corporation. Mototaka Miyake has patent #PCT/JP2022/018956 pending to National Cancer Center and Fujifilm Corporation. Ryuji Hamamoto has patent #PCT/JP2022/018956 pending to National Cancer Center and Fujifilm Corporation., (Copyright © 2023 The Author(s). Published by Elsevier B.V. All rights reserved.)

Aim: Gastrectomy is recommended for patients with early gastric cancer (EGC) because the possibility of lymph node metastasis (LNM) cannot be completely denied. The aim of this study was to develop a discrimination model to select patients who do not require surgery using machine learning., Methods: Data from 382 patients who received gastrectomy for gastric cancer and who were diagnosed with pT1b were extracted for developing a discrimination model. For the validation of this discrimination model, data from 140 consecutive patients who underwent endoscopic resection followed by gastrectomy, with a diagnosis of pT1b EGC, were extracted. We applied XGBoost to develop a discrimination model for clinical and pathological variables. The performance of the discrimination model was evaluated based on the number of cases classified as true negatives for LNM, with no false negatives for LNM allowed., Results: Lymph node metastasis was observed in 95 patients (25%) in the development cohort and 11 patients (8%) in the validation cohort. The discrimination model was developed to identify 27 (7%) patients with no indications for additional surgery due to the prediction of an LNM-negative status with no false negatives. In the validation cohort, 13 (9%) patients were identified as having no indications for additional surgery and no patients with LNM were classified into this group., Conclusion: The discrimination model using XGBoost algorithms could select patients with no risk of LNM from patients with pT1b EGC. This discrimination model was considered promising for clinical decision-making in relation to patients with EGC., Competing Interests: The authors declare no conflicts of interest for this article., (© 2023 The Authors. Annals of Gastroenterological Surgery published by John Wiley & Sons Australia, Ltd on behalf of The Japanese Society of Gastroenterological Surgery.)

The analysis of super-enhancers (SEs) has recently attracted attention in elucidating the molecular mechanisms of cancer and other diseases. SEs are genomic structures that strongly induce gene expression and have been reported to contribute to the overexpression of oncogenes. Because the analysis of SEs and integrated analysis with other data are performed using large amounts of genome-wide data, artificial intelligence technology, with machine learning at its core, has recently begun to be utilized. In promoting precision medicine, it is important to consider information from SEs in addition to genomic data; therefore, machine learning technology is expected to be introduced appropriately in terms of building a robust analysis platform with a high generalization performance. In this review, we explain the history and principles of SE, and the results of SE analysis using state-of-the-art machine learning and integrated analysis with other data are presented to provide a comprehensive understanding of the current status of SE analysis in the field of medical biology. Additionally, we compared the accuracy between existing machine learning methods on the benchmark dataset and attempted to explore the kind of data preprocessing and integration work needed to make the existing algorithms work on the benchmark dataset. Furthermore, we discuss the issues and future directions of current SE analysis., (© The Author(s) 2023. Published by Oxford University Press.)

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation., (© 2022. The Author(s).)

Introduction: Despite the fact that the number of peritoneal dialysis (PD) patients is increasing, there is little evidence on the surgical outcomes of PD patients who have colorectal cancer surgery, and there is no consensus on the safety and practicality of continuing PD., Methods: We retrospectively evaluated the short- and long-term results, as well as the feasibility of continuing PD, in eight patients with PD who had colorectal cancer surgery at our institution between January 2010 and January 2021., Results: The scheduled open-fashioned resection was performed in one patient, whereas the other seven surgeries were all conducted laparoscopically, with no intraoperative conversion to laparotomy necessary. Except for one patient with a history of recurring PD-related peritonitis, the PD catheter was kept in seven of the eight cases. Five of the seven patients continuing PD underwent temporary postoperative hemodialysis. At a median of 24.5 months of postoperative monitoring, no infectious complications were observed, six cases continued PD, and no recurrence of colorectal cancer was observed in all cases., Conclusions: Routine curative-intent colorectal cancer surgery with the preservation of the PD catheter is possible and safe in individuals receiving PD. This patient population's short- and long-term oncological results are comparable to general surgical outcomes of those without chronic kidney disease. PD can be maintained for a long period of time following major colorectal cancer surgery., Competing Interests: The authors have declared that no competing interests exist., (Copyright © 2022, Kouno et al.)

Background/purpose: The safety of laparoscopic liver resection in super-elderly patients with comorbidities is unknown. We used propensity score matching to evaluate the utility and safety of laparoscopic liver resection in super-elderly patients., Methods: Two-hundred and five patients who underwent laparoscopic liver resection were retrospectively reviewed. They were classified into two groups based on age: ≥80 years (elderly group, n = 49) and <80 years (control group, n = 156). Propensity score matching (PSM) was performed based on preoperative clinical parameters. The intraoperative and postoperative outcomes were compared., Results: After matching, 45 patients were included in each group. The intraoperative blood loss was identical between the control and elderly groups (60 vs 60 mL, respectively, P = .588); the frequency of serious postoperative complications (Clavien-Dindo class ≥3, 1/45 vs 1/45, P = 1.00) was also similar. There was no significant difference in terms of the exacerbation of malignancy (22.2% vs 11.1%, P = .258) or other diseases (8.9% vs 22.2%, P = .144). There was no difference in overall survival before and after PSM. However, 5-year overall survival excluding primary cancer-related death showed a difference after PSM (90.7% vs 70.4%; P = .048)., Conclusions: Laparoscopic liver resection is feasible and safe in super-elderly patients. The long-term prognosis was poor in patients affected by other illnesses compared to the younger population with similar risk profiles, but there was no difference in overall survival., (© 2021 Asia Endosurgery Task Force and Japan Society of Endoscopic Surgery and John Wiley & Sons Australia, Ltd.)

Background: The aim of the study was to confirm that glomerular hyperfiltration, an early and reversible stage of kidney damage, is associated in patients with prediabetes and prehypertension., Methods: In total, 5003 people aged between 35 and 69 years who had participated in the Shizuoka part of the Japan Multi-Institutional Collaborative Cohort (J-MICC) study took part in the study. Prevalence of hyperfiltration [the estimated glomerular filtration rate (eGFR) above the age- /sex-specific 95th percentile] was compared among different stages of prediabetes [fasting plasma glucose (FPG) < 100, 100-109, 110-125, and ≥126 mg/dL; and/or hemoglobin A1c (HbA1c) < 5.7, 5.7-6.0, 6.1-6.4 and ≥6.5% for no prediabetes, stage 1 prediabetes, stage 2 prediabetes, and overt diabetes, respectively] and prehypertension (blood pressure <120/80, 120-129/80-84, 130-139/85-89, and ≥140/90 mmHg for no prehypertension, stage 1 prehypertension, stage 2 prehypertension, and overt hypertension, respectively)., Results: The prevalence of hyperfiltration increased with increasing stages of prediabetes (odds ratios: 1.25, 1.68, and 2.37 using FPG, and 1.26, 2.15, and 2.45 using HbA1c for stage 1 prediabetes, stage 2 prediabetes, and diabetes, respectively, relative to no prediabetes). Prehypertension, however, was not associated with hyperfiltration., Conclusion: The results confirmed that the prevalence of glomerular hyperfiltration increased with increasing stages (i.e., worsening) of prediabetes. Because both FPG and HbA1c showed similar association with hyperfiltration, either of these can be used to identify subjects who are at increased risk of nephropathy. Therefore, the functioning of kidneys should be monitored in subjects with prediabetes. Prompt treatment of hyperglycemia is necessary in subjects with hyperfiltration to prevent it to cause nephropathy.

The title compound, C(30)H(20)N(2)O(4), exhibits a nematic phase in the wide temperature range between 498.5 and 538.6 K, in spite of the short linker moiety. Two crystal forms have been found. In both forms, the molecule is centrosymmetric. Form I has a planar biphenyl group, while form II has a twisted biphenyl group with a twist angle of 34.75 (6) degrees . The packing modes are also different. In form I the long molecular axes are tilted with respect to each other at about 30 degrees , while in form II the long molecular axes have an almost parallel arrangement.

We describe a rare male case of malignant hemangiopericytoma of the chest wall. An extrapleural chest wall mass about 1.5 x 4 cm in size was detected along the right 3rd rib on a chest roentgenogram when the patient was 58 years old. The tumor did not enlarge for over 12 years thereafter. At the age of 73 years, the patient came to our hospital for chest pain after a traffic accident. A roentgenogram revealed the extrapleural tumor of the chest, which was enlarged to 8 x 12 x 7 cm, and right hemothorax. The tumor was resected together with the 3rd and 4th ribs. Light and electron microscopy and immunostaining studies led to a diagnosis of malignant hemangiopericytoma. The postoperative course was uneventful, and radiotherapy and chemotherapy were performed. The patient has been well without recurrence for 18 months after the operation. We also reviewed 9 cases of this tumor reported in Japan.

From January 1991 to July 1993, 58 patients with MRSA infections in our clinic at Wakayama Medical College and six affiliated hospitals were administered with arbekacin (ABK). The clinical results were as follows: 1. The clinical efficacy rates of ABK were 84% in pneumonia, 100% in both wound infections and hepatobiliary tract infections, and 85% in total. The bacteriological efficacy rate was 83%. 2. Regarding the administration route, the clinical efficacy rates were 60-79% by the intravenous treatment and inhalation therapy. Especially by the local administration with ABK, MRSA was eradicated in all cases. 3. The sufficient efficacy was obtained by the treatment of ABK alone (89%) and by the combined treatment with ABK (82%) and another antibiotics. From these results, it is concluded that ABK is useful for the treatment of MRSA infections after gastrointestinal surgery.

Electrocardiogram-gated spin-echo magnetic resonance (MR) images of the chest were obtained in five normal controls and 35 patients with pulmonary disease (11 chronic obstructive pulmonary disease, 6 pulmonary thromboembolism, 5 primary pulmonary hypertension, 4 interstitial pulmonary disease, 4 pulmonary hypertension with disturbance of portal circulation, and 5 other diseases) who underwent right cardiac catheterization. In transverse images at the level of the right main pulmonary artery (rPA) and sagittal images at the level through the midsternal line and the spinal chord, the signal intensity of blood flow in the rPA was quantitatively evaluated, and the correlations with the MR signal intensity of intravascular flow and the parameters of hemodynamics were studied. In diastole MR images of both normal controls and patients mostly showed a significant signal intensity of flowing blood, but in systole some patients demonstrated significant signals and visible flow images. In systolic MR images, the mean values of hemodynamic parameters (mean pulmonary arterial pressure (mPAP), pulmonary arteriolar resistance (PAR), and cardiac index (CI)) were abnormal in patients with significant signal intensity of flow compared with those in patients without sufficient MR signal. The signal intensity was not correlated with mPAP; however, it significantly increased as PAR increased, and it increased as CI decreased both in diastole and in systole. Especially in systole, there was good correlation between the signal intensity in transverse MR images and CI (r = -0.85, P less than 0.01) and between signal intensity in sagittal MR images and PAR (r = 0.90, P less than 0.01). These results suggest that significant flow signal in the rPA in systole has pathophysiological significance, and signal intensity is considered to be significantly affected by changes of PAR and CI. The signal intensity of blood flow in the rPA on MR images can be used as an index of the severity of right heart failure associated with pulmonary disease. MR imaging is a useful modality to evaluate pulmonary circulation disturbance because of its ability to assess blood flow in the pulmonary artery noninvasively without interference from other structures such as bone and normal lung.

Three immunoglobulin G1 monoclonal antibodies, LuCa2, LuCa3, and LuCa4, were produced by fusing murine myeloma NS1 cells with splenocytes obtained from a BALB/c mouse immunized with SK-MES1 cells derived from human squamous cell carcinoma of the lung. These three monoclonal antibodies were shown to recognize different protein antigens on SK-MES1 cells by indirect immunoprecipitation and sodium dodecyl sulfate-polyacrylamide gel electrophoresis analysis. While the pattern of cell line distribution of antigens recognized by these antibodies was not tumor type specific, their reactivity with tissue and pleural effusion was much more informative than with cell lines. The presence of target antigens in vivo was analyzed by immunoperoxidase staining of frozen tissue sections and immunofluorescence staining of tumor cells in pleural effusions. LuCa2 antibody was reactive with lung squamous carcinoma and adenocarcinoma tumor tissues and pleural effusions, but only infrequently with those of small cell carcinoma. This antibody was also reactive with many tumor tissues from other organs as well as with various normal tissues, including alveoli and bronchus. LuCa3 and LuCa4 antibodies reacted with lung squamous carcinoma in tissues and pleural effusions, but not with lung adenocarcinoma nor with small cell carcinoma. These two antibodies reacted only weakly with normal squamous tissues of the esophagus, skin, and cervix uteri, but not with various other normal tissues. Moreover, LuCa3 had weak reactivity with squamous cell carcinoma tissue of tongue and esophagus, whereas LuCa4 had no reactivity with nonpulmonary tumor tissues. LuCa3 and LuCa4 antibodies should be of clinical interest, because our data suggest that these antibodies may be potentially useful for the diagnosis of the histological type of lung tumor cells in both cancer tissue and pleural effusions.