Technology and Health Care - Volume 33, issue 1

Authors: Sheela, K. Selva | Justus, Vivek | Asaad, Renas Rajab | Kumar, R. Lakshmana

Article Type: Research Article

Abstract: BACKGROUND: Liver cancer poses a significant health challenge due to its high incidence rates and complexities in detection and treatment. Accurate segmentation of liver tumors using medical imaging plays a crucial role in early diagnosis and treatment planning. OBJECTIVE: This study proposes a novel approach combining U-Net and ResNet architectures with the Adam optimizer and sigmoid activation function. The method leverages ResNet’s deep residual learning to address training issues in deep neural networks. At the same time, U-Net’s structure facilitates capturing local and global contextual information essential for precise tumor characterization. The model aims to enhance …segmentation accuracy by effectively capturing intricate tumor features and contextual details by integrating these architectures. The Adam optimizer expedites model convergence by dynamically adjusting the learning rate based on gradient statistics during training. METHODS: To validate the effectiveness of the proposed approach, segmentation experiments are conducted on a diverse dataset comprising 130 CT scans of liver cancers. Furthermore, a state-of-the-art fusion strategy is introduced, combining the robust feature learning capabilities of the UNet-ResNet classifier with Snake-based Level Set Segmentation. RESULTS: Experimental results demonstrate impressive performance metrics, including an accuracy of 0.98 and a minimal loss of 0.10, underscoring the efficacy of the proposed methodology in liver cancer segmentation. CONCLUSION: This fusion approach effectively delineates complex and diffuse tumor shapes, significantly reducing errors. Show more

Keywords: Adam optimizer, CT scans, deep learning, U-Net, ResNet

DOI: 10.3233/THC-230931

Citation: Technology and Health Care, vol. 33, no. 1, pp. 1-15, 2025

Authors: Lin, Ai-Ling | Hou, Jian-Hua

Article Type: Research Article

Abstract: BACKGROUND: This study explores the influence of Diagnosis-Related Groups (DRG) payment reform on hospital cost control and offers pertinent cost management strategies for public hospitals. It situates the research by elucidating the significance of the DRG payment method and comparing its advantages and drawbacks with the traditional ‘pay per project’ model. OBJECTIVE: The primary aim is to assess the impact of DRG payment reform on hospital cost control and propose effective cost management strategies for public hospitals. The objective is to provide insights into DRG payment implications and attempt practical recommendations for its implementation in the …public healthcare sector. METHODS: Employing a comprehensive approach, the study analyzes DRG payment, delineates advantages and drawbacks, and proposes cost management strategies. Methods include staff training, an information management platform, disease analysis, and optimized cost accounting. The study highlights the potential for improved medical diagnosis and treatment through industry-finance integration. RESULTS: Findings reveal advantages and limitations of DRG payment, emphasizing strategies for optimizing hospital operations. Enhanced medical diagnosis and treatment procedures through industry-finance integration contribute to overall cost control effectiveness. CONCLUSION: The study serves as a practical guide for implementing DRG payment reforms, offering valuable insights for policymakers and healthcare professionals in navigating the complexities of cost control in public healthcare. Show more

Keywords: DRG payment method, hospital cost control, public hospital, cost management, integration of industry and finance

DOI: 10.3233/THC-240110

Citation: Technology and Health Care, vol. 33, no. 1, pp. 17-24, 2025

Authors: Huang, Jie | Yang, Kun | Gao, Li | He, Quanmin | Ge, Song

Article Type: Research Article

Abstract: BACKGROUND: The human oral cavity contains over 700 types of bacteria that may protect the body against colonization by exogenous pathogens and maintain relative homeostasis. However, alterations in the immune status can disrupt the balance between microorganisms and the host, inducing various diseases such as oral cancer and diabetes mellitus. The mechanism underlying this process is not clearly understood. OBJECTIVE: The purpose of this study was to investigate the relationships between subgingival bacteria, T-cell receptor β -chain complementarity-determining region 3 (TCRβ CDR3), and the development oforal squamous cell carcinoma (OSCC). …METHODS: We grouped patients as “healthy periodontal” (H), “moderate-to-severe chronic periodontitis” (C), and “moderate-to-severe chronic periodontitis with OSCC” (T). Bacterial groups were “subgingival plaque” (bp) and “gingival/tumor tissue” (g). We also recorded patients’ age, gender, attachment level (AL), bleeding on probing (BOP), and probing depth (PD). We extracted and sequenced RNA from plaques, gingival tissues, tumors, and teeth. We performed high-throughput sequencing on TCRβ CDR3 and plaque bacteria. RESULTS: Synergistetes and Veillonella parvula were more abundant in the H group than in the T group. Granulicatella , Peptostreptococcus , and Streptococcus infantis were enriched in the T-bp group. AL, BOP, and PD were positively correlated with Granulicatella , Peptostreptococcus , and Pseudomonas but negatively correlated with Prevotella nigrescens and V. parvula . TCRβ CDR3 diversity was C > H > T. TCR β -chain Variable gene (TRBV)20-1 usage varied among the H, C, and T groups. TRBV2 and TRBV5-1 usage was greater in the T group than in the C group. TRBJ1-1 , TRBJ1-2 , TRBJ2-2 , TRBJ2-7 , and TRBJ2-5 were most frequently used. CONCLUSIONS: These trends and the reduction of gingival Synergistetes were correlated with OSCC. TCRβ CDR3 diversity was the lowest in patients in the T group, and there were considerable changes in the expression of TRBV2 and TRBJ . Therefore, plaque bacterial composition can influence TCRβ CDR3. Show more

Keywords: Chronic periodontitis, high-throughput sequencing, oral squamous cell carcinoma, subgingival plaque

DOI: 10.3233/THC-240218

Citation: Technology and Health Care, vol. 33, no. 1, pp. 25-51, 2025

Authors: Li, Han | Li, Hui | Tian, Yiyang | Hu, Xiefeng | Hu, Xianhui | Qin, Xin | Yin, Yong

Article Type: Research Article

Abstract: BACKGROUND: Laparoscopic partial nephrectomy (LPN) is a standard surgical treatment option for renal tumors. Prior to LPN, it is necessary to evaluate the tumor condition and develop a surgical plan using precise imaging. OBJECTIVE: To explore the clinical application value of 3D virtual model (3DVM) in LPN. METHODS: A total of 80 patients with renal tumor who underwent LPN were measured. Patients were divided into three cohorts (A, B, C) according to the difficulty of surgery. Each group was further divided into the test and control groups based on the application of preoperative …3DVM. Surgical safety and efficacy were assessed, and a questionnaire was developed to investigate the opinions of patients and physicians on 3DVM. RESULTS: The duration of LPN and intraoperative renal artery occlusion were significantly different between the test and control groups in both cohorts A and B (P < 0.05). In cohort C, the surgical duration, duration of intraoperative renal artery occlusion, length of stay, time to postoperative ambulation, intraoperative bleeding, incidence of postoperative bleeding were significantly between the two groups (P < 0.05). The analysis both of patients and physicians questionnaire scores were statistically significant (P < 0.05). CONCLUSIONS: 3DVM contributes to safer and more effective LPN. It benefits both doctors and patients. Show more

Keywords: Renal cell carcinoma, renal cancer, laparoscopic partial nephrectomy, 3D virtual model

DOI: 10.3233/THC-240421

Citation: Technology and Health Care, vol. 33, no. 1, pp. 53-63, 2025

Authors: Čehić, Ermin | Cerovac, Anis | Zulović, Tarik | Begić, Edin

Article Type: Research Article

Abstract: BACKGROUND: Thanks to modern methods of assisted reproduction (ART), parenthood has become an attainable goal for couples in which the male partner has experienced spinal cord injury (SCI). OBJECTIVE: The aim of our study was to determine the success of the treatment of infertile patients with SCI with intracytoplasmic sperm injection (ICSI) of cryopreserved sperm obtained by the testicular sperm aspiration (TESA) procedure. METHODS: In this retrospective study 156 infertile couples were included, in which the male partner is primarily infertile due to azoospermia. Infertile couples were divided into two groups. The first …group (n = 82) includes men with SCI, and the second (n = 74) men with obstructive azoospermia (OA) as the cause of infertility. All infertile men were examined and processed in the diagnostic procedure, and based on the urological findings, surgical extraction of sperm from the testicles was indicated. Exclusion criteria were the age of women over 40 and men over 45. RESULTS: We found that the quality of sperm was worse in the group with SCI, compared to the group with OA, but without statistical significance. Zenica and Johnsen score (p = 0.001; p = 0.000) showed worse semen characteristics in the group with SCI.     There were no significant differences in the average number of embryos (p = 0.698), pregnancy rates per cycle (p = 0.979) and pregnancy rates per embrio transfer (ET), clinical pregnancy rates per ET (p = 0.987) and delivery rates per ET (p = 0.804) in couples with SCI, compared to couples with OA. CONCLUSION: Based on the results of this research, the TESA and ICSI procedures can be recommended as a successful method in the treatment of male infertility caused by azoospermia due to SCI. Show more

Keywords: Azoospermia, male, pregnancy rate, sperm motility, sperm retrieval, spinal cord injuries

DOI: 10.3233/THC-240518

Citation: Technology and Health Care, vol. 33, no. 1, pp. 65-75, 2025

Authors: Tigga, Neha Prerna | Garg, Shruti | Goyal, Nishant | Raj, Justin | Das, Basudeb

Article Type: Research Article

Abstract: BACKGROUND: Brain variations are responsible for developmental impairments, including autism spectrum disorder (ASD). EEG signals efficiently detect neurological conditions by revealing crucial information about brain function abnormalities. OBJECTIVE: This study aims to utilize EEG data collected from both autistic and typically developing children to investigate the potential of a Graph Convolutional Neural Network (GCNN) in predicting ASD based on neurological abnormalities revealed through EEG signals. METHODS: In this study, EEG data were gathered from eight autistic children and eight typically developing children diagnosed using the Childhood Autism Rating Scale at the Central Institute …of Psychiatry, Ranchi. EEG recording was done using a HydroCel GSN with 257 channels, and 71 channels with 10-10 international equivalents were utilized. Electrodes were divided into 12 brain regions. A GCNN was introduced for ASD prediction, preceded by autoregressive and spectral feature extraction. RESULTS: The anterior-frontal brain region, crucial for cognitive functions like emotion, memory, and social interaction, proved most predictive of ASD, achieving 87.07% accuracy. This underscores the suitability of the GCNN method for EEG-based ASD detection. CONCLUSION: The detailed dataset collected enhances understanding of the neurological basis of ASD, benefiting healthcare practitioners involved in ASD diagnosis. Show more

Keywords: Autism, graph convolution neural network, electroencephalogram, deep learning, brain region

DOI: 10.3233/THC-240550

Citation: Technology and Health Care, vol. 33, no. 1, pp. 77-101, 2025

Authors: Chen, Bin | Yi, Yinqiao | Zhang, Chengxiu | Yan, Yulin | Wang, Xia | Shui, Wen | Zhou, Minzhi | Yang, Guang | Ying, Tao

Article Type: Research Article

Abstract: BACKGROUND: The anal sphincter complex comprises the anal sphincter and the U-shaped deep and superficial puborectalis muscle. As an important supporting structure of the posterior pelvic floor, together with its surrounding tissues and muscles, the anal sphincter complex maintains the normal physiological functions of defecation and continence. OBJECTIVE: The plane required for diagnosing anal sphincter injury and the diagnosis of anal sphincter integrity through pelvic floor ultrasound are highly dependent on sonographers’ experience. We developed a deep learning (DL) tool for the automatic diagnosis of anal sphincter integrity via pelvic floor ultrasound. METHODS: …A 2D detection network was trained to detect the bounding box of the anal sphincter. The pelvic floor ultrasound image and its corresponding oval mask were input into a 2D classification network to determine the integrity of the anal sphincter. The average precision (AP) and intersection over union (IoU) were used to evaluate the performance of anal sphincter detection. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the classification model. RESULTS: The Pearson correlation coefficients (r values) of the topmost and bottommost layers detected by the CNN and sonographers were 0.932 and 0.978, respectively. The best DL model yielded the highest area under the curve (AUC) of 0.808 (95% CI: 0.698–0.921) in the test cohort. The results from the CNN agreed well with the diagnostic results of experienced sonographers. CONCLUSIONS: We proposed, for the first time, a CNN to obtain the plane required for diagnosing anal sphincter injury on the basis of pelvic floor ultrasound and for preliminarily diagnosing anal sphincter injury. Show more

Keywords: Anal sphincter, convolutional neural network, deep learning, pelvic floor, artificial intelligence

DOI: 10.3233/THC-240569

Citation: Technology and Health Care, vol. 33, no. 1, pp. 103-114, 2025

Authors: Liu, Chunlin | Huang, Chungui

Article Type: Research Article

Abstract: BACKGROUND: The incidence of posterior malleolus fractures in ankle fractures ranges from 7% to 44%. Studies have indicated a poorer prognosis for ankle joint function when a posterior malleolar fracture is present, underscoring the significance of active intervention for optimal postoperative ankle function recovery. Hence, the selection of treatment for such fractures holds particular importance. OBJECTIVE: Screw fixation is a key treatment for posterior malleolus fractures (PMFs) or Haraguchi Type 1 fractures involving less than 25% of the distal tibia’s articular surface. However, the optimal screw placement direction – anteroposterior (AP) or posterior-anterior (PA) – remains …debated. This meta-analysis aims to compare these two approaches for treating posterior ankle fractures, focusing on the efficacy of PA fixation. METHODS: We searched the Cochrane Library, EMBASE, PubMed, SinoMed, and Web of Science databases from their inception to October 20, 2022. Methodological quality was assessed using the Cochrane Collaboration’s tool for assessing bias risk in randomized controlled trials (RCTs). Stata MP17 software was used to compare the American Orthopaedic Foot and Ankle Society (AOFAS) ankle-hindfoot score, full weight-bearing time, and fracture healing time at the last follow-up between the two fixation methods. RESULTS: A total of 403 patients with posterior malleolar fractures from six RCTs met the inclusion criteria. The meta-analysis revealed a higher AOFAS score at the last follow-up for PA placement compared to AP placement [SMD = 0.512, 95% CI (0.244 to 0.780), z = 3.74, P < 0.001]. Postoperative full weight-bearing time and fracture healing time did not show statistically significant differences between the two groups. CONCLUSION: PA fixation demonstrated a superior AOFAS score compared to AP fixation for posterior malleolar fractures. PA screw placement offers advantages in restoring ankle joint stability and enhancing joint function recovery post-surgery. Show more

Keywords: Posterior malleolus fracture (PMFs), posterior-anterior fixation (PA), anterior-posterior fixation (AP)

DOI: 10.3233/THC-240602

Citation: Technology and Health Care, vol. 33, no. 1, pp. 115-125, 2025

Authors: Zhao, Jie | Liu, Jianqiang | Wang, Shijie | Zhang, Pinzheng | Yu, Wenxue | Yang, Chunfeng | Zhang, Yudong | Chen, Yang

Article Type: Research Article

Abstract: BACKGROUND: In radiography procedures, radiographers’ suboptimal positioning and exposure parameter settings may necessitate image retakes, subjecting patients to unnecessary ionizing radiation exposure. Reducing retakes is crucial to minimize patient X-ray exposure and conserve medical resources. OBJECTIVE: We propose a Digital Radiography (DR) Pre-imaging All-round Assistant (PIAA) that leverages Artificial Intelligence (AI) technology to enhance traditional DR. METHODS: PIAA consists of an RGB-Depth (RGB-D) multi-camera array, an embedded computing platform, and multiple software components. It features an Adaptive RGB-D Image Acquisition (ARDIA) module that automatically selects the appropriate RGB camera based on the distance …between the cameras and patients. It includes a 2.5D Selective Skeletal Keypoints Estimation (2.5D-SSKE) module that fuses depth information with 2D keypoints to estimate the pose of target body parts. Thirdly, it also uses a Domain expertise (DE) embedded Full-body Exposure Parameter Estimation (DFEPE) module that combines 2.5D-SSKE and DE to accurately estimate parameters for full-body DR views. RESULTS: Optimizes DR workflow, significantly enhancing operational efficiency. The average time required for positioning patients and preparing exposure parameters was reduced from 73 seconds to 8 seconds. CONCLUSIONS: PIAA shows significant promise for extension to full-body examinations. Show more

Keywords: Digital radiography, patient positioning, deep learning, domain expertise, human pose estimation, automatic exposure control, RGB-D camera

DOI: 10.3233/THC-240639

Citation: Technology and Health Care, vol. 33, no. 1, pp. 127-142, 2025

Authors: Huang, Yucheng | Ma, Xuan | Wu, Shilei | Chen, Ming | Wang, Junwen | Jiao, Jing

Article Type: Research Article

Abstract: BACKGROUND: Current treatments do not support direct exposure of fracture fragments, resulting in the inability to directly observe the articular surface during surgery for accurate reduction and firm fixation. OBJECTIVE: The aim of the study was to explore the treatment effect of digital virtual reduction combined with individualized guide plate of lateral tibial condyle osteotomy on tibial plateau fracture involving the lateral posterior condyle collapse. METHODS: 41 patients with tibial plateau fracture involving the lateral posterior condyle collapse were recruited in the trial. All patients underwent Computed Tomography (CT) scanning before operation. After …operation, fracture reduction was evaluated using Rasmussen score and function of knee joint was assessed using hospital for special surgery (HSS) score. RESULTS: 41 patients were followed-up 6–26 months (mean, 15.2 months). Fracture reduction was good after operation, with an average of 13.3 weeks of fracture healing without serious complications. The excellent and good rate was 97.6%. The joint movement degree was - 5∘ ∼ 0∘ ∼ 135∘ with an average of 125.5∘ . CONCLUSIONS: Digital virtual reduction combined with individualized guide plate of lateral tibial condyle osteotomy was effectively for treating tibial plateau fracture involving the lateral posterior condyle collapse. Show more

Keywords: 3D printing, tibial fracture, osteotomy, fracture fixation

DOI: 10.3233/THC-240704

Citation: Technology and Health Care, vol. 33, no. 1, pp. 143-155, 2025